Skip to main content
placeholder image

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

Journal Article


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\times $ to $237.6\times $ reduction), a fast prediction time (from $1.2\times $ to $67.5\times $ 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.

Publication Date


  • 2022

Citation


  • Thanh Le, H., Phung, S. L., & Bouzerdoum, A. (2022). Bayesian Gabor Network with Uncertainty Estimation for Pedestrian Lane Detection in Assistive Navigation. IEEE Transactions on Circuits and Systems for Video Technology, 32(8), 5331-5345. doi:10.1109/TCSVT.2022.3144184

Scopus Eid


  • 2-s2.0-85123357837

Start Page


  • 5331

End Page


  • 5345

Volume


  • 32

Issue


  • 8

Place Of Publication


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\times $ to $237.6\times $ reduction), a fast prediction time (from $1.2\times $ to $67.5\times $ 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.

Publication Date


  • 2022

Citation


  • Thanh Le, H., Phung, S. L., & Bouzerdoum, A. (2022). Bayesian Gabor Network with Uncertainty Estimation for Pedestrian Lane Detection in Assistive Navigation. IEEE Transactions on Circuits and Systems for Video Technology, 32(8), 5331-5345. doi:10.1109/TCSVT.2022.3144184

Scopus Eid


  • 2-s2.0-85123357837

Start Page


  • 5331

End Page


  • 5345

Volume


  • 32

Issue


  • 8

Place Of Publication