毕设成品 深度学习社交距离检测系统（源码+论文）

    import argparse
    from utils.datasets import *
    from utils.utils import *
     
    def detect(save_img=False):
    out, source, weights, view_img, save_txt, imgsz = \
        opt.output, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
    webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt')
     
    # Initialize
    device = torch_utils.select_device(opt.device)
    if os.path.exists(out):
        shutil.rmtree(out)  # delete output folder
    os.makedirs(out)  # make new output folder
    half = device.type != 'cpu'  # half precision only supported on CUDA
     
    # Load model
    google_utils.attempt_download(weights)
    model = torch.load(weights, map_location=device)['model'].float()  # load to FP32
    # torch.save(torch.load(weights, map_location=device), weights)  # update model if SourceChangeWarning
    # model.fuse()
    model.to(device).eval()
    if half:
        model.half()  # to FP16
     
    # Second-stage classifier
    classify = False
    if classify:
        modelc = torch_utils.load_classifier(name='resnet101', n=2)  # initialize
        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model'])  # load weights
        modelc.to(device).eval()
     
    # Set Dataloader
    vid_path, vid_writer = None, None
    if webcam:
        view_img = True
        torch.backends.cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=imgsz)
    else:
        save_img = True
        dataset = LoadImages(source, img_size=imgsz)
     
    # Get names and colors
    names = model.names if hasattr(model, 'names') else model.modules.names
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))]
     
    # Run inference
    t0 = time.time()
    img = torch.zeros((1, 3, imgsz, imgsz), device=device)  # init img
    _ = model(img.half() if half else img) if device.type != 'cpu' else None  # run once
    for path, img, im0s, vid_cap in dataset:
        img = torch.from_numpy(img).to(device)
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        if img.ndimension() == 3:
            img = img.unsqueeze(0)
     
        # Inference
        t1 = torch_utils.time_synchronized()
        pred = model(img, augment=opt.augment)[0]
     
        # Apply NMS
        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres,
                                   fast=True, classes=opt.classes, agnostic=opt.agnostic_nms)
        t2 = torch_utils.time_synchronized()
     
        # Apply Classifier
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)
     
        # List to store bounding coordinates of people
        people_coords = []
     
        # Process detections
        for i, det in enumerate(pred):  # detections per image
            if webcam:  # batch_size >= 1
                p, s, im0 = path[i], '%g: ' % i, im0s[i].copy()
            else:
                p, s, im0 = path, '', im0s
     
            save_path = str(Path(out) / Path(p).name)
            s += '%gx%g ' % img.shape[2:]  # print string
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  #  normalization gain whwh
            if det is not None and len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
     
                # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    s += '%g %ss, ' % (n, names[int(c)])  # add to string
     
                # Write results
                for *xyxy, conf, cls in det:
                    if save_txt:  # Write to file
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                        with open(save_path[:save_path.rfind('.')] + '.txt', 'a') as file:
                            file.write(('%g ' * 5 + '\n') % (cls, *xywh))  # label format
     
                    if save_img or view_img:  # Add bbox to image
                        label = '%s %.2f' % (names[int(cls)], conf)
                        if label is not None:
                            if (label.split())[0] == 'person':
                                people_coords.append(xyxy)
                                # plot_one_box(xyxy, im0, line_thickness=3)
                                plot_dots_on_people(xyxy, im0)
     
            # Plot lines connecting people
            distancing(people_coords, im0, dist_thres_lim=(200,250))
     
            # Print time (inference + NMS)
            print('%sDone. (%.3fs)' % (s, t2 - t1))
     
            # Stream results
            if view_img:
                cv2.imshow(p, im0)
                if cv2.waitKey(1) == ord('q'):  # q to quit
                    raise StopIteration
     
            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'images':
                    cv2.imwrite(save_path, im0)
                else:
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()  # release previous video writer
     
                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*opt.fourcc), fps, (w, h))
                    vid_writer.write(im0)
     
    if save_txt or save_img:
        print('Results saved to %s' % os.getcwd() + os.sep + out)
        if platform == 'darwin':  # MacOS
            os.system('open ' + save_path)
     
    print('Done. (%.3fs)' % (time.time() - t0))
     
