Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking

TL;DR

This paper proposes an interactive multi-scale feature fusion method combining 2D image and 3D point cloud data to improve multi-object tracking accuracy, demonstrating superior performance on the KITTI benchmark.

Contribution

It introduces a novel multi-scale interactive feature fusion approach using PointNet++ and pixel-level fusion, enhancing multi-object tracking performance over existing methods.

Findings

Achieves state-of-the-art results on KITTI benchmark.

Demonstrates the effectiveness of multi-scale feature fusion.

Shows benefits of pre-training on single modalities.

Abstract

Multiple object tracking (MOT) is a significant task in achieving autonomous driving. Traditional works attempt to complete this task, either based on point clouds (PC) collected by LiDAR, or based on images captured from cameras. However, relying on one single sensor is not robust enough, because it might fail during the tracking process. On the other hand, feature fusion from multiple modalities contributes to the improvement of accuracy. As a result, new techniques based on different sensors integrating features from multiple modalities are being developed. Texture information from RGB cameras and 3D structure information from Lidar have respective advantages under different circumstances. However, it's not easy to achieve effective feature fusion because of completely distinct information modalities. Previous fusion methods usually fuse the top-level features after the backbones extract the features from different modalities. In this paper, we first introduce PointNet++ to obtain multi-scale deep representations of point cloud to make it adaptive to our proposed Interactive Feature Fusion between multi-scale features of images and point clouds. Specifically, through multi-scale interactive query and fusion between pixel-level and point-level features, our method, can obtain more distinguishing features to improve the performance of multiple object tracking. Besides, we explore the effectiveness of pre-training on each single modality and fine-tuning on the fusion-based model. The experimental results demonstrate that our method can achieve good performance on the KITTI benchmark and outperform other approaches without using multi-scale feature fusion. Moreover, the ablation studies indicates the effectiveness of multi-scale feature fusion and pre-training on single modality.