arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.00519cs.CV
收藏

利用稀疏点云中的更多信息进行三维单目标跟踪

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

Northeastern University(东北大学);Science and Technology on Near-Surface Detection Laboratory(近地面探测技术重点实验室);National Frontiers Science Center for Industrial Intelligence and Systems Optimization(工业智能与系统优化国家级前沿科学中心)

Yubo Cui, Jiayao Shan, Zuoxu Gu, Zhiheng Li, Zheng Fang

摘要:

三维单目标跟踪是三维计算机视觉中的一项关键任务。然而,点云的稀疏性使得计算相似性和定位目标变得困难,这给三维跟踪器带来了很大的挑战。以往的工作试图解决这个问题,并提高跟踪性能,在一些常见的场景,但他们通常失败,在一些极端稀疏的场景,如跟踪对象在长距离或部分遮挡。为了解决上述问题,在这封信中,我们提出了一个稀疏到密集和基于transformer的3D单目标跟踪框架。首先,我们将3D稀疏点转换为3D柱,然后将它们压缩为2D BEV特征以具有密集表示。然后,我们提出了一个基于注意力的编码器,以实现模板和搜索分支之间的全局相似性计算,这可以减轻稀疏性的影响。同时,编码器对多尺度特征进行关注,以弥补点云稀疏性和特征尺度单一所带来的信息不足。最后,我们使用集合预测跟踪对象通过两个阶段的解码器,也利用注意力。大量的实验表明,我们的方法在KITTI和NuScenes数据集上取得了非常有前途的结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