    
    
    python
    
    
![](https://ad.itadn.com/c/weblog/blog-img/images/2025-08-18/V2wvbmraudCWilAXUqB7pKySGkYt.png)

    def check_anchors(dataset, model, thr=4.0, imgsz=640):
    # Check anchor fit to data, recompute if necessary
    print('\nAnalyzing anchors... ', end='')
    m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1]  # Detect()
    shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
    wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)])).float()  # wh
    
    def metric(k):  # compute metric
        r = wh[:, None] / k[None]
        x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
        best = x.max(1)[0]  # best_x
        return (best > 1. / thr).float().mean()  #  best possible recall
    
    bpr = metric(m.anchor_grid.clone().cpu().view(-1, 2))
    print('Best Possible Recall (BPR) = %.4f' % bpr, end='')
    if bpr < 0.99:  # threshold to recompute
        print('. Attempting to generate improved anchors, please wait...' % bpr)
        na = m.anchor_grid.numel() // 2  # number of anchors
        new_anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
        new_bpr = metric(new_anchors.reshape(-1, 2))
        if new_bpr > bpr:  # replace anchors
            new_anchors = torch.tensor(new_anchors, device=m.anchors.device).type_as(m.anchors)
            m.anchor_grid[:] = new_anchors.clone().view_as(m.anchor_grid)  # for inference
            m.anchors[:] = new_anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1)  # loss
            print('New anchors saved to model. Update model *.yaml to use these anchors in the future.')
        else:
            print('Original anchors better than new anchors. Proceeding with original anchors.')
    print('')  # newline
    
    
    python
    
    
![](https://ad.itadn.com/c/weblog/blog-img/images/2025-08-18/970uq1XhkCxTMQEJLIcZsglaF8Ab.png)

    class TrackState:
    	'''
    	单个轨迹的三种状态
    	'''
    Tentative = 1 #不确定态
    Confirmed = 2 #确定态
    Deleted = 3 #删除态
    
    class Track:
    def __init__(self, mean, covariance, track_id, class_id, conf, n_init, max_age,
                 feature=None):
        '''
        mean:位置、速度状态分布均值向量，维度(8×1)
        convariance:位置、速度状态分布方差矩阵，维度(8×8)
        track_id:轨迹ID
        class_id:轨迹所属类别
        hits:轨迹更新次数(初始化为1)，即轨迹与目标连续匹配成功次数
        age:轨迹连续存在的帧数(初始化为1)，即轨迹出现到被删除的连续总帧数
        time_since_update:轨迹距离上次更新后的连续帧数(初始化为0)，即轨迹与目标连续匹配失败次数
        state:轨迹状态
        features:轨迹所属目标的外观语义特征，轨迹匹配成功时添加当前帧的新外观语义特征
        conf:轨迹所属目标的置信度得分
        _n_init:轨迹状态由不确定态到确定态所需连续匹配成功的次数
        _max_age:轨迹状态由不确定态到删除态所需连续匹配失败的次数
        '''   
        self.mean = mean
        self.covariance = covariance
        self.track_id = track_id
        self.class_id = int(class_id)
        self.hits = 1
        self.age = 1
        self.time_since_update = 0
    
        self.state = TrackState.Tentative
        self.features = []
        if feature is not None:
            self.features.append(feature) #若不为None，初始化外观语义特征
    
        self.conf = conf
        self._n_init = n_init
        self._max_age = max_age
    
    def increment_age(self):
    	'''
    	预测下一帧轨迹时调用
    	'''
        self.age += 1 #轨迹连续存在帧数+1
        self.time_since_update += 1 #轨迹连续匹配失败次数+1
    
    def predict(self, kf):
    	'''
    	预测下一帧轨迹信息
    	'''
        self.mean, self.covariance = kf.predict(self.mean, self.covariance) #卡尔曼滤波预测下一帧轨迹的状态均值和方差
        self.increment_age() #调用函数，age+1，time_since_update+1
    
    def update(self, kf, detection, class_id, conf):
    	'''
    	更新匹配成功的轨迹信息
    	'''
        self.conf = conf #更新置信度得分
        self.mean, self.covariance = kf.update(
            self.mean, self.covariance, detection.to_xyah()) #卡尔曼滤波更新轨迹的状态均值和方差
        self.features.append(detection.feature) #添加轨迹对应目标框的外观语义特征
        self.class_id = class_id.int() #更新轨迹所属类别
    
        self.hits += 1 #轨迹匹配成功次数+1
        self.time_since_update = 0 #匹配成功时，轨迹连续匹配失败次数归0
        if self.state == TrackState.Tentative and self.hits >= self._n_init:
            self.state = TrackState.Confirmed #当连续匹配成功次数达标时轨迹由不确定态转为确定态
    
    def mark_missed(self):
    	'''
    	将轨迹状态转为删除态
    	'''
        if self.state == TrackState.Tentative:
            self.state = TrackState.Deleted #当级联匹配和IOU匹配后仍为不确定态
        elif self.time_since_update > self._max_age:
            self.state = TrackState.Deleted #当连续匹配失败次数超标
    
    	'''
    	该部分还存在一些轨迹坐标转化及状态判定函数，具体可参考代码来源
    	'''
    
    
    
    python
    
    
![](https://ad.itadn.com/c/weblog/blog-img/images/2025-08-18/9NmcDKhvGZ6gTeEkWyQ105SRtfja.png)