Angle Based Feature Learning in GNN for 3D Object Detection using Point Cloud

TL;DR

This paper introduces an angular-based feature encoding method for GNNs to improve 3D object detection in point clouds, demonstrating better performance and rotation resistance compared to traditional methods.

Contribution

It proposes a novel angular-based feature encoding approach for GNNs in 3D object detection, outperforming existing distance-based methods on the KITTI dataset.

Findings

Angular-based encoding improves detection accuracy.

Combination of angle and relative distance outperforms other methods.

Angular encoding enhances rotation invariance in GNNs.

Abstract

In this paper, we present new feature encoding methods for Detection of 3D objects in point clouds. We used a graph neural network (GNN) for Detection of 3D objects namely cars, pedestrians, and cyclists. Feature encoding is one of the important steps in Detection of 3D objects. The dataset used is point cloud data which is irregular and unstructured and it needs to be encoded in such a way that ensures better feature encapsulation. Earlier works have used relative distance as one of the methods to encode the features. These methods are not resistant to rotation variance problems in Graph Neural Networks. We have included angular-based measures while performing feature encoding in graph neural networks. Along with that, we have performed a comparison between other methods like Absolute, Relative, Euclidean distances, and a combination of the Angle and Relative methods. The model is trained and evaluated on the subset of the KITTI object detection benchmark dataset under resource constraints. Our results demonstrate that a combination of angle measures and relative distance has performed better than other methods. In comparison to the baseline method(relative), it achieved better performance. We also performed time analysis of various feature encoding methods.