Adaptive Decision Support System for On-Line Multi-Class Learning and Object Detection

Applied Sciences

Chin-Teng Lin¹  Mukesh Prasad¹  Shreya Pare¹  Amit Saxena²  Guo-Jhang Hong³  Dong-Lin Li⁴ 

[1] Australian Artificial Intelligence Institute, School of Software, University of Technology Sydney, Sydney 2007, Australia;Department of Computer Science and IT, Guru Ghasidas University, Bilaspur 495009, India;Department of Electrical Engineering, National Chiao Tung University, Hsinchu 30010, Taiwan;Department of Electrical Engineering, National Taiwan Ocean University, Keelung 20224, Taiwan;

关键词: multi-class object detection;    on-line learning;    feature selection;    adaptive feature pool;   

DOI  :  10.3390/app112311268

来源: DOAJ

【 摘 要 】

A new online multi-class learning algorithm is proposed with three main characteristics. First, in order to make the feature pool fitter for the pattern pool, the adaptive feature pool is proposed to dynamically combine the three general features, Haar-like, Histogram of Oriented Gradient (HOG), and Local Binary Patterns (LBP). Second, the external model is integrated into the proposed model without re-training to enhance the efficacy of the model. Third, a new multi-class learning and updating mechanism are proposed that help to find unsuitable decisions and adjust them automatically. The performance of the proposed model is validated with multi-class detection and online learning system. The proposed model achieves a better score than other non-deep learning algorithms used in public pedestrian and multi-class databases. The multi-class databases contain data for pedestrians, faces, vehicles, motorcycles, bicycles, and aircraft.

【 授权许可】

Unknown