Skip to main content
SpringerLink
Log in

High-performance and deep pedestrian detection based on estimation of different parts

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Pedestrian detection, despite the recent advances, still is of a great challenge to computer vision in wide range of diversified applications such as urban autonomous driving and intelligent transportation. Deep convolutional neural network has greatly contributed to the recent advances in pedestrian detection algorithms. The aim of this paper is to use modified single-shot detector (SSD) approach in pedestrian detection and then improve it by a novel deep architecture. The proposed deep architecture extracts initial Region of Interests (RoIs) using SSD approach, while it employs nine parallel fast RCNNs based on inception modules to estimate nine different parts of body. The proposed method takes the advantage of a secure border in each initial RoI to both create an Extended Region of Candidate Pedestrian (ERCP) and also to extract multi-RoIs. It then selects a number of RoIs within the ERCP as detected pedestrians which satisfy few reasonable criteria. We also propose a new training approach based on different body parts estimation which searches the best RoIs. Comprehensive experimental results demonstrate that the proposed method, deep model based on parts in pedestrian proposals, is a highly effective method that achieves very competitive performance on two most popular pedestrian detection datasets: Caltech-USA and INRIA. We have improved the log-average miss rate on the Caltech-USA and INRIA pedestrian datasets to 7.28% and 4.96%, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

References

  1. Tian Y, Luo P, Wang X, Tang X (2015) Deep learning strong parts for pedestrian detection. In: IEEE, ICCV

  2. Jiang X, Pang Y, Li X, Pan J (2016) Speed up deep neural network based pedestrian detection by sharing features across multi-scale models. In: Neurocomputing, vol 185. Elsevier, pp 163–170

  3. Tome D, Monti F, Baroffio L, Bondi L, Tagliasacchi M, Tubaro S (2016) Deep convolutional neural networks for pedestrian detection. Sig Process Image Commun 47:482–489

    Article  Google Scholar 

  4. Cai Z, Saberian M, Vasconcelos N (2015) Learning complexity-aware cascades for deep pedestrian detection. In: IEEE, ICCV

  5. Zhang S, Yang J, Schiele B (2018) Occluded pedestrian detection through guided attention in cnn. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

  6. Li J, Liang X, Shen Sh, Xu T, Feng J, Yan S (2018) Scale-aware fast r-cnn for pedestrian detection. IEEE Trans Multimed 20(4):985–996

    Google Scholar 

  7. Wang S, Cheng J, Liu H, Tang M (2017) PCN: part and context information for pedestrian detection with cnns. In: BMVC

  8. Lin C, Lu J, Wang G, Zhou J (2018) Graininess-aware deep feature learning for pedestrian detection. In: ECCV. Springer

  9. Du X, EI-Khamy M, Morariu V, Lee J, Davis L (2016) Fused Deep Neural Networks for Efficient Pedestrian Detection. CoRR, 2016. https://arxiv.org/abs/1805.08688

  10. Zhang L, Lin L, Liang X, He K (2016) Is faster r-cnn doing well for pedestrian detection?. In: European Conference on Computer Vision. Springer, pp 443–457

  11. Tian Y, Luo P, Wang X, Tang X (2015) Pedestrian detection aided by deep learning semantic tasks. In: IEE, CVPR

  12. Cai Z, Fan Q, Feris R, Vasconcelos N (2016) A unified multi-scale deep convolutional neural network for fast object detection. In: ECCV

  13. Song T, Sun L, Xie D, Sun H, Pu S (2018) Small-scale pedestrian detection based on topological line localization and temporal feature aggregation. In: Proceedings of the ECCV, pp 536–551

  14. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of the NIPS

  15. Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional neural networks. In: Proceedings of the ECCV

  16. He K, Zhang X, Ren S, et al (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Proceedings of the ECCV

  17. Sermanet P, Eigen D, Zhang X, et al (2017) Overfeat: integrated recognition, localization and detection using convolutional networks. In: Proceedings of the ICLR

