lichen/detecttracking
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

20241217

Browse Source
This commit is contained in:
王庆刚
2024-12-17 17:32:09 +08:00
parent afd033b965
commit 39f94c7bd4
11 changed files with 768 additions and 250 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
contrast/event_test.py Normal file
View File

@ -0,0 +1,69 @@
# -*- coding: utf-8 -*-
"""
Created on Mon Dec 16 18:56:18 2024
@author: ym
"""
import os
import cv2
from utils.event import ShoppingEvent
def main():
evtpaths = r"\\192.168.1.28\share\测试视频数据以及日志\算法全流程测试\202412\images"
text1 = "one2n_Error.txt"
text2 = "one2SN_Error.txt"
events = []
text = (text1, text2)
for txt in text:
txtfile = os.path.join(evtpaths, txt)
with open(txtfile, "r") as f:
lines = f.readlines()
for i, line in enumerate(lines):
line = line.strip()
if line:
fpath=os.path.join(evtpaths, line)
events.append(fpath)
events = list(set(events))
'''定义当前事件存储地址及生成相应文件件'''
resultPath = r"\\192.168.1.28\share\测试视频数据以及日志\算法全流程测试\202412\result"
for evtpath in events:
evtname = os.path.basename(evtpath)
event = ShoppingEvent(evtpath)
img_cat = event.draw_tracks()
trajpath = os.path.join(resultPath, "trajectory")
if not os.path.exists(trajpath):
os.makedirs(trajpath)
traj_imgpath = os.path.join(trajpath, evtname+".png")
cv2.imwrite(traj_imgpath, img_cat)
## 保存序列图像和轨迹子图
subimgpath = os.path.join(resultPath, f"{evtname}", "subimg")
imgspath = os.path.join(resultPath, f"{evtname}", "imgs")
if not os.path.exists(subimgpath):
os.makedirs(subimgpath)
if not os.path.exists(imgspath):
os.makedirs(imgspath)
subimgpairs = event.save_event_subimg(subimgpath)
for subimgName, subimg in subimgpairs:
spath = os.path.join(subimgpath, subimgName)
cv2.imwrite(spath, subimg)
imgpairs = event.plot_save_image(imgspath)
for imgname, img in imgpairs:
spath = os.path.join(imgspath, imgname)
cv2.imwrite(spath, img)
print(f"{evtname}")
if __name__ == "__main__":
main()

