Exploring Self-Attention for Visual Intersection Classification

TL;DR

This paper introduces a self-attention mechanism into an intersection classification system for robot vision, combining first- and third-person views to improve recognition accuracy over traditional methods.

Contribution

The study proposes a novel self-attention-based approach for intersection classification and demonstrates its effectiveness when integrated with FPV and TPV modules.

Findings

Self-attention improves intersection classification accuracy.

The combined FPV and TPV system outperforms traditional methods.

Experiments on KITTI dataset validate the approach.

Abstract

In robot vision, self-attention has recently emerged as a technique for capturing non-local contexts. In this study, we introduced a self-attention mechanism into the intersection recognition system as a method to capture the non-local contexts behind the scenes. An intersection classification system comprises two distinctive modules: (a) a first-person vision (FPV) module, which uses a short egocentric view sequence as the intersection is passed, and (b) a third-person vision (TPV) module, which uses a single view immediately before entering the intersection. The self-attention mechanism is effective in the TPV module because most parts of the local pattern (e.g., road edges, buildings, and sky) are similar to each other, and thus the use of a non-local context (e.g., the angle between two diagonal corners around an intersection) would be effective. This study makes three major contributions. First, we proposed a self-attention-based approach for intersection classification using TPVs. Second, we presented a practical system in which a self-attention-based TPV module is combined with an FPV module to improve the overall recognition performance. Finally, experiments using the public KITTI dataset show that the above self-attention-based system outperforms conventional recognition based on local patterns and recognition based on convolution operations.