Abstract
Object detection has achieved significantly progresses in recent years. Proposal-based methods have become the mainstream object detectors, achieving excellent performance on accurate recognition and localization of objects. However, region proposal generation is still a bottleneck. In this paper, to address the limitations of conventional region proposal network (RPN) that defines dense anchor boxes with different scales and aspect ratios, we propose an anchor-free proposal generator named corner region proposal network (CRPN) which is based on a pair of key-points, including top-left corner and bottom-right corner of an object bounding box. First, we respectively predict the top-left corners and bottom-right corners by two sibling convolutional layers, then we obtain a set of object proposals by grouping strategy and non-maximum suppression algorithm. Finally, we further merge CRPN and fully convolutional network (FCN) into a unified network, achieving an end-to-end object detection. Our method has been evaluated on standard PASCAL VOC and MS COCO datasets using a deep residual network. Experiment results present that the proposed method outperforms previous detectors in the term of precision. Additionally, it runs with a speed of 76 ms per image on a single GPU by using ResNet-50 as the backbone, which is faster than other detectors.
Similar content being viewed by others
References
Alexe B, Deselaers T, Ferrari VJItopa, intelligence m (2012) Measuring the objectness of image windows. IEEE Trans Pattern Anal Mach Intell 34 (11):2189–2202
Arbelaez P, Pont-Tuset J, Barron JT, Marques F, Malik J (2014) Multiscale combinatorial grouping. In: Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 328–335. https://doi.org/10.1109/cvpr.2014.49
Belongie S, Malik J, Puzicha JJIToPA, Intelligence M (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522
Cai Z, Vasconcelos N (2018) Cascade R-CNN: Delving Into High Quality Object Detection. Paper presented at the computer vision and pattern recognition, pp 6154–6162
Cheng M-M, Zhang Z, Lin W-Y, Torr P (2014) BING: Binarized normed gradients for objectness estimation at 300fps. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3286–3293
Chu J, Guo Z, Leng LJIA (2018) Object Detection Based on Multi-Layer Convolution Feature Fusion and Online Hard Example Mining. IEEE Access 6:19959–19967
Dai J, Li Y, He K, Sun J (2016) R-FCN: Object detection via region-based fully convolutional networks. Adv Neural Inf Process Syst 29:379–387
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. Paper presented at the IEEE Computer Society Conference on Computer Vision & Pattern Recognition,pp 886–893
Fang F, Wang HL, Chen YH, Tang PJ (2018) Looking deeper and transferring attention for image captioning. Multimed Tools Appl 77(23):31159–31175. https://doi.org/10.1007/s11042-018-6228-6
Felzenszwalb PF, Girshick RB, McAllester D (2010) Cascade object detection with deformable part models. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, pp 2241–2248
Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE conference on computer vision and pattern recognition. IEEE, pp 1–8
Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2009) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645
Fu C, Liu W, Ranga A, Tyagi A, Berg ACJaCV (2017) DSSD: Deconvolutional Single Shot Detector. Computer Vision Pattern Recognition, arXiv
Ghodrati A, Diba A, Pedersoli M, Tuytelaars T, Van Gool L (2015) DeepProposal: Hunting objects by cascading deep convolutionall layers. Paper presented at the in: International Conference on Computer Vision,pp 2578–2586
Girshick R (2015) Fast r-cnn. Paper presented at the International Conference on Computer Vision, pp 1440–1448
Girshick RB, Felzenszwalb PF, Mcallester DA (2011) Object detection with grammar models. Paper presented at the Advances in Neural Information Processing Systems, pp 442–450
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 580–587. https://doi.org/10.1109/cvpr.2014.81
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):1904–1916
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
He K, Gkioxari G, Dollar P, Girshick R (2017) Mask R-CNN. In: the IEEE international conference on computer vision. IEEE, pp 2961–2969. https://doi.org/10.1109/tpami.2018.2844175
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet Classification with Deep Convolutional Neural Networks. Paper presented at the neural information processing systems,pp 1097–1105
Kumar N, Sukavanam N (2020) A cascaded CNN model for multiple human tracking and re-localization in complex video sequences with large displacement. Multimed Tools Appl 79(9–10):6109–6134. https://doi.org/10.1007/s11042-019-08501-4
Kuo W, Hariharan B, Malik J, Ieee (2015) DeepBox: Learning Objectness with Convolutional Networks. In: 2015 Ieee International Conference on Computer Vision. IEEE International Conference on Computer Vision. pp 2479–2487. https://doi.org/10.1109/iccv.2015.285
