Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking

by   Yubo Cui, et al.

3D single object tracking is a key task in 3D computer vision. However, the sparsity of point clouds makes it difficult to compute the similarity and locate the object, posing big challenges to the 3D tracker. Previous works tried to solve the problem and improved the tracking performance in some common scenarios, but they usually failed in some extreme sparse scenarios, such as for tracking objects at long distances or partially occluded. To address the above problems, in this letter, we propose a sparse-to-dense and transformer-based framework for 3D single object tracking. First, we transform the 3D sparse points into 3D pillars and then compress them into 2D BEV features to have a dense representation. Then, we propose an attention-based encoder to achieve global similarity computation between template and search branches, which could alleviate the influence of sparsity. Meanwhile, the encoder applies the attention on multi-scale features to compensate for the lack of information caused by the sparsity of point cloud and the single scale of features. Finally, we use set-prediction to track the object through a two-stage decoder which also utilizes attention. Extensive experiments show that our method achieves very promising results on the KITTI and NuScenes datasets.


3D Object Tracking with Transformer

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

Real-time 3D Single Object Tracking with Transformer

LiDAR-based 3D single object tracking is a challenging issue in robotics...

PTTR: Relational 3D Point Cloud Object Tracking with Transformer

In a point cloud sequence, 3D object tracking aims to predict the locati...

Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking

3D single object tracking with LiDAR points is an important task in the ...

Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer

With the prevalence of LiDAR sensors in autonomous driving, 3D object tr...

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency

3D single object tracking (SOT) is an indispensable part of automated dr...

Towards Object Re-Identification from Point Clouds for 3D MOT

In this work, we study the problem of object re-identification (ReID) in...

Please sign up or login with your details

Forgot password? Click here to reset