I am confused at how to get the confidence level when using HOG GPU implementation in OpenCV 3.
According to [OpenCV 3.1 cv::cuda::HOG::detectMultiScale Documentation](http://docs.opencv.org/3.1.0/de/da6/classcv_1_1cuda_1_1HOG.html#af4a3bf27a5a04817c6d584d9108f50b7), code replicated below:
virtual void
cv::cuda::HOG::detectMultiScale(InputArray img,
std::vector& found_locations,
std::vector* confidences = NULL)
You can pass a pointer to the third argument `confidences`. I've tried it but got `OpenCV Error: Assertion failed (confidence == NULL || group_threshold_ == 0)`.
Looking at the actual implementation ([hog.cpp:385](https://github.com/opencv/opencv/blob/05b15943d6a42c99e5f921b7dbaa8323f3c042c6/modules/cudaobjdetect/src/hog.cpp#L385)), it is checking the `confidences` and only allowing a `NULL` parameter (code replicated below):
CV_Assert( confidences == NULL || group_threshold_ == 0 );
The same question has also been asked on [StackOverflow](http://stackoverflow.com/questions/40015587/opencv-3-hog-detection-confidence) and hasn't been addressed. Please advice.
↧
