论文标题
在线多对象跟踪的运动和外观中的改进
Refinements in Motion and Appearance for Online Multi-Object Tracking
论文作者
论文摘要
现代多对象跟踪（MOT）系统通常涉及分离的模块，例如用于数据关联的位置和外观模型的运动模型。但是，运动和外观模型中的兼容问题始终被忽略。在本文中，通过无缝融合运动积分，三维（3D）积分图像和适应性外观特征融合的一般体系结构。由于通常会单独处理不确定的行人和摄像机动作，因此集成的运动模型是使用我们定义的相机运动的计划设计的。具体而言，提出了一种基于3D积分图像的空间阻塞方法，以有效地削减具有空间约束的轨迹和候选者之间的无用连接。然后，共同构建了外观模型和可见性预测。考虑到尺度，姿势和可见性，外观特征是自适应融合的，以克服特征错位问题。我们的基于MIF的跟踪器（MIFT）在MOT16和17挑战方面以60.1 MOTA实现了最先进的精度。
Modern multi-object tracking (MOT) system usually involves separated modules, such as motion model for location and appearance model for data association. However, the compatible problems within both motion and appearance models are always ignored. In this paper, a general architecture named as MIF is presented by seamlessly blending the Motion integration, three-dimensional(3D) Integral image and adaptive appearance feature Fusion. Since the uncertain pedestrian and camera motions are usually handled separately, the integrated motion model is designed using our defined intension of camera motion. Specifically, a 3D integral image based spatial blocking method is presented to efficiently cut useless connections between trajectories and candidates with spatial constraints. Then the appearance model and visibility prediction are jointly built. Considering scale, pose and visibility, the appearance features are adaptively fused to overcome the feature misalignment problem. Our MIF based tracker (MIFT) achieves the state-of-the-art accuracy with 60.1 MOTA on both MOT16&17 challenges.
