modify at output data format

contrast/one2one_contrast.py

@@ -52,10 +52,10 @@ from tracking.utils.read_data import extract_data, read_tracking_output, read_si
 from tracking.utils.plotting import Annotator, colors
 from feat_extract.config import config as conf
 from feat_extract.inference import FeatsInterface
-from utils.event import Event 
+from utils.event import ShoppingEvent 
 from genfeats import gen_bcd_features
 
-IMG_FORMAT = ['.bmp', '.jpg', '.jpeg', '.png']
+
 
 
 
@@ -83,148 +83,6 @@ def ft16_to_uint8(arr_ft16):
 
     return arr_uint8, arr_ft16_
 
-def creat_shopping_event(eventPath):
-    '''构造放入商品事件字典，这些事件需满足条件：
-        1) 前后摄至少有一条轨迹输出
-        2) 保存有帧图像，以便裁剪出 boxe 子图
-    '''
-
-    '''evtName 为一次购物事件'''    
-    evtName = os.path.basename(eventPath)
-    evtList = evtName.split('_')
-
-    '''================ 0. 检查 evtName 及 eventPath 正确性和有效性 ================'''
-    if evtName.find('2024')<0 and len(evtList[0])!=15:
-        return
-    if not os.path.isdir(eventPath): 
-        return
-    
-    if len(evtList)==1 or (len(evtList)==2 and len(evtList[1])==0):
-        barcode = ''
-    else:
-        barcode = evtList[-1]
-    
-    if len(evtList)==3 and evtList[-1]== evtList[-2]:
-        evtType = 'input'
-    else:
-        evtType = 'other'
-
-    '''================ 1. 构造事件描述字典，暂定 9 items ==============='''
-       
-
-    
-    
-    event = {}
-    event['barcode'] = barcode
-    event['type'] = evtType
-    event['filepath'] = eventPath
-    event['back_imgpaths'] = []
-    event['front_imgpaths'] = []
-    event['back_boxes'] = np.empty((0, 9), dtype=np.float64)
-    event['front_boxes'] = np.empty((0, 9), dtype=np.float64)
-    event['back_feats'] = np.empty((0, 256), dtype=np.float64)
-    event['front_feats'] = np.empty((0, 256), dtype=np.float64)
-    event['feats_compose'] = np.empty((0, 256), dtype=np.float64)
-    event['one2one'] = None
-    event['one2n'] = None
-    event['feats_select'] = np.empty((0, 256), dtype=np.float64)
-    
-    
-    '''================= 2. 读取 data 文件 ============================='''
-    for dataname in os.listdir(eventPath):
-        # filename = '1_track.data'
-        datapath = os.path.join(eventPath, dataname)
-        if not os.path.isfile(datapath): continue
-        
-        CamerType = dataname.split('_')[0]
-        ''' 2.1 读取 0/1_track.data 中数据，暂不考虑'''
-        # if dataname.find("_track.data")>0:
-        #     bboxes, ffeats, trackerboxes, tracker_feat_dict, trackingboxes, tracking_feat_dict = extract_data(datapath)
-  
-        ''' 2.2 读取 0/1_tracking_output.data 中数据'''
-        if dataname.find("_tracking_output.data")>0:
-            tracking_output_boxes, tracking_output_feats = read_tracking_output(datapath)
-            if len(tracking_output_boxes) != len(tracking_output_feats): continue
-            if CamerType == '0':
-                event['back_boxes'] = tracking_output_boxes
-                event['back_feats'] = tracking_output_feats
-            elif CamerType == '1':
-                event['front_boxes'] = tracking_output_boxes
-                event['front_feats'] = tracking_output_feats
-                
-        if dataname.find("process.data")==0:
-            simiDict = read_similar(datapath)
-            event['one2one'] = simiDict['one2one']
-            event['one2n'] = simiDict['one2n']
-
-
-    if len(event['back_boxes'])==0 or len(event['front_boxes'])==0:
-        return None
-    
-    '''2.3 事件的特征表征方式: 特征选择、特征集成'''
-    bk_feats = event['back_feats']
-    ft_feats = event['front_feats']
-    
-    '''2.3.1 特征集成'''
-    feats_compose = np.empty((0, 256), dtype=np.float64)
-    if len(ft_feats):
-        feats_compose = np.concatenate((feats_compose, ft_feats), axis=0)
-    if len(bk_feats):
-        feats_compose = np.concatenate((feats_compose, bk_feats), axis=0)
-    event['feats_compose'] = feats_compose
-            
-    '''2.3.1 特征选择'''
-    if len(ft_feats):
-        event['feats_select'] = ft_feats
-
-
-    '''================ 3. 读取图像文件地址，并按照帧ID排序 ============='''
-    frontImgs, frontFid = [], []
-    backImgs, backFid = [], []
-    for imgname in os.listdir(eventPath):
-        name, ext = os.path.splitext(imgname)
-        if ext not in IMG_FORMAT or name.find('frameId')<0: continue
-
-        CamerType = name.split('_')[0]
-        frameId = int(name.split('_')[3])
-        imgpath = os.path.join(eventPath, imgname)
-        if CamerType == '0':
-            backImgs.append(imgpath)
-            backFid.append(frameId)
-        if CamerType == '1':
-            frontImgs.append(imgpath)
-            frontFid.append(frameId)
-    
-    frontIdx = np.argsort(np.array(frontFid))
-    backIdx = np.argsort(np.array(backFid))
-    
-    '''3.1 生成依据帧 ID 排序的前后摄图像地址列表'''
-    frontImgs = [frontImgs[i] for i in frontIdx]
-    backImgs = [backImgs[i] for i in backIdx]
-
-    '''3.2 将前、后摄图像路径添加至事件字典'''   
-    
-    
-    bfid = event['back_boxes'][:, 7].astype(np.int64)
-    ffid = event['front_boxes'][:, 7].astype(np.int64)
-    if len(bfid) and max(bfid) <= len(backImgs):
-        event['back_imgpaths'] = [backImgs[i-1] for i in bfid]
-    if len(ffid) and max(ffid) <= len(frontImgs):
-        event['front_imgpaths'] = [frontImgs[i-1] for i in ffid]
-
-    
-    '''================ 4. 判断当前事件有效性，并添加至事件列表 =========='''
-    condt1 = len(event['back_imgpaths'])==0 or len(event['front_imgpaths'])==0
-    condt2 = len(event['front_feats'])==0 and len(event['back_feats'])==0
-    
-    if condt1 or condt2:
-        print(f"Event: {evtName}, Error, condt1: {condt1}, condt2: {condt2}")
-        return None
-
-    return event
-
-
-
 