180
contrast/one2one_contrast.py
View File

@ -84,82 +84,84 @@ def ft16_to_uint8(arr_ft16):
return arr_uint8, arr_ft16_
def plot_save_image(event, savepath):
cameras = ('front', 'back')
for camera in cameras:
if camera == 'front':
boxes = event.front_trackerboxes
imgpaths = event.front_imgpaths
else:
boxes = event.back_trackerboxes
imgpaths = event.back_imgpaths
def array2list(bboxes):
'''[x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]'''
frame_ids = bboxes[:, 7].astype(int)
fID = np.unique(bboxes[:, 7].astype(int))
fboxes = []
for f_id in fID:
idx = np.where(frame_ids==f_id)[0]
box = bboxes[idx, :]
fboxes.append((f_id, box))
return fboxes
fboxes = array2list(boxes)
for fid, fbox in fboxes:
imgpath = imgpaths[int(fid-1)]
image = cv2.imread(imgpath)
annotator = Annotator(image.copy(), line_width=2)
for i, *xyxy, tid, score, cls, fid, bid in enumerate(fbox):
label = f'{int(id), int(cls)}'
if tid >=0 and cls==0:
color = colors(int(cls), True)
elif tid >=0 and cls!=0:
color = colors(int(id), True)
else:
color = colors(19, True) # 19为调色板的最后一个元素
annotator.box_label(xyxy, label, color=color)
im0 = annotator.result()
spath = os.path.join(savepath, Path(imgpath).name)
cv2.imwrite(spath, im0)
def save_event_subimg(event, savepath):
'''
功能: 保存一次购物事件的轨迹子图
9 items: barcode, type, filepath, back_imgpaths, front_imgpaths,
back_boxes, front_boxes, back_feats, front_feats,
feats_compose, feats_select
子图保存次序：先前摄、后后摄，以 k 为编号，和 "feats_compose" 中次序相同
'''
cameras = ('front', 'back')
for camera in cameras:
if camera == 'front':
boxes = event.front_boxes
imgpaths = event.front_imgpaths
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
imgpath = imgpaths[int(fid-1)]
image = cv2.imread(imgpath)
subimg = image[int(y1/2):int(y2/2), int(x1/2):int(x2/2), :]
camerType, timeTamp, _, frameID = os.path.basename(imgpath).split('.')[0].split('_')
subimgName = f"cam{camerType}_{i}_tid{int(tid)}_fid({int(fid)}, {frameID}).png"
spath = os.path.join(savepath, subimgName)
cv2.imwrite(spath, subimg)
# basename = os.path.basename(event['filepath'])
print(f"Image saved: {os.path.basename(event.eventpath)}")
# =============================================================================
# def plot_save_image(event, savepath):
# cameras = ('front', 'back')
# for camera in cameras:
# if camera == 'front':
# boxes = event.front_trackerboxes
# imgpaths = event.front_imgpaths
# else:
# boxes = event.back_trackerboxes
# imgpaths = event.back_imgpaths
#
# def array2list(bboxes):
# '''[x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]'''
# frame_ids = bboxes[:, 7].astype(int)
# fID = np.unique(bboxes[:, 7].astype(int))
# fboxes = []
# for f_id in fID:
# idx = np.where(frame_ids==f_id)[0]
# box = bboxes[idx, :]
# fboxes.append((f_id, box))
# return fboxes
#
# fboxes = array2list(boxes)
#
# for fid, fbox in fboxes:
# imgpath = imgpaths[int(fid-1)]
#
# image = cv2.imread(imgpath)
#
# annotator = Annotator(image.copy(), line_width=2)
# for i, *xyxy, tid, score, cls, fid, bid in enumerate(fbox):
# label = f'{int(id), int(cls)}'
# if tid >=0 and cls==0:
# color = colors(int(cls), True)
# elif tid >=0 and cls!=0:
# color = colors(int(id), True)
# else:
# color = colors(19, True) # 19为调色板的最后一个元素
# annotator.box_label(xyxy, label, color=color)
#
# im0 = annotator.result()
# spath = os.path.join(savepath, Path(imgpath).name)
# cv2.imwrite(spath, im0)
#
#
# def save_event_subimg(event, savepath):
# '''
# 功能: 保存一次购物事件的轨迹子图
# 9 items: barcode, type, filepath, back_imgpaths, front_imgpaths,
# back_boxes, front_boxes, back_feats, front_feats,
# feats_compose, feats_select
# 子图保存次序：先前摄、后后摄，以 k 为编号，和 "feats_compose" 中次序相同
# '''
# cameras = ('front', 'back')
# for camera in cameras:
# if camera == 'front':
# boxes = event.front_boxes
# imgpaths = event.front_imgpaths
# 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
#
# imgpath = imgpaths[int(fid-1)]
# image = cv2.imread(imgpath)
#
# subimg = image[int(y1/2):int(y2/2), int(x1/2):int(x2/2), :]
#
# camerType, timeTamp, _, frameID = os.path.basename(imgpath).split('.')[0].split('_')
# subimgName = f"cam{camerType}_{i}_tid{int(tid)}_fid({int(fid)}, {frameID}).png"
# spath = os.path.join(savepath, subimgName)
#
# cv2.imwrite(spath, subimg)
# # basename = os.path.basename(event['filepath'])
# print(f"Image saved: {os.path.basename(event.eventpath)}")
# =============================================================================
def data_precision_compare(stdfeat, evtfeat, evtMessage, save=True):
@ -296,7 +298,11 @@ def one2one_simi():
if not os.path.exists(pairpath):
os.makedirs(pairpath)
try:
save_event_subimg(event, pairpath)
subimgpairs = event.save_event_subimg(pairpath)
for subimgName, subimg in subimgpairs:
spath = os.path.join(pairpath, subimgName)
cv2.imwrite(spath, subimg)
except Exception as e:
error_event.append(evtname)
@ -304,11 +310,17 @@ def one2one_simi():
if not os.path.exists(img_path):
os.makedirs(img_path)
try:
plot_save_image(event, img_path)
imgpairs = event.plot_save_image(img_path)
for imgname, img in imgpairs:
spath = os.path.join(img_path, imgname)
cv2.imwrite(spath, img)
except Exception as e:
error_event.append(evtname)
errfile = os.path.join(subimgPath, f'error_event.txt')
with open(errfile, 'w', encoding='utf-8') as f:
for line in error_event:
@ -353,7 +365,6 @@ def one2one_simi():
matrix = 1 - cdist(stdfeat, evtfeat, 'cosine')
matrix[matrix < 0] = 0
simi_mean = np.mean(matrix)
simi_max = np.max(matrix)
stdfeatm = np.mean(stdfeat, axis=0, keepdims=True)
@ -436,7 +447,10 @@ def gen_eventdict(sourcePath, saveimg=True):
errEvents = []
k = 0
for source_path in sourcePath:
bname = os.path.basename(source_path)
evtpath, bname = os.path.split(source_path)
bname = r"20241126-135911-bdf91cf9-3e9a-426d-94e8-ddf92238e175_6923555210479"
source_path = os.path.join(evtpath, bname)
pickpath = os.path.join(eventDataPath, f"{bname}.pickle")
if os.path.isfile(pickpath): continue
@ -451,9 +465,9 @@ def gen_eventdict(sourcePath, saveimg=True):
errEvents.append(source_path)
print(e)
# k += 1
# if k==10:
# break
k += 1
if k==1:
break
errfile = os.path.join(eventDataPath, f'error_events.txt')
with open(errfile, 'w', encoding='utf-8') as f:

