Real-time monocular depth estimation with adaptive receptive fields

Monocular depth estimation is a popular research topic in the field of autonomous driving. Nowadays many models are leading in accuracy but performing poorly in a real-time scenario. To effectively increase the depth estimation efficiency, we propose a novel model combining a multi-scale pyramid arc...

ver descrição completa

Detalhes bibliográficos
Autores: Ji, Zhenyan, Song, Xiaojun, Guo, Xiaoxuan, Wang, Fangshi, Armendáriz Íñigo, José Enrique
Tipo de documento: artigo
Estado:Versión aceptada para publicación
Data de publicação:2020
País:España
Recursos:Universidad Pública de Navarra
Repositório:Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
OAI Identifier:oai:academica-e.unavarra.es:2454/55938
Acesso em linha:https://hdl.handle.net/2454/55938
Access Level:Acceso aberto
Palavra-chave:Monocular depth estimation
Adaptive receptive field
Real-time performance
Convolutional neural network
Descrição
Resumo:Monocular depth estimation is a popular research topic in the field of autonomous driving. Nowadays many models are leading in accuracy but performing poorly in a real-time scenario. To effectively increase the depth estimation efficiency, we propose a novel model combining a multi-scale pyramid architecture for depth estimation together with adaptive receptive fields. The pyramid architecture reduces the trainable parameters from dozens of mega to less than 10 mega. Adaptive receptive fields are more sensitive to objects at different depth/distances in images, leading to better accuracy. We have adopted stacked convolution kernels instead of raw kernels to compress the model. Thus, the model that we proposed performs well in both real-time performance and estimation accuracy. We provide a set of experiments where our model performs better in terms of Eigen split than other previously known models. Furthermore, we show that our model is also better in runtime performance in regard to the depth estimation to the rest of models but the Pyd-Net model. Finally, our model is a lightweight depth estimation model with state-of-the-art accuracy.