Tensorflow对象检测：计算边界框和警报区域之间的距离

如何解决Tensorflow对象检测：计算边界框和警报区域之间的距离

我正在使用CV2捕获视频并在视频帧中定义感兴趣的区域

cap = cv2.VideoCapture(0)
image_np = cap.read()    
pts = np.array([[57,69],[215,65],[270,476],[3,476]],np.int32)
cv2.polylines(image_np,[pts],isClosed = True,color=(255,0),thickness=2)

在定义了上述感兴趣的区域之后，每当我的对象检测模型检测到带有框的对象，并且一旦它进入定义的区域，我都需要发出警报。我该如何处理？以下是来自tensorflow反对回购的功能

def show_inference(model,image_path):
  # the array based representation of the image will be used later in order to prepare the
  # result image with boxes and labels on it.
  image_np = np.array(Image.open(image_path))
  # Actual detection.
  output_dict = run_inference_for_single_image(model,image_np)
  # Visualization of the results of a detection.
  vis_util.visualize_boxes_and_labels_on_image_array(
      image_np,output_dict['detection_boxes'],output_dict['detection_classes'],output_dict['detection_scores'],category_index,instance_masks=output_dict.get('detection_masks_reframed',None),use_normalized_coordinates=True,line_thickness=8)
  display(Image.fromarray(image_np))

我稍后将定义一个函数，该函数可以给我以下警告

if (distance_from_polygon <= 0) :
   posii=int(image_np.shape[1]/2)        
   cv2.putText(image_np,"ALERT",(posii,50),cv2.FONT_HERSHEY_SIMPLEX,0.75,(255,2)
   playsound(r"C:\Project\alert.wav")
   cv2.rectangle(image_np,(posii-20,20),(posii+85,60),thickness=3,lineType=8,shift=0)           
        return 1
    else:
       return 0

如何获取distance_from_polygon的值，即定义的区域与边界框之间的距离？