326
contrast/one2one_onsite.py
View File

@ -105,27 +105,56 @@ def test_compare():
plot_pr_curve(simiList)
def one2one_pr(paths):
'''
1:1
'''
paths = Path(paths)
# evtpaths = [p for p in paths.iterdir() if p.is_dir() and len(p.name.split('_'))>=2]
evtpaths = [p for p in paths.iterdir() if p.is_dir()]
evtpaths = []
for p in paths.iterdir():
condt1 = p.is_dir()
condt2 = len(p.name.split('_'))>=2
condt3 = len(p.name.split('_')[-1])>8
condt4 = p.name.split('_')[-1].isdigit()
if condt1 and condt2 and condt3 and condt4:
evtpaths.append(p)
# evtpaths = [p for p in paths.iterdir() if p.is_dir() and len(p.name.split('_'))>=2 and len(p.name.split('_')[-1])>8]
# evtpaths = [p for p in paths.iterdir() if p.is_dir()]
events, similars = [], []
##===================================== 扫A放A, 扫A放B场景
##===================================== 扫A放A, 扫A放B场景()
one2oneAA, one2oneAB = [], []
one2SNAA, one2SNAB = [], []
##===================================== 应用于展厅 1：N
##===================================== 应用于 1：1
_tp_events, _fn_events, _fp_events, _tn_events = [], [], [], []
_tp_simi, _fn_simi, _tn_simi, _fp_simi = [], [], [], []
##===================================== 应用于 1：SN
tp_events, fn_events, fp_events, tn_events = [], [], [], []
tp_simi, fn_simi, tn_simi, fp_simi = [], [], [], []
##===================================== 应用于1:n
tpevents, fnevents, fpevents, tnevents = [], [], [], []
tpsimi, fnsimi, tnsimi, fpsimi = [], [], [], []
other_event, other_simi = [], []
##===================================== barcodes总数、比对错误事件
bcdList, one2onePath = [], []
bcdList = []
one2onePath, one2onePath1 = [], []
one2SNPath, one2SNPath1 = [], []
one2nPath = []
errorFile_one2one, errorFile_one2SN, errorFile_one2n = [], [], []
for path in evtpaths:
barcode = path.stem.split('_')[-1]
datapath = path.joinpath('process.data')
@ -140,35 +169,74 @@ def one2one_pr(paths):
except Exception as e:
print(f"{path.stem}, Error: {e}")
'''放入为 1:1，相似度取最大值；取出时为 1:SN, 相似度取均值'''
one2one = SimiDict['one2one']
one2SN = SimiDict['one2SN']
one2n = SimiDict['one2n']
'''================== 0. 1:1 ==================='''
barcodes, similars = [], []
for dt in one2one:
one2onePath.append((path.stem))
if dt['similar']==0:
one2onePath1.append((path.stem))
continue
barcodes.append(dt['barcode'])
similars.append(dt['similar'])
if len(barcodes)!=len(similars) or len(barcodes)==0:
continue
##===================================== 扫A放A, 扫A放B场景
if len(barcodes)==len(similars) and len(barcodes)!=0:
## 扫A放A, 扫A放B场景
simAA = [similars[i] for i in range(len(barcodes)) if barcodes[i]==barcode]
simAB = [similars[i] for i in range(len(barcodes)) if barcodes[i]!=barcode]
one2oneAA.extend(simAA)
one2oneAB.extend(simAB)
one2onePath.append(path.stem)
##===================================== 以下应用适用于展厅 1：N
## 相似度排序，barcode相等且排名第一为TP，适用于多的barcode相似度比较
max_idx = similars.index(max(similars))
max_sim = similars[max_idx]
# max_bcd = barcodes[max_idx]
if path.stem.find('100321')>0:
print("hhh")
for i in range(len(one2one)):
bcd, simi = barcodes[i], similars[i]
if bcd==barcode and simi==max_sim:
_tp_simi.append(simi)
_tp_events.append(path.stem)
elif bcd==barcode and simi!=max_sim:
_fn_simi.append(simi)
_fn_events.append(path.stem)
elif bcd!=barcode and simi!=max_sim:
_tn_simi.append(simi)
_tn_events.append(path.stem)
elif bcd!=barcode and simi==max_sim and barcode in barcodes:
_fp_simi.append(simi)
_fp_events.append(path.stem)
else:
errorFile_one2one.append(path.stem)
'''================== 2. 取出场景下的 1 : Small N ==================='''
barcodes, similars = [], []
for dt in one2SN:
barcodes.append(dt['barcode'])
similars.append(dt['similar'])
if len(barcodes)==len(similars) and len(barcodes)!=0:
## 扫A放A, 扫A放B场景
simAA = [similars[i] for i in range(len(barcodes)) if barcodes[i]==barcode]
simAB = [similars[i] for i in range(len(barcodes)) if barcodes[i]!=barcode]
one2SNAA.extend(simAA)
one2SNAB.extend(simAB)
one2SNPath.append(path.stem)
if len(simAA)==0:
one2SNPath1.append(path.stem)
## 相似度排序，barcode相等且排名第一为TP，适用于多的barcode相似度比较
max_idx = similars.index(max(similars))
max_sim = similars[max_idx]
# max_bcd = barcodes[max_idx]
for i in range(len(one2SN)):
bcd, simi = barcodes[i], similars[i]
if bcd==barcode and simi==max_sim:
tp_simi.append(simi)
@ -179,12 +247,15 @@ def one2one_pr(paths):
elif bcd!=barcode and simi!=max_sim:
tn_simi.append(simi)
tn_events.append(path.stem)
else:
elif bcd!=barcode and simi==max_sim and barcode in barcodes:
fp_simi.append(simi)
fp_events.append(path.stem)
else:
errorFile_one2SN.append(path.stem)
##===================================== 以下应用适用1:n
'''===================== 3. 取出场景下的 1:n ========================'''
