Learning the Incremental Warp for 3D Vehicle Tracking in LiDAR Point Clouds
Open Access
- 14 July 2021
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 13 (14) , 2770
Abstract
Object tracking from LiDAR point clouds, which are always incomplete, sparse, and unstructured, plays a crucial role in urban navigation. Some existing methods utilize a learned similarity network for locating the target, immensely limiting the advancements in tracking accuracy. In this study, we leveraged a powerful target discriminator and an accurate state estimator to robustly track target objects in challenging point cloud scenarios. Considering the complex nature of estimating the state, we extended the traditional Lucas and Kanade (LK) algorithm to 3D point cloud tracking. Specifically, we propose a state estimation subnetwork that aims to learn the incremental warp for updating the coarse target state. Moreover, to obtain a coarse state, we present a simple yet efficient discrimination subnetwork. It can project 3D shapes into a more discriminatory latent space by integrating the global feature into each point-wise feature. Experiments on KITTI and PandaSet datasets showed that compared with the most advanced of other methods, our proposed method can achieve significant improvements—in particular, up to 13.68% on KITTI.Keywords
Funding Information
- National Natural Science Foundation of China (61976040, U1811463)
- National Key Research and Development Program of China (2020YFB1708902)
This publication has 49 references indexed in Scilit:
- Fast R-CNN2015
- Robust real-time tracking combining 3D shape, color, and motionThe International Journal of Robotics Research, 2015
- Object Tracking BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Tracking Revisited Using RGBD Camera: Unified Benchmark and Baselines2013
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Supervised Descent Method and Its Applications to Face Alignment2013
- Automatic detection and tracking of pedestrians from a moving stereo rigISPRS Journal of Photogrammetry and Remote Sensing, 2010
- Lucas-Kanade 20 Years On: A Unifying FrameworkInternational Journal of Computer Vision, 2004
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992