 def plot_save_image(event, savepath):
     cameras = ('front', 'back')
@@ -286,9 +144,6 @@ def save_event_subimg(event, savepath):
         else:
             boxes = event.back_boxes
             imgpaths = event.back_imgpaths
-            
-
-            
 
         for i, box in enumerate(boxes):
             x1, y1, x2, y2, tid, score, cls, fid, bid = box
@@ -491,8 +346,8 @@ def one2one_simi():
 
         ##============================================ float32
         stdfeat = stdDict[stdbcd]["feats_ft32"]
-        evtfeat = event.feats_compose
+        
-
+        evtfeat = event.feats_compose    
         if len(evtfeat)==0: continue
 
         matrix = 1 - cdist(stdfeat, evtfeat, 'cosine')
@@ -585,28 +440,9 @@ def gen_eventdict(sourcePath, saveimg=True):
         
         pickpath = os.path.join(eventDataPath, f"{bname}.pickle")
         if os.path.isfile(pickpath): continue
-    
-        # if bname != "20241129-100321-a9dae9e3-7db5-4e31-959c-d7dfc228923e_6972636670213":
-        #     continue
-            
 
- 
-        # eventDict = creat_shopping_event(eventPath)
-        # if eventDict:
-        #     eventList.append(eventDict)
-        #     with open(pickpath, 'wb') as f:
-        #         pickle.dump(eventDict, f)
-        #     print(f"Event: {eventName}, have saved!")
-            
-        # if saveimg and eventDict:
-        #     basename = os.path.basename(eventDict['filepath'])
-        #     savepath = os.path.join(subimgPath, basename)
-        #     if not os.path.exists(savepath):
-        #         os.makedirs(savepath)
-        #     save_event_subimg(eventDict, savepath)
-        
         try:
-            event = Event(source_path)
+            event = ShoppingEvent(source_path, stype="data")
             eventList.append(event)
             with open(pickpath, 'wb') as f:
                 pickle.dump(event, f)
@@ -624,9 +460,7 @@ def gen_eventdict(sourcePath, saveimg=True):
         for line in errEvents:
             f.write(line + '\n')
             
-    
 
-    
 
 def test_one2one(): 
     bcdList, event_spath = [], []

contrast/utils/dotest.py

@@ -0,0 +1,155 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Dec 10 14:30:16 2024
+
+@author: ym
+"""
+import os
+import sys
+import numpy as np
+sys.path.append(r"D:\DetectTracking")
+from tracking.utils.read_data import read_tracking_output, read_similar #, extract_data, read_deletedBarcode_file
+
+
+IMG_FORMAT = ['.bmp', '.jpg', '.jpeg', '.png']
+
+
+def creat_shopping_event(eventPath):
+    '''构造放入商品事件字典，这些事件需满足条件：
+        1) 前后摄至少有一条轨迹输出
+        2) 保存有帧图像，以便裁剪出 boxe 子图
+    '''
+
+    '''evtName 为一次购物事件'''    
+    evtName = os.path.basename(eventPath)
+    evtList = evtName.split('_')
+
+    '''================ 0. 检查 evtName 及 eventPath 正确性和有效性 ================'''
+    if evtName.find('2024')<0 and len(evtList[0])!=15:
+        return
+    if not os.path.isdir(eventPath): 
+        return
+    
+    if len(evtList)==1 or (len(evtList)==2 and len(evtList[1])==0):
+        barcode = ''
+    else:
+        barcode = evtList[-1]
+    
+    if len(evtList)==3 and evtList[-1]== evtList[-2]:
+        evtType = 'input'
+    else:
+        evtType = 'other'
+
+    '''================ 1. 构造事件描述字典，暂定 9 items ==============='''
+       
+
+    
+    
+    event = {}
+    event['barcode'] = barcode
+    event['type'] = evtType
+    event['filepath'] = eventPath
+    event['back_imgpaths'] = []
+    event['front_imgpaths'] = []
+    event['back_boxes'] = np.empty((0, 9), dtype=np.float64)
+    event['front_boxes'] = np.empty((0, 9), dtype=np.float64)
+    event['back_feats'] = np.empty((0, 256), dtype=np.float64)
+    event['front_feats'] = np.empty((0, 256), dtype=np.float64)
+    event['feats_compose'] = np.empty((0, 256), dtype=np.float64)
+    event['one2one'] = None
+    event['one2n'] = None
+    event['feats_select'] = np.empty((0, 256), dtype=np.float64)
+    
+    
+    '''================= 2. 读取 data 文件 ============================='''
+    for dataname in os.listdir(eventPath):
+        # filename = '1_track.data'
+        datapath = os.path.join(eventPath, dataname)
+        if not os.path.isfile(datapath): continue
+        
+        CamerType = dataname.split('_')[0]
+        ''' 2.1 读取 0/1_track.data 中数据，暂不考虑'''
+        # if dataname.find("_track.data")>0:
+        #     bboxes, ffeats, trackerboxes, tracker_feat_dict, trackingboxes, tracking_feat_dict = extract_data(datapath)
+  
+        ''' 2.2 读取 0/1_tracking_output.data 中数据'''
+        if dataname.find("_tracking_output.data")>0:
+            tracking_output_boxes, tracking_output_feats = read_tracking_output(datapath)
+            if len(tracking_output_boxes) != len(tracking_output_feats): continue
+            if CamerType == '0':
+                event['back_boxes'] = tracking_output_boxes
+                event['back_feats'] = tracking_output_feats
+            elif CamerType == '1':
+                event['front_boxes'] = tracking_output_boxes
+                event['front_feats'] = tracking_output_feats
+                
+        if dataname.find("process.data")==0:
+            simiDict = read_similar(datapath)
+            event['one2one'] = simiDict['one2one']
+            event['one2n'] = simiDict['one2n']
+
+
+    if len(event['back_boxes'])==0 or len(event['front_boxes'])==0:
+        return None
+    
+    '''2.3 事件的特征表征方式: 特征选择、特征集成'''
+    bk_feats = event['back_feats']
+    ft_feats = event['front_feats']
+    
+    '''2.3.1 特征集成'''
+    feats_compose = np.empty((0, 256), dtype=np.float64)
+    if len(ft_feats):
+        feats_compose = np.concatenate((feats_compose, ft_feats), axis=0)
+    if len(bk_feats):
+        feats_compose = np.concatenate((feats_compose, bk_feats), axis=0)
+    event['feats_compose'] = feats_compose
+            
+    '''2.3.1 特征选择'''
+    if len(ft_feats):
+        event['feats_select'] = ft_feats
+
+
+    '''================ 3. 读取图像文件地址，并按照帧ID排序 ============='''
+    frontImgs, frontFid = [], []
+    backImgs, backFid = [], []
+    for imgname in os.listdir(eventPath):
+        name, ext = os.path.splitext(imgname)
+        if ext not in IMG_FORMAT or name.find('frameId')<0: continue
+
+        CamerType = name.split('_')[0]
+        frameId = int(name.split('_')[3])
+        imgpath = os.path.join(eventPath, imgname)
+        if CamerType == '0':
+            backImgs.append(imgpath)
+            backFid.append(frameId)
+        if CamerType == '1':
+            frontImgs.append(imgpath)
+            frontFid.append(frameId)
+    
+    frontIdx = np.argsort(np.array(frontFid))
+    backIdx = np.argsort(np.array(backFid))
+    
+    '''3.1 生成依据帧 ID 排序的前后摄图像地址列表'''
+    frontImgs = [frontImgs[i] for i in frontIdx]
+    backImgs = [backImgs[i] for i in backIdx]
+
+    '''3.2 将前、后摄图像路径添加至事件字典'''   
+    
+    
+    bfid = event['back_boxes'][:, 7].astype(np.int64)
+    ffid = event['front_boxes'][:, 7].astype(np.int64)
+    if len(bfid) and max(bfid) <= len(backImgs):
+        event['back_imgpaths'] = [backImgs[i-1] for i in bfid]
+    if len(ffid) and max(ffid) <= len(frontImgs):
+        event['front_imgpaths'] = [frontImgs[i-1] for i in ffid]
+
+    
+    '''================ 4. 判断当前事件有效性，并添加至事件列表 =========='''
+    condt1 = len(event['back_imgpaths'])==0 or len(event['front_imgpaths'])==0
+    condt2 = len(event['front_feats'])==0 and len(event['back_feats'])==0
+    
+    if condt1 or condt2:
+        print(f"Event: {evtName}, Error, condt1: {condt1}, condt2: {condt2}")
+        return None
+
+    return event

