Deep Convolutional Neural Networks for pedestrian detection

作者：

Highlights：

• A deep convolutional neural network for pedestrian detection is proposed.

• The proposed method improves the accuracy performance with respect to handcrafted features.

• Our method detects pedestrians with a good accuracy and has a reasonable computational complexity.

摘要

Highlights•A deep convolutional neural network for pedestrian detection is proposed.•The proposed method improves the accuracy performance with respect to handcrafted features.•Our method detects pedestrians with a good accuracy and has a reasonable computational complexity.

论文关键词：Deep learning,Pedestrian detection,Convolutional Neural Networks,Optimization

论文评审过程：Received 15 October 2015, Revised 27 February 2016, Accepted 7 May 2016, Available online 13 May 2016, Version of Record 29 September 2016.

论文官网地址：https://doi.org/10.1016/j.image.2016.05.007