arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.07889cs.CV
收藏

学习用于多对象跟踪的建议分类器

Learning a Proposal Classifier for Multiple Object Tracking

Tsinghua University(清华大学);Aibee Inc(爱笔公司)

Peng Dai, Renliang Weng, Wongun Choi, Changshui Zhang, Zhangping He, Wei Ding

摘要:

多目标跟踪(MOT)的最新趋势是利用深度学习来提高跟踪性能。然而,以端到端的方式解决数据关联问题并非易事。在本文中,我们提出了一种新的基于提案的可学习框架,模型MOT作为一个建议的生成,建议评分和轨迹推理范式上的亲和图。该框架类似于两阶段对象检测器Faster RCNN,可以以数据驱动的方式解决MOT问题。对于建议生成,我们提出了一个迭代图聚类方法,以减少计算成本,同时保持所生成的建议的质量。对于提案评分,我们部署了一个可训练的图卷积网络(GCN)来学习生成的提案的结构模式,并根据估计的质量分数对其进行排名。对于轨迹推断,采用简单的去重叠策略来生成跟踪输出,同时遵守不能将检测分配给多个轨迹的约束。我们的实验表明,所提出的方法实现了明显的性能改善,在MOTA和IDF1相对于以前的国家的最先进的两个公共基准。我们的代码可在https://github.com/daip13/LPC_MOT.git上获得。

英文摘要:

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. However, it is not trivial to solve the data-association problem in an end-to-end fashion. In this paper, we propose a novel proposal-based learnable framework, which models MOT as a proposal generation, proposal scoring and trajectory inference paradigm on an affinity graph. This framework is similar to the two-stage object detector Faster RCNN, and can solve the MOT problem in a data-driven way. For proposal generation, we propose an iterative graph clustering method to reduce the computational cost while maintaining the quality of the generated proposals. For proposal scoring, we deploy a trainable graph-convolutional-network (GCN) to learn the structural patterns of the generated proposals and rank them according to the estimated quality scores. For trajectory inference, a simple deoverlapping strategy is adopted to generate tracking output while complying with the constraints that no detection can be assigned to more than one track. We experimentally demonstrate that the proposed method achieves a clear performance improvement in both MOTA and IDF1 with respect to previous state-of-the-art on two public benchmarks. Our code is available at https://github.com/daip13/LPC_MOT.git.

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。

↑