contrast/utils/event.py

@@ -5,6 +5,7 @@ Created on Tue Nov 26 17:35:05 2024
 @author: ym
 """
 import os
+import pickle
 import numpy as np
 from pathlib import Path
 
@@ -15,9 +16,9 @@ from tracking.utils.read_data import extract_data, read_tracking_output, read_si
 IMG_FORMAT = ['.bmp', '.jpg', '.jpeg', '.png']
 VID_FORMAT = ['.mp4', '.avi']
 
-class Event:
+class ShoppingEvent:
     def __init__(self, eventpath, stype="data"):  
-        '''stype: str, 'video', 'image', 'data', '''
+        '''stype: str, 'pickle', 'data', '''
         
         self.eventpath = eventpath
         self.evtname = str(Path(eventpath).stem)
@@ -35,37 +36,115 @@ class Event:
         self.one2n = None
         
         '''=========== 0/1_track.data ============================='''
-        self.back_yolobboxes = np.empty((0, 6), dtype=np.float64)
+        self.back_yolobboxes = []
-        self.back_yolofeats = np.empty((0, 256), dtype=np.float64)
+        self.back_yolofeats = []
-        self.back_trackerboxes = np.empty((0, 9), dtype=np.float64)
+        self.back_trackerboxes = np.empty((0, 9), dtype=np.float64) ##和类doTracks兼容 
-        self.back_trackerfeats = np.empty((0, 256), dtype=np.float64)
+        self.back_trackerfeats = {}
-        self.back_trackingboxes = np.empty((0, 9), dtype=np.float64)
+        self.back_trackingboxes = []
-        self.back_trackingfeats = np.empty((0, 256), dtype=np.float64)
+        self.back_trackingfeats = []
         
-        self.front_yolobboxes = np.empty((0, 6), dtype=np.float64)
+        self.front_yolobboxes = []
-        self.front_yolofeats = np.empty((0, 256), dtype=np.float64)
+        self.front_yolofeats = []
-        self.front_trackerboxes = np.empty((0, 9), dtype=np.float64)
+        self.front_trackerboxes = np.empty((0, 9), dtype=np.float64) ##和类doTracks兼容
-        self.front_trackerfeats = np.empty((0, 256), dtype=np.float64)
+        self.front_trackerfeats = {}
-        self.front_trackingboxes = np.empty((0, 9), dtype=np.float64)
+        self.front_trackingboxes = []
-        self.front_trackingfeats = np.empty((0, 256), dtype=np.float64)
+        self.front_trackingfeats = []
 
