Multi Object Trackers基于 Python 的多对象跟踪器-技术圈

Multi Object Trackers 是一个基于 Python，易于使用的各种多对象跟踪算法的实现。

可用的多对象跟踪器

CentroidTracker
IOUTracker
CentroidKF_Tracker
SORT

可用的基于 OpenCV 的物体检测器：

detector.TF_SSDMobileNetV2
detector.Caffe_SSDMobileNet
detector.YOLOv3

安装

OpenCV（版本 3.4.3 或更高版本）的 Pip install 可以使用以下命令完成：

git clone https://github.com/adipandas/multi-object-tracker
cd multi-object-tracker
pip install -r requirements.txt
pip install -e .

如何使用？

每个跟踪器的界面都很简单而相似，可参考下面的示例模板：

from motrackers import CentroidTracker # or IOUTracker, CentroidKF_Tracker, SORT
input_data = ...
detector = ...
tracker = CentroidTracker(...) # or IOUTracker(...), CentroidKF_Tracker(...), SORT(...)
while True:
    done, image = 
      
       
    if done:
        break
    detection_bboxes, detection_confidences, detection_class_ids = detector.detect(image)
    # NOTE: 
    # * `detection_bboxes` are numpy.ndarray of shape (n, 4) with each row containing (bb_left, bb_top, bb_width, bb_height)
    # * `detection_confidences` are numpy.ndarray of shape (n,);
    # * `detection_class_ids` are numpy.ndarray of shape (n,).
    output_tracks = tracker.update(detection_bboxes, detection_confidences, detection_class_ids)
    # `output_tracks` is a list with each element containing tuple of
    # (, 
       
        , 
        
         , 
         
          , 
          
           , 
           
            , 
            
             , 
             
              , 
              
               , 
               
                ) for track in output_tracks: frame, id, bb_left, bb_top, bb_width, bb_height, confidence, x, y, z = track assert len(track) == 10 print(track)
               
              
             
            
           
          
         
        
       
      (input_data)>


                              
                              
                              
                              
                              
                              
                              
                              
                              
                               
                              
                              
                              
                              
                              
                              
                              
                              
                              
                              (input_data)>有关更多详细信息，请参阅此存储库的示例文件夹。您可以克隆和运行示例。