Skip to main content
Erschienen in: Neural Processing Letters 3/2019

25.04.2018

Rapid Pedestrian Detection Based on Deep Omega-Shape Features with Partial Occlusion Handing

verfasst von: Yuting Xu, Xue Zhou, Pengfei Liu, Hongbing Xu

Erschienen in: Neural Processing Letters | Ausgabe 3/2019

Einloggen

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Region-based Fully ConvNet (R-FCN) designed for general object detection is difficult to be directly applied for pedestrian detection, due to being with large human pose and scale changes, and even with partial occlusion in surveillance scenarios. This paper presents a rapid pedestrian detection method with partial occlusion handling, which builds on the framework of R-FCN. We introduce a deep Omega-shape feature learning and multi-paths detection to make our detector be robust to human pose and scale changes. A novel predicted boxes fusion strategy is proposed to reduce the number of false negatives caused by partial occlusion in crowded environment. Our end-to-end approach achieved 95.35% mAP on the Caltech dataset, 96.22% mAP on DukeMTMC dataset and 97.43% mAP on Bronze dataset at a test-time speed of approximate 86 ms per image.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Dai J, Li, Y, He, K, Sun J (2016) R-FCN: object Detection via region-based fully convolutional networks. In: Advances in neural information processing systems, pp 379–387 Dai J, Li, Y, He, K, Sun J (2016) R-FCN: object Detection via region-based fully convolutional networks. In: Advances in neural information processing systems, pp 379–387
2.
Zurück zum Zitat Everingham M et al (2010) The PASCAL visual object classes (VOC) challenge. IJCV 88(2):303–338CrossRef Everingham M et al (2010) The PASCAL visual object classes (VOC) challenge. IJCV 88(2):303–338CrossRef
3.
Zurück zum Zitat Liu W et al (2016) SSD: single Shot multibox detector. In: ECCV, pp 21–37 Liu W et al (2016) SSD: single Shot multibox detector. In: ECCV, pp 21–37
5.
Zurück zum Zitat Piotr D et al (2012) Pedestrian detection: an evaluation of the state of the art. TPAMI 34(4):734–761 Piotr D et al (2012) Pedestrian detection: an evaluation of the state of the art. TPAMI 34(4):734–761
6.
Zurück zum Zitat Li M et al (2009) Rapid and robust human detection and tracking based on omega-shape features. In: IEEE international conference on image processing, pp 2545–2548 Li M et al (2009) Rapid and robust human detection and tracking based on omega-shape features. In: IEEE international conference on image processing, pp 2545–2548
7.
Zurück zum Zitat Li M et al (2008) Estimating the number of people in crowded scenes by mid-based foreground segmentation and head-shoulder detection. In: International conference on pattern recognition, pp 1–4 Li M et al (2008) Estimating the number of people in crowded scenes by mid-based foreground segmentation and head-shoulder detection. In: International conference on pattern recognition, pp 1–4
8.
Zurück zum Zitat Shen F et al (2018) Unsupervised deep hashing with similarity-adaptive and discrete optimization. In: IEEE transactions on pattern analysis and machine intelligence Shen F et al (2018) Unsupervised deep hashing with similarity-adaptive and discrete optimization. In: IEEE transactions on pattern analysis and machine intelligence
9.
10.
Zurück zum Zitat Liliang Z, Liang L, Xiaodan L, Kaiming H (2016) Is faster R-CNN doing well for pedestrian detection?. In: ECCV, pp 443–457 Liliang Z, Liang L, Xiaodan L, Kaiming H (2016) Is faster R-CNN doing well for pedestrian detection?. In: ECCV, pp 443–457
11.
Zurück zum Zitat Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal network. In: NIPS, pp 91–99 Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal network. In: NIPS, pp 91–99
12.
Zurück zum Zitat Shen F, Tang Z, Jingsong X (2013) Locality constrained representation based classification with spatial pyramid patches. Neurocomputing 101:104–115CrossRef Shen F, Tang Z, Jingsong X (2013) Locality constrained representation based classification with spatial pyramid patches. Neurocomputing 101:104–115CrossRef
13.
Zurück zum Zitat Huang J et al (2017) Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR Huang J et al (2017) Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR
14.
Zurück zum Zitat Dollar P et al (2009) Integral channel features. In: British machine vision conference Dollar P et al (2009) Integral channel features. In: British machine vision conference
15.
Zurück zum Zitat Tian Y, Luo P, Wang X, Tang X (2015) Pedestrian detection aided by deep learning semantic tasks. In: CVPR, pp 5079–5087 Tian Y, Luo P, Wang X, Tang X (2015) Pedestrian detection aided by deep learning semantic tasks. In: CVPR, pp 5079–5087
