No GPU? No problem: an ultra fast 3D detection of road users with a simple proposal generator and energy-based out-of-distribution PointNets

TL;DR

This paper introduces a fast, CPU-efficient 3D road user detection method using simple geometrical rules and energy-based out-of-distribution detection, achieving real-time performance without GPU reliance.

Contribution

The paper proposes a novel point cloud detection architecture based on classical geometrical rules combined with energy-based out-of-distribution detection, enabling real-time CPU performance.

Findings

Achieves comparable mAP to state-of-the-art methods.

Operates in real-time on a single CPU core.

Introduces a new ground segmentation method evaluated on SemanticKITTI.

Abstract

This paper presents a novel architecture for point cloud road user detection, which is based on a classical point cloud proposal generator approach, that utilizes simple geometrical rules. New methods are coupled with this technique to achieve extremely small computational requirement, and mAP that is comparable to the state-of-the-art. The idea is to specifically exploit geometrical rules in hopes of faster performance. The typical downsides of this approach, e.g. global context loss, are tackled in this paper, and solutions are presented. This approach allows real-time performance on a single core CPU, which is not the case with end-to-end solutions presented in the state-of-the-art. We have evaluated the performance of the method with the public KITTI dataset, and with our own annotated dataset collected with a small mobile robot platform. Moreover, we also present a novel ground segmentation method, which is evaluated with the public SemanticKITTI dataset.