Skip to main content
Erschienen in: International Journal of Machine Learning and Cybernetics 11/2019

26.08.2019 | Original Article

Enhance the recognition ability to occlusions and small objects with Robust Faster R-CNN

verfasst von: Tao Zhou, Zhixin Li, Canlong Zhang

Erschienen in: International Journal of Machine Learning and Cybernetics | Ausgabe 11/2019

Einloggen

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

search-config
loading …

Abstract

Recognizing objects with vastly different size scales and objects with occlusions is a fundamental challenge in computer vision. This paper addresses this issue by proposing a novel approach denoted as Robust Faster R-CNN for detecting objects in multi-label images. Robust Faster R-CNN employs a cascaded network structure based on the Faster R-CNN architecture to extract features from objects with different size scales. However, the proposed design provides greater robustness than Faster R-CNN by replacing the RoIPooling operation with RoIAligns to eliminate the harsh quantization conducted by RoIPooling, and we design a multi-scale RoIAligns operation by adding multiple pool sizes for adapting the detection ability of the network to objects with different sizes. Furthermore, we combine an adversarial network with the proposed network to generate training samples with occlusions significantly affecting the classification ability of the model, which improves its robustness to occlusions. Experimental results for the PASCAL VOC 2012 and 2007 datasets demonstrate the superiority of the proposed object detection approach relative to several state-of-the-art approaches.

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!

