A closer look at Faster R-CNN for vehicle detection

Faster R-CNN achieves state-of-the-art performance on generic object detection. However, a simple application of this method to a large vehicle dataset performs unimpressively. In this paper, we take a closer look at this approach as it applies to vehicle detection. We conduct a wide range of experiments and provide a comprehensive analysis of the underlying structure of this model. We show that through suitable parameter tuning and algorithmic modification, we can significantly improve the performance of Faster R-CNN on vehicle detection and achieve competitive results on the KITTI vehicle dataset. We believe our studies are instructive for other researchers investigating the application of Faster R-CNN to their problems and datasets.

[1]  Sebastian Thrun,et al.  A probabilistic framework for car detection in images using context and scale , 2012, 2012 IEEE International Conference on Robotics and Automation.

[2]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Huimin Ma,et al.  3D Object Proposals for Accurate Object Class Detection , 2015, NIPS.

[4]  C. Lawrence Zitnick,et al.  Edge Boxes: Locating Object Proposals from Edges , 2014, ECCV.

[5]  Gang Hua,et al.  Accurate Object Detection with Location Relaxation and Regionlets Re-localization , 2014, ACCV.

[6]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[7]  Akihiro Takeuchi,et al.  On-Road Multivehicle Tracking Using Deformable Object Model and Particle Filter With Improved Likelihood Estimation , 2012, IEEE Transactions on Intelligent Transportation Systems.

[8]  Sharath Pankanti,et al.  Efficient 24/7 object detection in surveillance videos , 2015, 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[9]  Mohan M. Trivedi,et al.  Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis , 2013, IEEE Transactions on Intelligent Transportation Systems.

[10]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[11]  Quanfu Fan,et al.  Self-calibration from vehicle information , 2015, 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[12]  Ming Yang,et al.  Regionlets for Generic Object Detection , 2013, 2013 IEEE International Conference on Computer Vision.

[13]  Silvio Savarese,et al.  Data-driven 3D Voxel Patterns for object category recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[15]  Christoph H. Lampert,et al.  Efficient Subwindow Search: A Branch and Bound Framework for Object Localization , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Yi Yang,et al.  DenseBox: Unifying Landmark Localization with End to End Object Detection , 2015, ArXiv.

[17]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Fernando A. Mujica,et al.  An Empirical Evaluation of Deep Learning on Highway Driving , 2015, ArXiv.

[19]  Luis Miguel Bergasa,et al.  Supervised learning and evaluation of KITTI's cars detector with DPM , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[20]  Deva Ramanan,et al.  Analyzing 3D Objects in Cluttered Images , 2012, NIPS.

[21]  Pietro Perona,et al.  Fast Feature Pyramids for Object Detection , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Miao Sun,et al.  Generic Object Detection with Dense Neural Patterns and Regionlets , 2014, BMVC.

[23]  Song-Chun Zhu,et al.  Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model , 2014, ECCV.