diff --git a/.gitignore b/.gitignore index c12045c..7cba0ed 100644 --- a/.gitignore +++ b/.gitignore @@ -54,6 +54,7 @@ VOC/ # Neural Network weights ----------------------------------------------------------------------------------------------- *.weights *.pt +*.pth *.pb *.onnx *.engine diff --git a/featureVal.py b/featureVal.py new file mode 100644 index 0000000..fa272a6 --- /dev/null +++ b/featureVal.py @@ -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() + + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/track_reid.py b/track_reid.py index 9fdfc32..6f107a9 100644 --- a/track_reid.py +++ b/track_reid.py @@ -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) diff --git a/tracking/dotrack/__pycache__/dotracks.cpython-39.pyc b/tracking/dotrack/__pycache__/dotracks.cpython-39.pyc index 10c7a0a..284ec6f 100644 Binary files a/tracking/dotrack/__pycache__/dotracks.cpython-39.pyc and b/tracking/dotrack/__pycache__/dotracks.cpython-39.pyc differ diff --git a/tracking/dotrack/__pycache__/dotracks_back.cpython-39.pyc b/tracking/dotrack/__pycache__/dotracks_back.cpython-39.pyc index ff055b2..35a02d7 100644 Binary files a/tracking/dotrack/__pycache__/dotracks_back.cpython-39.pyc and b/tracking/dotrack/__pycache__/dotracks_back.cpython-39.pyc differ diff --git a/tracking/dotrack/__pycache__/dotracks_front.cpython-39.pyc b/tracking/dotrack/__pycache__/dotracks_front.cpython-39.pyc index 917e917..1f4227f 100644 Binary files a/tracking/dotrack/__pycache__/dotracks_front.cpython-39.pyc and b/tracking/dotrack/__pycache__/dotracks_front.cpython-39.pyc differ diff --git a/tracking/dotrack/__pycache__/track_back.cpython-39.pyc b/tracking/dotrack/__pycache__/track_back.cpython-39.pyc index 8d8b22b..4d0685b 100644 Binary files a/tracking/dotrack/__pycache__/track_back.cpython-39.pyc and b/tracking/dotrack/__pycache__/track_back.cpython-39.pyc differ diff --git a/tracking/dotrack/__pycache__/track_front.cpython-39.pyc b/tracking/dotrack/__pycache__/track_front.cpython-39.pyc index 2f53f33..48551a6 100644 Binary files a/tracking/dotrack/__pycache__/track_front.cpython-39.pyc and b/tracking/dotrack/__pycache__/track_front.cpython-39.pyc differ diff --git a/tracking/dotrack/dotracks.py b/tracking/dotrack/dotracks.py index 843ad2f..3fdad4b 100644 --- a/tracking/dotrack/dotracks.py +++ b/tracking/dotrack/dotracks.py @@ -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) diff --git a/tracking/dotrack/dotracks_back.py b/tracking/dotrack/dotracks_back.py index 71f369e..28fa8ca 100644 --- a/tracking/dotrack/dotracks_back.py +++ b/tracking/dotrack/dotracks_back.py @@ -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 ''' diff --git a/tracking/dotrack/dotracks_front.py b/tracking/dotrack/dotracks_front.py index ccfc97c..6b50522 100644 --- a/tracking/dotrack/dotracks_front.py +++ b/tracking/dotrack/dotracks_front.py @@ -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 -# ============================================================================= - \ No newline at end of file diff --git a/tracking/dotrack/track_back.py b/tracking/dotrack/track_back.py index 391e4c8..e7533fd 100644 --- a/tracking/dotrack/track_back.py +++ b/tracking/dotrack/track_back.py @@ -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) 3 - # cont2 = sum(abs(y1) 3 - cont3 = sum(abs(x2-self.imgshape[0]) 3 - # cont4 = sum(abs(y2-self.imgshape[1]) 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 \ No newline at end of file diff --git a/tracking/dotrack/track_front.py b/tracking/dotrack/track_front.py index 83e178c..e027408 100644 --- a/tracking/dotrack/track_front.py +++ b/tracking/dotrack/track_front.py @@ -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}") diff --git a/tracking/test_tracking.py b/tracking/test_tracking.py index 8e35b60..21a4ba1 100644 --- a/tracking/test_tracking.py +++ b/tracking/test_tracking.py @@ -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) diff --git a/tracking/test_val.py b/tracking/test_val.py new file mode 100644 index 0000000..e5ff032 --- /dev/null +++ b/tracking/test_val.py @@ -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() + + diff --git a/tracking/trackers/reid/__pycache__/config.cpython-39.pyc b/tracking/trackers/reid/__pycache__/config.cpython-39.pyc index dd93c80..437dbd0 100644 Binary files a/tracking/trackers/reid/__pycache__/config.cpython-39.pyc and b/tracking/trackers/reid/__pycache__/config.cpython-39.pyc differ diff --git a/tracking/trackers/reid/__pycache__/reid_interface.cpython-39.pyc b/tracking/trackers/reid/__pycache__/reid_interface.cpython-39.pyc index 57544c5..bd3111e 100644 Binary files a/tracking/trackers/reid/__pycache__/reid_interface.cpython-39.pyc and b/tracking/trackers/reid/__pycache__/reid_interface.cpython-39.pyc differ diff --git a/tracking/trackers/reid/config.py b/tracking/trackers/reid/config.py index 722b2a0..7419dd0 100644 --- a/tracking/trackers/reid/config.py +++ b/tracking/trackers/reid/config.py @@ -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') diff --git a/tracking/trackers/reid/reid_interface.py b/tracking/trackers/reid/reid_interface.py index 2845e09..0ce0fe5 100644 --- a/tracking/trackers/reid/reid_interface.py +++ b/tracking/trackers/reid/reid_interface.py @@ -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()