Description : SPiKeS-T (SuperPixel-Keypoints Structure Tracker) is a model-free tracker I developed during my master of research. In a video, the target to follow is only defined by a bounding box in the first frame. The goal is to track that target in each frame of the video. The method I proposed is based on superpixels, keypoints and voting strategy. A paper is currently in review but it can already be downloaded here.
Context : Master's project at Polytechnique Montreal.
Tools : C++, OpenCV and CUDA.
Source code : https://github.com/fderue/SPIKES
The target is represented by a Spikes-based model. A Spikes is a modified superpixel linked with surrounding keypoints to result in a structure easy to match.
Each spikes of the model looks for a match in the current frame. This video shows consistent matches as the red lines are parallel.