Browse > Article
http://dx.doi.org/10.9717/kmms.2019.22.1.044

CycleGAN-based Object Detection under Night Environments  

Cho, Sangheum (Dept. of Software and Computer Engineering, Ajou University)
Lee, Ryong (Korea Institute of Science and Technology Information)
Na, Jaemin (Dept. of Software and Computer Engineering, Ajou University)
Kim, Youngbin (Dept. of Software and Computer Engineering, Ajou University)
Park, Minwoo (Korea Institute of Science and Technology Information)
Lee, Sanghwan (Korea Institute of Science and Technology Information)
Hwang, Wonjun (Dept. of Software and Computer Engineering, Ajou University)
Publication Information
Journal of Korea Multimedia Society / v.22, no.1, 2019 , pp. 44-54 More about this Journal
Abstract
Recently, image-based object detection has made great progress with the introduction of Convolutional Neural Network (CNN). Many trials such as Region-based CNN, Fast R-CNN, and Faster R-CNN, have been proposed for achieving better performance in object detection. YOLO has showed the best performance under consideration of both accuracy and computational complexity. However, these data-driven detection methods including YOLO have the fundamental problem is that they can not guarantee the good performance without a large number of training database. In this paper, we propose a data sampling method using CycleGAN to solve this problem, which can convert styles while retaining the characteristics of a given input image. We will generate the insufficient data samples for training more robust object detection without efforts of collecting more database. We make extensive experimental results using the day-time and night-time road images and we validate the proposed method can improve the object detection accuracy of the night-time without training night-time object databases, because we converts the day-time training images into the synthesized night-time images and we train the detection model with the real day-time images and the synthesized night-time images.
Keywords
CycleGAN; Data Sampling; Image-to-Image Translation;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 J.Y. Zhu, T. Park, P. Isola, and A.A. Efros, "Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks," Proceeding of International Conference on Computer Vision, pp. 2242-2251, 2017.
2 Y. Choi, M. Choi, M. Kim, JW. Ha, S. Kim, J. Choo, et al., "StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation," Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 8789-8797, 2018.
3 I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, et al., "Generative Adversarial Nets," Proceeding of Conference on Neural Information Processing Systems, pp. 1-9, 2014.
4 P. Isola, J.Y. Zhu, T. Zhou, and A.A. Efros, "Image-to-Image Translation with Conditional Adversarial Networks," Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 5967-5976, 2017.
5 W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, CY. Fu, et al., "SSD: Single Shot Multibox Detector," Proceeding of European Conference on Computer Vision, pp. 21-37, 2016.
6 J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 6517-6525, 2017.
7 M. Everingham, L. Van Gool, C.K.I. Williams, J. Winn, and A. Zisserman, “The PASCAL Visual Object Classes (VOC) Challenge,” International J ournal of Computer Vision, Vol. 88, No. 2, pp. 303-338, 2010.   DOI
8 T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, et al., "Microsoft COCO: Common Objects in Context," Proceeding of European Conference on Computer Vision, pp. 740-755, 2014.
9 F. Yu, W. Xian, Y. Chen, F. Liu, M. Liao, V. Madhavan, et al., "BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling," arXiv Preprint arXiv:1805.04687, 2018.
10 E. Denton, S. Chintala, A. Szlam, and R. Fergus, "Deep Generative Image Models Using a Laplacian Pyramid of Adversarial Networks," Proceeding of Conference on Neural Information Processing Systems, pp. 1486-1494, 2015.
11 A. Radford, L. Metz, and S. Chintala, "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks," Proceeding of International Conference on Learning Representations, pp. 1-16, 2016.
12 M. Mirza and S. Osindero, "Conditional Generative Adversarial Nets," arXiv Preprint arXiv:1411.1784, 2014.
13 M.Y. Liu and O. Tuzel, "Coupled Generative Adversarial Networks," Proceeding of Conference on Neural Information Processing Systems, pp. 469-477, 2016.
14 L.A. Gatys, A.S. Ecker, and M. Bethge, "Image Style Transfer Using Convolutional Neural Networks," Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 2414-2423, 2016.
15 M.Y. Liu, T. Breuel, and J. Kautz, "Unsupervised Image-to-Image Translation Networks," Proceeding of Conference on Neural Information Processing Systems, pp. 700-708, 2017.
16 T. Kim, M. Cha, H. Kim, J.K. Lee, and J. Kim, "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks," Proceeding of International Conference on Machine Learning, pp. 1857-1865, 2017.
17 J. Johnson, A. Alahi, and L. Fei-Fei, "Perceptual Losses for Real-Time Style Transfer and Super-Resolution," Proceeding of European Conference on Computer Vision, pp. 694-711, 2016.
18 K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
19 D.P. Kingma and J.L. Ba, "ADAM: A Method for Stochastic Optimization," Proceeding of International Conference on Learning Representations, pp. 1-15, 2015.
20 J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only Look Once: Unified, Real-Time Object Detection," Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016.
21 H.S. Ha and B.Y. Hwang, “Enhancement Method of CCTV Video Quality Based on SRGAN,” Journal of Korea Multimedia Society, Vol. 21, No. 9, pp. 1027-1034, 2018.   DOI