Selective experience replay in reinforcement learning for reidentification

Person reidentification is a problem of recognizing a person across non-overlapping camera views. Pose variations, illumination conditions, low resolution images, and occlusion are the main challenges encountered in reidentification. Due to the uncontrolled environment in which the videos are captur...

Full description

Saved in:
Bibliographic Details
Main Authors: Thakoor, Ninad, Bhanu, Bir
Format: Conference Proceeding
Language:English
Subjects:
Cameras
Context
Learning (artificial intelligence)
Legged locomotion
Measurement
Reidentification
Reinforcement Learning
Videos
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Person reidentification is a problem of recognizing a person across non-overlapping camera views. Pose variations, illumination conditions, low resolution images, and occlusion are the main challenges encountered in reidentification. Due to the uncontrolled environment in which the videos are captured, people could appear in different poses and due to which the appearance of a person could vary significantly. The walking direction of a person can provide a good estimation of their pose. Therefore, in this paper, we propose a reidentification system which adaptively selects an appropriate distance metric based on context of walking direction using reinforcement learning. Though experiments, we show that such a dynamic strategy outperforms static strategy learned or designed offline.
ISSN:2381-8549
DOI:10.1109/ICIP.2016.7533161