Motion Shadow Detection Method Based on Bagging Algorithm
Hong Cheng Zhou, Zhi Peng Jiang · Applied Mechanics and Materials · 2014
Focusing on the disturbance of moving cast shadow, a Bagging-ensemble-based moving cast shadow removal method is proposed. Collecting shadow discrimination features from multiple shadow discrimination models, a shadow detector is trained by employing Bagging ensemble based learning framework. The shadow detector can automatically select effective shadow discrimination features and be updated online adaptively. Experimental results demonstrate the effectiveness of the proposed method.