基于稀疏编码的迁移学习及其在行人检测中的应用

行人检测是计算机视觉领域中的研究热点,其实质是一个二分类问题.目前基于统计的行人检测技术已取得了一定进展,但大都需要大量的训练数据.针对这一问题,提出了一种基于迁移学习的半监督行人分类方法:首先基于稀疏编码,从任意的未标记样本中,学习到一个紧凑、有效的特征表示;然后通过迁移学习,将学习到的特征表示方法迁移到行人分类中.在MIT行人数据库上的实验结果表明:该方法能有效地刻画出行人的特征,提高行人分类的性能,在标记样本少的情况下仍具有良好的分类效果,因此可应用于行人检测中.

Transfer Learning Based on Sparse Coding and It's Application in Pedestrian Detection

Pedestrian detection has become one of the hottest topics in the domain of computer vision.It can be considered as a two-classification problem.Though it has achieved some progress,most of previous methods need lots of training data.This paper proposed a novel semi-supervised method for pedestrian classification,which was based on transfer learning and just needed only a few labeled data.Firstly,we used sparse coding to learn a slightly higher-level,more succinct feature representation from the unlabeled da...