events, evt_barcodes, evt_similars, evt_types = [], [], [], []
for dt in one2n:
events.append(dt["event"])
@ -192,9 +263,10 @@ def one2one_pr(paths):
evt_similars.append(dt["similar"])
evt_types.append(dt["type"])
if len(events)!=len(evt_barcodes) or len(evt_barcodes)!=len(evt_similars) \
or len(evt_barcodes)!=len(evt_similars) or len(events)==0: continue
if len(events)==len(evt_barcodes) and len(evt_barcodes)==len(evt_similars) \
and len(evt_similars)==len(evt_types) and len(events)>0:
one2nPath.append(path.stem)
maxsim = evt_similars[evt_similars.index(max(evt_similars))]
for i in range(len(one2n)):
bcd, simi = evt_barcodes[i], evt_similars[i]
@ -208,90 +280,102 @@ def one2one_pr(paths):
elif bcd!=barcode and simi!=maxsim:
tnsimi.append(simi)
tnevents.append(path.stem)
elif bcd!=barcode and simi==maxsim:
elif bcd!=barcode and simi==maxsim and barcode in evt_barcodes:
fpsimi.append(simi)
fpevents.append(path.stem)
else:
other_simi.append(simi)
other_event.append(path.stem)
errorFile_one2n.append(path.stem)
'''命名规则:
1:1 1:n 1:N
TP_ TP TPX
PPrecise_ PPrecise PPreciseX
1:1 (max) 1:1 (max) 1:n 1:N
_TP TP_ TP TPX
_PPrecise PPrecise_ PPrecise PPreciseX
tpsimi tp_simi
'''
''' 1:1 数据存储'''
''' 1:1 数据存储, 相似度计算方式：最大值、均值'''
_PPrecise, _PRecall = [], []
_NPrecise, _NRecall = [], []
PPrecise_, PRecall_ = [], []
NPrecise_, NRecall_ = [], []
''' 1:n 数据存储'''
PPrecise, PRecall = [], []
NPrecise, NRecall = [], []
''' 展厅 1:N 数据存储'''
''' 1:SN 数据存储，需根据相似度排序'''
PPreciseX, PRecallX = [], []
NPreciseX, NRecallX = [], []
''' 1:n 数据存储，需根据相似度排序'''
PPrecise, PRecall = [], []
NPrecise, NRecall = [], []
Thresh = np.linspace(-0.2, 1, 100)
for th in Thresh:
'''============================= 1:1'''
TP_ = sum(np.array(one2oneAA) >= th)
FP_ = sum(np.array(one2oneAB) >= th)
FN_ = sum(np.array(one2oneAA) < th)
TN_ = sum(np.array(one2oneAB) < th)
'''(Precise, Recall) 计算方式, 若 1:1 与 1:SN 相似度选择方式相同，则可以合并'''
'''===================================== 1:1 最大值'''
_TP = sum(np.array(one2oneAA) >= th)
_FP = sum(np.array(one2oneAB) >= th)
_FN = sum(np.array(one2oneAA) < th)
_TN = sum(np.array(one2oneAB) < th)
_PPrecise.append(_TP/(_TP+_FP+1e-6))
_PRecall.append(_TP/(len(one2oneAA)+1e-6))
_NPrecise.append(_TN/(_TN+_FN+1e-6))
_NRecall.append(_TN/(len(one2oneAB)+1e-6))
'''===================================== 1:SN 均值'''
TP_ = sum(np.array(one2SNAA) >= th)
FP_ = sum(np.array(one2SNAB) >= th)
FN_ = sum(np.array(one2SNAA) < th)
TN_ = sum(np.array(one2SNAB) < th)
PPrecise_.append(TP_/(TP_+FP_+1e-6))
# PRecall_.append(TP_/(TP_+FN_+1e-6))
PRecall_.append(TP_/(len(one2oneAA)+1e-6))
PRecall_.append(TP_/(len(one2SNAA)+1e-6))
NPrecise_.append(TN_/(TN_+FN_+1e-6))
# NRecall_.append(TN_/(TN_+FP_+1e-6))
NRecall_.append(TN_/(len(one2oneAB)+1e-6))
NRecall_.append(TN_/(len(one2SNAB)+1e-6))
'''============================= 1:n'''
TP = sum(np.array(tpsimi) >= th)
FP = sum(np.array(fpsimi) >= th)
FN = sum(np.array(fnsimi) < th)
TN = sum(np.array(tnsimi) < th)
PPrecise.append(TP/(TP+FP+1e-6))
# PRecall.append(TP/(TP+FN+1e-6))
PRecall.append(TP/(len(tpsimi)+len(fnsimi)+1e-6))
NPrecise.append(TN/(TN+FN+1e-6))
# NRecall.append(TN/(TN+FP+1e-6))
NRecall.append(TN/(len(tnsimi)+len(fpsimi)+1e-6))
'''============================= 1:N 展厅'''
'''适用于 (Precise, Recall) 计算方式：多个相似度计算并排序，barcode相等且排名第一为 TP '''
'''===================================== 1:SN '''
TPX = sum(np.array(tp_simi) >= th)
FPX = sum(np.array(fp_simi) >= th)
FNX = sum(np.array(fn_simi) < th)
TNX = sum(np.array(tn_simi) < th)
PPreciseX.append(TPX/(TPX+FPX+1e-6))
# PRecallX.append(TPX/(TPX+FNX+1e-6))
PRecallX.append(TPX/(len(tp_simi)+len(fn_simi)+1e-6))
NPreciseX.append(TNX/(TNX+FNX+1e-6))
# NRecallX.append(TNX/(TNX+FPX+1e-6))
NRecallX.append(TNX/(len(tn_simi)+len(fp_simi)+1e-6))
'''============================= 1:1 曲线'''
'''===================================== 1:n'''
TP = sum(np.array(tpsimi) >= th)
FP = sum(np.array(fpsimi) >= th)
FN = sum(np.array(fnsimi) < th)
TN = sum(np.array(tnsimi) < th)
PPrecise.append(TP/(TP+FP+1e-6))
PRecall.append(TP/(len(tpsimi)+len(fnsimi)+1e-6))
NPrecise.append(TN/(TN+FN+1e-6))
NRecall.append(TN/(len(tnsimi)+len(fpsimi)+1e-6))
'''1. ============================= 1:1 最大值方案 曲线'''
fig, ax = plt.subplots()
ax.plot(Thresh, PPrecise_, 'r', label='Precise_Pos: TP/TPFP')
ax.plot(Thresh, PRecall_, 'b', label='Recall_Pos: TP/TPFN')
ax.plot(Thresh, NPrecise_, 'g', label='Precise_Neg: TN/TNFP')
ax.plot(Thresh, NRecall_, 'c', label='Recall_Neg: TN/TNFN')
ax.plot(Thresh, _PPrecise, 'r', label='Precise_Pos: TP/TPFP')
ax.plot(Thresh, _PRecall, 'b', label='Recall_Pos: TP/TPFN')
ax.plot(Thresh, _NPrecise, 'g', label='Precise_Neg: TN/TNFP')
ax.plot(Thresh, _NRecall, 'c', label='Recall_Neg: TN/TNFN')
ax.set_xlim([0, 1])
ax.set_ylim([0, 1])
ax.grid(True)
ax.set_title('1:1 Precise & Recall')
ax.set_xlabel(f"Event Num: {len(one2oneAA)}")
ax.set_xlabel(f"Event Num: {len(one2oneAA)+len(one2oneAB)}")
ax.legend()
plt.show()
'''============================= 1:1 直方图'''
## ============================= 1:1 最大值方案 直方图'''
fig, axes = plt.subplots(2, 1)
axes[0].hist(np.array(one2oneAA), bins=60, edgecolor='black')
axes[0].set_xlim([-0.2, 1])
@ -301,7 +385,63 @@ def one2one_pr(paths):
axes[1].set_title('BB')
plt.show()
'''============================= 1:n 曲线'''
'''2. ============================= 1:1 均值方案 曲线'''
fig, ax = plt.subplots()
ax.plot(Thresh, PPrecise_, 'r', label='Precise_Pos: TP/TPFP')
ax.plot(Thresh, PRecall_, 'b', label='Recall_Pos: TP/TPFN')
ax.plot(Thresh, NPrecise_, 'g', label='Precise_Neg: TN/TNFP')
ax.plot(Thresh, NRecall_, 'c', label='Recall_Neg: TN/TNFN')
ax.set_xlim([0, 1])
ax.set_ylim([0, 1])
ax.grid(True)
ax.set_title('1:1 Precise & Recall')
ax.set_xlabel(f"Event Num: {len(one2SNAA)}")
ax.legend()
plt.show()
## ============================= 1:1 均值方案 直方图'''
fig, axes = plt.subplots(2, 1)
axes[0].hist(np.array(one2SNAA), bins=60, edgecolor='black')
axes[0].set_xlim([-0.2, 1])
axes[0].set_title('AA')
axes[1].hist(np.array(one2SNAB), bins=60, edgecolor='black')
axes[1].set_xlim([-0.2, 1])
axes[1].set_title('BB')
plt.show()
''''3. ============================= 1:SN 曲线'''
fig, ax = plt.subplots()
ax.plot(Thresh, PPreciseX, 'r', label='Precise_Pos: TP/TPFP')
ax.plot(Thresh, PRecallX, 'b', label='Recall_Pos: TP/TPFN')
ax.plot(Thresh, NPreciseX, 'g', label='Precise_Neg: TN/TNFP')
ax.plot(Thresh, NRecallX, 'c', label='Recall_Neg: TN/TNFN')
ax.set_xlim([0, 1])
ax.set_ylim([0, 1])
ax.grid(True)
ax.set_title('1:SN Precise & Recall')
ax.set_xlabel(f"Event Num: {len(one2SNAA)}")
ax.legend()
plt.show()
## ============================= 1:N 展厅 直方图'''
fig, axes = plt.subplots(2, 2)
axes[0, 0].hist(tp_simi, bins=60, edgecolor='black')
axes[0, 0].set_xlim([-0.2, 1])
axes[0, 0].set_title('TP')
axes[0, 1].hist(fp_simi, bins=60, edgecolor='black')
axes[0, 1].set_xlim([-0.2, 1])
axes[0, 1].set_title('FP')
axes[1, 0].hist(tn_simi, bins=60, edgecolor='black')
axes[1, 0].set_xlim([-0.2, 1])
axes[1, 0].set_title('TN')
axes[1, 1].hist(fn_simi, bins=60, edgecolor='black')
axes[1, 1].set_xlim([-0.2, 1])
axes[1, 1].set_title('FN')
plt.show()
'''4. ============================= 1:n 曲线,'''
fig, ax = plt.subplots()
ax.plot(Thresh, PPrecise, 'r', label='Precise_Pos: TP/TPFP')
ax.plot(Thresh, PRecall, 'b', label='Recall_Pos: TP/TPFN')
@ -311,11 +451,10 @@ def one2one_pr(paths):
ax.set_ylim([0, 1])
ax.grid(True)
ax.set_title('1:n Precise & Recall')
ax.set_xlabel(f"Event Num: {len(one2oneAA)}")
ax.set_xlabel(f"Event Num: {len(tpsimi)+len(fnsimi)}")
ax.legend()
plt.show()
'''============================= 1:n 直方图'''
## ============================= 1:n 直方图'''
fig, axes = plt.subplots(2, 2)
axes[0, 0].hist(tpsimi, bins=60, edgecolor='black')
axes[0, 0].set_xlim([-0.2, 1])
@ -332,35 +471,18 @@ def one2one_pr(paths):
plt.show()
'''============================= 1:N 展厅 曲线'''
fig, ax = plt.subplots()
ax.plot(Thresh, PPreciseX, 'r', label='Precise_Pos: TP/TPFP')
ax.plot(Thresh, PRecallX, 'b', label='Recall_Pos: TP/TPFN')
ax.plot(Thresh, NPreciseX, 'g', label='Precise_Neg: TN/TNFP')
ax.plot(Thresh, NRecallX, 'c', label='Recall_Neg: TN/TNFN')
ax.set_xlim([0, 1])
ax.set_ylim([0, 1])
ax.grid(True)
ax.set_title('1:N Precise & Recall')
ax.set_xlabel(f"Event Num: {len(one2oneAA)}")
ax.legend()
plt.show()
fpsnErrFile = str(paths.joinpath("one2SN_Error.txt"))
with open(fpsnErrFile, "w") as file:
for item in fp_events:
file.write(item + "\n")
fpErrFile = str(paths.joinpath("one2n_Error.txt"))
with open(fpErrFile, "w") as file:
for item in fpevents:
file.write(item + "\n")
'''============================= 1:N 展厅 直方图'''
fig, axes = plt.subplots(2, 2)
axes[0, 0].hist(tp_simi, bins=60, edgecolor='black')
axes[0, 0].set_xlim([-0.2, 1])
axes[0, 0].set_title('TP')
axes[0, 1].hist(fp_simi, bins=60, edgecolor='black')
axes[0, 1].set_xlim([-0.2, 1])
axes[0, 1].set_title('FP')
axes[1, 0].hist(tn_simi, bins=60, edgecolor='black')
axes[1, 0].set_xlim([-0.2, 1])
axes[1, 0].set_title('TN')
axes[1, 1].hist(fn_simi, bins=60, edgecolor='black')
axes[1, 1].set_xlim([-0.2, 1])
axes[1, 1].set_title('FN')
plt.show()
# bcdSet = set(bcdList)
# one2nErrFile = str(paths.joinpath("one_2_Small_n_Error.txt"))
@ -378,7 +500,7 @@ def one2one_pr(paths):
if __name__ == "__main__":
evtpaths = 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\1129_展厅模型v801测试组测试"
evtpaths = r"\\192.168.1.28\share\测试视频数据以及日志\算法全流程测试\202412\images"
one2one_pr(evtpaths)

BIN
contrast/utils/__pycache__/event.cpython-39.pyc
View File

Binary file not shown.

236
contrast/utils/event.py
View File

@ -5,17 +5,43 @@ Created on Tue Nov 26 17:35:05 2024
@author: ym
"""
import os
import cv2
import pickle
import numpy as np
from pathlib import Path
import sys
sys.path.append(r"D:\DetectTracking")
from tracking.utils.plotting import Annotator, colors
from tracking.utils.drawtracks import drawTrack
from tracking.utils.read_data import extract_data, read_tracking_output, read_similar
IMG_FORMAT = ['.bmp', '.jpg', '.jpeg', '.png']
VID_FORMAT = ['.mp4', '.avi']
def array2list(bboxes):
'''
将 bboxes 变换为 track 列表
bboxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
Return：
lboxes：列表，列表中元素具有同一 track_id，x1y1x2y2 格式
[x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
'''
lboxes = []
if len(bboxes)==0:
return []
trackID = np.unique(bboxes[:, 4].astype(int))
track_ids = bboxes[:, 4].astype(int)
for t_id in trackID:
idx = np.where(track_ids == t_id)[0]
box = bboxes[idx, :]
lboxes.append(box)
return lboxes
class ShoppingEvent:
def __init__(self, eventpath, stype="data"):
'''stype: str, 'pickle', 'data', '''
@ -253,14 +279,218 @@ class ShoppingEvent:
elif len(self.back_feats):
self.feats_select = self.back_feats
def main():
pklpath = r"D:\DetectTracking\evtresult\images2\ShoppingDict.pkl"
def plot_save_image(self, savepath):
evt = ShoppingEvent(pklpath, stype='pickle')
def array2list(bboxes):
'''[x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]'''
frame_ids = bboxes[:, 7].astype(int)
fID = np.unique(bboxes[:, 7].astype(int))
fboxes = []
for f_id in fID:
idx = np.where(frame_ids==f_id)[0]
box = bboxes[idx, :]
fboxes.append((f_id, box))
return fboxes
imgpairs = []
cameras = ('front', 'back')
for camera in cameras:
if camera == 'front':
boxes = self.front_trackerboxes
imgpaths = self.front_imgpaths
else:
boxes = self.back_trackerboxes
imgpaths = self.back_imgpaths
fboxes = array2list(boxes)
for fid, fbox in fboxes:
imgpath = imgpaths[int(fid-1)]
image = cv2.imread(imgpath)
annotator = Annotator(image.copy(), line_width=2)
for i, box in enumerate(fbox):
x1, y1, x2, y2, tid, score, cls, fid, bid = box
label = f'{int(tid), int(cls)}'
if tid >=0 and cls==0:
color = colors(int(cls), True)
elif tid >=0 and cls!=0:
color = colors(int(tid), True)
else:
color = colors(19, True) # 19为调色板的最后一个元素
xyxy = (x1/2, y1/2, x2/2, y2/2)
annotator.box_label(xyxy, label, color=color)
im0 = annotator.result()
imgpairs.append((Path(imgpath).name, im0))
# spath = os.path.join(savepath, Path(imgpath).name)
# cv2.imwrite(spath, im0)
return imgpairs
def save_event_subimg(self, savepath):
'''
功能: 保存一次购物事件的轨迹子图
9 items: barcode, type, filepath, back_imgpaths, front_imgpaths,
back_boxes, front_boxes, back_feats, front_feats,
feats_compose, feats_select
子图保存次序：先前摄、后后摄，以 k 为编号，和 "feats_compose" 中次序相同
'''
imgpairs = []
cameras = ('front', 'back')
for camera in cameras:
boxes = np.empty((0, 9), dtype=np.float64) ##和类doTracks兼容
if camera == 'front':
for b in self.front_boxes:
boxes = np.concatenate((boxes, b), axis=0)
imgpaths = self.front_imgpaths
else:
for b in self.back_boxes:
boxes = np.concatenate((boxes, b), axis=0)
imgpaths = self.back_imgpaths
for i, box in enumerate(boxes):
x1, y1, x2, y2, tid, score, cls, fid, bid = box
imgpath = imgpaths[int(fid-1)]
image = cv2.imread(imgpath)
subimg = image[int(y1/2):int(y2/2), int(x1/2):int(x2/2), :]
camerType, timeTamp, _, frameID = os.path.basename(imgpath).split('.')[0].split('_')
subimgName = f"cam{camerType}_{i}_tid{int(tid)}_fid({int(fid)}, {frameID}).png"
imgpairs.append((subimgName, subimg))
# spath = os.path.join(savepath, subimgName)
# cv2.imwrite(spath, subimg)
return imgpairs
# basename = os.path.basename(event['filepath'])
print(f"Image saved: {os.path.basename(self.eventpath)}")
def draw_tracks(self):
front_edge = cv2.imread(r"D:\DetectTracking\tracking\shopcart\cart_tempt\board_ftmp_line.png")
back_edge = cv2.imread(r"D:\DetectTracking\tracking\shopcart\cart_tempt\edgeline.png")
front_trackerboxes = array2list(self.front_trackerboxes)
back_trackerboxes = array2list(self.back_trackerboxes)
# img1, img2 = edgeline.copy(), edgeline.copy()
img1 = drawTrack(front_trackerboxes, front_edge.copy())
img2 = drawTrack(self.front_trackingboxes, front_edge.copy())
img3 = drawTrack(back_trackerboxes, back_edge.copy())
img4 = drawTrack(self.back_trackingboxes, back_edge.copy())
imgcat1 = np.concatenate((img1, img2), axis = 1)
H, W = imgcat1.shape[:2]
cv2.line(imgcat1, (int(W/2), 0), (int(W/2), H), (128, 255, 128), 2)
imgcat2 = np.concatenate((img3, img4), axis = 1)
H, W = imgcat2.shape[:2]
cv2.line(imgcat2, (int(W/2), 0), (int(W/2), H), (128, 255, 128), 2)
illus = [imgcat1, imgcat2]
if len(illus):
img_cat = np.concatenate(illus, axis = 1)
if len(illus)==2:
H, W = img_cat.shape[:2]
cv2.line(img_cat, (int(W/2), 0), (int(W/2), int(H)), (128, 128, 255), 3)
return img_cat
def main():
# pklpath = r"D:\DetectTracking\evtresult\images2\ShoppingDict.pkl"
# evt = ShoppingEvent(pklpath, stype='pickle')
evtpath = r"\\192.168.1.28\share\测试视频数据以及日志\算法全流程测试\202412\images\20241209-160248-08edd5f6-1806-45ad-babf-7a4dd11cea60_6973226721445"
evt = ShoppingEvent(evtpath, stype='data')
img_cat = evt.draw_tracks()
cv2.imwrite("a.png", img_cat)
# =============================================================================
# def main1():
# evtpaths = r"\\192.168.1.28\share\测试视频数据以及日志\算法全流程测试\202412\images"
# text1 = "one2n_Error.txt"
# text2 = "one2SN_Error.txt"
# events = []
# text = (text1, text2)
# for txt in text:
# txtfile = os.path.join(evtpaths, txt)
# with open(txtfile, "r") as f:
# lines = f.readlines()
# for i, line in enumerate(lines):
# line = line.strip()
# if line:
# fpath=os.path.join(evtpaths, line)
# events.append(fpath)
#
#
# events = list(set(events))
#
# '''定义当前事件存储地址及生成相应文件件'''
# resultPath = r"\\192.168.1.28\share\测试视频数据以及日志\算法全流程测试\202412\result"
# # eventDataPath = os.path.join(resultPath, "evtobjs")
# # subimgPath = os.path.join(resultPath, "subimgs")
# # imagePath = os.path.join(resultPath, "image")
#
# # if not os.path.exists(eventDataPath):
# # os.makedirs(eventDataPath)
# # if not os.path.exists(subimgPath):
# # os.makedirs(subimgPath)
# # if not os.path.exists(imagePath):
# # os.makedirs(imagePath)
#
#
# for evtpath in events:
# event = ShoppingEvent(evtpath)
#
#
# evtname = os.path.basename(evtpath)
# subimgpath = os.path.join(resultPath, f"{evtname}", "subimg")
# imgspath = os.path.join(resultPath, f"{evtname}", "imgs")
# if not os.path.exists(subimgpath):
# os.makedirs(subimgpath)
# if not os.path.exists(imgspath):
# os.makedirs(imgspath)
#
# subimgpairs = event.save_event_subimg(subimgpath)
#
# for subimgName, subimg in subimgpairs:
# spath = os.path.join(subimgpath, subimgName)
# cv2.imwrite(spath, subimg)
#
# imgpairs = event.plot_save_image(imgspath)
# for imgname, img in imgpairs:
# spath = os.path.join(imgspath, imgname)
# cv2.imwrite(spath, img)
#
# =============================================================================
if __name__ == "__main__":
main()
# main1()

