Real-Time RGB-D based Template Matching Pedestrian Detection

TL;DR

This paper introduces a real-time RGB-D based pedestrian detection method using depth templates, multiple training strategies, and a combined appearance verification to improve detection accuracy in challenging scenarios.

Contribution

It proposes a novel depth-based template matching approach with multiple templates and a weighted template method, combined with appearance verification, for enhanced pedestrian detection.

Findings

Outperforms state-of-the-art methods on ETH dataset

Handles various pedestrian orientations and distances effectively

Achieves real-time detection performance

Abstract

Pedestrian detection is one of the most popular topics in computer vision and robotics. Considering challenging issues in multiple pedestrian detection, we present a real-time depth-based template matching people detector. In this paper, we propose different approaches for training the depth-based template. We train multiple templates for handling issues due to various upper-body orientations of the pedestrians and different levels of detail in depth-map of the pedestrians with various distances from the camera. And, we take into account the degree of reliability for different regions of sliding window by proposing the weighted template approach. Furthermore, we combine the depth-detector with an appearance based detector as a verifier to take advantage of the appearance cues for dealing with the limitations of depth data. We evaluate our method on the challenging ETH dataset sequence. We show that our method outperforms the state-of-the-art approaches.