Naslov
Dense Disparity Estimation in Ego-motion Reduced Search Space

Autori
Fućek, Luka ; Marković, Ivan ; Cvišić, Igor ; Petrović, Ivan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
IFAC World Congress / - , 2017

Skup
IFAC World Congress

Mjesto i datum
Toulouse, Francuska, 09.07.2017. - 14.07.2017

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Stereo Vision ; Visual odometry ; Disparity estimation

Sažetak
Depth estimation from stereo images remains a challenge even though studied for decades. The KITTI benchmark shows that the state-of-the-art solutions offer accurate depth estimation, but are still computationally complex and often require a GPU or FPGA implementation. In this paper we aim at increasing the accuracy of depth map estimation and reducing the computational complexity by using information from previous frames. We propose to transform the disparity map of the previous frame into the current frame, relying on the estimated ego-motion, and use this map as the prediction for the Kalman filter in the disparity space. Then, we update the predicted disparity map using the newly matched one. This way we reduce disparity search space and flickering between consecutive frames, thus increasing the computational efficiency of the algorithm. In the end, we validate the proposed approach on real-world data from the KITTI benchmark suite and show that the proposed algorithm yields more accurate results, while at the same time reducing the disparity search space.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Temeljne tehničke znanosti

POVEZANOST RADA