一种面向复杂场景的图像边缘检测方法
An Image Edge Detection Method for Complicated Scenes
DOI: 10.12677/CSA.2021.1111263, PDF,    科研立项经费支持
作者: 李金中, 汪 玉：国网安徽省电力有限公司电力科学研究院，安徽 合肥；左宇晨, 王子磊：中国科学技术大学，安徽 合肥
关键词: 多任务学习；语义分割；边缘检测；计算机视觉；Muti-Task Learning； Semantic Segmentation； