modify dotrack module
This commit is contained in:
王庆刚
1
.gitignore
vendored
1
.gitignore
vendored
@ -54,6 +54,7 @@ VOC/
|
||||
# Neural Network weights -----------------------------------------------------------------------------------------------
|
||||
*.weights
|
||||
*.pt
|
||||
*.pth
|
||||
*.pb
|
||||
*.onnx
|
||||
*.engine
|
||||
|
||||
218
featureVal.py
Normal file
218
featureVal.py
Normal file
@ -0,0 +1,218 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Created on Fri May 31 14:50:21 2024
|
||||
|
||||
@author: ym
|
||||
"""
|
||||
import cv2
|
||||
import numpy as np
|
||||
import torch
|
||||
from scipy.spatial.distance import cdist
|
||||
from tracking.trackers.reid.config import config as ReIDConfig
|
||||
from tracking.trackers.reid.reid_interface import ReIDInterface
|
||||
ReIDEncoder = ReIDInterface(ReIDConfig)
|
||||
|
||||
def read_data_file(datapath):
|
||||
|
||||
with open(datapath, 'r') as file:
|
||||
lines = file.readlines()
|
||||
Videos = []
|
||||
FrameBoxes, FrameFeats = [], []
|
||||
boxes, feats = [], []
|
||||
|
||||
bboxes, ffeats = [], []
|
||||
timestamp = []
|
||||
t1 = None
|
||||
for line in lines:
|
||||
if line.find('CameraId') >= 0:
|
||||
t = int(line.split(',')[1].split(':')[1])
|
||||
timestamp.append(t)
|
||||
|
||||
if len(boxes) and len(feats):
|
||||
FrameBoxes.append(np.array(boxes, dtype = np.float32))
|
||||
FrameFeats.append(np.array(feats, dtype = np.float32))
|
||||
|
||||
boxes, feats = [], []
|
||||
|
||||
if t1 and t - t1 > 1e4:
|
||||
Videos.append((FrameBoxes, FrameFeats))
|
||||
FrameBoxes, FrameFeats = [], []
|
||||
t1 = int(line.split(',')[1].split(':')[1])
|
||||
|
||||
if line.find('box') >= 0:
|
||||
box = line.split(':', )[1].split(',')[:-1]
|
||||
boxes.append(box)
|
||||
bboxes.append(boxes)
|
||||
|
||||
|
||||
if line.find('feat') >= 0:
|
||||
feat = line.split(':', )[1].split(',')[:-1]
|
||||
feats.append(feat)
|
||||
ffeats.append(feat)
|
||||
|
||||
|
||||
|
||||
|
||||
FrameBoxes.append(np.array(boxes, dtype = np.float32))
|
||||
FrameFeats.append(np.array(feats, dtype = np.float32))
|
||||
Videos.append((FrameBoxes, FrameFeats))
|
||||
|
||||
TimeStamp = np.array(timestamp, dtype = np.float32)
|
||||
DimesDiff = np.diff((timestamp))
|
||||
|
||||
return Videos
|
||||
|
||||
def inference_image(image, detections):
|
||||
H, W, _ = np.shape(image)
|
||||
imgs = []
|
||||
batch_patches = []
|
||||
patches = []
|
||||
for d in range(np.size(detections, 0)):
|
||||
tlbr = detections[d, :4].astype(np.int_)
|
||||
tlbr[0] = max(0, tlbr[0])
|
||||
tlbr[1] = max(0, tlbr[1])
|
||||
tlbr[2] = min(W - 1, tlbr[2])
|
||||
tlbr[3] = min(H - 1, tlbr[3])
|
||||
img1 = image[tlbr[1]:tlbr[3], tlbr[0]:tlbr[2], :]
|
||||
|
||||
img = img1[:, :, ::-1].copy() # the model expects RGB inputs
|
||||
patch = ReIDEncoder.transform(img)
|
||||
|
||||
imgs.append(img1)
|
||||
# patch = patch.to(device=self.device).half()
|
||||
if str(ReIDEncoder.device) != "cpu":
|
||||
patch = patch.to(device=ReIDEncoder.device).half()
|
||||
else:
|
||||
patch = patch.to(device=ReIDEncoder.device)
|
||||
|
||||
patches.append(patch)
|
||||
if (d + 1) % ReIDEncoder.batch_size == 0:
|
||||
patches = torch.stack(patches, dim=0)
|
||||
batch_patches.append(patches)
|
||||
patches = []
|
||||
|
||||
if len(patches):
|
||||
patches = torch.stack(patches, dim=0)
|
||||
batch_patches.append(patches)
|
||||
|
||||
features = np.zeros((0, ReIDEncoder.embedding_size))
|
||||
for patches in batch_patches:
|
||||
pred = ReIDEncoder.model(patches)
|
||||
pred[torch.isinf(pred)] = 1.0
|
||||
feat = pred.cpu().data.numpy()
|
||||
features = np.vstack((features, feat))
|
||||
|
||||
return imgs, features
|
||||
|
||||
def test_dog():
|
||||
|
||||
|
||||
datapath = r"D:\datasets\ym\Img_ResnetData\dog_224x224\dog_224x224.txt"
|
||||
with open(datapath, 'r') as file:
|
||||
lines = file.readlines()
|
||||
dlist = lines[0].split(',')
|
||||
dfloat = [float(d) for d in dlist]
|
||||
|
||||
afeat = np.array(dfloat).reshape(1, -1)
|
||||
|
||||
|
||||
|
||||
imgpath = r"D:\datasets\ym\Img_ResnetData\dog_224x224\dog_224x224.jpg"
|
||||
image = cv2.imread(imgpath)
|
||||
patches = []
|
||||
|
||||
img = image[:, :, ::-1].copy() # the model expects RGB inputs
|
||||
patch = ReIDEncoder.transform(img)
|
||||
|
||||
patch = patch.to(device=ReIDEncoder.device)
|
||||
|
||||
patches.append(patch)
|
||||
patches = torch.stack(patches, dim=0)
|
||||
pred = ReIDEncoder.model(patches)
|
||||
pred[torch.isinf(pred)] = 1.0
|
||||
bfeat = pred.cpu().data.numpy()
|
||||
|
||||
|
||||
|
||||
|
||||
aafeat = afeat / np.linalg.norm(afeat, ord=2, axis=1, keepdims=True)
|
||||
bbfeat = bfeat / np.linalg.norm(bfeat, ord=2, axis=1, keepdims=True)
|
||||
|
||||
|
||||
cost_matrix = 1 - np.maximum(0.0, cdist(aafeat, bbfeat, 'cosine'))
|
||||
|
||||
|
||||
|
||||
|
||||
print("Done!!!")
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def main():
|
||||
imgpath = r"D:\datasets\ym\Img_ResnetData\20240531-103547_0354b1cb-53fa-48de-86cd-ac3c5b127ada_6921168593576\3568800050000_0.jpeg"
|
||||
datapath = r"D:\datasets\ym\Img_ResnetData\0_tracker_inout.data"
|
||||
savepath = r"D:\datasets\ym\Img_ResnetData\result"
|
||||
|
||||
image = cv2.imread(imgpath)
|
||||
|
||||
|
||||
Videos = read_data_file(datapath)
|
||||
|
||||
bboxes, afeats = Videos[0][0][0], Videos[0][1][0]
|
||||
imgs, bfeats = inference_image(image, bboxes)
|
||||
|
||||
|
||||
aafeats = afeats / np.linalg.norm(afeats, ord=2, axis=1, keepdims=True)
|
||||
bbfeats = bfeats / np.linalg.norm(bfeats, ord=2, axis=1, keepdims=True)
|
||||
|
||||
|
||||
cost_matrix = 1 - np.maximum(0.0, cdist(aafeats, bbfeats, 'cosine'))
|
||||
|
||||
|
||||
for i, img in enumerate(imgs):
|
||||
cv2.imwrite(savepath + f"\{i}.png", img)
|
||||
|
||||
|
||||
|
||||
print("Done!!!!")
|
||||
|
||||
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
||||
# test_dog()
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@ -110,8 +110,6 @@ def inference_image(image, detections):
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def init_trackers(tracker_yaml = None, bs=1):
|
||||
"""
|
||||
Initialize trackers for object tracking during prediction.
|
||||
@ -177,7 +175,7 @@ def run(
|
||||
save_dir = Path(project) / Path(source).stem
|
||||
if save_dir.exists():
|
||||
print(Path(source).stem)
|
||||
return
|
||||
# return
|
||||
|
||||
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
|
||||
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
|
||||
@ -215,6 +213,9 @@ def run(
|
||||
track_boxes = np.empty((0, 9), dtype = np.float32)
|
||||
det_boxes = np.empty((0, 9), dtype = np.float32)
|
||||
|
||||
DetBoxes = np.empty((0, 6), dtype = np.float32)
|
||||
TrackerBoxes = np.empty((0, 9), dtype = np.float32)
|
||||
TrackerFeats = np.empty((0, 256), dtype = np.float32)
|
||||
|
||||
features_dict = {}
|
||||
TracksDict = {}
|
||||
@ -267,38 +268,40 @@ def run(
|
||||
|
||||
det = det.cpu().numpy()
|
||||
det = np.concatenate([det[:, :4], np.arange(nd).reshape(-1, 1), det[:, 4:]], axis=-1)
|
||||
|
||||
DetBoxes = np.concatenate([DetBoxes, det[:, :6]], axis=0)
|
||||
|
||||
#
|
||||
def static_estimate(box1, box2, TH1=8, TH2=12):
|
||||
dij_abs = max(np.abs(box1 - box2))
|
||||
dij_euc = max([np.linalg.norm((box1[:2] - box2[:2])),
|
||||
np.linalg.norm((box1[2:4] - box2[2:4]))
|
||||
])
|
||||
if dij_abs < TH1 and dij_euc < TH2:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
## ============================================================ 前后帧相同 boxes 的特征赋值
|
||||
# def static_estimate(box1, box2, TH1=8, TH2=12):
|
||||
# dij_abs = max(np.abs(box1 - box2))
|
||||
# dij_euc = max([np.linalg.norm((box1[:2] - box2[:2])),
|
||||
# np.linalg.norm((box1[2:4] - box2[2:4]))
|
||||
# ])
|
||||
# if dij_abs < TH1 and dij_euc < TH2:
|
||||
# return True
|
||||
# else:
|
||||
# return False
|
||||
|
||||
nw = 3 # 向前递推检查的窗口大小
|
||||
nf = len(BoxesFeats) # 已经检测+特征提取的帧数
|
||||
feat_curr = [None] * nd # nd: 当前帧检测出的boxes数
|
||||
for ii in range(nd):
|
||||
box = det[ii, :4]
|
||||
# nw = 3 # 向前递推检查的窗口大小
|
||||
# nf = len(BoxesFeats) # 已经检测+特征提取的帧数
|
||||
# feat_curr = [None] * nd # nd: 当前帧检测出的boxes数
|
||||
# for ii in range(nd):
|
||||
# box = det[ii, :4]
|
||||
|
||||
kk=1
|
||||
feat = None
|
||||
while kk <= nw and nf>=kk:
|
||||
ki = -1 * kk
|
||||
boxes_ = BoxesFeats[ki][0]
|
||||
feats_ = BoxesFeats[ki][1]
|
||||
# kk=1
|
||||
# feat = None
|
||||
# while kk <= nw and nf>=kk:
|
||||
# ki = -1 * kk
|
||||
# boxes_ = BoxesFeats[ki][0]
|
||||
# feats_ = BoxesFeats[ki][1]
|
||||
|
||||
flag = [jj for jj in range(len(boxes_)) if static_estimate(box, boxes_[jj, :4])]
|
||||
if len(flag) == 1:
|
||||
feat = feats_[flag[0]]
|
||||
break
|
||||
kk += 1
|
||||
if feat is not None:
|
||||
feat_curr[ii] = feat
|
||||
# flag = [jj for jj in range(len(boxes_)) if static_estimate(box, boxes_[jj, :4])]
|
||||
# if len(flag) == 1:
|
||||
# feat = feats_[flag[0]]
|
||||
# break
|
||||
# kk += 1
|
||||
# if feat is not None:
|
||||
# feat_curr[ii] = feat
|
||||
|
||||
|
||||
|
||||
@ -319,7 +322,11 @@ def run(
|
||||
'''================== 1. 存储 dets/subimgs/features Dict ============='''
|
||||
imgs, features = inference_image(im0, tracks)
|
||||
|
||||
BoxesFeats.append((tracks, features))
|
||||
|
||||
TrackerFeats = np.concatenate([TrackerFeats, features], axis=0)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
imgdict = {}
|
||||
@ -532,7 +539,10 @@ def main_loop(opt):
|
||||
# r"D:\datasets\ym\广告板遮挡测试\8\2500441577966_20240508-175946_front_addGood_70f75407b7ae_155_17788571404.mp4"
|
||||
# ]
|
||||
|
||||
# files = [r"D:\datasets\ym\videos\标记视频\test_20240402-173935_6920152400975_back_174037372.mp4"]
|
||||
# files = [r"D:\datasets\ym\视频\20240529\110518062-090ac04c-0a8c-479f-bc18-cb3553c90683-0_seek0.017962635633665514.mp4"]
|
||||
files = [r"D:\datasets\ym\视频\20240529\110518060-550b7c4d-9946-4aa4-9131-81008692cd65-1_seek0.7670042724609232.mp4"]
|
||||
|
||||
|
||||
for file in files:
|
||||
optdict["source"] = file
|
||||
run(**optdict)
|
||||
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -84,7 +84,6 @@ class Track:
|
||||
boxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
|
||||
0 1 2 3 4 5 6 7 8
|
||||
'''
|
||||
# 不满足以下条件时会如何？
|
||||
# assert len(set(boxes[:, 4].astype(int))) == 1, "For a Track, track_id more than 1"
|
||||
# assert len(set(boxes[:, 6].astype(int))) == 1, "For a Track, class number more than 1"
|
||||
|
||||
@ -110,7 +109,8 @@ class Track:
|
||||
'''5个关键点（中心点、左上点、右上点、左下点、右下点 ）坐标'''
|
||||
self.compute_cornpoints()
|
||||
|
||||
'''5个关键点轨迹特征，可以在子类中实现，降低顺序处理时的计算量'''
|
||||
'''5个关键点轨迹特征，可以在子类中实现，降低顺序处理时的计算量
|
||||
（中心点、左上点、右上点、左下点、右下点 ）轨迹特征'''
|
||||
self.compute_cornpts_feats()
|
||||
|
||||
|
||||
@ -341,8 +341,6 @@ class Track:
|
||||
|
||||
return
|
||||
|
||||
|
||||
|
||||
|
||||
class doTracks:
|
||||
def __init__(self, bboxes, TracksDict):
|
||||
@ -394,42 +392,7 @@ class doTracks:
|
||||
lfeats.append(afeat)
|
||||
|
||||
return lfeats
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
'''
|
||||
def classify(self):
|
||||
|
||||
tracks = self.tracks
|
||||
|
||||
|
||||
# 提取手的frame_id，并和动目标的frame_id 进行关联
|
||||
hand_tracks = [t for t in tracks if t.cls==0]
|
||||
self.Hands.extend(hand_tracks)
|
||||
tracks = self.sub_tracks(tracks, hand_tracks)
|
||||
|
||||
|
||||
|
||||
# 提取小孩的track，并计算状态：left, right, incart
|
||||
kid_tracks = [t for t in tracks if t.cls==9]
|
||||
kid_states = [self.kid_state(t) for t in kid_tracks]
|
||||
self.Kids = [x for x in zip(kid_tracks, kid_states)]
|
||||
|
||||
tracks = self.sub_tracks(tracks, kid_tracks)
|
||||
|
||||
|
||||
static_tracks = [t for t in tracks if t.frnum>1 and t.is_static()]
|
||||
self.Static.extend(static_tracks)
|
||||
|
||||
|
||||
# 剔除静止目标后的 tracks
|
||||
tracks = self.sub_tracks(tracks, static_tracks)
|
||||
|
||||
return tracks
|
||||
'''
|
||||
|
||||
|
||||
def similarity(self):
|
||||
nt = len(self.tracks)
|
||||
|
||||
@ -23,34 +23,6 @@ class doBackTracks(doTracks):
|
||||
|
||||
self.shopcart = ShoppingCart(bboxes)
|
||||
|
||||
# =============================================================================
|
||||
# def array2list(self):
|
||||
# ''' 0, 1, 2, 3, 4, 5, 6, 7, 8
|
||||
# bboxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
|
||||
# lboxes：[x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
|
||||
# '''
|
||||
#
|
||||
# track_ids = set(self.bboxes[:, 4])
|
||||
# lboxes = []
|
||||
# for t_id in track_ids:
|
||||
# idx = np.where(self.bboxes[:, 4] == t_id)[0]
|
||||
# box = self.bboxes[idx, :]
|
||||
#
|
||||
# x = (box[:, 0] + box[:, 2]) / 2
|
||||
# y = (box[:, 1] + box[:, 3]) / 2
|
||||
#
|
||||
# # box: [x, y, w, h, track_id, score, cls, frame_index]
|
||||
# box[:, 2] = box[:, 2] - box[:, 0]
|
||||
# box[:, 3] = box[:, 3] - box[:, 1]
|
||||
# box[:, 0] = x
|
||||
# box[:, 1] = y
|
||||
#
|
||||
# lboxes.append(box)
|
||||
#
|
||||
#
|
||||
# return lboxes
|
||||
# =============================================================================
|
||||
|
||||
def classify(self):
|
||||
'''功能：对 tracks 中元素分类 '''
|
||||
|
||||
|
||||
@ -122,25 +122,6 @@ class doFrontTracks(doTracks):
|
||||
"""
|
||||
对不同id，但可能是同一商品的目标进行归并
|
||||
"""
|
||||
# =============================================================================
|
||||
# mergedTracks = []
|
||||
# alist = [t for t in Residual]
|
||||
# while alist:
|
||||
# atrack = alist[0]
|
||||
# cur_list = []
|
||||
# cur_list.append(atrack)
|
||||
# alist.pop(0)
|
||||
#
|
||||
# blist = [b for b in alist]
|
||||
# alist = []
|
||||
# for btrack in blist:
|
||||
# if track_equal_track(atrack, btrack, self.TracksDict):
|
||||
# cur_list.append(btrack)
|
||||
# else:
|
||||
# alist.append(btrack)
|
||||
#
|
||||
# mergedTracks.append(cur_list)
|
||||
# =============================================================================
|
||||
mergedTracks = self.base_merge_tracks(Residual)
|
||||
|
||||
oldtracks, newtracks = [], []
|
||||
@ -175,27 +156,3 @@ class doFrontTracks(doTracks):
|
||||
|
||||
return merged
|
||||
|
||||
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# def array2list(self):
|
||||
# '''
|
||||
# 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]
|
||||
# '''
|
||||
# track_ids = set(self.bboxes[:, 4])
|
||||
# lboxes = []
|
||||
# for t_id in track_ids:
|
||||
# # print(f"The ID is: {t_id}")
|
||||
# idx = np.where(self.bboxes[:, 4] == t_id)[0]
|
||||
# box = self.bboxes[idx, :]
|
||||
#
|
||||
# lboxes.append(box)
|
||||
#
|
||||
# return lboxes
|
||||
# =============================================================================
|
||||
|
||||
@ -48,7 +48,6 @@ class backTrack(Track):
|
||||
# self.PCA()
|
||||
|
||||
|
||||
|
||||
def isimgborder(self, BoundPixel=10, BoundThresh=0.3):
|
||||
|
||||
x1, y1 = self.cornpoints[:,2], self.cornpoints[:,3],
|
||||
@ -74,69 +73,12 @@ class backTrack(Track):
|
||||
MarginState = [condtA, condtB, condtC, condtD, condtE, condtF, condtG]
|
||||
|
||||
return isCornpoint, MarginState
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# def PositionState(self, camerType="back"):
|
||||
# '''
|
||||
# 已迁移至基类
|
||||
# camerType: back, 后置摄像头
|
||||
# front, 前置摄像头
|
||||
# '''
|
||||
# if camerType=="front":
|
||||
# incart = cv2.imread("./shopcart/cart_tempt/incart.png", cv2.IMREAD_GRAYSCALE)
|
||||
# outcart = cv2.imread("./shopcart/cart_tempt/outcart.png", cv2.IMREAD_GRAYSCALE)
|
||||
# else:
|
||||
# incart = cv2.imread("./shopcart/cart_tempt/incart_ftmp.png", cv2.IMREAD_GRAYSCALE)
|
||||
# outcart = cv2.imread("./shopcart/cart_tempt/outcart_ftmp.png", cv2.IMREAD_GRAYSCALE)
|
||||
#
|
||||
# xc, yc = self.cornpoints[:,0].clip(0,self.imgshape[0]-1).astype(np.int64), self.cornpoints[:,1].clip(0,self.imgshape[1]-1).astype(np.int64)
|
||||
# x1, y1 = self.cornpoints[:,6].clip(0,self.imgshape[0]-1).astype(np.int64), self.cornpoints[:,7].clip(0,self.imgshape[1]-1).astype(np.int64)
|
||||
# x2, y2 = self.cornpoints[:,8].clip(0,self.imgshape[0]-1).astype(np.int64), self.cornpoints[:,9].clip(0,self.imgshape[1]-1).astype(np.int64)
|
||||
#
|
||||
# # print(self.tid)
|
||||
# Cent_inCartnum = np.count_nonzero(incart[(yc, xc)])
|
||||
# LB_inCartnum = np.count_nonzero(incart[(y1, x1)])
|
||||
# RB_inCartnum = np.count_nonzero(incart[(y2, x2)])
|
||||
#
|
||||
# Cent_outCartnum = np.count_nonzero(outcart[(yc, xc)])
|
||||
# LB_outCartnum = np.count_nonzero(outcart[(y1, x1)])
|
||||
# RB_outCartnum = np.count_nonzero(outcart[(y2, x2)])
|
||||
#
|
||||
# '''Track完全在车内：左下角点、右下角点与 outcart 的交集为 0'''
|
||||
# self.isWholeInCart = False
|
||||
# if LB_outCartnum + RB_outCartnum == 0:
|
||||
# self.isWholeInCart = True
|
||||
#
|
||||
# '''Track完全在车外：左下角点、中心点与 incart 的交集为 0
|
||||
# 右下角点、中心点与 incart 的交集为 0
|
||||
# '''
|
||||
# self.isWholeOutCart = False
|
||||
# if Cent_inCartnum + LB_inCartnum == 0 or Cent_inCartnum + RB_inCartnum == 0:
|
||||
# self.isWholeOutCart = True
|
||||
#
|
||||
#
|
||||
# self.Cent_isIncart = False
|
||||
# self.LB_isIncart = False
|
||||
# self.RB_isIncart = False
|
||||
# if Cent_inCartnum: self.Cent_isIncart = True
|
||||
# if LB_inCartnum: self.LB_isIncart = True
|
||||
# if RB_inCartnum: self.RB_isIncart = True
|
||||
#
|
||||
# self.posState = self.Cent_isIncart+self.LB_isIncart+self.RB_isIncart
|
||||
# =============================================================================
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def PCA(self):
|
||||
self.pca = PCA()
|
||||
|
||||
X = self.cornpoints[:, 0:2]
|
||||
self.pca.fit(X)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def compute_ious_feat(self):
|
||||
@ -194,96 +136,8 @@ class backTrack(Track):
|
||||
|
||||
self.feature_ious = (incart_iou, outcart_iou, cartboarder_iou, maxbox_iou, minbox_iou)
|
||||
self.incartrates = incartrates
|
||||
|
||||
|
||||
|
||||
|
||||
def compute_static_fids(self, thresh1 = 12, thresh2 = 3):
|
||||
'''
|
||||
计算 track 的轨迹中相对处于静止状态的轨迹点的（start_frame_id, end_frame_id）
|
||||
thresh1: 相邻两帧目标中心点是否静止的的阈值，以像素为单位，
|
||||
thresh2: 连续捕捉到目标处于静止状态的帧数,当 thresh2 = 3时,至少连续 4个点,
|
||||
产生3个相邻点差值均小于 thresh1 时，判定为连续静止.
|
||||
处理过程中利用了插值技术，因此start、end并非 self.boxes 中对应的帧索引
|
||||
'''
|
||||
|
||||
BoundPixel = 8
|
||||
x1, y1 = self.cornpoints[:,2], self.cornpoints[:,3],
|
||||
x2, y2 = self.cornpoints[:,8], self.cornpoints[:,9]
|
||||
cont1 = sum(abs(x1)<BoundPixel) > 3
|
||||
# cont2 = sum(abs(y1)<BoundPixel) > 3
|
||||
cont3 = sum(abs(x2-self.imgshape[0])<BoundPixel) > 3
|
||||
# cont4 = sum(abs(y2-self.imgshape[1])<BoundPixel) > 3
|
||||
cont = not(cont1 or cont3)
|
||||
|
||||
## ============== 下一步，启用中心点，选择具有最小运动幅度的角点作为参考点
|
||||
static_index = []
|
||||
if self.frnum>=2 and cont:
|
||||
x1 = self.boxes[1:,7]
|
||||
x2 = [i for i in range(int(min(x1)), int(max(x1)+1))]
|
||||
dist_adjc = np.interp(x2, x1, self.trajmin)
|
||||
|
||||
|
||||
# dist_adjc = self.trajmin
|
||||
|
||||
static_thresh = (dist_adjc < thresh1)[:, None].astype(np.uint8)
|
||||
static_cnts, _ = cv2.findContours(static_thresh, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
|
||||
|
||||
for cnt in static_cnts:
|
||||
_, start, _, num = cv2.boundingRect(cnt)
|
||||
end = start + num
|
||||
if num < thresh2:
|
||||
continue
|
||||
static_index.append((start, end))
|
||||
|
||||
static_index = np.array(static_index)
|
||||
if static_index.size:
|
||||
indx = np.argsort(static_index[:, 0])
|
||||
static_index = static_index[indx]
|
||||
|
||||
return static_index
|
||||
|
||||
def compute_dynamic_fids(self, thresh1 = 12, thresh2 = 3):
|
||||
'''
|
||||
计算 track 的轨迹中运动轨迹点的（start_frame_id, end_frame_id）
|
||||
thresh1: 相邻两帧目标中心点是否运动的阈值，以像素为单位，
|
||||
thresh2: 连续捕捉到目标连续运动的帧数
|
||||
目标：
|
||||
1. 计算轨迹方向
|
||||
2. 计算和手部运动的关联性
|
||||
'''
|
||||
moving_index = []
|
||||
if self.frnum>=2:
|
||||
x1 = self.boxes[1:,7]
|
||||
x2 = [i for i in range(int(min(x1)), int(max(x1)+1))]
|
||||
dist_adjc = np.interp(x2, x1, self.trajmin)
|
||||
|
||||
moving_thresh = (dist_adjc >= thresh1)[:, None].astype(np.uint8)
|
||||
moving_cnts, _ = cv2.findContours(moving_thresh, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
|
||||
|
||||
for cnt in moving_cnts:
|
||||
_, start, _, num = cv2.boundingRect(cnt)
|
||||
if num < thresh2:
|
||||
continue
|
||||
end = start + num
|
||||
moving_index.append((start, end))
|
||||
|
||||
# =============================================================================
|
||||
# '''========= 输出帧id，不太合适 ========='''
|
||||
# moving_fids = []
|
||||
# for i in range(len(moving_index)):
|
||||
# i1, i2 = moving_index[i]
|
||||
# fid1, fid2 = boxes[i1, 7], boxes[i2, 7]
|
||||
# moving_fids.append([fid1, fid2])
|
||||
# moving_fids = np.array(moving_fids)
|
||||
# =============================================================================
|
||||
moving_index = np.array(moving_index)
|
||||
if moving_index.size:
|
||||
indx = np.argsort(moving_index[:, 0])
|
||||
moving_index = moving_index[indx]
|
||||
|
||||
return moving_index
|
||||
|
||||
def compute_static_dynamic_fids(self):
|
||||
|
||||
if self.MarginState[0] or self.MarginState[2]:
|
||||
@ -319,17 +173,6 @@ class backTrack(Track):
|
||||
|
||||
return static, dynamic
|
||||
|
||||
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# static_dynamic_fids = []
|
||||
# for traj in self.trajectory:
|
||||
# static, dynamic = self.pt_state_fids(traj)
|
||||
# static_dynamic_fids.append((static, dynamic))
|
||||
#
|
||||
# return static_dynamic_fids
|
||||
# =============================================================================
|
||||
|
||||
def is_static(self):
|
||||
'''静态情况 1: 目标关键点最小相对运动轨迹 < 0.2, 指标值偏大
|
||||
@ -354,7 +197,6 @@ class backTrack(Track):
|
||||
# and self.posState >= 2
|
||||
# and self.TrajFeat[0] < 240 \
|
||||
|
||||
|
||||
'''静态情况 3: 目标初始状态和最终状态均为静止'''
|
||||
condt3 = self.static_index.shape[0] >= 2 \
|
||||
and self.static_index[0, 0] <= 2 \
|
||||
@ -370,50 +212,23 @@ class backTrack(Track):
|
||||
and self.static_index[0, 1] >= 6 \
|
||||
and self.static_index[-1, 0] <= self.frnum-5 \
|
||||
and self.static_index[-1, 1] >= self.frnum-2
|
||||
|
||||
|
||||
|
||||
condt = condt1 or condt2 or condt3 or condt4
|
||||
|
||||
return condt
|
||||
|
||||
# =============================================================================
|
||||
# track1 = [t for t in tracks if t.TrajFeat[5] < 0.2
|
||||
# or t.TrajFeat[3] < 120
|
||||
# ]
|
||||
#
|
||||
# track2 = [t for t in tracks if t.static_index.size > 0
|
||||
# and t.static_index[0, 0] <= 2
|
||||
# and t.TrajFeat[5] < 0.5]
|
||||
#
|
||||
# track3 = [t for t in tracks if t.static_index.shape[0] >= 2
|
||||
# and t.static_index[0, 0] <= 2
|
||||
# and t.static_index[-1, 1] >= t.frnum-3]
|
||||
#
|
||||
# track12 = self.join_tracks(track1, track2)
|
||||
#
|
||||
# '''提取静止状态的 track'''
|
||||
# static_tracks = self.join_tracks(track12, track3)
|
||||
# self.Static.extend(static_tracks)
|
||||
#
|
||||
# =============================================================================
|
||||
|
||||
def is_OutTrack(self):
|
||||
if self.posState <= 1:
|
||||
isout = True
|
||||
else:
|
||||
isout = False
|
||||
return isout
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def compute_distance(self):
|
||||
pass
|
||||
|
||||
|
||||
|
||||
def move_start_fid(self):
|
||||
pass
|
||||
|
||||
|
||||
def move_end_fid(self):
|
||||
pass
|
||||
@ -15,17 +15,9 @@ class frontTrack(Track):
|
||||
def __init__(self, boxes, features, imgshape=(1024, 1280)):
|
||||
|
||||
super().__init__(boxes, features, imgshape)
|
||||
|
||||
'''5个关键点（中心点、左上点、右上点、左下点、右下点 ）轨迹特征'''
|
||||
# self.compute_cornpts_feats()
|
||||
|
||||
|
||||
self.CART_HIGH_THRESH1 = imgshape[1]/2.98
|
||||
|
||||
|
||||
# if self.tid==10:
|
||||
# print(f"ID: {self.tid}")
|
||||
|
||||
'''y1、y2静止状态区间，值是 boxes 中对 axis=0 的索引，不是帧索引'''
|
||||
det_y1 = np.diff(boxes[:, 1], axis=0)
|
||||
det_y2 = np.diff(boxes[:, 3], axis=0)
|
||||
@ -78,69 +70,6 @@ class frontTrack(Track):
|
||||
condt = all(self.boxes[:, 3] > self.imgshape[1]-20)
|
||||
|
||||
return condt
|
||||
|
||||
# def is_OutTrack(self):
|
||||
# isout = False
|
||||
# if self.posState <= 1:
|
||||
# isout = True
|
||||
# return isout
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# def compute_static_fids(self, det_y, STATIC_THRESH = 8):
|
||||
# '''
|
||||
# 前摄时，y一般选择为 box 的 y1 坐标，且需限定商品在购物车内。
|
||||
# inputs：
|
||||
# y：1D array，
|
||||
# parameters：
|
||||
# STATIC_THRESH：轨迹处于静止状态的阈值。
|
||||
# outputs：
|
||||
# 输出为差分值小于 STATIC_THRESH 的y中元素的（start, end）索引
|
||||
# ranges = [(x1, y1),
|
||||
# (x1, y1),
|
||||
# ...]
|
||||
# '''
|
||||
# # print(f"The ID is: {self.tid}")
|
||||
#
|
||||
# # det_y = np.diff(y, axis=0)
|
||||
# ranges, rangex = [], []
|
||||
#
|
||||
# static_indices = np.where(np.abs(det_y) < STATIC_THRESH)[0]
|
||||
#
|
||||
# if len(static_indices) == 0:
|
||||
# rangex.append((0, len(det_y)))
|
||||
# return ranges, rangex
|
||||
#
|
||||
# start_index = static_indices[0]
|
||||
#
|
||||
# for i in range(1, len(static_indices)):
|
||||
# if static_indices[i] != static_indices[i-1] + 1:
|
||||
# ranges.append((start_index, static_indices[i-1] + 1))
|
||||
# start_index = static_indices[i]
|
||||
# ranges.append((start_index, static_indices[-1] + 1))
|
||||
#
|
||||
# if len(ranges) == 0:
|
||||
# rangex.append((0, len(det_y)))
|
||||
# return ranges, rangex
|
||||
#
|
||||
# idx1, idx2 = ranges[0][0], ranges[-1][1]
|
||||
#
|
||||
# if idx1 != 0:
|
||||
# rangex.append((0, idx1))
|
||||
#
|
||||
# # 轨迹的最后阶段是运动状态
|
||||
# for k in range(1, len(ranges)):
|
||||
# index1 = ranges[k-1][1]
|
||||
# index2 = ranges[k][0]
|
||||
# rangex.append((index1, index2))
|
||||
#
|
||||
# if idx2 != len(det_y):
|
||||
# rangex.append((idx2, len(det_y)))
|
||||
#
|
||||
# return ranges, rangex
|
||||
#
|
||||
# =============================================================================
|
||||
|
||||
|
||||
|
||||
def is_static(self):
|
||||
@ -202,14 +131,6 @@ class frontTrack(Track):
|
||||
return condt
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def is_upward(self):
|
||||
'''判断商品是否取出，'''
|
||||
print(f"The ID is: {self.tid}")
|
||||
|
||||
@ -16,9 +16,6 @@ import pandas as pd
|
||||
from scipy.spatial.distance import cdist
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
|
||||
# ================= using for import ultralytics
|
||||
import sys
|
||||
sys.path.append(r"D:\DetectTracking")
|
||||
@ -85,13 +82,13 @@ def save_subimgs(vts, file, TracksDict):
|
||||
cv2.imwrite(str(imgdir) + f"/{tid}_{fid}_{bid}.png", img)
|
||||
|
||||
def have_tracked():
|
||||
trackdict = r'./data/trackdicts_1'
|
||||
trackdict = r'./data/trackdicts'
|
||||
alltracks = []
|
||||
k = 0
|
||||
gt = Profile()
|
||||
for filename in os.listdir(trackdict):
|
||||
# filename = 'test_20240402-173935_6920152400975_back_174037372.pkl'
|
||||
filename = '加购_91.pkl'
|
||||
# filename = '加购_91.pkl'
|
||||
|
||||
file, ext = os.path.splitext(filename)
|
||||
filepath = os.path.join(trackdict, filename)
|
||||
@ -123,9 +120,9 @@ def have_tracked():
|
||||
|
||||
|
||||
|
||||
k += 1
|
||||
if k==1:
|
||||
break
|
||||
# k += 1
|
||||
# if k==1:
|
||||
# break
|
||||
|
||||
if len(alltracks):
|
||||
drawFeatures(alltracks, save_dir)
|
||||
|
||||
223
tracking/test_val.py
Normal file
223
tracking/test_val.py
Normal file
@ -0,0 +1,223 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Created on Thu May 30 14:03:03 2024
|
||||
|
||||
@author: ym
|
||||
"""
|
||||
import os
|
||||
import cv2
|
||||
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 import Boxes, IterableSimpleNamespace, yaml_load
|
||||
from tracking.trackers import BOTSORT, BYTETracker
|
||||
from tracking.dotrack.dotracks_back import doBackTracks
|
||||
from tracking.dotrack.dotracks_front import doFrontTracks
|
||||
from tracking.utils.drawtracks import plot_frameID_y2, draw_all_trajectories
|
||||
|
||||
W, H = 1024, 1280
|
||||
|
||||
Mode = 'front' #'back'
|
||||
|
||||
def read_data_file(datapath):
|
||||
|
||||
with open(datapath, 'r') as file:
|
||||
lines = file.readlines()
|
||||
Videos = []
|
||||
FrameBoxes, FrameFeats = [], []
|
||||
boxes, feats = [], []
|
||||
|
||||
bboxes, ffeats = [], []
|
||||
timestamp = []
|
||||
t1 = None
|
||||
for line in lines:
|
||||
if line.find('CameraId') >= 0:
|
||||
t = int(line.split(',')[1].split(':')[1])
|
||||
timestamp.append(t)
|
||||
|
||||
if len(boxes) and len(feats):
|
||||
FrameBoxes.append(np.array(boxes, dtype = np.float32))
|
||||
FrameFeats.append(np.array(feats, dtype = np.float32))
|
||||
|
||||
boxes, feats = [], []
|
||||
|
||||
if t1 and t - t1 > 1e4:
|
||||
Videos.append((FrameBoxes, FrameFeats))
|
||||
FrameBoxes, FrameFeats = [], []
|
||||
t1 = int(line.split(',')[1].split(':')[1])
|
||||
|
||||
if line.find('box') >= 0:
|
||||
box = line.split(':', )[1].split(',')[:-1]
|
||||
boxes.append(box)
|
||||
bboxes.append(boxes)
|
||||
|
||||
|
||||
if line.find('feat') >= 0:
|
||||
feat = line.split(':', )[1].split(',')[:-1]
|
||||
feats.append(feat)
|
||||
ffeats.append(feat)
|
||||
|
||||
|
||||
|
||||
|
||||
FrameBoxes.append(np.array(boxes, dtype = np.float32))
|
||||
FrameFeats.append(np.array(feats, dtype = np.float32))
|
||||
Videos.append((FrameBoxes, FrameFeats))
|
||||
|
||||
TimeStamp = np.array(timestamp, dtype = np.float32)
|
||||
DimesDiff = np.diff((timestamp))
|
||||
|
||||
return Videos
|
||||
|
||||
def video2imgs(path):
|
||||
vpath = os.path.join(path, "videos")
|
||||
|
||||
k = 0
|
||||
have = False
|
||||
for filename in os.listdir(vpath):
|
||||
file, ext = os.path.splitext(filename)
|
||||
imgdir = os.path.join(path, file)
|
||||
if os.path.exists(imgdir):
|
||||
continue
|
||||
else:
|
||||
os.mkdir(imgdir)
|
||||
|
||||
vfile = os.path.join(vpath, filename)
|
||||
cap = cv2.VideoCapture(vfile)
|
||||
i = 0
|
||||
while True:
|
||||
ret, frame = cap.read()
|
||||
if not ret:
|
||||
break
|
||||
|
||||
i += 1
|
||||
imgp = os.path.join(imgdir, file+f"_{i}.png")
|
||||
cv2.imwrite(imgp, frame)
|
||||
|
||||
print(filename+f": {i}")
|
||||
|
||||
|
||||
cap.release()
|
||||
|
||||
k+=1
|
||||
if k==1000:
|
||||
break
|
||||
|
||||
def draw_boxes():
|
||||
datapath = r'D:\datasets\ym\videos_test\20240530\1_tracker_inout(1).data'
|
||||
VideosData = read_data_file(datapath)
|
||||
|
||||
bboxes = VideosData[0][0]
|
||||
ffeats = VideosData[0][1]
|
||||
|
||||
videopath = r"D:\datasets\ym\videos_test\20240530\134458234-1cd970cf-f8b9-4e80-9c2e-7ca3eec83b81-1_seek0.10415589124891511.mp4"
|
||||
|
||||
cap = cv2.VideoCapture(videopath)
|
||||
i = 0
|
||||
while True:
|
||||
ret, frame = cap.read()
|
||||
if not ret:
|
||||
break
|
||||
|
||||
|
||||
annotator = Annotator(frame.copy(), line_width=3)
|
||||
|
||||
|
||||
boxes = bboxes[i]
|
||||
|
||||
for *xyxy, conf, cls in reversed(boxes):
|
||||
label = f'{int(cls)}: {conf:.2f}'
|
||||
|
||||
color = colors(int(cls), True)
|
||||
annotator.box_label(xyxy, label, color=color)
|
||||
|
||||
img = annotator.result()
|
||||
|
||||
imgpath = r"D:\datasets\ym\videos_test\20240530\result\int8_front\{}.png".format(i+1)
|
||||
cv2.imwrite(imgpath, img)
|
||||
|
||||
print(f"Output: {i}")
|
||||
i += 1
|
||||
cap.release()
|
||||
|
||||
def init_tracker(tracker_yaml = None, bs=1):
|
||||
"""
|
||||
Initialize tracker for object tracking during prediction.
|
||||
"""
|
||||
TRACKER_MAP = {'bytetrack': BYTETracker, 'botsort': BOTSORT}
|
||||
cfg = IterableSimpleNamespace(**yaml_load(tracker_yaml))
|
||||
|
||||
tracker = TRACKER_MAP[cfg.tracker_type](args=cfg, frame_rate=30)
|
||||
|
||||
return tracker
|
||||
|
||||
def tracking(bboxes, ffeats):
|
||||
tracker_yaml = r"./trackers/cfg/botsort.yaml"
|
||||
tracker = init_tracker(tracker_yaml)
|
||||
|
||||
track_boxes = np.empty((0, 9), dtype = np.float32)
|
||||
features_dict = {}
|
||||
|
||||
'''==================== 执行跟踪处理 ======================='''
|
||||
for dets, feats in zip(bboxes, ffeats):
|
||||
# 需要根据frame_id重排序
|
||||
det_tracking = Boxes(dets).cpu().numpy()
|
||||
tracks = tracker.update(det_tracking, feats)
|
||||
|
||||
if len(tracks):
|
||||
track_boxes = np.concatenate([track_boxes, tracks], axis=0)
|
||||
feat_dict = {int(x.idx): x.curr_feat for x in tracker.tracked_stracks if x.is_activated}
|
||||
frame_id = tracks[0, 7]
|
||||
features_dict.update({int(frame_id): feat_dict})
|
||||
|
||||
return det_tracking, features_dict
|
||||
|
||||
|
||||
|
||||
def main():
|
||||
datapath = r'D:\datasets\ym\videos_test\20240530\1_tracker_inout(1).data'
|
||||
VideosData = read_data_file(datapath)
|
||||
|
||||
bboxes = VideosData[0][0]
|
||||
ffeats = VideosData[0][1]
|
||||
|
||||
bboxes, feats_dict = tracking(bboxes, ffeats)
|
||||
|
||||
|
||||
|
||||
if Mode == "front":
|
||||
vts = doFrontTracks(bboxes, feats_dict)
|
||||
vts.classify()
|
||||
|
||||
|
||||
plt = plot_frameID_y2(vts)
|
||||
plt.savefig('front_y2.png')
|
||||
# plt.close()
|
||||
else:
|
||||
vts = doBackTracks(bboxes, feats_dict)
|
||||
vts.classify()
|
||||
|
||||
edgeline = cv2.imread("./shopcart/cart_tempt/edgeline.png")
|
||||
draw_all_trajectories(vts, edgeline, save_dir, filename)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
filename = 'traj.png'
|
||||
save_dir = Path('./result')
|
||||
if not save_dir.exists():
|
||||
save_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
main()
|
||||
|
||||
|
||||
Binary file not shown.
Binary file not shown.
@ -15,8 +15,11 @@ class Config:
|
||||
embedding_size = 256
|
||||
img_size = 224
|
||||
|
||||
ckpt_path = r"ckpts\resnet18_1220\best.pth"
|
||||
ckpt_path = r"ckpts\best_resnet18_1887_0311.pth"
|
||||
|
||||
current_path = os.path.dirname(os.path.abspath(__file__))
|
||||
model_path = os.path.join(current_path, r"ckpts\resnet18_1220\best.pth")
|
||||
model_path = os.path.join(current_path, ckpt_path)
|
||||
|
||||
# model_path = "./trackers/reid/ckpts/resnet18_1220/best.pth"
|
||||
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
||||
|
||||
@ -46,6 +46,8 @@ class ReIDInterface:
|
||||
|
||||
|
||||
self.model = nn.DataParallel(model).to(self.device)
|
||||
|
||||
self.model = model
|
||||
self.model.load_state_dict(torch.load(self.model_path, map_location=self.device))
|
||||
self.model.eval()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user