Combining LiDAR Space Clustering and Convolutional Neural Networks for Pedestrian Detection

TL;DR

This paper introduces a novel pedestrian detection method combining LiDAR space clustering with CNNs, improving detection recall and reducing misses by leveraging 3D point cloud data alongside visual information.

Contribution

It presents a new approach that uses LiDAR data for region proposal generation, enhancing CNN-based pedestrian detection in autonomous vehicle scenarios.

Findings

LiDAR-based region proposals increase recall rates.

The method reduces false negatives in pedestrian detection.

Extensive evaluation on KITTI dataset confirms effectiveness.

Abstract

Pedestrian detection is an important component for safety of autonomous vehicles, as well as for traffic and street surveillance. There are extensive benchmarks on this topic and it has been shown to be a challenging problem when applied on real use-case scenarios. In purely image-based pedestrian detection approaches, the state-of-the-art results have been achieved with convolutional neural networks (CNN) and surprisingly few detection frameworks have been built upon multi-cue approaches. In this work, we develop a new pedestrian detector for autonomous vehicles that exploits LiDAR data, in addition to visual information. In the proposed approach, LiDAR data is utilized to generate region proposals by processing the three dimensional point cloud that it provides. These candidate regions are then further processed by a state-of-the-art CNN classifier that we have fine-tuned for pedestrian detection. We have extensively evaluated the proposed detection process on the KITTI dataset. The experimental results show that the proposed LiDAR space clustering approach provides a very efficient way of generating region proposals leading to higher recall rates and fewer misses for pedestrian detection. This indicates that LiDAR data can provide auxiliary information for CNN-based approaches.