High accuracy object detection via bounding box regression network

doi:10.1007/s12200-019-0853-1

Front. Optoelectron.

2019, Vol. 12

Issue (3) : 324-331 https://doi.org/10.1007/s12200-019-0853-1

RESEARCH ARTICLE

High accuracy object detection via bounding box regression network

Lipeng SUN¹, Shihua ZHAO¹, Gang LI², Binbing LIU³(

)

¹. State Grid Hunan Electric Power Corporation Limited Research Institute, Changsha 410007, China
². State Grid Hunan Electric Power Corporation Limited, Changsha 410007, China
³. School of Optical and Electronics Information, Huazhong University of Science and Technology, Wuhan 430074, China

Download: PDF(1565 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

As one of the primary computer vision problems, object detection aims to find and locate semantic objects in digital images. Different with object classification, which only recognizes an object to a certain class, object detection also needs to extract accurate locations of objects. In the state-of-the-art object detection algorithms, bounding box regression plays a critical role in order to achieve high localization accuracy. Almost all the popular deep learning based object detection algorithms have utilized bounding box regression for fine tuning of object locations. However, while bounding box regression is widely used, there is few study focused on the underlying rationale, performance dependencies, and performance evaluation. In this paper, we proposed a dedicated deep neural network for bounding box regression, and presented several methods to improve its performance. Some ad hoc experiments are conducted to prove the effectiveness of the network. Also, we apply the network as an auxiliary module to the faster R-CNN algorithm and test them on some real-world images. Experiment results show certain performance improvements on detection accuracy in term of mean IOU.

Keywords deep learning object detection bounding box regression IOU distribution

Corresponding Author(s): Binbing LIU

Online First Date: 18 June 2019 Issue Date: 16 September 2019

Cite this article:

Lipeng SUN,Shihua ZHAO,Gang LI, et al. High accuracy object detection via bounding box regression network[J]. Front. Optoelectron., 2019, 12(3): 324-331.

URL:

https://academic.hep.com.cn/foe/EN/10.1007/s12200-019-0853-1
https://academic.hep.com.cn/foe/EN/Y2019/V12/I3/324

Fig.1 Object detection: find and locate objects in images

Fig.2 Schematic diagram of bounding box regression

Fig.3 Flow chart of the proposed method

Fig.4 Comparison of adjusted distribution with original distribution of IOU. (a) IOU distribution on uniformly distributed BTC; (b) IOU distribution on Laplacian distributed BTC

Fig.5 Convergence curve of RMSE

Tab.1 Improvement of IOU in three algorithm configurations

Fig.6 Detection results of BBR network on some real-world images

1	K Mikolajczyk, C Schmid. An affine invariant interest point detector. Vancouver, Canada. In: Proceedings of European Conference on Computer Vision. Beilin: Springer, 2002, 128–142
2	N Dalal, B. Triggs Histograms of oriented gradients for human detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005, 886–893
3	D G Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91–110 https://doi.org/10.1023/B:VISI.0000029664.99615.94
4	O Russakovsky, J Deng, H Su, J Krause, S Satheesh, S Ma, Z Huang, A Karpathy, A Khosla, M S Bernstein, A C Berg, F Li F. ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 2015, 115(3): 211–252 https://doi.org/10.1007/s11263-015-0816-y
5	K He, X Zhang, S Ren, J. Sun Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2015, 770–778
6	J Han, D Zhang, G Cheng, N Liu, D Xu. Advanced deep-learning techniques for salient and category-specific object detection: a survey. IEEE Signal Processing Magazine, 2018, 35(1): 84–100 https://doi.org/10.1109/MSP.2017.2749125
7	H Jiang, M M Cheng, S J Li, A Borji, J Wang. Joint salient object detection and existence prediction. Frontiers of Computer Science, 2018, https://doi.org/10.1007/s11704-017-6613-8
8	R B Girshick, J Donahue, T Darrell, J. Malik Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014, 580–587
9	S Ren, K He, R Girshick, J Sun. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137–1149 https://doi.org/10.1109/TPAMI.2016.2577031 pmid: 27295650
10	W Liu, D Anguelov, D Erhan, C Szegedy, S E Reed, C Fu, A C. Berg SSD: single shot multibox detector. In: Proceedings of European Conference on Computer Vision. Berlin: Springer, 2016, 21–37
11	J Redmon, S K Divvala, R B Girshick, A. Farhadi You only look once: unified, real-time object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016, 779–788
12	T Y Lin, P Dollar, R Girshick, K He, B Hariharan, S Belongie. Feature pyramid networks for object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017, 936–944
13	K He, G Gkioxari, P Dollar, R. Girshick Mask R-CNN. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2018, doi:10.1109/TPAMI.2018.2844175
14	M Everingham, S M A Eslami, L V Gool, C K I Williams, J Winn, A Zisserman. The pascal visual object classes challenge: A Retrospective. International Journal of Computer Vision, 2015, 111(1): 98–136 https://doi.org/10.1007/s11263-014-0733-5
15	J R R Uijlings, K E A van de Sande, T Gevers, A W M Smeulders. Selective search for object recognition. International Journal of Computer Vision, 2013, 104(2): 154–171 https://doi.org/10.1007/s11263-013-0620-5
16	P F Felzenszwalb, R B Girshick, D McAllester, D Ramanan. Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627–1645 https://doi.org/10.1109/TPAMI.2009.167 pmid: 20634557
17	H M Park, D Y Cho, K J Yoon. Greedy refinement of object proposals via boundary-aligned minimum bounding box search. IET Computer Vision, 2018, 12(3): 357–363 https://doi.org/10.1049/iet-cvi.2017.0208
18	M Everingham, L Van Gool, C K I Williams, J Winn, A Zisserman. The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 2010, 88(2): 303–338 https://doi.org/10.1007/s11263-009-0275-4
19	A Geiger, P Lenz, R. Urtasun Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Providence: IEEE, 2012, 3354–3361
20	K Simonyan, A Zisserman. Very deep convolutional networks for large-scale image recognition. 2014, arXiv:1409.1556
21	Z Chen, T Zhang, C Ouyang. End-to-end airplane detection using transfer learning in remote sensing images. Remote Sensing, 2018, 10(1): 139 https://doi.org/10.3390/rs10010139
22	S J Pan, Q Yang. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345–1359 https://doi.org/10.1109/TKDE.2009.191
23	J Deng, W Dong, R Socher, L J Li, K Li, F F Li. ImageNet: a large-scale hierarchical image database. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE, 2009, 248–255

[1]	Shihua ZHAO, Lipeng SUN, Gang LI, Yun LIU, Binbing LIU. A CCD based machine vision system for real-time text detection[J]. Front. Optoelectron., 2020, 13(4): 418-424.

Viewed

Full text

Abstract

Cited

Shared

Discussed