Speed up deep neural network based pedestrian detection by sharing features across multi-scale models

Neurocomputing

Volumn 185, Issue , 2016, Pages 163-170

  Jiang, Xiaoheng ^a   Pang, Yanwei ^a   Li, Xuelong ^b   Pan, Jing ^a,c  

^a TIANJIN UNIVERSITY   (China)

^b XI AN INSTITUTE OF OPTICS AND PRECISION MECHANICS   (China)

^c TIANJIN UNIVERSITY OF TECHNOLOGY AND EDUCATION   (China)

Author keywords

Convolutional neural networks; Deep neural networks; Pedestrian detection; Share features

Indexed keywords

COMPLEX NETWORKS; COMPUTATIONAL EFFICIENCY; COMPUTER GRAPHICS; EFFICIENCY; NEURAL NETWORKS; OBJECT DETECTION; PROGRAM PROCESSORS;

COMPUTATIONAL BURDEN; CONVOLUTIONAL NEURAL NETWORK; DEEP NEURAL NETWORKS; DETECTION EFFICIENCY; DETECTION PERFORMANCE; GRAPHICS PROCESSING UNITS; PEDESTRIAN DETECTION; SHARE FEATURES;

FEATURE EXTRACTION;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; DEEP NEURAL NETWORK; FALSE POSITIVE RESULT; IMAGE PROCESSING; INTERMETHOD COMPARISON; MEASUREMENT ACCURACY; PEDESTRIAN; PRIORITY JOURNAL;

EID: 84952684616     PISSN: 09252312     EISSN: 18728286     Source Type: Journal    
DOI: 10.1016/j.neucom.2015.12.042     Document Type: Article

References (35)

1. P. Agrawal, R. Girshick, J. Malik, Analyzing the performance of multilayer neural networks for object recognition, in: Proceedings of European Conference on Computer Vision, 2014, pp. 329-344.
2. R. Benenson, M. Omran, J. Hosang, B. Schiele, Ten years of pedestrian detection, what have we learned? in: European Conference on Computer Vision, CVRSUAD workshop, 2014.
3. N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2005, pp. 886-893.
4. Dollar P., Wojek C., Schiele B., Perona P. Pedestrian detection. an evaluation of the state-of-the-art. IEEE Trans. Pattern Anal. Mach. Intell. 2012, 34(4):743-761.
5. Felzenszwalb P., Girshick R., McAllester D., Ramanan D. Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 2010, 32(9):1627-1645.
6. P. Fischer, A. Dosovitskiy, T. Brox, Descriptor matching with convolutional neural networks: a comparison to sift, 2014. http://arXiv:1405.5769.
7. R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2014, pp. 580-587.
8. A. Giusti, D. Ciresan, J. Masci, L. Gambardella, J. Schmidhuber, Fast image scanning with deep max-pooling convolutional neural networks, in: Proceedings of IEEE International Conference on Image Processing, 2013, pp. 4034-4038.
9. K. He, X. Zhang, S. Ren, J. Sun, Spatial pyramid pooling in deep convolutional networks for visual recognition, in: Proceedings of European Conference on Computer Vision, 2014, pp 346-361.
10. J. Hosang, M. Omran, R. Benenson, B. Schiele, Taking a deeper look at pedestrians, 2015. http://arXiv:1501.05790.
11. Jeonga S., Parkb Y., Mallipeddia R., Tanic J., Leea M. Goal-oriented behavior sequence generation based on semantic commands using multiple timescales recurrent neural network with initial state correction. Neurocomputing 2014, 129(4):67-77.
12. Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, T. Darrell, Caffe: convolutional architecture for fast feature embedding, in: Proceedings of the ACM International Conference on Multimedia, 2014, pp. 675-678.
13. Jiang X., Pang Y., Pan J., Li X. Flexible sliding windows with adaptive pixel strides. Signal Process. 2015, 110:37-45.
14. A. Krizhevsky, Learning multiple layers of features from tiny images, Technical Report, University of Toronto, 2009.
15. Krizhevsky A., Sutskever I., Hinton G. Imagenet classification with deep convolutional neural networks. Proc. Adv. Neural Inf. Process. Syst. 2012, 1097-1105.
16. A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, F. Li, Large-scale video classification with convolutional neural networks, in: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2014, pp. 1725-1732.
17. Liu M., Li S., Shan S., Chen X. AU-inspired deep networks for facial expression feature learning. Neurocomputing 2015, 159(2):126-136.
18. P. Luo, Y. Tian, X. Wang, X. Tang, Switchable deep network for pedestrian detection, in: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2014, pp. 899-906.
19. Montaze G., Giveki D. An improved radial basis function neural network for object image retrieval. Neurocomputing 2015, 168(11):221-233.
20. W. Ouyang, P. Luo, X. Zeng, S. Qiu, Y. Tian, H. Li, S. Yang, Z. Wang, Y. Xiong, C. Qian, Z. Zhu, R. Wang, C. Loy, X. Wang, X. Tang, DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection, 2014. http://arXiv:1409.3505.
21. W. Ouyang, X. Wang, A discriminative deep model for pedestrian detection with occlusion handling, in: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2012, pp. 3258-3265.
22. W. Ouyang, X. Wang, Joint deep learning for pedestrian detection, in: Proceedings of IEEE International Conference on Computer Vision, 2013, pp. 2056-2063.
23. W. Ouyang, X. Wang, Single-pedestrian detection aided by multi-pedestrian detection, in: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2013, pp. 3198-3205.
24. Pang Y., Zhang K., Yuan Y., Wang K. Distributed object detection with linear SVMs. IEEE Trans. Cybern. 2014, 44(11):2122-2133.
25. A. Razavian, H. Azizpour, J. Sullivan, S. Carlsson, Cnn features off-the-shelf: an astounding baseline for recognition, in: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2014, pp. 512-519.
26. P. Sermanet, K. Kavukcuoglu, S. Chintala, Y. LeCun, Pedestrian detection with unsupervised multi-stage feature learning, in: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2013, pp. 3626-3633.
27. Pang Y., Jiang X., Li X., Pan J. Efficient object detection by prediction in 3D space. Signal Process. 2015, 112:64-73.
28. Simonyan K., Zisserman A. Two-stream convolutional networks for action recognition in videos. Proc. Adv. Neural Inf. Process. Syst. 2014, 568-576.
29. K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, 2014. http://arXiv:1409.1556.
30. P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, Y. LeCun, Overfeat: Integrated recognition, localization and detection using convolutional networks, .arXiv:1312.6229v4, 2013.
31. Uijlings J., van de Sande K., Gevers T., Smeulders A. Selective search for object recognition. Int. J. Comput. Vis. 2013, 104(2):154-171.
32. S. Walk, N. Majer, K. Schindler, B. Schiele, New features and insights for pedestrian detection, in: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2010, pp. 1030-1037.
33. C. Zitnick, P. Dollár, Edge boxes: locating object proposals from edges. in: Proceedings of European Conference on Computer Vision, 2014, pp. 391-405.
34. M. Zeiler, R. Fergus, Visualizing and understanding convolutional networks, in: Proceedings of European Conference on Computer Vision, 2014, pp. 818-833.
35. X. Zeng, W. Ouyang, X. Wang, Multi-stage contextual deep learning for pedestrian detection, in: Proceedings of IEEE International Conference on Computer Vision, 2013, pp. 121-128.