Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/137677
|
| Title: | 水下顯著物目標檢測
Underwater Salient Object Detection |
| Authors: | 林祐丞
Lin, Yu-Cheng |
| Contributors: | 彭彥璁
Peng, Yan-Tsung
林祐丞
Lin, Yu-Cheng |
| Keywords: | 顯著物偵測
資料擴增
深度學習
Underwater salient object detection
Data augmentation
Deep learning |
| Date: | 2021 |
| Issue Date: | 2021-11-01 12:00:43 (UTC+8) |
| Abstract: | 顯著物偵測(SOD)在深度學習架構下已達到相當先進的成果。然而既有的研究大部分都專注在陸上場景，水下場景的顯著物偵測仍有待發展。在這篇論文中，我們蒐集並標註一水下顯著物資料集，用以驗證我們提出的模型方法。本論文中提出二種方法提昇顯著物偵測準確度。第一，我們先嘗試利用了水下影像模糊特性，幫助深度網路學習顯著物偵測。首先，我們會從原圖計算生成模糊圖，並與原圖一起輸入模型抽取特徵並融合，藉以提昇顯著物偵測準確度。第二，我們提出基於模糊圖對原圖增益作調整的一種資料擴增的方法。實驗結果顯示在最新顯著物偵測模型上，使用這兩種方法，皆可有效提昇效能。而提出的資料擴增方法的成效，比第一種方法更為有效。
Salient object detection (SOD) has achieved state-of-the-art performance with the help of deep networks. However, most of the works focus on terrestrial scenes, and underwater scenes for SOD are still unexplored. In this work, we propose two practical approaches to boost the performance of underwater SOD. First, we utilize image blurriness to enable a more accurate SOD prediction. The blurriness map is calculated based on the input image, fed into the model with the input, and fused with the input image to produce the saliency map. Next, we propose a data augmentation method called FocusAugment for underwater SOD, which adjusts the image intensity based on the blurriness map. We can modify images by highlighting less blurred regions or enlarging the difference of pixels based on the blurriness maps. We test underwater SOD by the proposed dataset collected and annotated by ourselves for evaluation. The experimental results show that both of our approaches work; moreover, the presented FocusAugment works better than the blurriness-guided SOD model. |
| Reference: | [1] D. V. Ruiz, B. A. Krinski, and E. Todt, “Ida: Improved data augmentation applied to salient object detection,” in 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE, 2020.
[2] Y. Pang, X. Zhao, L. Zhang, and H. Lu, “Multiscale interactive network for salient object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
[3] D. Zhang, D. Meng, L. Zhao, and J. Han, “Bridging saliency detection to weakly supervised object detection based on selfpaced curriculum learning,” arXiv preprint arXiv:1703.01290, 2017.
[4] Z. Ren, S. Gao, L.T. Chia, and I. W.H. Tsang, “Regionbased saliency detection and its application in object recognition,” IEEE Transactions on Circuits and Systems for Video Technology, 2013.
[5] S. P. Bharati, S. Nandi, Y. Wu, Y. Sui, and G. Wang, “Fast and robust object tracking with adaptive detection,” in 2016 IEEE 28th international conference on tools with artificial intelligence (ICTAI). IEEE, 2016.
[6] H. Lee and D. Kim, “Salient regionbased online object tracking,” in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2018. 30
[7] M. Cornia, L. Baraldi, G. Serra, and R. Cucchiara, “Paying more attention to saliency: Image captioning with saliency and context attention,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2018.
[8] H. Hadizadeh and I. V. Bajić, “Saliencyaware video compression,” IEEE Transactions on Image Processing, vol. 23, no. 1, pp. 19–33, 2013.
[9] Q.G. Ji, Z.D. Fang, Z.H. Xie, and Z.M. Lu, “Video abstraction based on the visual attention model and online clustering,” Signal Processing: Image Communication, vol. 28, no. 3, pp. 241–253, 2013.
[10] Y. Ban and K. Lee, “Reenrichment learning: Metadata saliency for the evolutive personalization of a recommender system,” Applied Sciences, vol. 11, no. 4, p. 1733, 2021.
