![Limb detection opencv](https://kumkoniak.com/33.jpg)
![limb detection opencv limb detection opencv](https://images2015.cnblogs.com/blog/976394/201703/976394-20170317010251713-1602906154.png)
![limb detection opencv limb detection opencv](https://geekconfig.com/tutorial-cover/post/Mac%EC%97%90%20OpenCV%204%EB%A5%BC%20%EC%84%A4%EC%B9%98%ED%95%A9%EB%8B%88%EB%8B%A4%20Python%EC%97%90%EC%84%9C%20Face%20Recognition%EC%9D%84%20%EC%8B%A4%ED%96%89%ED%95%B4%20%EB%B3%B4%EC%9E%90%20.png)
The buffy stickman approach of the Calvin group :.Class specific hough forests by Gall and Lempitsky :.LatentSVM, discovered by Felzenszwalb :.You need a body part detection algorithm designed for these purposes. Like already pointed out, you are looking to the wrong set of algorithms. What is a good solution to detecting rotation and scale invariant objects such as human limbs in an image? Particularly for this example, what would be a good solution to detecting all orientations of forearms in an image? I have also asked the same question on Stack Overflow: Question: If possible, I would like to steer clear of any non-free solutions such as those pertaining to Sift, Surf, or Haar.
![limb detection opencv limb detection opencv](https://ypupid.fairyworld.info/templates/f16dc396e088c7c707eabe9d7479e7a2/img/11767ba94d33ed050fd2e43f67baf09f.png)
I have reviewed many research papers on the topic trying to resolve or improve this, including the original from Dalal & Triggs : It also seems that the assumptions made for detecting whole humans do not necessary apply to detecting individual features (particularly the assumption that all humans are standing up seems to suggest HOG is not a good route for rotation invariant detection like that of forearms). I suspect the issue is that the gradients produced by each positive image do not produce very consistent results when saved into the Histogram. So far I have done some in depth research on using HOG descriptors to solve this problem, but I am finding that the variety of poses produced by forearms in my positives training set is producing very low detection scores in actual images. It is possible to have images of forearms that are pointing in any direction in an image, thus the complexity. A forearm can have multiple orientations, the primary distinct features probably being its contour edges. Lets focus on forearms for this discussion. I used a 32x32 window with a variety of different input parameters but was never able to to retrieve accurate detection in images. One solution I have tried so far to no avail is HOG detection for forearm identification. The only problem being that I can't seem to find a reasonable feature detector or classifier to detect this in a rotation and scale invariant way (as is needed by objects such as forearms). I would like to find a way to identify individual body part limbs in an image (ie such as Forearm or lower leg).
![Limb detection opencv](https://kumkoniak.com/33.jpg)