YOLOv4-DeepSort目标跟踪如何从track对象取分数并打印到边界框

解决方法 #

你使用的YOLOv4-DeepSort项目中，Track对象默认已经存储了匹配到的检测目标置信度，直接通过track.conf属性即可获取。如果需要在边界框上标注该值，只需修改你现有代码中绘制文本的逻辑即可，修改后的代码如下：

def process_detections(tracker, detections, nms_max_overlap, frame):
    """
    Process objects detected by YOLO with deepsort
    Returns processed frame
    """
    #initialize color map
    cmap = plt.get_cmap('tab20b')
    colors = [cmap(i)[:3] for i in np.linspace(0, 1, 20)]

    # run non-maxima supression
    boxs = np.array([d.tlwh for d in detections])
    scores = np.array([d.confidence for d in detections])
    classes = np.array([d.class_name for d in detections])
    indices = preprocessing.non_max_suppression(boxs, classes, nms_max_overlap, scores)
    detections = [detections[i] for i in indices]       

    # Call the tracker
    tracker.predict()
    tracker.update(detections)

    # update tracks
    for track in tracker.tracks:
        if not track.is_confirmed() or track.time_since_update > 1:
            continue 
        bbox = track.to_tlbr()
        class_name = track.get_class()
        # 新增：获取跟踪置信度，保留两位小数
        track_conf = round(track.conf, 2)
        
        # draw bbox on screen
        color = colors[int(track.track_id) % len(colors)]
        color = [i * 255 for i in color]
        cv2.rectangle(frame, (int(bbox[0]), int(bbox[1])), (int(bbox[2]), int(bbox[3])), color, 1)
        # 拼接包含置信度的标注文本
        label_text = f"{class_name}-{track.track_id} 置信度:{track_conf}"
        # 调整顶部填充框宽度适配新增的文本长度
        cv2.rectangle(frame, (int(bbox[0]), int(bbox[1]-30)), 
                (int(bbox[0]) + len(label_text)*17, int(bbox[1])), color, -1)
        cv2.putText(frame, label_text,(int(bbox[0]), 
                int(bbox[1]-10)),0, 0.5, (255,255,255), 1)

        # if enable info flag then print details about each track
        if FLAGS.info:
            print("Tracker ID: {}, Class: {}, 置信度: {}, BBox Coords (xmin, ymin, xmax, ymax): {}".format(str(track.track_id), 
                class_name, track_conf, (int(bbox[0]), int(bbox[1]), int(bbox[2]), int(bbox[3]))))
    return frame

如果你使用的版本没有内置track.conf属性，可以手动补充该属性：

• 找到项目下deep_sort/track.py文件，在Track类的__init__方法中新增一行self.conf = 0.0
• 找到同文件中的update方法，在匹配到检测框的逻辑分支下新增一行self.conf = detection.confidence即可。

内容的提问来源于stack exchange，提问作者user3410517