[11] J. Zhang, X. Yu, A. Li, P. Song, B. Liu, and Y. Dai, “Weaklysupervised salient object detection via scribble annotations,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 12 546–12 555.
[12] P. Siva, C. Russell, T. Xiang, and L. Agapito, “Looking beyond the image: Unsupervised learning for object saliency and detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2013, pp. 3238–3245.
[13] L. Wang, H. Lu, Y. Wang, M. Feng, D. Wang, B. Yin, and X. Ruan, “Learning to detect salient objects with imagelevel supervision,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 136–145.
[14] D.P. Fan, T. Li, Z. Lin, G.P. Ji, D. Zhang, M.M. Cheng, H. Fu, and J. Shen, “Rethinking cosalient object detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
[15] M. J. Islam, R. Wang, K. de Langis, and J. Sattar, “Svam: Saliencyguided visual attention modeling by autonomous underwater robots,” arXiv preprint arXiv:2011.06252, 2020.
[16] M. J. Islam, P. Luo, and J. Sattar, “Simultaneous enhancement and superresolution of underwater imagery for improved visual perception,” arXiv preprint arXiv:2002.01155, 2020.
[17] L. Zhang, B. He, Y. Song, and T. Yan, “Underwater image feature extraction and matching based on visual saliency detection,” in OCEANS 2016Shanghai. IEEE, 2016.
[18] A. MaldonadoRamírez and L. A. TorresMéndez, “Robotic visual tracking of relevant cues in underwater environments with poor visibility conditions,” Journal of Sensors, 2016.
[19] Microsoft azure cognitive services computer vision. Accessed on Nov. 2020.[Online]. Available: https://azure.microsoft.com/enus/services/cognitiveservices/computervision/
[20] R. Zhao, W. Ouyang, H. Li, and X. Wang, “Saliency detection by multicontext deep learning,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1265–1274.
[21] G. Li and Y. Yu, “Visual saliency based on multiscale deep features,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015.
[22] X. Li, L. Zhao, L. Wei, M.H. Yang, F. Wu, Y. Zhuang, H. Ling, and J. Wang, “Deep saliency: Multitask deep neural network model for salient object detection,” IEEE transactions on image processing, vol. 25, no. 8, pp. 3919–3930, 2016.
[23] L. Wang, L. Wang, H. Lu, P. Zhang, and X. Ruan, “Saliency detection with recurrent fully convolutional networks,” in European conference on computer vision. Springer, 2016, pp. 825–841.
[24] D. A. Klein and S. Frintrop, “Centersurround divergence of feature statistics for salient object detection,” in 2011 International Conference on Computer Vision IEEE, 2011.
[25] M.M. Cheng, N. J. Mitra, X. Huang, P. H. Torr, and S.M. Hu, “Global contrast based salient region detection,” IEEE transactions on pattern analysis and machine intelligence, 2014.
[26] Z. Wang, D. Xiang, S. Hou, and F. Wu, “Backgrounddriven salient object detection,” IEEE transactions on multimedia, 2016.
[27] Ç. Aytekin, H. Possegger, T. Mauthner, S. Kiranyaz, H. Bischof, and M. Gabbouj, “Spatiotemporal saliency estimation by spectral foreground detection,” IEEE Transactions on Multimedia, 2017.
[28] H. Peng, B. Li, W. Xiong, W. Hu, and R. Ji, “Rgbd salient object detection: a benchmark and algorithms,” in European conference on computer vision. Springer, 2014, pp. 92–109.
[29] J. Han, H. Chen, N. Liu, C. Yan, and X. Li, “Cnnsbased rgbd saliency detection via crossview transfer and multiview fusion,” IEEE transactions on cybernetics, vol. 48, no. 11, pp. 3171–3183, 2017.
[30] Y.T. Peng, X. Zhao, and P. C. Cosman, “Single underwater image enhancement using depth estimation based on blurriness,” in 2015 IEEE International Conference on Image Processing (ICIP). IEEE, 2015, pp. 4952–4956.
[31] D. V. Ruiz, B. A. Krinski, and E. Todt, “Anda: A novel data augmentation technique applied to salient object detection,” in 2019 19th International Conference on Advanced Robotics (ICAR). IEEE, 2019.
