Event-based vision, as realized by bio-inspired Dynamic Vision Sensors (DVS), is gaining more and more popularity due to its advantages of high temporal resolution, wide dynamic range and power efficiency at the same time. Potential applications include surveillance, robotics, and autonomous navigation under uncontrolled environment conditions. In this paper, we deal with event-based vision for 3D reconstruction of dynamic scene content by using two stationary DVS in a stereo configuration. We focus on a cooperative stereo approach and suggest an improvement over a previously published algorithm that reduces the measured mean error by over 50 percent. An available ground truth data set for stereo event data is utilized to analyze the algorithm´s sensitivity to parameter variation and for comparison with competing techniques.
E. Piatkowska, J. Kogler, A. Belbachir, M. Gelautz: "Improved Cooperative Stereo Matching for Dynamic Vision Sensors with Ground Truth Evaluation"; Poster: 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, Hawaii; 07-21-2017 - 07-26-2017; in: "Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)", Institute of Electrical and Electronics Engineers (IEEE), (2017), ISBN: 978-1-5386-0733-6; 370 - 377.
Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.