         '''=========== 0/1_tracking_output.data ==================='''
-        self.back_boxes = np.empty((0, 9), dtype=np.float64)
+        self.back_boxes = []
-        self.front_boxes = np.empty((0, 9), dtype=np.float64)
+        self.back_feats = []
-        self.back_feats = np.empty((0, 256), dtype=np.float64)
+        self.front_boxes = []
-        self.front_feats = np.empty((0, 256), dtype=np.float64)
+        self.front_feats = []
-        self.feats_compose = np.empty((0, 256), dtype=np.float64)
+        
-        self.feats_select = np.empty((0, 256), dtype=np.float64)
 
         if stype=="data":
             self.from_datafile(eventpath)
+        if stype=="pickle":
+            self.from_pklfile(eventpath)
+            
+        self.feats_select = []
+        self.feats_compose = np.empty((0, 256), dtype=np.float64)
+        self.select_feats()
+        self.compose_feats()
+        
+        # if stype=="image":
+        #     self.from_image(eventpath)
+    
+    def kerndata(self, ShoppingDict, camtype="backCamera"):
+        '''
+        camtype: str, "backCamera" or "frontCamera"
+        '''
+        yoloboxes, resfeats = [], []
+        trackerboxes = np.empty((0, 9), dtype=np.float64)
+        trackefeats = {}
+        trackingboxes, trackingfeats  = [], []
+        
+        frameDictList =  ShoppingDict[camtype]["yoloResnetTracker"]
+        for frameDict in frameDictList:
+            yoloboxes.append(frameDict["bboxes"])
 
-        if stype=="video":
+            tboxes = frameDict["tboxes"]
-            self.from_video(eventpath)
+            trackefeats.update(frameDict["feats"])
+            
+            trackerboxes = np.concatenate((trackerboxes, np.array(tboxes)), axis=0)
+
+        Residual = ShoppingDict[camtype]["tracking"].Residual        
+        for track in Residual:
+            trackingboxes.append(track.boxes)
+            trackingfeats.append(track.features)
+        kdata = (yoloboxes, resfeats, trackerboxes, trackefeats, trackingboxes, trackingfeats)
+
+
+        tracking_out_boxes, tracking_out_feats = [], [] 
+        Confirmed = ShoppingDict[camtype]["tracking"].Confirmed        
+        for track in Confirmed:
+            tracking_out_boxes.append(track.boxes)
+            tracking_out_feats.append(track.features)   
+        outdata = (tracking_out_boxes, tracking_out_feats)
+  
+        return kdata, outdata
+
+    
+    def from_pklfile(self, eventpath):
         
-        if stype=="image":
+        with open(eventpath, 'rb') as f:
-            self.from_image(eventpath)
+            ShoppingDict = pickle.load(f)
         
+            
+        self.eventpath = ShoppingDict["eventPath"]
+        self.evtname = ShoppingDict["eventName"]
+        self.barcode = ShoppingDict["barcode"]
+        
+        '''=========== path of image and video =========== '''
+        self.back_videopath = ShoppingDict["backCamera"]["videoPath"]
+        self.front_videopath = ShoppingDict["frontCamera"]["videoPath"]
+        self.back_imgpaths = ShoppingDict["backCamera"]["imagePaths"]
+        self.front_imgpaths = ShoppingDict["frontCamera"]["imagePaths"]
+        
+        '''===========对应于 0/1_track.data ============================='''
+        backdata, back_outdata = self.kerndata(ShoppingDict, "backCamera")
+        frontdata, front_outdata = self.kerndata(ShoppingDict, "frontCamera")
+        self.back_yolobboxes = backdata[0]
+        self.back_yolofeats = backdata[1]
+        self.back_trackerboxes = backdata[2]
+        self.back_trackerfeats = [3]
+        self.back_trackingboxes = [4]
+        self.back_trackingfeats = [5]
+        
+        self.front_yolobboxes = frontdata[0]
+        self.front_yolofeats = frontdata[1]
+        self.front_trackerboxes = frontdata[2]
+        self.front_trackerfeats = frontdata[3]
+        self.front_trackingboxes = frontdata[4]
+        self.front_trackingfeats = frontdata[5]
+
+        '''===========对应于 0/1_tracking_output.data ============================='''
+        self.back_boxes = back_outdata[0]
+        self.back_feats = back_outdata[1]
+        self.front_boxes = front_outdata[0]
+        self.front_feats = front_outdata[1]
+
+
     def from_datafile(self, eventpath):
         evtList = self.evtname.split('_')
         if len(evtList)>=2 and len(evtList[-1])>=10 and evtList[-1].isdigit():
@@ -127,21 +206,21 @@ class Event:
             
             '''========== 0/1_track.data =========='''
             if dataname.find("_track.data")>0:
-                bboxes, ffeats, trackerboxes, tracker_feat_dict, trackingboxes, tracking_feat_dict = extract_data(datapath)
+                bboxes, ffeats, trackerboxes, trackerfeats, trackingboxes, trackingfeats = extract_data(datapath)
                 if CamerType == '0':
                     self.back_yolobboxes = bboxes
                     self.back_yolofeats = ffeats
                     self.back_trackerboxes = trackerboxes
-                    self.back_trackerfeats = tracker_feat_dict
+                    self.back_trackerfeats = trackerfeats
                     self.back_trackingboxes = trackingboxes
-                    self.back_trackingfeats = tracking_feat_dict
+                    self.back_trackingfeats = trackingfeats
                 if CamerType == '1':
                     self.front_yolobboxes = bboxes
                     self.front_yolofeats = ffeats
                     self.front_trackerboxes = trackerboxes
-                    self.front_trackerfeats = tracker_feat_dict
+                    self.front_trackerfeats = trackerfeats
                     self.front_trackingboxes = trackingboxes
-                    self.front_trackingfeats = tracking_feat_dict
+                    self.front_trackingfeats = trackingfeats
 
