Toyota Research Institute, North America, Ann Arbor, MI 48105, USA.
IEEE Trans Image Process. 2013 Jul;22(7):2661-75. doi: 10.1109/TIP.2013.2255301. Epub 2013 Mar 28.
Recently, sparse representation has been applied to visual tracking to find the target with the minimum reconstruction error from a target template subspace. Though effective, these L1 trackers require high computational costs due to numerous calculations for l1 minimization. In addition, the inherent occlusion insensitivity of the l1 minimization has not been fully characterized. In this paper, we propose an efficient L1 tracker, named bounded particle resampling (BPR)-L1 tracker, with a minimum error bound and occlusion detection. First, the minimum error bound is calculated from a linear least squares equation and serves as a guide for particle resampling in a particle filter (PF) framework. Most of the insignificant samples are removed before solving the computationally expensive l1 minimization in a two-step testing. The first step, named τ testing, compares the sample observation likelihood to an ordered set of thresholds to remove insignificant samples without loss of resampling precision. The second step, named max testing, identifies the largest sample probability relative to the target to further remove insignificant samples without altering the tracking result of the current frame. Though sacrificing minimal precision during resampling, max testing achieves significant speed up on top of τ testing. The BPR-L1 technique can also be beneficial to other trackers that have minimum error bounds in a PF framework, especially for trackers based on sparse representations. After the error-bound calculation, BPR-L1 performs occlusion detection by investigating the trivial coefficients in the l1 minimization. These coefficients, by design, contain rich information about image corruptions, including occlusion. Detected occlusions are then used to enhance the template updating. For evaluation, we conduct experiments on three video applications: biometrics (head movement, hand holding object, singers on stage), pedestrians (urban travel, hallway monitoring), and cars in traffic (wide area motion imagery, ground-mounted perspectives). The proposed BPR-L1 method demonstrates an excellent performance as compared with nine state-of-the-art trackers on eleven challenging benchmark sequences.
最近，稀疏表示已被应用于视觉跟踪，以从目标模板子空间中找到具有最小重建误差的目标。虽然这些 L1 跟踪器很有效，但由于 l1 最小化的大量计算，它们需要很高的计算成本。此外，l1 最小化的固有遮挡不敏感性尚未得到充分表征。在本文中，我们提出了一种高效的 L1 跟踪器，名为有界粒子重采样 (BPR)-L1 跟踪器，具有最小误差边界和遮挡检测。首先，从线性最小二乘方程计算最小误差边界，并作为粒子滤波器 (PF) 框架中粒子重采样的指导。在两步测试之前，在计算昂贵的 l1 最小化之前，大多数不重要的样本会被删除。第一步称为 τ 测试，它将样本观测似然与有序阈值集进行比较，以在不损失重采样精度的情况下删除不重要的样本。第二步称为最大测试，它确定相对于目标的最大样本概率，以进一步去除不重要的样本，而不会改变当前帧的跟踪结果。虽然在重采样过程中牺牲了最小精度，但最大测试在 τ 测试的基础上实现了显著的加速。BPR-L1 技术也可以有益于其他具有 PF 框架中最小误差边界的跟踪器，特别是对于基于稀疏表示的跟踪器。在误差边界计算之后，BPR-L1 通过研究 l1 最小化中的平凡系数来执行遮挡检测。这些系数，通过设计，包含有关图像损坏的丰富信息，包括遮挡。然后使用检测到的遮挡来增强模板更新。为了评估，我们在三个视频应用程序上进行了实验：生物识别（头部运动、手持物体、舞台上的歌手）、行人（城市旅行、走廊监控）和交通中的汽车（广域运动图像、地面安装视角）。与十一个具有挑战性的基准序列上的九个最先进的跟踪器相比，所提出的 BPR-L1 方法表现出出色的性能。
