3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization

TL;DR

This paper introduces a novel data augmentation and multi-layer projection technique for deep multi-camera pedestrian detection, significantly improving accuracy under occlusion conditions.

Contribution

It proposes a 3D occlusion simulation and multi-plane feature projection method to enhance multi-view pedestrian localization.

Findings

Improved detection accuracy over state-of-the-art methods

Effective reduction of overfitting in training

Enhanced utilization of multi-view features

Abstract

Although deep-learning based methods for monocular pedestrian detection have made great progress, they are still vulnerable to heavy occlusions. Using multi-view information fusion is a potential solution but has limited applications, due to the lack of annotated training samples in existing multi-view datasets, which increases the risk of overfitting. To address this problem, a data augmentation method is proposed to randomly generate 3D cylinder occlusions, on the ground plane, which are of the average size of pedestrians and projected to multiple views, to relieve the impact of overfitting in the training. Moreover, the feature map of each view is projected to multiple parallel planes at different heights, by using homographies, which allows the CNNs to fully utilize the features across the height of each pedestrian to infer the locations of pedestrians on the ground plane. The proposed 3DROM method has a greatly improved performance in comparison with the state-of-the-art deep-learning based methods for multi-view pedestrian detection.