             '''========== 0/1_tracking_output.data =========='''
             if dataname.find("_tracking_output.data")>0:
@@ -152,26 +231,37 @@ class Event:
                 elif CamerType == '1':
                     self.front_boxes = tracking_output_boxes
                     self.front_feats = tracking_output_feats        
-        self.select_feat()
+        
-        self.compose_feats()
 
         
     def compose_feats(self):
         '''事件的特征集成'''
         feats_compose = np.empty((0, 256), dtype=np.float64)
         if len(self.front_feats):
-            feats_compose = np.concatenate((feats_compose, self.front_feats), axis=0)
+            for feat in self.front_feats:
+                feats_compose = np.concatenate((feats_compose, feat), axis=0)
         if len(self.back_feats):
-            feats_compose = np.concatenate((feats_compose, self.back_feats), axis=0)
+            for feat in self.back_feats:
+                feats_compose = np.concatenate((feats_compose, feat), axis=0)
         self.feats_compose = feats_compose
         
     def select_feats(self):
         '''事件的特征选择'''
+        self.feats_select = []
         if len(self.front_feats):
             self.feats_select = self.front_feats
-        else:
+        elif len(self.back_feats):
             self.feats_select = self.back_feats
-        
+
+def main():
+    pklpath = r"D:\DetectTracking\evtresult\images2\ShoppingDict.pkl"
+    
+    evt = ShoppingEvent(pklpath, stype='pickle')
+    
+
+if __name__ == "__main__": 
+    main()
+    
 
 
             

pipeline.py

@@ -45,7 +45,7 @@ def get_interbcd_inputenents():
 
 def pipeline(        
         eventpath,
-        savepath,
+        savepath = '',
         SourceType = "image",   # video
         stdfeat_path = None 
         ):
@@ -53,47 +53,120 @@ def pipeline(
         vpaths = get_video_pairs(eventpath)
     elif SourceType == "image":
         vpaths = get_image_pairs(eventpath)
-
+    '''
+    eventpath: 单个事件的存储路径
+    
+    '''
+    
     '''======== 函数 yolo_resnet_tracker() 的参数字典 ========'''
     opt = parse_opt()
     optdict = vars(opt)
+    
+    
+    optdict["weights"] = r'D:\DetectTracking\ckpts\best_cls10_0906.pt' 
     optdict["is_save_img"] = True
     optdict["is_save_video"] = True
     
     event_tracks = []
+    
+    ## 构造购物事件字典
+    evtname = Path(eventpath).stem
+    barcode = evtname.split('_')[-1] if  len(evtname.split('_'))>=2 \
+                                     and len(evtname.split('_')[-1])>=8 \
+                                     and evtname.split('_')[-1].isdigit() else ''
+    '''事件结果存储文件夹'''
+    if not savepath:
+        savepath = Path(__file__).resolve().parents[0] / "evtresult"
+    save_dir_event = Path(savepath) / evtname
+    
+
+    ShoppingDict = {"eventPath": eventpath, 
+                    "eventName": evtname,
+                    "barcode": barcode,
+                    "eventType": '',   # "input", "output", "other"
+                    "frontCamera": {}, 
+                    "backCamera": {}}
+
     for vpath in vpaths:
-        '''事件结果文件夹'''
+        '''相机事件字典构造'''
-        save_dir_event = Path(savepath) / Path(os.path.basename(eventpath))
+        CameraEvent = {"cameraType": '',   # "front", "back"
+                       "videoPath": '',
+                       "imagePaths": [],
+                       "yoloResnetTracker": [],
+                       "tracking": [],
+                       }
+        
         if isinstance(vpath, list):
-            save_dir_video = save_dir_event / Path("images")
+            CameraEvent["imagePaths"] = vpath
+            bname = os.path.basename(vpath[0])
+        if not isinstance(vpath, list):
+            CameraEvent["videoPath"] = vpath
+            bname = os.path.basename(vpath)
+        if bname.split('_')[0] == "0" or bname.find('back')>=0:
+            CameraEvent["cameraType"] = "back"
+        if  bname.split('_')[0] == "1" or bname.find('front')>=0:
+            CameraEvent["cameraType"] = "front"
+            
+        '''事件结果存储文件夹'''
+        
+        if isinstance(vpath, list):
+            save_dir_video = save_dir_event / Path("images") 
         else:
             save_dir_video = save_dir_event / Path(str(Path(vpath).stem))
-        
         if not save_dir_video.exists():
             save_dir_video.mkdir(parents=True, exist_ok=True)
         
+        
         '''Yolo + Resnet + Tracker'''
         optdict["source"] = vpath
         optdict["save_dir"] = save_dir_video        
         
+        yrtOut = yolo_resnet_tracker(**optdict)
         
-        tracksdict = yolo_resnet_tracker(**optdict)
+        CameraEvent["yoloResnetTracker"] = yrtOut
         
-        bboxes = tracksdict['TrackBoxes']
         
-        bname = os.path.basename(vpath[0]) if isinstance(vpath, list) else os.path.basename(vpath)
+        # bboxes = np.empty((0, 9), dtype = np.float32)
-        if bname.split('_')[0] == "0" or bname.find('back')>=0:
+        # for frameDict in yrtOut:            
-            vts = doBackTracks(bboxes, tracksdict)
+        #     bboxes = np.concatenate([bboxes, frameDict["tboxes"]], axis=0)
-            vts.classify()
             
+        trackerboxes = np.empty((0, 9), dtype=np.float64)
+        trackefeats = {}
+        for frameDict in yrtOut:            
+            tboxes = frameDict["tboxes"]
+            ffeats = frameDict["feats"]
+            
+            trackerboxes = np.concatenate((trackerboxes, np.array(tboxes)), axis=0)
+            for i in range(len(tboxes)):
+                fid, bid = int(tboxes[i, 7]), int(tboxes[i, 8])
+                trackefeats.update({f"{fid}_{bid}": ffeats[f"{fid}_{bid}"]})
+            
+
+        '''tracking'''
+        if CameraEvent["cameraType"] == "back":
+            vts = doBackTracks(trackerboxes, trackefeats)
+            vts.classify()
             event_tracks.append(("back", vts))
             
-        if  bname.split('_')[0] == "1" or bname.find('front')>=0:
+            CameraEvent["tracking"] = vts
-            vts = doFrontTracks(bboxes, tracksdict)
+            ShoppingDict["backCamera"] = CameraEvent
+            
+        if  CameraEvent["cameraType"] == "front":
+            vts = doFrontTracks(trackerboxes, trackefeats)
             vts.classify()
             event_tracks.append(("front", vts))
+            
+            CameraEvent["tracking"] = vts
+            ShoppingDict["frontCamera"] = CameraEvent
     