[32] Q. Hou, M.M. Cheng, X. Hu, A. Borji, Z. Tu, and P. H. Torr, “Deeply supervised salient object detection with short connections,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 3203–3212.
[33] G. Lee, Y.W. Tai, and J. Kim, “Deep saliency with encoded low level distance map and high level features,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 660–668.
[34] N. Liu and J. Han, “Dhsnet: Deep hierarchical saliency network for salient object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 678–686.
[35] J. Wei, S. Wang, and Q. Huang, “F3net: Fusion, feedback and focus for salient object detection,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2020.
[36] X. Qin, Z. Zhang, C. Huang, C. Gao, M. Dehghan, and M. Jagersand, “Basnet: Boundaryaware salient object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.
[37] X. Zhao, Y. Pang, L. Zhang, H. Lu, and L. Zhang, “Suppress and balance: A simple gated network for salient object detection,” in European Conference on Computer Vision. Springer, 2020, pp. 35–51.
[38] H. Zhou, X. Xie, J.H. Lai, Z. Chen, and L. Yang, “Interactive twostream decoder for accurate and fast saliency detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
[39] Z. Wu, L. Su, and Q. Huang, “Cascaded partial decoder for fast and accurate salient object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 3907–3916.
[40] X. Li, W. Wang, X. Hu, and J. Yang, “Selective kernel networks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 510–519.
[41] N. Liu, N. Zhang, and J. Han, “Learning selective selfmutual attention for rgbd saliency detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 13 756–13 765.
[42] B. Jiang, Z. Zhou, X. Wang, J. Tang, and B. Luo, “Cmsalgan: Rgbd salient object detection with crossview generative adversarial networks,” IEEE Transactions on Multimedia, vol. 23, pp. 1343–1353, 2020.
[43] J.X. Zhao, J.J. Liu, D.P. Fan, Y. Cao, J. Yang, and M.M. Cheng, “Egnet: Edge guidance network for salient object detection,” in Proc. Int’l Conf. Computer Vision, 2019.
[44] W. Wang, S. Zhao, J. Shen, S. C. Hoi, and A. Borji, “Salient object detection with pyramid attention and salient edges,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 1448–1457.
[45] H. Feng, X. Yin, L. Xu, G. Lv, Q. Li, and L. Wang, “Underwater salient object detection jointly using improved spectral residual and fuzzy cmeans,” Journal of Intelligent & Fuzzy Systems, vol. 37, no. 1, pp. 329–339, 2019.
[46] Z. Chen, H. Gao, Z. Zhang, H. Zhou, X. Wang, and Y. Tian, “Underwater salient object detection by combining 2d and 3d visual features,” Neurocomputing, vol. 391, pp. 249–259, 2020.
[47] B. Xu, H. Liang, R. Liang, and P. Chen, “Locate globally, segment locally: A progressive architecture with knowledge review network for salient object detection,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2021.
[48] M. Ma, C. Xia, and J. Li, “Pyramidal feature shrinking for salient object detection,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2021.
[49] X. Qin, Z. Zhang, C. Huang, M. Dehghan, O. R. Zaiane, and M. Jagersand, “U2net: Going deeper with nested ustructure for salient object detection,” Pattern Recognition, 2020.
[50] Z. Chen, Q. Xu, R. Cong, and Q. Huang, “Global contextaware progressive aggregation network for salient object detection,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2020.
[51] J. Wei, S. Wang, Z. Wu, C. Su, Q. Huang, and Q. Tian, “Label decoupling framework for salient object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
[52] S.H. Gao, Y.Q. Tan, M.M. Cheng, C. Lu, Y. Chen, and S. Yan, “Highly efficient salient object detection with 100k parameters,” in European Conference on Computer Vision. Springer, 2020.
[53] S. Mohammadi, M. Noori, A. Bahri, S. G. Majelan, and M. Havaei, “Cagnet: Contentaware guidance for salient object detection,” Pattern Recognition, 2020.
[54] M. Feng, H. Lu, and E. Ding, “Attentive feedback network for boundaryaware salient object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.
[55] J.J. Liu, Q. Hou, M.M. Cheng, J. Feng, and J. Jiang, “A simple poolingbased design for realtime salient object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.
