arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.04308cs.CVcs.LG
收藏

SSP-GNN:通过双层优化学习跟踪

SSP-GNN: Learning to Track via Bilevel Optimization

Applied Physics Laboratory(应用物理实验室);University of Washington(华盛顿大学);Paul G. Allen School of Computer Science(保罗·G·艾伦计算机科学学院)

Griffin Golias, Masa Nakura-Fan, Vitaly Ablavsky

AI总结:

SSP-GNN通过双层优化学习跟踪,利用图神经网络和 successive shortest paths 算法实现多目标跟踪。

摘要:

我们提出了一种基于图的多目标跟踪(MOT)公式,其中目标检测包含运动学信息和重新识别特征(属性)。我们的方法将 successive shortest paths(SSP)算法应用于一个在帧批上定义的跟踪图。该跟踪图的边成本通过消息传递网络,一种图神经网络(GNN)变体来计算。GNN的参数,因此跟踪器的参数,通过在示例真实轨迹和检测的训练集上端到端学习。具体来说,学习形式为由我们新提出的损失函数引导的双层优化。我们在模拟场景中评估我们的算法,以了解其对场景方面和模型超参数的敏感性。在各种场景复杂性下,我们的方法在与强基线相比时表现良好。

英文摘要:

We propose a graph-based tracking formulation for multi-object tracking (MOT) where target detections contain kinematic information and re-identification features (attributes). Our method applies a successive shortest paths (SSP) algorithm to a tracking graph defined over a batch of frames. The edge costs in this tracking graph are computed via a message-passing network, a graph neural network (GNN) variant. The parameters of the GNN, and hence, the tracker, are learned end-to-end on a training set of example ground-truth tracks and detections. Specifically, learning takes the form of bilevel optimization guided by our novel loss function. We evaluate our algorithm on simulated scenarios to understand its sensitivity to scenario aspects and model hyperparameters. Across varied scenario complexities, our method compares favorably to a strong baseline.

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。

↑