-    
+    # pklpath = save_dir_event / "ShoppingDict.pkl"
+    # with open(str(pklpath), 'wb') as f:
+    #     pickle.dump(ShoppingDict, f)    
+    pklpath = Path(savepath) / evtname+".pkl"
+    with open(str(pklpath), 'wb') as f:
+        pickle.dump(ShoppingDict, f)
+        
+
     '''轨迹显示模块'''
     illus = [None, None]
     for CamerType, vts in event_tracks:
@@ -182,14 +255,39 @@ def main():
     '''
     函数：pipeline()，遍历事件文件夹，选择类型 image 或 video,
     '''
-    parmDict = {}
+    evtdir = r"\\192.168.1.28\share\测试视频数据以及日志\各模块测试记录\比对测试\1209永辉超市测试"
-    parmDict["eventpath"] = r"\\192.168.1.28\share\测试视频数据以及日志\各模块测试记录\展厅测试\1120_展厅模型v801测试\扫A放A\20241121-144855-dce94b09-1100-43f1-92e8-33a1b538b159_6924743915848_6924743915848"
+    evtdir = Path(evtdir) 
     
-    parmDict["savepath"] = r"D:\contrast\detect"
+    parmDict = {}
+    parmDict["savepath"] = r"D:\contrast\detect\pipeline"
     parmDict["SourceType"] = "image"   # video, image
     parmDict["stdfeat_path"] = None
-
+    
-    pipeline(**parmDict)
+    k = 1
+    errEvents = []
+    for item in evtdir.iterdir():
+        if item.is_dir():
+            item = r"D:\exhibition\images\images2\images2"
+            
+            
+            parmDict["eventpath"] = item
+            
+            
+            try:
+                pipeline(**parmDict)
+            except Exception as e:
+                errEvents.append(item)
+                
+            
+        # k+=1
+        # if k==1:
+        #     break
+            
+    errfile = os.path.join(parmDict["savepath"], f'error_events.txt')
+    with open(errfile, 'w', encoding='utf-8') as f:
+        for line in errEvents:
+            f.write(line + '\n')
+            
     
 
 if __name__ == "__main__": 

track_reid.py

@@ -196,8 +196,8 @@ def yolo_resnet_tracker(
     tracker = init_trackers(tracker_yaml, bs)[0]
     
     dt = (Profile(), Profile(), Profile())
-    track_boxes = np.empty((0, 9), dtype = np.float32)
+    # trackerBoxes = np.empty((0, 9), dtype = np.float32)
-    TracksDict = {}
+    yoloResnetTracker = []
     for path, im, im0s, vid_cap, s in dataset:
         with dt[0]:
             im = torch.from_numpy(im).to(model.device)
@@ -245,24 +245,23 @@ def yolo_resnet_tracker(
                     
                 tracks[:, 7] = frameId
                     
-                
+                # trackerBoxes = np.concatenate([trackerBoxes, tracks], axis=0)
                 '''================== 1. 存储 dets/subimgs/features Dict ============='''
                 imgs, features = ReIDEncoder.inference(im0, tracks)
-                
-                # imgs, features = inference_image(im0, tracks)
-
-                # TrackerFeats = np.concatenate([TrackerFeats, features], axis=0)
-
-                imgdict = {}
-                boxdict = {}
                 featdict = {}
                 for ii, bid in enumerate(tracks[:, 8]):
-                    imgdict.update({int(bid): imgs[ii]})                    # [f"img_{int(bid)}"] = imgs[i]
+                    featdict.update({f"{int(frameId)}_{int(bid)}": features[ii, :]})            # [f"feat_{int(bid)}"] = features[i, :]
-                    boxdict.update({int(bid): tracks[ii, :]})               # [f"box_{int(bid)}"] = tracks[i, :]
+
-                    featdict.update({int(bid): features[ii, :]})            # [f"feat_{int(bid)}"] = features[i, :]
+                frameDict = {"path": path, 
-                TracksDict[f"frame_{int(frameId)}"] = {"imgs":imgdict, "boxes":boxdict, "feats":featdict}
+                             "fid": int(frameId),
-                
+                             "bboxes": det,
-                track_boxes = np.concatenate([track_boxes, tracks], axis=0)
+                             "tboxes": tracks,
+                             "imgs": imgs,
+                             "feats": featdict} 
+                yoloResnetTracker.append(frameDict)
+
+                # imgs, features = inference_image(im0, tracks)
+                # TrackerFeats = np.concatenate([TrackerFeats, features], axis=0)
 
                 '''================== 2. 提取手势位置 ==================='''
                 for *xyxy, id, conf, cls, fid, bid in reversed(tracks):
@@ -314,11 +313,8 @@ def yolo_resnet_tracker(
         # Print time (inference-only)
         LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
     
-    ## track_boxes: Array, [x1, y1, x2, y2, track_id, score, cls, frame_index, box_id]
+    
-    TracksDict.update({"TrackBoxes": track_boxes})
+    return yoloResnetTracker
-
-
-    return TracksDict
     
 
 

tracking/dotrack/dotracks.py

@@ -394,21 +394,24 @@ class Track:
 
     
 class doTracks:
-    def __init__(self, bboxes, TracksDict):
+    def __init__(self, bboxes, trackefeats):
-        '''fundamental property'''
+        '''fundamental property
+        trackefeats: dict, key 格式 "fid_bid"
+        '''
         self.bboxes = bboxes
         # self.TracksDict = TracksDict
         self.frameID = np.unique(bboxes[:, 7].astype(int))
         self.trackID = np.unique(bboxes[:, 4].astype(int))
         
         self.lboxes = self.array2list() 
-        self.lfeats = self.getfeats(TracksDict)
+        self.lfeats = self.getfeats(trackefeats)
         
