{"version":"1.0","type":"rich","title":"To extract an individual running in the foreground of a video clip from the background to analyze their running gait.","description":"This example segments a runner in the foreground of a video clip by constructing a background mosaic from multiple frames, then uses the extracted foreground images for gait recognition. It detects SURF keypoints and descriptors with OpenCV’s `FeatureDetector_create` and `DescriptorExtractor_create`, matches features via `flann_Index.knnSearch`, and computes homographies with `cv2.warpPerspective` to align frames into a panorama. The code relies on Python 2.7, OpenCV, and NumPy, with helper functions for correspondence drawing and display.","provider_name":"VizHub AI Studio","provider_url":"https://next.vizhub.com","html":"<iframe src=\"https://next.vizhub.com/viz/gist-18ba4da4d26649bd3bfc?mode=embed\" width=\"960\" height=\"500\" scrolling=\"no\" frameborder=\"1\"></iframe>","width":960,"height":500,"cache_age":3600}