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 2409.00487cs.CV
收藏

TrackSSM:一种基于状态空间模型的通用运动预测器

TrackSSM: A General Motion Predictor by State-Space Model

Huazhong University of Science and Technology(华中科技大学)

Bin Hu, Run Luo, Zelin Liu, Cheng Wang, Wenyu Liu

AI总结:

本文提出 TrackSSM,利用数据相关状态空间模型与 Flow-SSM 流解码器构建通用编码器-解码器运动预测框架,并通过 S²L 训练策略提升多目标跟踪性能。

摘要:

时间运动建模一直是多目标跟踪(MOT)中的关键组成部分,它能够确保轨迹运动平滑,并提供准确的位置信息以提升关联精度。然而,当前的运动模型难以在不同应用场景中同时兼顾效率与有效性。为此,我们受近期流行的状态空间模型(SSM)启发,提出了 TrackSSM,这是一个统一的编码器-解码器运动框架,使用依赖于数据的状态空间模型来执行轨迹的时间运动建模。具体而言,我们提出了 Flow-SSM 模块,该模块利用来自历史轨迹的位置和运动信息来引导目标边界框的时间状态转移。基于 Flow-SSM,我们设计了一个流解码器。它由采用 Flow-SSM 的级联运动解码模块组成,能够利用编码后的流信息完成轨迹的时间位置预测。此外,我们提出了逐步线性(S²L)训练策略。通过在目标于前一帧和当前帧的位置之间执行线性插值,我们构建了逐步线性训练的伪标签,确保轨迹流信息能够更好地引导目标边界框完成时间转移。TrackSSM 使用简单的 Mamba-Block 构建面向历史轨迹的运动编码器,并与流解码器共同构成具有编码器-解码器结构的时间运动模型。TrackSSM 适用于多种跟踪场景,并在多个基准上取得优异的跟踪性能,进一步拓展了类 SSM 时间运动模型在多目标跟踪任务中的潜力。代码和模型已公开发布于 https://github.com/Xavier-Lin/TrackSSM。

英文摘要:

Temporal motion modeling has always been a key component in multiple object tracking (MOT) which can ensure smooth trajectory movement and provide accurate positional information to enhance association precision. However, current motion models struggle to be both efficient and effective across different application scenarios. To this end, we propose TrackSSM inspired by the recently popular state space models (SSM), a unified encoder-decoder motion framework that uses data-dependent state space model to perform temporal motion of trajectories. Specifically, we propose Flow-SSM, a module that utilizes the position and motion information from historical trajectories to guide the temporal state transition of object bounding boxes. Based on Flow-SSM, we design a flow decoder. It is composed of a cascaded motion decoding module employing Flow-SSM, which can use the encoded flow information to complete the temporal position prediction of trajectories. Additionally, we propose a Step-by-Step Linear (S$^2$L) training strategy. By performing linear interpolation between the positions of the object in the previous frame and the current frame, we construct the pseudo labels of step-by-step linear training, ensuring that the trajectory flow information can better guide the object bounding box in completing temporal transitions. TrackSSM utilizes a simple Mamba-Block to build a motion encoder for historical trajectories, forming a temporal motion model with an encoder-decoder structure in conjunction with the flow decoder. TrackSSM is applicable to various tracking scenarios and achieves excellent tracking performance across multiple benchmarks, further extending the potential of SSM-like temporal motion models in multi-object tracking tasks. Code and models are publicly available at \url{https://github.com/Xavier-Lin/TrackSSM}.

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。

↑