Fast Obstacle Detection Using Sparse Edge-Based Disparity Maps
Dexmont Alejandro Pena Carrillo, Alistair Sutherland · 2016
This paper presents a fast approach for computing imagestixels from a sparse edge-based disparity map. The use ofedge-based disparity maps speeds up the computation of thestixels as only a few pixels must be processed compared toapproaches which use dense disparity maps. The proposedapproach produces as output the stixels in one of the viewsof the stereo-pair and a segmentation of the edge-pointsinto obstacle. Additionally the proposed approach allowsthe identification of partially occluded objects by allowingmore than one stixel per image column. The proposed ap-proach is fast to compute with no loss on accuracy.