Title

Bayesian Gabor Network with Uncertainty Estimation for Pedestrian Lane Detection in Assistive Navigation

Publication Name

IEEE Transactions on Circuits and Systems for Video Technology

Abstract

Automatic pedestrian lane detection is a challenging problem that is of great interest in assistive navigation and autonomous driving. Such a detection system must cope well with variations in lane surfaces and illumination conditions so that a vision-impaired user can navigate safely in unknown environments. This paper proposes a new lightweight Bayesian Gabor Network (BGN) for camera-based detection of pedestrian lanes in unstructured scenes. In our approach, each Gabor parameter is represented as a learnable Gaussian distribution using variational Bayesian inference. For the safety of vision-impaired users, in addition to an output segmentation map, the network provides two full-resolution maps of aleatoric uncertainty and epistemic uncertainty as well-calibrated confidence measures. Our Gabor-based method has fewer weights than the standard CNNs, therefore it is less prone to overfitting and requires fewer operations to compute. Compared to the state-of-the-art semantic segmentation methods, the BGN maintains a competitive segmentation performance while achieving a significantly compact model size (from 1.8× to 237.6× reduction), a fast prediction time (from 1.2× to 67.5× faster), and a well-calibrated uncertainty measure. We also introduce a new lane dataset of 10,000 images for objective evaluation in pedestrian lane detection research.

Open Access Status

This publication is not available as open access

Share

COinS
 

Link to publisher version (DOI)

http://dx.doi.org/10.1109/TCSVT.2022.3144184