Abstract
Pedestrian detection based on Deep Convolutional Neural Networks (DCNNs) has made great stride in the last few years. Researchers have recently employed different DCNN-based techniques to detect pedestrian more accurately than before. In this paper, we propose a new Deep Model based on Changes in Camera Viewing Angle (DM-CCVA) to detect pedestrian. The proposed novel DM-CCVA is based on integrating a modified Single-Shot Detector (SSD) and a set of parallel Fast Region-based Convolutional Neural Networks (FRCNNs) to accurately detect pedestrian. The proposed deep architecture extracts initial candidate pedestrians using a modified SSD model, while utilizing five parallel Fast RCNNs to detect pedestrians in five different sets of camera viewing angles. We also propose a new training approach based on changes in camera viewing angle which searches the best Region of Interests (RoIs). Moreover, by exploiting a secure border in each initial candidate pedestrian, the proposed method both creates an Extended Region of Candidate Pedestrian (ERCP) and extracts multi-RoIs. It then selects a number of RoIs within the ERCP as detected pedestrians which satisfy few reasonable criteria. Comprehensive experimental results demonstrate that the proposed DM-CCVA is a highly effective method that achieves very competitive performance on two most popular pedestrian detection datasets: Caltech-USA and INRIA.
Similar content being viewed by others
References
Tian, Y., Luo, P., Wang, X., Tang, X.: Pedestrian detection aided by deep learning semantic tasks. In: IEEE, CVPR, 2015
Tian, Y., Luo, P., Wang, X., Tang, X.: Deep learning strong parts for pedestrian detection. In: IEEE, ICCV, 2015
Cai, Z., Saberian, M., Vasconcelos, N.: Learning complexity-aware cascades for deep pedestrian detection. In: IEEE, ICCV, 2015
Zhang, L., Lin, L., Liang, X., He, K.: Is faster r-cnn doing well for pedestrian detection? In: ECCV, pp. 443–457, Springer, 2016
Zhang, S., Yang, J., Schiele, B.: Occluded pedestrian detection through guided attention in cnn. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018
Li, J., Liang, X., Shen, S., Xu, T., Feng, J., Yan, S.: Scale-aware fast r-cnn for pedestrian detection. IEEE Trans. Multimedia 20(4), 985–996 (2018)
Lin, C., Lu, J., Wang, G., Zhou, J.: Graininess-aware deep feature learning for pedestrian detection. In: ECCV. Springer, 2018
Du, X., EI-Khamy, M., Morariu, V., Lee, J., Davis, L.: Fused Deep Neural Networks for Efficient Pedestrian Detection. In: CoRR, 2016, https://arxiv.org/abs/1805.08688
Wang, S., Cheng, J., Liu, H., Tang, M.: PCN: part and context information for pedestrian detection with cnns. In: BMVC, 2017
Cai, Z., Fan, Q., Feris, R., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: ECCV, 2016
Song, T., Sun, L., Xie, D., Sun, H., Pu, S.: Small-scale pedestrian detection based on topological line localization and temporal feature aggregation. In: Proceedings of the ECCV, pp. 536–551, 2018
Jiang, X., Pang, Y., Li, X., Pan, J.: Speed up deep neural network based pedestrian detection by sharing features across multi-scale models, pp. 163–170. Elsevier, New York (2016)
Tome, D., Monti, F., Baroffio, L., Bondi, L., Tagliasacchi, M., Tubaro, S.: Deep convolutional neural networks for pedestrian detection. Sig. Process. Image Commun. 47, 482–489 (2016)
Luo, P., Tian, Y., Wang, X., Tang, X.: Switchable deep network for pedestrian detection. In: CVPR, 2014
Zeng, X., Ouyang, W., Wang, X.: Multi-stage contextual learning pedestrian detection. In: ICCV, 2013
Riberio, D., Nascimento, J.C., Bernardino, A., Carneiro, G.: Improving the performance of pedestrian detectors using convolutional learning, Elsevier. Pattern Recognit. 2017, 641–649 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the ICLR, 2015
Krizhevsky, A., Sutskever, I., Hinton, G. E.: Imagenet classification with deep convolutional neural networks. In: proceedings of the NIPS, 2012
Zeiler, M. D., Fergus, R.: Visualizing and understanding convolutional neural networks. In: Proceedings of the ECCV, 2014
He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Proceedings of the ECCV, 2014
Sermanet, P., Eigen, D., Zhang, X., et al.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: Proceedings of the ICLR, 2014
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the CVPR, 2015
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)
Dollar, P., Tu, Z., Perona, P., Belongie, S.: Integral Channel Features. In: Proceedings of BMVC (2009)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the CVPR (2005)
Benenson, R., Mathias, M., Tuytelaars, T., Van Gool, L.: Seeking the strongest rigid detector. In: CVPR, 2013
Levi, D., Silberstein, S., Bar-Hillel, A.: Fast multiple-part based object detection using kd-ferns. In: CVPR, 2013
Dollar, P., Apple, R., Perona, S.: Fast feature pyramids for object detection. In: PAMI, 2014
Felzenszwalb, P. F., Grishick, R. B., McAllister, D., Ramanan, D.: Object detection with discriminatively trained part based models. In: IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 99, 2010
Enzweiler, M., Eigenstetter, A., Schiele, B., Gavrila, D. M.: Multi-cue pedestrian classification with partial occlusion handling. In: CVPR, 2010
Gao, T., Packer, B., Koller, D.: A segmentation-aware object detection model with occlusion handling. In: CVPR, 2011
Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the CVPR, 2014
Girshick, R.: Fast R-CNN. In: Proceedings of the ICCV, 2015
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the NIPS, 2015
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., Berg, A. C.: SSD: Single Shot MultiBox Detector. In: ECCV, 2016, pp. 21–37
Saeidi, M., Ahmadi, A.: Deep learning based on CNN for pedestrian detection: an overview and analysis. In: IEEE, IST, 2018
Saeidi, M., Ahmadi, A.: Pedestrian detection using an extended fast RCNN based on a secure margin in RoI feature maps. In: IEEE, IST, 2018
Saeidi, M., Ahmadi, A.: Deep Learning based on Parallel CNN for Pedestrian Detection. In: IJICT (2018)
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. In: PAMI, vol. 5, 2012
Everingham, M., Vangool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge: a retrospective. IJCV 111(1), 98–136 (2015)
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: CVPR, 2009
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR, 2015
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Saeidi, M., Ahmadi, A. A novel approach for deep pedestrian detection based on changes in camera viewing angle. SIViP 14, 1273–1281 (2020). https://doi.org/10.1007/s11760-020-01662-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-020-01662-y