hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.1080/00051144.2018.1503137

Depth sensing with disparity space images and three-dimensional recursive search

Miroslav Rožić ; Zagrebačka Banka d.d., Zagreb, Croatia
Tomislav Pribanić ; Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia

Puni tekst: engleski, pdf (3 MB) str. 131-142 preuzimanja: 112* citiraj
APA 6th Edition
Rožić, M. i Pribanić, T. (2018). Depth sensing with disparity space images and three-dimensional recursive search. Automatika, 59 (2), 131-142. https://doi.org/10.1080/00051144.2018.1503137
MLA 8th Edition
Rožić, Miroslav i Tomislav Pribanić. "Depth sensing with disparity space images and three-dimensional recursive search." Automatika, vol. 59, br. 2, 2018, str. 131-142. https://doi.org/10.1080/00051144.2018.1503137. Citirano 10.07.2020.
Chicago 17th Edition
Rožić, Miroslav i Tomislav Pribanić. "Depth sensing with disparity space images and three-dimensional recursive search." Automatika 59, br. 2 (2018): 131-142. https://doi.org/10.1080/00051144.2018.1503137
Harvard
Rožić, M., i Pribanić, T. (2018). 'Depth sensing with disparity space images and three-dimensional recursive search', Automatika, 59(2), str. 131-142. https://doi.org/10.1080/00051144.2018.1503137
Vancouver
Rožić M, Pribanić T. Depth sensing with disparity space images and three-dimensional recursive search. Automatika [Internet]. 2018 [pristupljeno 10.07.2020.];59(2):131-142. https://doi.org/10.1080/00051144.2018.1503137
IEEE
M. Rožić i T. Pribanić, "Depth sensing with disparity space images and three-dimensional recursive search", Automatika, vol.59, br. 2, str. 131-142, 2018. [Online]. https://doi.org/10.1080/00051144.2018.1503137

Sažetak
We present a coarse-to-fine stereo matching optimization applicable to methods utilizing the Disparity Space Image (DSI) structure. With the Three-dimensional Recursive Search algorithm (3DRS), a coarse disparity seed is obtained first, with minimal computational effort. The coarse disparity seed is then used as a guidance to locally compute the DSI disparity space with a reduced number of disparity hypotheses, yielding significantly shorter execution times for the disparity computation. The method performance was measured on the well-known Dynamic Programming (DP) DSI-based method and the images from the Middlebury set. The DP method with the DSI optimization applied maintains or improves the overall level of disparity map accuracy while delivering a near sevenfold speed-up of execution in comparison to DP alone. We furthermore show that the optimized method’s performance does not depend on the expected input disparity range, which is commonly restricted, or expected to be defined upfront, for DSI-based stereo matching methods

Ključne riječi
Stereo vision; disparity computation; dynamic programming; DSI; 3DRS; census transform

Hrčak ID: 225187

URI
https://hrcak.srce.hr/225187

Posjeta: 178 *