Cargando…

Monocular catadioptric panoramic depth estimation via improved end-to-end neural network model

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Yan, Fei, Liu, Lan, Ding, Xupeng, Zhang, Qiong, Liu, Yunqing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10560983/
https://www.ncbi.nlm.nih.gov/pubmed/37818233
http://dx.doi.org/10.3389/fnbot.2023.1278986
Descripción
Sumario: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.