標題: A novel online self-learning system with automatic object detection model for multimedia applications
作者: Cheng, Eric Juwei
Prasad, Mukesh
Yang, Jie
Zheng, Ding Rong
Tao, Xian
Mery, Domingo
Young, Ku Young
Lin, Chin Teng
交大名義發表
National Chiao Tung University
關鍵字: Object detection;Online learning;Real-time learning;Feature pool;Classifier
公開日期: 1-Jan-1970
摘要: This paper proposes a novel online self-learning detection system for different types of objects. It allows users to random select detection target, generating an initial detection model by selecting a small piece of image sample and continue training the detection model automatically. The proposed framework is divided into two parts: First, the initial detection model and the online reinforcement learning. The detection model is based on the proportion of users of the Haar-like features to generate feature pool, which is used to train classifiers and get positive-negative (PN) classifier model. Second, as the videos plays, the detecting model detects the new sample by Nearest Neighbor (NN) Classifier to get the PN similarity for new model. Online reinforcement learning is used to continuously update classifier, PN model and new classifier. The experiment shows the result of less detection sample with automatic online reinforcement learning is satisfactory.
URI: http://dx.doi.org/10.1007/s11042-020-09055-6
http://hdl.handle.net/11536/154880
ISSN: 1380-7501
DOI: 10.1007/s11042-020-09055-6
期刊: MULTIMEDIA TOOLS AND APPLICATIONS
起始頁: 0
結束頁: 0
Appears in Collections:Articles