Can I receive a boudingPoly for LABEL_DETECTION results?

问题

How can this be completed with the Google Vision-API please?

1. send image to vision-api
2. request: 'features': [{': 'LABEL_DETECTION','maxResults': 10,}]
3. receive the labels in particular the one I'm interest in is a "clock"
4. receive the boundingPoly so that I know the exact location of the clock within the image
5. having received the boundingPoly I would want to use it to create a dynamic AR marker to be tracked by the AR library

Currently it doesn't look like Google Vision-API supports a boudingPoly for LABELS hence the question if there is a way to solve it with the Vision-API.

回答1:

Currently Label Detection does not provide this functionality. We are always looking at ways to enhance the API

回答2:

After two years, its the same. I am facing similar challenges and I am thinking of opting other solutions. I think custom solutions like TensorFlow object detection API or DarkNet YOLO object API will do this job very easily.

来源：https://stackoverflow.com/questions/35737830/can-i-receive-a-boudingpoly-for-label-detection-results