![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextgreen.png)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextred.png)
![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextgreen.png)
![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltext_open_medium.gif)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextred.png)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltext_restricted_medium.gif)
ACF Based Feature Extraction and Mixture of Expert CNNs for Pedestrian Detection
Subscribe/Renew Journal
As the community strives towards developing systems with increasing levels of autonomy, the problem of detecting pedestrians in real world scenarios has become a pivotal problem to ensure safety concerns in domains like self driving cars and assistive robotics. While handcrafted features were the norm until a few years ago, deep learning has lead to an unprecedented surge in accuracies on benchmark datasets. This paper proposes a two stage pedestrian detector, wherein the first stage involves a cascade of Aggregated Channel Features (ACF) to extract candidate pedestrian windows from an image. This is followed by introducing a thresholding technique on the ACF confidence scores that isolates candidate windows lying at the extremes of the ACF score distribution. The windows with ACF scores in between the upper and lower bounds are passed on to a Mixture of Expert (MoE) CNNs for more refined classification in the second stage. Results show that the designed detector yields close to state-of-the-art performance on the INRIA and CALTECH benchmark datasets[3] and yields a miss rate of 10.35% and 23.6% respectively at FPPI=10−1.
Keywords
- Z. Cai, M. Saberian, and N. Vasconcelos. Learning complexity-aware cascades for deep pedestrian detec- tion. arXiv preprint arXiv:1507.05348, 2015. 1, 2
- X. Chen, P. Wei, W. Ke, Q. Ye, and J. Jiao. Pedestrian detection with deep convolutional neural network. In Computer Vision-ACCV 2014 Workshops, pages 354–365. Springer, 2014. 1, 2, 7
- N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Com- puter Society Conference on, volume 1, pages 886–893. IEEE, 2005. 1, 2, 7
- P. Dolla´r, R. Appel, S. Belongie, and P. Perona. Fast feature pyramids for object detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 36(8):1532–1545, 2014. 1, 2, 7
- P. Dolla´r, Z. Tu, P. Perona, and S. Belongie. Integral channel features. In BMVC, volume 2, page 5, 2009. 2
- P. Dolla´r and C. L. Zitnick. Structured forests for fast edge detection. In Computer Vision (ICCV), 2013 IEEE International Conference on, pages 1841–1848. IEEE, 2013.
- M. Enzweiler and D. M. Gavrila. A multilevel mixture-of-experts framework for pedestrian classi- fication. Image Processing, IEEE Transactions on, 20(10):2967–2979, 2011. 2
- P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan. Object detection with discrimi- natively trained part-based models. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 32(9):1627–1645, 2010. 1, 2
- R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Computer Vision and Pat- tern Recognition (CVPR), 2014 IEEE Conference on, pages 580–587. IEEE, 2014. 1
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. Im- agenet classification with deep convolutional neural networks. In F. Pereira, C. Burges, L. Bottou, and K. Weinberger, editors, Advances in Neural Informa- tion Processing Systems 25, pages 1097–1105. Curran Associates, Inc., 2012. 1, 2, 3, 7
- S. J. Nowlan and G. E. Hinton. Evaluation of adaptive mixtures of competing experts. In NIPS, volume 3, pages 774–780, 1990. 2
- W. Ouyang and X. Wang. Joint deep learning for pedestrian detection. In Computer Vision (ICCV), 2013 IEEE International Conference on, pages 2056–2063. IEEE, 2013. 1, 2
- P. Sermanet, K. Kavukcuoglu, S. Chintala, and Y. Le- Cun. Pedestrian detection with unsupervised multi- stage feature learning. In Computer Vision and Pat- tern Recognition (CVPR), 2013 IEEE Conference on, pages 3626–3633. IEEE, 2013. 1, 2
- P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In Computer Vi- sion and Pattern Recognition, 2001. CVPR 2001. Pro- ceedings of the 2001 IEEE Computer Society Confer- ence on, volume 1, pages I–511. IEEE, 2001. 1, 2, 7.
- P. Viola, M. J. Jones, and D. Snow. Detecting pedes- trians using patterns of motion and appearance. Inter- national Journal of Computer Vision, 63(2):153–161, 2005. 2
- X. Wang, T. X. Han, and S. Yan. An hog-lbp human detector with partial occlusion handling. In Computer Vision, 2009 IEEE 12th International Conference on, pages 32–39. IEEE, 2009. 2
- S. E. Yuksel, J. N. Wilson, and P. D. Gader. Twenty years of mixture of experts. Neural Networks and Learning Systems, IEEE Transactions on, 23(8):1177–1193, 2012. 2
- X. Zeng, W. Ouyang, M. Wang, and X. Wang. Deep learning of scene-specific classifier for pedestrian detection. In Computer Vision–ECCV 2014, pages 472–487. Springer, 2014. 1, 2
- Woonhyun Nam, Piotr Dollár, and Joon Hee Han. 2014. Local decorrelation for improved pedestrian detection. In Proceedings of (NIPS'14), Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger (Eds.), Vol. 1. MIT Press, Cambridge, MA, USA, 424-432.
- Ross Girshick. 2015. Fast R-CNN. In Proceedings of the 2015 IEEE ICCV (2015). IEEE Computer Society, Washington, DC, USA, 1440-1448. DOI=http://dx.doi.org/10.1109/ICCV.2015.169
- Shaoqing Ren , Kaiming He , Ross Girshick , Jian Sun, Faster R-CNN: towards real-time object detection with region proposal networks, NIPS(2015), p.91-99, December 07-12, 2015, Montreal, Canada.
- Cai, Zhaowei et al. “A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection.” ECCV (2016) ,pages 354–370. Springer, 2016.
- S. Gidaris and N. Komodakis. Object detection via a multiregion and semantic segmentation-aware cnn model. In Proceedings of the IEEE ICCV (2015), pages 1134–1142.
- F. Yang, W. Choi, and Y. Lin. Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers. In Proceedings of the CVPR (2016), pages 2129–2137.
- J. Li, X. Liang, S. Shen, T. Xu, J. Feng, and S. Yan. Scaleaware fast r-cnn for pedestrian detection. arXiv preprint arXiv:1510.08160, 2015.
- Y. Tian, P. Luo, X. Wang, and X. Tang. Deep learning strong parts for pedestrian detection. In Proceedings of the ICCV (2015), pages 1904–1912.
- L. Zhang, L. Lin, X. Liang, and K. He. Is faster rcnn doing well for pedestrian detection? arXiv preprint arXiv:1607.07032, 2016.
- Brazil, Garrick et al. “Illuminating Pedestrians via Simultaneous Detection & Segmentation.” (2017), arXiv: 1706.08564.
- Mao, Jiayuan et al. “What Can Help Pedestrian Detection?” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017): 6034-6043.
- Verma, Ankit et al. “Pedestrian Detection via Mixture of CNN Experts and Thresholded Aggregated Channel Features.” 2015 IEEE International Conference on Computer Vision Workshop (ICCVW) (2015): 555-563.
![](https://i-scholar.in/public/site/images/abstractview.png)
Abstract Views: 218
![](https://i-scholar.in/public/site/images/pdfview.png)
PDF Views: 3