Pedestrian Detection with RPN and Boosted Forest
Human Centric Visual Analysis with Deep Learning(2020)
摘要
Although recent deep learning object detectors have shown excellent performance for general object detection, they have limited success in detecting pedestrians; therefore, previous leading pedestrian detectors were generally hybrid methods combining handcrafted and deep convolutional features. In this chapter, we propose a very simple but effective baseline for pedestrian detection using an RPN followed by boosted forest on shared high-resolution convolutional feature maps. We comprehensively evaluate this method on several benchmarks and find that it shows competitive accuracy and good speed.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络