Weitere Produktempfehlungen anzeigen
Literatur
1.
Zurück zum Zitat Chen Y, Wang Z, Peng Y, Zhang Z, Yu G, Sun J (2018) Cascaded pyramid network for multi-person pose estimation. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7103–7112 Chen Y, Wang Z, Peng Y, Zhang Z, Yu G, Sun J (2018) Cascaded pyramid network for multi-person pose estimation. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7103–7112
2.
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
3.
Zurück zum Zitat Everingham M, Williams C (2010) The pascal visual object classes challenge 2010 (voc2010). In: International conference on machine learning, pp 117–176 Everingham M, Williams C (2010) The pascal visual object classes challenge 2010 (voc2010). In: International conference on machine learning, pp 117–176
4.
Zurück zum Zitat Girshick R (2015) Fast r-cnn. In: Advances in neural information processing systems, pp 91–99 Girshick R (2015) Fast r-cnn. In: Advances in neural information processing systems, pp 91–99
5.
Zurück zum Zitat Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 580–587 Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 580–587
6.
Zurück zum Zitat He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904CrossRef He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904CrossRef
7.
Zurück zum Zitat He K, Gkioxari G, Dollar P, Girshick R (2017) Mask r-cnn. IEEE Trans Pattern Anal Mach Intell 99:1–1 He K, Gkioxari G, Dollar P, Girshick R (2017) Mask r-cnn. IEEE Trans Pattern Anal Mach Intell 99:1–1
8.
Zurück zum Zitat Huang G, Liu Z, Laurens VDM, Weinberger KQ (2016) Densely connected convolutional networks. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 2261–2269 Huang G, Liu Z, Laurens VDM, Weinberger KQ (2016) Densely connected convolutional networks. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 2261–2269
9.
Zurück zum Zitat Jiang Y, Zhu X, Wang X, Yang S, Li W, Wang H, Fu P, Luo Z (2017) R2cnn: Rotational region cnn for orientation robust scene text detection. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 2261–2269 Jiang Y, Zhu X, Wang X, Yang S, Li W, Wang H, Fu P, Luo Z (2017) R2cnn: Rotational region cnn for orientation robust scene text detection. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 2261–2269
10.
Zurück zum Zitat Kong T, Yao A, Chen Y, Sun F (2016) Hypernet: Towards accurate region proposal generation and joint object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 845–853 Kong T, Yao A, Chen Y, Sun F (2016) Hypernet: Towards accurate region proposal generation and joint object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 845–853
11.
Zurück zum Zitat Kong T, Sun F, Yao A, Liu H, Lu M, Chen Y (2017) Ron: Reverse connection with objectness prior networks for object detection. In: Proceedings of IEEE international conference on computer vision and pattern recognition, vol 1 Kong T, Sun F, Yao A, Liu H, Lu M, Chen Y (2017) Ron: Reverse connection with objectness prior networks for object detection. In: Proceedings of IEEE international conference on computer vision and pattern recognition, vol 1
12.
Zurück zum Zitat Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105 Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
13.
Zurück zum Zitat Lin TY, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117–2125 Lin TY, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117–2125
14.
Zurück zum Zitat Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2015) Ssd: Single shot multibox detector. In: European conference on computer vision, pp 21–37 Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2015) Ssd: Single shot multibox detector. In: European conference on computer vision, pp 21–37
15.
Zurück zum Zitat Oquab M, Bottou L, Laptev I, Sivic J (2014) Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 1717–1724 Oquab M, Bottou L, Laptev I, Sivic J (2014) Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 1717–1724
16.
Zurück zum Zitat Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Computer vision and pattern recognition Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Computer vision and pattern recognition
17.
Zurück zum Zitat Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91–99 Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91–99
18.
Zurück zum Zitat Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115(3):211–252MathSciNetCrossRef Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115(3):211–252MathSciNetCrossRef
19.
Zurück zum Zitat Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, Lecun Y (2013) Overfeat: Integrated recognition, localization and detection using convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, Lecun Y (2013) Overfeat: Integrated recognition, localization and detection using convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition
20.
Zurück zum Zitat Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556 Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:​14091556
21.
Zurück zum Zitat Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the thirty-first AAAI conference on artificial intelligence Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the thirty-first AAAI conference on artificial intelligence
22.
Zurück zum Zitat Tao Z, Li Z, Zhang C, Lan L (2018) An improved convolutional neural network model with adversarial net for multi-label image classification. In: Pacific Rim international conference on artificial intelligence Tao Z, Li Z, Zhang C, Lan L (2018) An improved convolutional neural network model with adversarial net for multi-label image classification. In: Pacific Rim international conference on artificial intelligence
23.
Zurück zum Zitat Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Vision 104(2):154–171CrossRef Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Vision 104(2):154–171CrossRef
24.
Zurück zum Zitat Wang X, Shrivastava A, Gupta A (2017) A-fast-rcnn: Hard positive generation via adversary for object detection. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 21–26 Wang X, Shrivastava A, Gupta A (2017) A-fast-rcnn: Hard positive generation via adversary for object detection. In: Proceedings of IEEE international conference on computer vision and pattern recognition, pp 21–26
25.
Zurück zum Zitat Wei S, Li Z, Zhang C (2018) Combined constraint-based with metric-based in semi-supervised clustering ensemble. Int J Mach Learn Cybernet 9(7):1085–1100CrossRef Wei S, Li Z, Zhang C (2018) Combined constraint-based with metric-based in semi-supervised clustering ensemble. Int J Mach Learn Cybernet 9(7):1085–1100CrossRef
26.
Zurück zum Zitat Wei Y, Xia W, Lin M, Huang J, Ni B, Dong J, Zhao Y, Yan S (2016) Hcp: A flexible cnn framework for multi-label image classification. IEEE Trans Pattern Anal Mach Intell 38(9):1901–1907CrossRef Wei Y, Xia W, Lin M, Huang J, Ni B, Dong J, Zhao Y, Yan S (2016) Hcp: A flexible cnn framework for multi-label image classification. IEEE Trans Pattern Anal Mach Intell 38(9):1901–1907CrossRef
27.
Zurück zum Zitat Zheng Y, Li Z, Zhang C (2018) A hybrid architecture based on cnn for cross-modal semantic instance annotation. Multimedia Tools and Applications 77(7):8695–8710CrossRef Zheng Y, Li Z, Zhang C (2018) A hybrid architecture based on cnn for cross-modal semantic instance annotation. Multimedia Tools and Applications 77(7):8695–8710CrossRef
Metadaten
Titel
Enhance the recognition ability to occlusions and small objects with Robust Faster R-CNN
verfasst von
Tao Zhou
Zhixin Li
Canlong Zhang
Publikationsdatum
26.08.2019
Verlag
Springer Berlin Heidelberg
Erschienen in
International Journal of Machine Learning and Cybernetics / Ausgabe 11/2019
Print ISSN: 1868-8071
Elektronische ISSN: 1868-808X
DOI
https://doi.org/10.1007/s13042-019-01006-4

Weitere Artikel der Ausgabe 11/2019

International Journal of Machine Learning and Cybernetics 11/2019 Zur Ausgabe

Neuer Inhalt