Reproduce “Local Histogram Matching for Efficient Optical Flow Computation Applied to Velocity Estimation on Pocket Drones” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Kimberly McGuire, Guido de Croon, Christophe de Wagter, Bart Remes, Karl Tuyls, Hilbert Kappen

EdgeFlow estimates image motion for pocket-drone velocity control by matching one-dimensional edge histograms across frames and adapting the time horizon to detect slow, sub-pixel motion. It ran on a 4 g stereo-camera board and fed a 40 g drone’s control loop. In a 370-second flight, horizontal MSE was 0.0041 and NMXM 0.9631 against OptiTrack, demonstrating this tested setup, not general navigation.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.