arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1612.02155cs.CV
收藏

利用个人、社会和环境约束重新识别人群中的人类

Re-identification of Humans in Crowds using Personal, Social and Environmental Constraints

Shayan Modiri Assari, Haroon Idrees, Mubarak Shah

摘要:

研究了人群中非重叠摄像机对人的重新识别问题,由于人群数量多、遮挡频繁,加上摄像机的属性和曝光不同,导致其外观发生变化,因此在人群中重新识别是一个具有挑战性的问题。为了解决这个问题,我们模拟多个人,社会和环境(PSE)的限制,对人体运动的摄像机。个人约束包括假设跨非重叠相机相似的每个个体的外观和偏好速度。社会影响(约束)在本质上是二次的,即发生在成对的个体之间,并通过分组和避免冲突来建模。最后,环境约束捕获不同摄像机中的门(入口/出口)之间的转移概率,定义为所有门对之间的转移时间和目的地的多模态分布。我们将这些限制到一个能量最小化的框架,解决人类重新识别。当建模PSE约束时,消除$1-1$对应性是NP难的。我们提出了一种随机局部搜索算法来限制假设的搜索空间,并在线性和二次PSE约束下获得了$1-1$解。此外,我们提出了一个替代的优化使用Frank-Wolfe算法,解决了凸近似的目标函数与线性松弛二进制变量,并产生一个数量级的速度比随机局部搜索性能略有下降。我们评估我们的方法,使用累积匹配曲线以及$1-1$分配数千帧的大中央,PRID和DukeMTMC数据集,并获得显着更好的结果相比,现有的重新识别方法。

英文摘要:

This paper addresses the problem of human re-identification across non-overlapping cameras in crowds.Re-identification in crowded scenes is a challenging problem due to large number of people and frequent occlusions, coupled with changes in their appearance due to different properties and exposure of cameras. To solve this problem, we model multiple Personal, Social and Environmental (PSE) constraints on human motion across cameras. The personal constraints include appearance and preferred speed of each individual assumed to be similar across the non-overlapping cameras. The social influences (constraints) are quadratic in nature, i.e. occur between pairs of individuals, and modeled through grouping and collision avoidance. Finally, the environmental constraints capture the transition probabilities between gates (entrances / exits) in different cameras, defined as multi-modal distributions of transition time and destination between all pairs of gates. We incorporate these constraints into an energy minimization framework for solving human re-identification. Assigning $1-1$ correspondence while modeling PSE constraints is NP-hard. We present a stochastic local search algorithm to restrict the search space of hypotheses, and obtain $1-1$ solution in the presence of linear and quadratic PSE constraints. Moreover, we present an alternate optimization using Frank-Wolfe algorithm that solves the convex approximation of the objective function with linear relaxation on binary variables, and yields an order of magnitude speed up over stochastic local search with minor drop in performance. We evaluate our approach using Cumulative Matching Curves as well $1-1$ assignment on several thousand frames of Grand Central, PRID and DukeMTMC datasets, and obtain significantly better results compared to existing re-identification methods.

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。

↑