36
pipeline.py
View File

@ -77,8 +77,13 @@ def pipeline(
'''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
pickpath = Path(savepath)/"pickfile"
if not pickpath.exists():
pickpath.mkdir(parents=True, exist_ok=True)
ShoppingDict = {"eventPath": eventpath,
"eventName": evtname,
@ -117,6 +122,8 @@ def pipeline(
save_dir_video.mkdir(parents=True, exist_ok=True)
'''Yolo + Resnet + Tracker'''
optdict["source"] = vpath
optdict["save_dir"] = save_dir_video
@ -162,14 +169,16 @@ def pipeline(
# 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:
pf_path = Path(pickpath) / Path(str(evtname)+".pkl")
with open(str(pf_path), 'wb') as f:
pickle.dump(ShoppingDict, f)
'''轨迹显示模块'''
illus = [None, None]
for CamerType, vts in event_tracks:
if len(vts.tracks)==0: continue
if CamerType == 'front':
edgeline = cv2.imread("./tracking/shopcart/cart_tempt/board_ftmp_line.png")
@ -255,7 +264,7 @@ def main():
'''
函数：pipeline()，遍历事件文件夹，选择类型 image 或 video,
'''
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"
evtdir = r"\\192.168.1.28\share\测试视频数据以及日志\算法全流程测试\202412\images"
evtdir = Path(evtdir)
parmDict = {}
@ -263,25 +272,22 @@ def main():
parmDict["SourceType"] = "image" # video, image
parmDict["stdfeat_path"] = None
k = 1
k = 0
errEvents = []
for item in evtdir.iterdir():
if item.is_dir():
item = r"D:\exhibition\images\images2\images2"
# item = r"D:\exhibition\images\images2\images2"
parmDict["eventpath"] = item
try:
pipeline(**parmDict)
except Exception as e:
errEvents.append(item)
# try:
# pipeline(**parmDict)
# except Exception as e:
# errEvents.append(str(item))
# k+=1
# if k==1:
# break
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:

73
shopper.py Normal file
View File

@ -0,0 +1,73 @@
# -*- coding: utf-8 -*-
"""
Created on Tue Dec 17 10:45:10 2024
@author: ym
"""
import os
import numpy as np
import pandas as pd
from pathlib import Path
xpath = r"\\192.168.1.28\share\模型\部署相关\永辉金源广场店商品信息.xlsx"
xroot, xfilename = os.path.split(xpath)
xfile, ext = os.path.splitext(xfilename)
spath = os.path.join(xroot, xfile+'_diff.xlsx')
df = pd.read_excel(xpath)
barcodes = df["商品条码"].tolist()
names_caojq = df["商品名称"].tolist()
stdpath = r"\\192.168.1.28\share\数据\已完成数据\比对数据\barcode\all_totalBarocde\totalBarcode"
stdpath = Path(stdpath)
stdBarcodes = [int(f.stem) for f in stdpath.iterdir() if f.is_dir() and f.stem.isdigit() and len(f.stem)>=8]
barcodes_s = set(barcodes)
stdBarcodes_s = set(stdBarcodes)
A = barcodes_s - stdBarcodes_s
record_bcd, record_name = [], []
for bcd in A:
if np.isnan(bcd): continue
try:
index = barcodes.index(bcd)
name = names_caojq[index]
record_bcd.append(bcd)
record_name.append(name)
except ValueError:
print(f"元素 {bcd} 不在列表中")
df_save = pd.DataFrame({
'商品条码': record_bcd,
'商品名称': record_name
})
df.to_excel(spath, index=False)
print("Done")

BIN
tracking/utils/__pycache__/drawtracks.cpython-39.pyc
View File

Binary file not shown.

BIN
tracking/utils/__pycache__/read_data.cpython-39.pyc
View File

Binary file not shown.

3
tracking/utils/drawtracks.py
View File

@ -364,6 +364,9 @@ def drawTrack(tracks, img):
annotator = TrackAnnotator(img, line_width=2)
for track in tracks:
if isinstance(track, np.ndarray):
annotator.plotting_track(track)
else:
annotator.plotting_track(track.boxes)
img = annotator.result()

11
tracking/utils/read_data.py
View File

@ -202,9 +202,9 @@ def read_tracking_output(filepath):
if len(feats) != len(boxes):
return np.array([]), np.array([])
return [np.array([])], [np.array([])]
return np.array(boxes), np.array(feats)
return [np.array(boxes)], [np.array(feats)]
def read_deletedBarcode_file(filePath):
@ -408,6 +408,7 @@ def read_similar(filePath):
if len(one2one_list): SimiDict['one2one'] = one2one_list
if len(one2n_list): SimiDict['one2n'] = one2n_list
if len(one2SN_list): SimiDict['one2SN'] = one2SN_list
return SimiDict
@ -532,13 +533,12 @@ def main():
break
def main1():
fpath = r'\\192.168.1.28\share\测试_202406\1101\images\20241101-140456-44dc75b5-c406-4cb2-8317-c4660bb727a3_6922130101355_6922130101355\process.data'
simidct = read_one2one_simi(fpath)
fpath = 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\20241209-155924-117e1941-70f8-4287-8de1-4866868548a6_6926475209967\process.data'
simidct = read_similar(fpath)
print(simidct)
if __name__ == "__main__":
# main()
main1()
@ -552,3 +552,4 @@ if __name__ == "__main__":