         '''对 self.tracks 中的元素进行分类，将 track 归入相应列表中'''
         self.Hands = []
         self.Kids = []
         self.Static = []
-        self.Residual = []    
+        self.Residual = []
+        self.Confirmed = []
         self.DownWard = []    # subset of self.Residual
         self.UpWard = []      # subset of self.Residual
         self.FreeMove = []    # subset of self.Residual
@@ -435,15 +438,22 @@ class doTracks:
         
         return lboxes
     
-    def getfeats(self, TracksDict):
+    def getfeats(self, trackefeats):
         lboxes = self.lboxes
         lfeats = []
         for boxes in lboxes:
-            afeat = readDict(boxes, TracksDict)       
+            feats = []
-            lfeats.append(afeat)
+            for i in range(boxes.shape[0]):
+                fid, bid = int(boxes[i, 7]), int(boxes[i, 8])   
+                key = f"{int(fid)}_{int(bid)}"
+                if key in trackefeats:
+                    feats.append(trackefeats[key])
+            feats = np.asarray(feats, dtype=np.float32)
+            lfeats.append(feats)
         
         return lfeats
-        
+    
+  
 
     def similarity(self):
         nt = len(self.tracks)

tracking/dotrack/dotracks_back.py

@@ -6,6 +6,7 @@ Created on Mon Mar  4 18:36:31 2024
 """
 import numpy as np
 import cv2
+import copy
 from tracking.utils.mergetrack import track_equal_track
 from scipy.spatial.distance import cdist
 from pathlib import Path
@@ -19,9 +20,9 @@ from .track_back import backTrack
 
 
 class doBackTracks(doTracks):
-    def __init__(self, bboxes, TracksDict):
+    def __init__(self, bboxes, trackefeats):
         
-        super().__init__(bboxes, TracksDict)
+        super().__init__(bboxes, trackefeats)
         
         self.tracks = [backTrack(b, f) for b, f in zip(self.lboxes, self.lfeats)]
         
@@ -113,6 +114,22 @@ class doBackTracks(doTracks):
         #     self.merge_based_hands(htrack)
        
         self.Residual = tracks
+        self.Confirmed = self.confirm_track()
+        
+    def confirm_track(self):
+        Confirmed = None
+        mindist = 0
+        for track in self.Residual:
+            md = min(track.trajrects_wh)
+            if md > mindist:
+                mindist = copy.deepcopy(md)
+                Confirmed = copy.deepcopy(track)
+                
+        if Confirmed is not None:
+            return [Confirmed]
+
+        return []
+        
     
     # def merge_based_hands(self, htrack):
     #     gtracks = htrack.Goods
@@ -122,6 +139,8 @@ class doBackTracks(doTracks):
     #         btrack, bfious = gtracks[1]
     
     
+
+    
     def associate_with_hand(self, htrack, gtrack):
         ''' 
         迁移至基类：

tracking/dotrack/dotracks_front.py

@@ -5,6 +5,7 @@ Created on Mon Mar  4 18:38:20 2024
 @author: ym
 """
 import cv2
+import copy
 import numpy as np
 from pathlib import Path
 
@@ -16,8 +17,8 @@ from .dotracks import doTracks
 from .track_front import frontTrack
 
 class doFrontTracks(doTracks):
-    def __init__(self, bboxes, TracksDict):
+    def __init__(self, bboxes, frameDictList):
-        super().__init__(bboxes, TracksDict)
+        super().__init__(bboxes, frameDictList)
         
         # self.tracks = [frontTrack(b) for b in self.lboxes]
         self.tracks = [frontTrack(b, f) for b, f in zip(self.lboxes, self.lfeats)]
@@ -84,11 +85,24 @@ class doFrontTracks(doTracks):
         tracks = self.sub_tracks(tracks, static_tracks)            
 
         freemoved_tracks = [t for t in tracks if t.is_free_move()]
-        
         tracks = self.sub_tracks(tracks, freemoved_tracks)
-                    
+        
-
         self.Residual = tracks
+        self.Confirmed = self.confirm_track()
+        
+    def confirm_track(self):
+        Confirmed = None
+        mindist = 0
+        for track in self.Residual:
+            md = min(track.trajrects_wh)
+            if md > mindist:
+                mindist = copy.deepcopy(md)
+                Confirmed = copy.deepcopy(track)
+                
+        if Confirmed is not None:
+            return [Confirmed]
+
+        return []
   
     def associate_with_hand(self, htrack, gtrack):
         ''' 

tracking/utils/read_data.py

@@ -34,10 +34,12 @@ def find_samebox_in_array(arr, target):
     return -1
 
 
-
 def extract_data(datapath):
     '''
     0/1_track.data 数据读取
+    对于特征，需要构造两个对象：
+    (1) tracking输出 boxes，依据 (fid, bid) 找到对应的 feats, tracker_feat_dict 实现较为方便
+    (2) frameDictList 中元素为 frameDict，输出同一接口
     '''
     bboxes, ffeats = [], []
     
@@ -45,9 +47,7 @@ def extract_data(datapath):
     trackerfeats = np.empty((0, 256), dtype=np.float64)
     
     boxes, feats, tboxes, tfeats = [], [], [], []
-    
     timestamps, frameIds = [], []
-
     with open(datapath, 'r', encoding='utf-8') as lines:
         for line in lines:  
             line = line.strip()  # 去除行尾的换行符和可能的空白字符  
@@ -102,16 +102,17 @@ def extract_data(datapath):
     assert(len(bboxes)==len(ffeats)), "Error at Yolo output!"
     assert(len(trackerboxes)==len(trackerfeats)), "Error at tracker output!"
     
