Robust object proposals re-ranking for object detection in autonomous driving using convolutional neural networks

作者：

Highlights：

• We present a robust object proposals re-ranking algorithm for object detection in autonomous driving.

• Both RGB images and depth features are included in the proposed two-stream CNN architecture called DeepStereoOP.

• Initial object proposals are generated from a customized class-independent 3DOP method.

• Experiments show that the proposed algorithm outperforms all existing object proposals algorithms.

• The combination of DeepStereoOP and Fast R-CNN achieves one of the best detection results on KITTI benchmark.

摘要

Highlights•We present a robust object proposals re-ranking algorithm for object detection in autonomous driving.•Both RGB images and depth features are included in the proposed two-stream CNN architecture called DeepStereoOP.•Initial object proposals are generated from a customized class-independent 3DOP method.•Experiments show that the proposed algorithm outperforms all existing object proposals algorithms.•The combination of DeepStereoOP and Fast R-CNN achieves one of the best detection results on KITTI benchmark.

论文关键词：Object proposals,Autonomous driving,Object detection,Convolutional neural networks,Stereo vision.

论文评审过程：Received 12 November 2016, Revised 26 January 2017, Accepted 16 February 2017, Available online 20 February 2017, Version of Record 27 February 2017.

论文官网地址：https://doi.org/10.1016/j.image.2017.02.007