  18. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the ICLR

  19. Szegedy C, Liu W, Jia Y, et al (2015) Going deeper with convolutions. In: Proceedings of the CVPR

  20. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceeding of CVPR

  21. Girshick R, Donahue J, Darrell T, et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the CVPR

  22. Girshick R (2015) Fast R-CNN. In: Proceedings of the ICCV

  23. Ren S, He K, Girshick R, et al (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the NIPS

  24. Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: CVPR

  25. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector. In: ECCV, pp 21–37

  26. Everingham M, Vangool L, Williams CKI, Winn J, Zisserman A (2015) The PASCAL visual object classes challenge: a retrospective. IJCV 111(1):98–136

    Article  Google Scholar 

  27. Dollar P, Wojek C, Schiele B, Perona P (2009) Pedestrian detection: a benchmark. In: CVPR

  28. Saeidi M, Ahmadi A (2020) A novel approach for deep pedestrian detection based on changes in camera viewing angle. In: SIVP

  29. Saeidi M, Ahmadi A (2018) Deep learning based on parallel CNN for pedestrian detection. In: IJICT

  30. Saeidi M, Ahmadi A (2018) Deep learning based on CNN for pedestrian detection: an overview and analysis. In: IEEE, IST

  31. Saeidi M, Ahmadi A (2018) Pedestrian detection using an extended fast RCNN based on a secure margin in RoI feature maps. In: IEEE, IST

  32. Viola PA, Jones M (2004) Robust real-time face detection. J Comput Vis 57(2):137–154

    Article  Google Scholar 

  33. Dollar P, Tu Z, Perona P, Belongie S (2009) Integral channel features. In: Proceedings of British Machine Vision Conference

  34. Wojek C, Schiele B (2008) A performance evaluation of single and multi-feature people detection. In: DAGM Symposium Pattern Recognition

  35. Walk S, Majer N, Schindler K, Schiele B (2010) New features and insights for pedestrian detection. In CVPR

  36. Marin, J., Vazquez, D., Lopez, A., Amores, J., Leibl, B.: Random Forest of local experts for pedestrian detection. In: ICCV. (2013)

  37. Levi D, Silberstein S, Bar-Hillel A (2013) Fast multiple-part based object detection using kd-ferns. In: CVPR

  38. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the CVPR

  39. Dollar P, Appel R, Belongie S, Perona P (2014) Fast feature pyramids for object detection. In: PAMI

  40. Nam W, Dollar P, Han JH (2014) Local decorrelation for improved pedestrian detection. In: NIPS

  41. Zhang S, Bauchhage C, Cremers AB (2014) Informed haar-like features improve pedestrian detection. In: CVPR

  42. Paisitkriangkrai S, Shen C, Van den Hengel A (2014) Pedestrian detection with spatially pooled features and structured ensemble learning. IEEE Trans Pattern Anal Mach Intell 38(6):1243–1257

    Article  Google Scholar 

  43. Benenson R, Omran M, Hosang J, Schiele B (2014) Ten years of pedestrian detection, what have we learned. In: ECCV, CVRSUAD Workshop

  44. Yan J, Zhang X, Lei Z, Liao S, Li SZ (2013) Robust multi-resolution pedestrian detection in traffic scenes. In: CVPR

  45. Ouyang W, Wang X (2013) Single-pedestrian detection aided by multi-pedestrian detection. In: CVPR

  46. Park D, Ramanan D, Fowlkes C (2010) Mltiresolution models for object detection. In: ECCV

  47. Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: CVPR

  48. Felzenszwalb P, Girshick R, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. In: PAMI

  49. Zhang S, Benenson R, Schiele B (2015) Filtered channel features for pedestrian detection. In: CVPR

  50. Park D, Zitnick CL, Ramanan D, Dollar P (2013) Exploring weak stabilization for motion feature extraction. In: CVPR

  51. Costea AD, Nedevschi S (2014) Word channel based multiscale pedestrian detection without image resizing and using only one classifier. In: CVPR