-    tracker_feat_dict = {}
+    ## 生成帧为单位的特征列表
-    tracker_feat_dict["timestamps"] = timestamps
+    tracker_feats = {}  
-    tracker_feat_dict["frameIds"] = frameIds
+    frmIDs = np.sort(np.unique(trackerboxes[:, 7].astype(int)))
- 
+    for fid in frmIDs:
-    for i in range(len(trackerboxes)):
+        idx = np.where(trackerboxes[:, 7] == fid)[0]
-        tid, fid, bid = int(trackerboxes[i, 4]), int(trackerboxes[i, 7]), int(trackerboxes[i, 8])
+        boxes = trackerboxes[idx, :]
-        if f"frame_{fid}" not in tracker_feat_dict:
+        feats = trackerfeats[idx, :]
-            tracker_feat_dict[f"frame_{fid}"]= {"feats": {}}
+        
-        tracker_feat_dict[f"frame_{fid}"]["feats"].update({bid: trackerfeats[i, :]})
+        for i in range(len(boxes)):
-    
+            f, b = int(boxes[i, 7]), int(boxes[i, 8])
+            tracker_feats.update({f"{f}_{b}": feats[i, :]})  
     
     boxes, trackingboxes= [], []
     tracking_flag = False    
@@ -137,18 +138,41 @@ def extract_data(datapath):
     if len(boxes): 
         trackingboxes.append(np.array(boxes))
         
-    tracking_feat_dict = {}
+    # tracking_feat_dict = {}
+    # try:
+    #     for i, boxes in enumerate(trackingboxes):
+    #         for box in boxes:
+    #             tid, fid, bid = int(box[4]), int(box[7]), int(box[8])
+    #             if f"track_{tid}" not in tracking_feat_dict:
+    #                 tracking_feat_dict[f"track_{tid}"]= {"feats": {}}
+    #             tracking_feat_dict[f"track_{tid}"]["feats"].update({f"{fid}_{bid}": tracker_feat_dict[f"frame_{fid}"]["feats"][bid]})
+    # except Exception as e:
+    #     print(f'Path: {datapath}, tracking_feat_dict can not be structured correcttly, Error: {e}') 
+    
+    # tracker_feat_dict = {}
+    # tracker_feat_dict["timestamps"] = timestamps
+    # tracker_feat_dict["frameIds"] = frameIds
+ 
+    # for i in range(len(trackerboxes)):
+    #     fid, bid = int(trackerboxes[i, 7]), int(trackerboxes[i, 8])
+    #     if f"frame_{fid}" not in tracker_feat_dict:
+    #         tracker_feat_dict[f"frame_{fid}"]= {"feats": {}}
+    #     tracker_feat_dict[f"frame_{fid}"]["feats"].update({bid: trackerfeats[i, :]})
+    
+    trackingfeats = []
     try:
         for i, boxes in enumerate(trackingboxes):
+            feats = []
             for box in boxes:
-                tid, fid, bid = int(box[4]), int(box[7]), int(box[8])
+                fid, bid = int(box[7]), int(box[8])
-                if f"track_{tid}" not in tracking_feat_dict:
+                feat = tracker_feats[f"{fid}_{bid}"]
-                    tracking_feat_dict[f"track_{tid}"]= {"feats": {}}
+                feats.append(feat)
-                tracking_feat_dict[f"track_{tid}"]["feats"].update({f"{fid}_{bid}": tracker_feat_dict[f"frame_{fid}"]["feats"][bid]})
+            trackingfeats.append(np.array(feats))
     except Exception as e:
-        print(f'Path: {datapath}, tracking_feat_dict can not be structured correcttly, Error: {e}') 
+        print(f'Path: {datapath}, trackingfeats can not be structured correcttly, Error: {e}') 
 
-    return bboxes, ffeats, trackerboxes, tracker_feat_dict, trackingboxes, tracking_feat_dict
+    # return bboxes, ffeats, trackerboxes, tracker_feat_dict, trackingboxes, trackingfeats
+    return bboxes, ffeats, trackerboxes, tracker_feats, trackingboxes, trackingfeats
 
 def read_tracking_output(filepath):
     '''
@@ -236,8 +260,6 @@ def read_returnGoods_file(filePath):
         lines = f.readlines()
         clean_lines = [line.strip().replace("'", '').replace('"', '') for line in lines]
 
-
-
         all_list = []
         split_flag, dict = False, {} 
         barcode_list, similarity_list = [], []
@@ -318,14 +340,15 @@ def read_seneor(filepath):
 def read_similar(filePath):
     SimiDict = {}
     SimiDict['one2one'] = []
+    SimiDict['one2SN'] = []
     SimiDict['one2n'] = []
     
     with open(filePath, 'r', encoding='utf-8') as f:
         lines = f.readlines()
         clean_lines = [line.strip().replace("'", '').replace('"', '') for line in lines]  
-        one2one_list, one2n_list = [], []
+        one2one_list, one2SN_list, one2n_list = [], [], []
         
-        Flag_1to1, Flag_1ton = False, False
+        Flag_1to1, Flag_1toSN, Flag_1ton = False, False, False
         for i, line in enumerate(clean_lines):
             line = line.strip()
             if line.endswith(','):  
@@ -334,18 +357,26 @@ def read_similar(filePath):
 
             if not line:
                 if len(one2one_list): SimiDict['one2one'] = one2one_list
+                if len(one2SN_list): SimiDict['one2SN'] = one2SN_list
                 if len(one2n_list): SimiDict['one2n'] = one2n_list
-                one2one_list, one2n_list = [], []
+                
-                Flag_1to1, Flag_1ton = False, False
+                
+                one2one_list, one2SN_list, one2n_list = [], [], []
+                Flag_1to1, Flag_1toSN, Flag_1ton = False, False, False
                 continue
                 
             if line.find('oneToOne')>=0:
-                Flag_1to1, Flag_1ton = True, False
+                Flag_1to1, Flag_1toSN, Flag_1ton = True, False,False
+                continue
+            if line.find('oneToSN')>=0:
+                Flag_1to1, Flag_1toSN, Flag_1ton = False, True, False
                 continue
             if line.find('oneTon')>=0:
-                Flag_1to1, Flag_1ton = False, True
+                Flag_1to1, Flag_1toSN, Flag_1ton = False, False, True
                 continue
             
+            
+            
             if Flag_1to1:
                 barcode = line.split(',')[0].strip()
                 value = line.split(',')[1].split(':')[1].strip()
@@ -353,6 +384,14 @@ def read_similar(filePath):
                 Dict['similar'] = float(value)
                 one2one_list.append(Dict)
                 continue
+            
+            if Flag_1toSN:
+                barcode = line.split(',')[0].strip()
+                value = line.split(',')[1].split(':')[1].strip()
+                Dict['barcode'] = barcode
+                Dict['similar'] = float(value)
+                one2SN_list.append(Dict)
+                continue
 
             if Flag_1ton:
                 label = line.split(':')[0].strip()