DeepAI AI Chat
Log In Sign Up

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

by   Guangming Wang, et al.
Shanghai Jiao Tong University

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.


page 1

page 4

page 5

page 7

page 8

page 9


3D Object Tracking with Transformer

Feature fusion and similarity computation are two core problems in 3D ob...

Segment-based fusion of multi-sensor multi-scale satellite soil moisture retrievals

Synergetic use of sensors for soil moisture retrieval is attracting cons...

Multi-scale Geometric Summaries for Similarity-based Sensor Fusion

In this work, we address fusion of heterogeneous sensor data using wavel...

AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognition

Recent years have witnessed the increasing application of place recognit...

Robust Multi-Modality Multi-Object Tracking

Multi-sensor perception is crucial to ensure the reliability and accurac...

From One to Many: Dynamic Cross Attention Networks for LiDAR and Camera Fusion

LiDAR and cameras are two complementary sensors for 3D perception in aut...

Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking

We address the problem of multi-modal object tracking in video and explo...