16.
Zurück zum Zitat Piotr D et al (2014) Fast feature pyramids for object detection. PAMI 36(8):1532–1545CrossRef Piotr D et al (2014) Fast feature pyramids for object detection. PAMI 36(8):1532–1545CrossRef
17.
Zurück zum Zitat Zhang S, Benenson R, Schiele B (2015) Filtered channel features for pedestrian detection. In: CVPR Zhang S, Benenson R, Schiele B (2015) Filtered channel features for pedestrian detection. In: CVPR
18.
Zurück zum Zitat Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. CVPR 1:886–893 Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. CVPR 1:886–893
19.
Zurück zum Zitat Felzenszwalb PF et al (2010) Object detection with discriminatively trained part based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645CrossRef Felzenszwalb PF et al (2010) Object detection with discriminatively trained part based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645CrossRef
20.
Zurück zum Zitat Hosang J, Omran M, Benenson R, Schiele B (2015) Taking a deeper look at pedestrians. In: CVPR, pp 4073–4082 Hosang J, Omran M, Benenson R, Schiele B (2015) Taking a deeper look at pedestrians. In: CVPR, pp 4073–4082
21.
Zurück zum Zitat Cai Z, Saberian M, Vasconcelos N (2015) Learning complexity-aware cascades for deep pedestrian detection. In: ICCV, pp 3361–3369 Cai Z, Saberian M, Vasconcelos N (2015) Learning complexity-aware cascades for deep pedestrian detection. In: ICCV, pp 3361–3369
22.
Zurück zum Zitat Wang X, Shrivastava A, Gupta A (2017) A-fast-RCNN: hard positive genneration via adversary for object detection. arXiv preprint arXiv:1704.03414 Wang X, Shrivastava A, Gupta A (2017) A-fast-RCNN: hard positive genneration via adversary for object detection. arXiv preprint arXiv:​1704.​03414
23.
Zurück zum Zitat Goodfellow I et al (2014) Generative adversarial nets. In: NIPS, pp 2672–2680 Goodfellow I et al (2014) Generative adversarial nets. In: NIPS, pp 2672–2680
25.
26.
Zurück zum Zitat Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: CVPR, pp 3431–3440 Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: CVPR, pp 3431–3440
27.
Zurück zum Zitat He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778 He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778
28.
Zurück zum Zitat Stewart R, Andriluka M, Ng AY (2016) End-to-end people detection in crowded scenes. In: CVPR, pp 2325–2333 Stewart R, Andriluka M, Ng AY (2016) End-to-end people detection in crowded scenes. In: CVPR, pp 2325–2333
29.
Zurück zum Zitat Liu P, Zhou X, Cai S (2016) Omega-shape feature learning for robust human detection. In: CCPR, pp 290–303 Liu P, Zhou X, Cai S (2016) Omega-shape feature learning for robust human detection. In: CCPR, pp 290–303
31.
Zurück zum Zitat Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. In: CVPR, pp 761–769 Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. In: CVPR, pp 761–769
32.
Zurück zum Zitat Zitnick CL, Dollar P (2014) Edge boxes: Locating object proposals from edges? In: ECCV, pp 391–405 Zitnick CL, Dollar P (2014) Edge boxes: Locating object proposals from edges? In: ECCV, pp 391–405
33.
Zurück zum Zitat Bodla N et al (2017) Soft-NMS—improving object detection with one line of code. In: ICCV, pp 5561–5569 Bodla N et al (2017) Soft-NMS—improving object detection with one line of code. In: ICCV, pp 5561–5569
34.
Zurück zum Zitat Ristani E et al (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV, pp 17–35 Ristani E et al (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV, pp 17–35
35.
Zurück zum Zitat Jia Y et al (2014) Caffe: convolutional architecture for fast feature embedding. In: ACM, pp 675–678 Jia Y et al (2014) Caffe: convolutional architecture for fast feature embedding. In: ACM, pp 675–678
36.
Zurück zum Zitat Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The kitti vision benchmark suite. In: CVPR, pp 3354–3361 Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The kitti vision benchmark suite. In: CVPR, pp 3354–3361
37.
Zurück zum Zitat Lin T-Y et al (2017) Feature pyramid networks for object detection. In: CVPR Lin T-Y et al (2017) Feature pyramid networks for object detection. In: CVPR
Metadaten
Titel
Rapid Pedestrian Detection Based on Deep Omega-Shape Features with Partial Occlusion Handing
verfasst von
Yuting Xu
Xue Zhou
Pengfei Liu
Hongbing Xu
Publikationsdatum
25.04.2018
Verlag
Springer US
Erschienen in
Neural Processing Letters / Ausgabe 3/2019
Print ISSN: 1370-4621
Elektronische ISSN: 1573-773X
DOI
https://doi.org/10.1007/s11063-018-9837-1

Weitere Artikel der Ausgabe 3/2019

Neural Processing Letters 3/2019 Zur Ausgabe