Improved pedestrian detection with peer AdaBoost cascade

Abstract

Focusing on data imbalance and intraclass variation, an improved pedestrian detection with a cascade of complex peer AdaBoost classifiers is proposed. The series of the AdaBoost classifiers are learned greedily, along with negative example mining. The complexity of classifiers in the cascade is not limited, so more negative examples are used for training. Furthermore, the cascade becomes an ensemble of strong peer classifiers, which treats intraclass variation. To locally train the AdaBoost classifiers with a high detection rate, a refining strategy is used to discard the hardest negative training examples rather than decreasing their thresholds. Using the aggregate channel feature (ACF), the method achieves miss rates of 35% and 14% on the Caltech pedestrian benchmark and Inria pedestrian dataset, respectively, which are lower than that of increasingly complex AdaBoost classifiers, i.e., 44% and 17%, respectively. Using deep features extracted by the region proposal network (RPN), the method achieves a miss rate of 10.06% on the Caltech pedestrian benchmark, which is also lower than 10.53% from the increasingly complex cascade. This study shows that the proposed method can use more negative examples to train the pedestrian detector. It outperforms the existing cascade of increasingly complex classifiers.

Keywords

peer classifier / hard negative refining / pedestrian detection / cascade

References

[1] LiJ, LiangX, ShenS, XuT, FengJ, YanS. Scale-aware fast R-CNN for pedestrian detection. IEEE Transactions on Multimedia, 2018, 20(4): 985-996

[2] BRAZIL G, LIU X. Pedestrian detection with autoregressive network phases [C]// Computer Vision and Pattern Recognition (CVPR). IEEE, 2019: 7231–7240. DOI: https://doi.org/10.1109/CVPR.2019.00740.

[3] XiaL-M, HuX-J, WangJ. Anomaly detection in traffic surveillance with sparse topic model. Journal of Central South University, 2018, 25(9): 2245-2257

[4] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection [C]// Computer Vision and Pattern Recognition (CVPR). IEEE, 2005: 886–893. DOI: https://doi.org/10.1109/CVPR.2005.177.

[5] BENENSON R, MATHIAS M, TUYTELAARS T, GOOL L V. Seeking the strongest rigid detector [C]// Computer Vision and Pattern Recognition (CVPR). IEEE, 2013. DOI: https://doi.org/10.1109/CVPR.2013.470.

[6] YanY, RenJ, ZhaoH, SunG, WangZ, ZhengJ, MarshallS, SoraghanJ J. Cognitive fusion of thermal and visible imagery for effective detection and tracking of pedestrians in videos. Cognitive Computation, 2018, 10(1): 94-104

[7] FelzenszwalbP F, GirshickR, McallesterD, RamananD. Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645

[8] OuyangW, ZengX, WangX. Learning mutual visibility relationship for pedestrian detection with a deep model. International Journal of Computer Vision, 2016, 120(1): 14-27

[9] ChenY, ZhangL, LiiuX, ChenC. Pedestrian detection by learning a mixture mask model and its implementation. Information Sciences, 2016, 372: 148-161

[10] DollarP, AppelR, BelongieS, PeronaP. Fast feature pyramids for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(8): 1532-1545

[11] HuangC, LoyC C, TangX. Discriminative sparse neighbor approximation for imbalanced learning. IEEE Transactions on Neural Networks, 2018, 29(5): 1503-1513

[12] LinT, GoyalP, GirshickR, HeK, DollarP. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318-327

[13] ZhangX, ZhuC, WuH, LiuZ, XuY. An imbalance compensation framework for background subtraction. IEEE Transactions on Multimedia, 2017, 19(11): 2425-2438

[14] ZHANG L, LIN L, LIANG X, HE K. Is faster RCNN doing well for pedestrian detection? [C]// European Conference on Computer Vision. 2016: 443–457. DOI: https://doi.org/10.1007/978-3-319-46475-628.

[15] WengR, LuJ, TanY, ZhouJ. Learning cascaded deep auto-encoder networks for face alignment. IEEE Transactions on Multimedia, 2016, 18(10): 2066-2078

[16] CAI Z, VASCONCELOS N. Cascade R-CNN: Delving into high quality object detection [C]// Computer Vision and Pattern Recognition (CVPR). IEEE, 2018. DOI: https://doi.org/10.1109/cvpr.2018.00644.

[17] BOURDEV L, BRANDT J. Robust object detection via soft cascade [C]// Computer Vision and Pattern Recognition (CVPR). IEEE, 2005. DOI: 10.1109/CVPR.2005.310.

[18] WenG, HouZ, LiH, LiD, JiangL, XunE. Ensemble of deep neural networks with probability-based fusion for facial expression recognition. Cognitive Computation, 2017, 9(5): 597-610

[19] ViolaP, JonesM J. Robust real-time face detection. International Journal of Computer Vision, 2004, 57(2): 137-154

[20] FreundY, SchapireR E. A decision-theoretic generalization of on-line learning and an application to boosting. Conference on Learning Theory, 1997, 55(1): 119-139

[21] FuH-P, ZouB-J. A fast training method for AdaBoost classifier. Journal of Yunnan University: Natural Sciences Edition, 2020, 42(1): 50-57

[22] WEI Gao, HOU Zhi-hua. On the doubt about margin explanation of boosting [J]. Artificial Intelligence, 2013: 1–18. DOI: https://doi.org/10.1016/j.artint.2013.07.002.

[23] DollarP, WojekC, SchieleB, PeronaP. Pedestrian detection: An evaluation of the state of the art. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(4): 743-761