期刊
NEURAL COMPUTING & APPLICATIONS
卷 29, 期 12, 页码 1485-1494出版社
SPRINGER LONDON LTD
DOI: 10.1007/s00521-016-2639-3
关键词
Machine learning; Support vector machine; Privileged information; Pedestrian detection
资金
- National Natural Science Foundation of China [61402429, 61472390, 11271361, 11201472, 11331012, 71331005]
- Major International (Regional) Joint Research Project [71110107026]
The pedestrian detection is always a challenging issue in the computer vision. Unlike the object recognition problem, the detection's speed is a critical factor. In order to accelerate detection speed while maintaining competitive accuracy, in this paper we introduce a new model: twin support vector machine based on privileged information (called TSVMPI, in this paper) (Qi et al. in Neurocomputing 129:146-152, 2014) to detect pedestrian. TSVMPI uses two nonparallel hyperplane classifiers to decide the label of an unknown sample and is superior to the standard SVM, especially in the linear kernel case, resulting in a significant advantage to deal with the special task. All experimental results demonstrate our strategy's effectiveness and show that the privileged information indeed offers a significant improvement for the pedestrian detection.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据