Law H, Deng J (2018) CornerNet: Detecting Objects as Paired Keypoints. arXiv e-prints
LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LDJNC (1989) Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput 1(4):541–551
Li J, Bao H, Han XM, Pan F, Pan WG, Zhang FF, Wang D (2017) Real-time self-driving car navigation and obstacle avoidance using mobile 3D laser scanner and GNSS. Multimed Tools Appl 76(21):23017–23039. https://doi.org/10.1007/s11042-016-4211-7
Li K, Cheng G, Bu S, You X (2018) Rotation-insensitive and context-augmented object detection in remote sensing images. IEEE Trans Geosci Remote Sens 56(4):2337–2348. https://doi.org/10.1109/tgrs.2017.2778300
Li TP, Zhou PP, Liu H (2019) Multiple features fusion based video face tracking. Multimed Tools Appl 78(15):21963–21980. https://doi.org/10.1007/s11042-019-7414-x
Li K, Ma W, Sajid U, Wu Y, Wang G (2020) Object Detection with Convolutional Neural Networks. CRC Press, Boca Raton, pp 41–62. https://doi.org/10.1201/9781351003827-2
Lin T-Y, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. Paper presented at the Conference on Computer Vision and Pattern Recognition, pp 2117–2125
Lin TY, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. Paper presented at the in: International Conference on Computer Vision,pp 2980–2988
Liu L, Ouyang W, Wang X, Fieguth P, Chen J, Liu X, Pietikainen M (2020) Deep Learning for Generic Object Detection: A Survey. Int J Comput Vision 128(2):261–318. https://doi.org/10.1007/s11263-019-01247-4
Lowe DGJIjocv (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vision 60(2):91–110
Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the seventh IEEE international conference on computer vision, vol 2, pp 1150–1157
Malisiewicz T, Gupta A, Efros A (2011) Ensemble of exemplar-svms for object detection and beyond. Paper presented at the 2011 International conference on computer vision,pp 89–96
Nagarajan MB, Vision MBHJM, Applications Classification of small lesions in dynamic breast MRI: eliminating the need for precise lesion segmentation through spatio-temporal analysis of contrast enhancement. 24 (7):1371–1381
Redmon J, Divvala SK, Girshick R, Farhadi A (2016) You Only Look Once: Unified, Real-Time Object Detection. In: computer vision and pattern recognition, pp 779–788
Ren SQ, He KM, Girshick R, Sun J (2017) Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149. https://doi.org/10.1109/tpami.2016.2577031
Sekaran K, Chandana P, Krishna NM, Kadry S (2020) Deep learning convolutional neural network (CNN) With Gaussian mixture model for predicting pancreatic cancer. Multimed Tools Appl 79(15–16):10233–10247. https://doi.org/10.1007/s11042-019-7419-5
Tao K, Yao A, Chen Y, Sun F (2016) HyperNet: Towards accurate region proposal generation and joint object detection. Paper presented at the Conference on Computer Vision and Recognition P, IEEE,pp 845–853
Tychsen-Smith L, Petersson L (2017) DeNet: Scalable real-time object detection with directed dparse sampling. In: in: International Conference on Computer Vision. IEEE International Conference on Computer Vision. IEEE, pp 428–436. https://doi.org/10.1109/iccv.2017.54
Uijlings JRR, van de Sande KEA, Gevers T, Smeulders AWM (2013) Selective search for object recognition. Int J Comput Vision 104(2):154–171. https://doi.org/10.1007/s11263-013-0620-5
Wang S, Lan L, Zhang X, Luo ZJMT (2020) GateCap: Gated spatial and semantic attention model for image captioning. Multimedia Tools Applications:1–19
Yang B, Yan J, Lei Z, Li SZ (2016) Craft objects from images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6043–6051
Yang WK, Zhou LK, Li TH, Wang HR (2019) A Face Detection Method Based on Cascade Convolutional Neural Network. Multimed Tools Appl 78(17):24373–24390. https://doi.org/10.1007/s11042-018-6995-0
Zhang Y, Lv PH, Lu XB, Li J (2019) Face detection and alignment method for driver on highroad based on improved multi-task cascaded convolutional networks. Multimed Tools Appl 78(18):26661–26679. https://doi.org/10.1007/s11042-019-07836-2
Zhang Y, Chu J, Leng L, Miao JJS (2020) Mask-Refined R-CNN: A Network for Refining Object Details in Instance Segmentation. Sensors 20(4):1010
Zitnick CL, Dollár P (2014) Edge boxes: Locating object proposals from edges. Paper presented at the European conference on computer vision, pp 391–405
Acknowledgements
This work was supported by the National Natural Science Foundation of China (grant numbers 31671586, 61773360).
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
Jiao, L., Wang, R. & Xie, C. C-FCN: Corners-based fully convolutional network for visual object detection. Multimed Tools Appl 79, 28841–28857 (2020). https://doi.org/10.1007/s11042-020-09503-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09503-3