  52. Benenson R, Mathias M, Tuytelaars T, Van Gool L (2013) Seeking the strongest rigid detector. In: CVPR

  53. Dollar P, Wojek C, Schiele B, Perona P (2012) Pedestrian detection: an evaluation of the state of the art. In: PAMI, vol 34

  54. Alexe B, Deselares T, Ferrari V (2012) Measuring the objectness of image windows. In: TPAMI

  55. Uijlings J, Sande K, Gevers T, Smeulders A (2013) Selective search for object recognition. In: IJCV

  56. Endres I, Hoiem D (2010) Category independent object proposals. In: ECCV

  57. Cheng MM, Zhang Z, Lin WY, et al (2014) BING: binarized normed gradients for objectness estimation at 300fps. In: Proceedings of the CVPR

  58. Zitnick CL, Dollar P (2014) Edge boxes: locating object proposals from edges. In: Proceedings of the ECCV

  59. Cortes C, Vapnik V (1995) Support-vector networks. In: Machine Learning, pp 237–297

  60. Laptev I (2009) Improving object detection with boosted histograms. In: Image and vision computing, vol 27. Elsevier, pp 535–544

  61. Severance C, Dowd K High Performance Computing. http://cnx.org/content/col11136/1.5

  62. Cui H, Ganger GR, Gibbons PB (2015) Scalable deep learning on distributed GPUs with a GPU-specialized parameter server. CMU-PDL-15-107

  63. Cai C, Gao J, Minjie B, Zhang P, Gao H (2015) Fast pedestrian detection with adaboost algorithm using GPU. Int J Database Theory Appl 8(6):125–132

    Article  Google Scholar 

  64. Benenson R, Mathias M, Timofte R, Gool L (2012) Pedestrian detection at 100 frames per second. In: CVPR

  65. Machida T, Naito T (2011) GPU & CPU cooperative accelerated pedestrian and vehicle detection. In: Proceeding of IEEE ICCV Workshops

  66. Fukui H, Yamashita T, Yamauchi Y, Fujiyoshi H, Murase H (2015) Pedestrian detection based on deep convolutional neural network with ensemble inference network. In: IEEE Intelligent Vehicle Symposium (IV)

  67. Shakeri A, Moshiri B, Garakani HG (2018) Pedestrian detection using image fusion and stereo vision in autonomous vehicles. In: IEEE, IST

  68. Russakovsky O, Deng J, Su H, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. In: IJCV

  69. Zhang S, Benenson R, Schiele B (2017) A diverse dataset for pedestrian detection. In: CVPR

  70. Kingma D, Ba J (2015) Adam: a method for stochastic optimization. In: ICLR

  71. Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: AISTATS

  72. Ess A, Leibe B, Schindler K, Van Gool L (2008) A mobile vision system for robust multi-person tracking. In: CVPR, IEEE Press

  73. Wojek C, Walk S, Schiele B (2009) Multi-cue onboard pedestrian detection. In: CVPR

  74. Viola P, Jones M, Snow D (2003) Detecting pedestrians using patterns of motion and appearance. In: CVPR

  75. Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR

  76. Park D, Ramanan D, Fowlkes C (2010) Multiresolution models for object detection. In: ECCV

  77. Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2011) The PASCAL visual object classes challenge 2011 (VOC2011) results. http://www.pascalnetwork.org/challenges/VOC/voc2011/workshop/index.html

Download references

Author information

Authors and Affiliations

  1. Faculty of Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran

    Mahmoud Saeidi & Ali Ahmadi

  2. School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran

    Ali Ahmadi

Authors
  1. Mahmoud Saeidi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ali Ahmadi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mahmoud Saeidi.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Saeidi, M., Ahmadi, A. High-performance and deep pedestrian detection based on estimation of different parts. J Supercomput 77, 2033–2068 (2021). https://doi.org/10.1007/s11227-020-03345-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-020-03345-4

Keywords

Search

Navigation