Faster Pedestrian Recognition Using Deformable Part Models

Authors: Alessandro Preziosi, Antonio Prioletti, Luca Castangia

Abstract:

Deformable part models achieve high precision in pedestrian recognition, but all publicly available implementations are too slow for real-time applications. We implemented a deformable part model algorithm fast enough for real-time use by exploiting information about the camera position and orientation. This implementation is both faster and more precise than alternative DPM implementations. These results are obtained by computing convolutions in the frequency domain and using lookup tables to speed up feature computation. This approach is almost an order of magnitude faster than the reference DPM implementation, with no loss in precision. Knowing the position of the camera with respect to horizon it is also possible prune many hypotheses based on their size and location. The range of acceptable sizes and positions is set by looking at the statistical distribution of bounding boxes in labelled images. With this approach it is not needed to compute the entire feature pyramid: for example higher resolution features are only needed near the horizon. This results in an increase in mean average precision of 5% and an increase in speed by a factor of two. Furthermore, to reduce misdetections involving small pedestrians near the horizon, input images are supersampled near the horizon. Supersampling the image at 1.5 times the original scale, results in an increase in precision of about 4%. The implementation was tested against the public KITTI dataset, obtaining an 8% improvement in mean average precision over the best performing DPM-based method. By allowing for a small loss in precision computational time can be easily brought down to our target of 100ms per image, reaching a solution that is faster and still more precise than all publicly available DPM implementations.

Keywords: Autonomous vehicles, deformable part model, dpm, pedestrian recognition.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1126758

References:

[1] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part-based models,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 32, no. 9, pp. 1627–1645, 2010.
[2] P. F. Felzenszwalb, R. B. Girshick, and D. McAllester, “Cascade object detection with deformable part models,” in Computer vision and pattern recognition (CVPR), 2010 IEEE conference on. IEEE, 2010, pp. 2241–2248.
[3] “Discriminatively trained deformable part models, release 4,” http://people.cs.uchicago.edu/ pff/latent-release4/, (Accessed: 2015-09-30).
[4] M. A. Sadeghi and D. Forsyth, “Fast template evaluation with vector quantization,” in Advances in Neural Information Processing Systems, 2013, pp. 2949–2957.
[5] H. Jegou, M. Douze, and C. Schmid, “Product quantization for nearest neighbor search,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 33, no. 1, pp. 117–128, 2011.
[6] C. Dubout and F. Fleuret, “Exact acceleration of linear object detectors,” in Computer Vision–ECCV 2012. Springer, 2012, pp. 301–311.
[7] J. Yan, Z. Lei, L. Wen, and S. Z. Li, “The fastest deformable part model for object detection.”
[8] M. Frigo and S. G. Johnson, “The design and implementation of FFTW3,” Proceedings of the IEEE, vol. 93, no. 2, pp. 216–231, 2005, special issue on “Program Generation, Optimization, and Platform Adaptation”.
[9] G. G. Benot Jacob, “Eigen library v3.1,” http://eigen.tuxfamily.org, 2014, (Accessed: 2015-09-30).
[10] M. Sadeghi and D. Forsyth, “30hz object detection with dpm v5,” in Computer Vision ECCV 2014, ser. Lecture Notes in Computer Science, 2014, vol. 8689, pp. 65–79.
[11] P. Doll´ar, R. Appel, S. Belongie, and P. Perona, “Fast feature pyramids for object detection,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 36, no. 8, pp. 1532–1545, 2014.
[12] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 1. IEEE, 2005, pp. 886–893.
[13] S. Imahori, M. Yagiura, and H. Nagamochi, “Practical algorithms for two-dimensional packing,” Handbook of Approximation Algorithms and Metaheuristics. Chapman & Hall/CRC Computer & Information Science Series, vol. 13, 2007.
[14] C. Premebida, J. Carreira, J. Batista, and U. Nunes, “Pedestrian detection combining rgb and dense lidar data,” in IROS, 2014.
[15] J. Xu, S. Ramos, D. Vzquez, and A. M. Lpez, “Hierarchical Adaptive Structural SVM for Domain Adaptation,” in arXiv:1408.5400, 2014.
[16] J. Yebes, L. M. Bergasa, R. Arroyo, and A. Lzaro, “Supervised learning and evaluation of KITTI’s cars detector with DPM,” in IV, Detroit, USA, June 2014, pp. 768–773.
[17] A. Geiger, “Kitti object detection evaluation,” http://www.cvlibs.net/datasets/kitti/eval object.php, 2014, (Accessed: 2015-09-30).