[56] E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q. V. Le, “Autoaugment: Learning augmentation policies from data,” arXiv preprint arXiv:1805.09501, 2018.
[57] S. Lim, I. Kim, T. Kim, C. Kim, and S. Kim, “Fast autoaugment,” arXiv preprint arXiv:1905.00397, 2019.
[58] E. D. Cubuk, B. Zoph, J. Shlens, and Q. V. Le, “Randaugment: Practical automated data augmentation with a reduced search space,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.
[59] L. Perez and J. Wang, “The effectiveness of data augmentation in image classification using deep learning,” arXiv preprint arXiv:1712.04621, 2017.
[60] J. Lemley, S. Bazrafkan, and P. Corcoran, “Smart augmentation learning an optimal data augmentation strategy,” Ieee Access, 2017.
[61] M. FridAdar, I. Diamant, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, “Ganbased synthetic medical image augmentation for increased cnn performance in liver lesion classification,” Neurocomputing, 2018.
[62] G. Mariani, F. Scheidegger, R. Istrate, C. Bekas, and C. Malossi, “Bagan: Data augmentation with balancing gan,” arXiv preprint arXiv:1803.09655, 2018.
[63] Hawaii udersea research laboratory. Accessed on Jun. 2019. [Online]. Available: http://www.soest.hawaii.edu/HURL/galleries.php
[64] Bubble vision. Accessed on Jun. 2019. [Online]. Available: https://www.bubblevision.com/
[65] National geographic. Accessed on Jun. 2019. [Online]. Available: https:// nationalgeographic.com/
[66] A. Bréhéret, “Pixel annotation tool,” https://github.com/abreheret/PixelAnnotationTool, 2017.
[67] J. Shi, Q. Yan, L. Xu, and J. Jia, “Hierarchical image saliency detection on extended cssd,” IEEE transactions on pattern analysis and machine intelligence, 2015.
[68] C. Yang, L. Zhang, H. Lu, X. Ruan, and M.H. Yang, “Saliency detection via graphbased manifold ranking,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2013.
[69] Y. Li, X. Hou, C. Koch, J. M. Rehg, and A. L. Yuille, “The secrets of salient object segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014.
[70] L. Wang, H. Lu, Y. Wang, M. Feng, D. Wang, B. Yin, and X. Ruan, “Learning to detect salient objects with imagelevel supervision,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017.
[71] X. Xiao, Y. Zhou, and Y.J. Gong, “Rgb‘d’saliency detection with pseudo depth,” IEEE Transactions on Image Processing, vol. 28, no. 5, pp. 2126–2139, 2018.
[72] A. Galdran, D. Pardo, A. Picón, and A. AlvarezGila, “Automatic redchannel underwater image restoration,” Journal of Visual Communication and Image Representation, vol. 26, pp. 132–145, 2015.
[73] R. Achanta, S. Hemami, F. Estrada, and S. Susstrunk, “Frequencytuned salient region detection,” in Proc. Conf. Computer Vision and Pattern Recognition, 2009.
[74] R. Margolin, L. ZelnikManor, and A. Tal, “How to evaluate foreground maps?” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 248–255.
[75] F. Perazzi, P. Krähenbühl, Y. Pritch, and A. Hornung, “Saliency filters: Contrast based filtering for salient region detection,” in Proc. Conf. Computer Vision and Pattern Recognition, 2012.
[76] D. Fan, M. Cheng, Y. Liu, T. Li, and A. Borji, “Structuremeasure: A new way to evaluate foreground maps,” in Proc. Int’l Conf. Computer Vision, 2017.
[77] D.P. Fan, C. Gong, Y. Cao, B. Ren, M.M. Cheng, and A. Borji, “Enhancedalignment measure for binary foreground map evaluation,” arXiv preprint arXiv:1805.10421, 2018. |
| Description: | 碩士
國立政治大學
資訊科學系
108753209 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0108753209 |
| Data Type: | thesis |
| DOI: | 10.6814/NCCU202101682 |
| Appears in Collections: | [資訊科學系] 學位論文
|
Files in This Item:
| File |
Size | Format | |
|---|
| 320901.pdf | 4239Kb | Adobe PDF2 | 5 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
