AUTHOR=Yan Fei , Liu Lan , Ding Xupeng , Zhang Qiong , Liu Yunqing TITLE=Monocular catadioptric panoramic depth estimation via improved end-to-end neural network model JOURNAL=Frontiers in Neurorobotics VOLUME=17 YEAR=2023 URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2023.1278986 DOI=10.3389/fnbot.2023.1278986 ISSN=1662-5218 ABSTRACT=

In this paper, we propose a monocular catadioptric panoramic depth estimation algorithm based on an improved end-to-end neural network model. First, we use an enhanced concentric circle approximation unfolding algorithm to unfold the panoramic images captured by the catadioptric panoramic camera and then extract the effective regions. In addition, the integration of the Non-local attention mechanism is exploited to improve image understanding. Finally, a depth smoothness loss strategy is implemented to further enhance the reliability and precision of the estimated depths. Experimental results confirm that this refined algorithm is capable of providing highly accurate estimates of object depth.