Multi-shot Pedestrian Re-identification via Sequential Decision Making
نویسندگان
چکیده
Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing works that aggregate single frames features by time series model such as recurrent neural network, in this paper, we propose an interpretable reinforcement learning based approach to this problem. Particularly, we train an agent to verify a pair of images at each time. The agent could choose to output the result (same or different) or request another pair of images to see (unsure). By this way, our model implicitly learns the difficulty of image pairs, and postpone the decision when the model does not accumulate enough evidence. Moreover, by adjusting the reward for unsure action, we can easily trade off between speed and accuracy. In three open benchmarks, our method are competitive with the state-of-the-art methods while only using 3% to 6% images. These promising results demonstrate that our method is favorable in both efficiency and performance.
منابع مشابه
Identification and Prioritization of Factors Affecting Sustainable Energy Management with Multi-criteria Decision Making Approach (Case Study: Farabi Hospital in Bastak, Hormozgan Province)
متن کامل
PaMM: Pose-aware Multi-shot Matching for Improving Person Re-identification
Person re-identification is the problem of recognizing people across different images or videos with non-overlapping views. Although there has been much progress in person reidentification over the last decade, it remains a challenging task because appearances of people can seem extremely different across diverse camera viewpoints and person poses. In this paper, we propose a novel framework fo...
متن کاملPedestrian Gap Acceptance Logit Model in Unsignalized Crosswalks Conflict Zone
Pedestrians are the most vulnerable road users. For evaluating and modifying pedestrian safety in unsignalized crosswalks,the first important issue is to identify and explore factors affecting the interaction behavior of pedestrians andvehicles in conflict areas. By analyzing those factors and determining how they affect road user's behavior, we canrepresent the plans and proc...
متن کاملA Multi-Agent Cellular Automata Model of Pedestrian Movement
This paper reports on the development of a multi-agent cellular automata model of pedestrian movement and decision making within the built environment. The approach will lead to a system that may serve as a tool in the design process to better understand how a design will influence user behaviour.
متن کاملConstrained consumable resource allocation in alternative stochastic networks via multi-objective decision making
Many real projects complete through the realization of one and only one path of various possible network paths. Here, these networks are called alternative stochastic networks (ASNs). It is supposed that the nodes of considered network are probabilistic with exclusive-or receiver and exclusive-or emitter. First, an analytical approach is proposed to simplify the structure of t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1712.07257 شماره
صفحات -
تاریخ انتشار 2017