VLASE: Vehicle Localization by Aggregating Semantic Edges

TL;DR

VLASE leverages semantic edge features from images, extracted via CASENet, and employs VLAD for image retrieval to improve on-road vehicle localization accuracy over existing methods.

Contribution

This work introduces a generalized semantic edge-based localization framework using 19 classes and demonstrates its superiority over prior skyline-focused approaches.

Findings

Achieves better localization accuracy than SIFT-VLAD and NetVLAD.

Semantic edges from 19 classes improve localization performance.

Ablation study highlights the importance of multiple semantic classes.

Abstract

In this paper, we propose VLASE, a framework to use semantic edge features from images to achieve on-road localization. Semantic edge features denote edge contours that separate pairs of distinct objects such as building-sky, road- sidewalk, and building-ground. While prior work has shown promising results by utilizing the boundary between prominent classes such as sky and building using skylines, we generalize this approach to consider semantic edge features that arise from 19 different classes. Our localization algorithm is simple, yet very powerful. We extract semantic edge features using a recently introduced CASENet architecture and utilize VLAD framework to perform image retrieval. Our experiments show that we achieve improvement over some of the state-of-the-art localization algorithms such as SIFT-VLAD and its deep variant NetVLAD. We use ablation study to study the importance of different semantic classes and show that our unified approach achieves better performance compared to individual prominent features such as skylines.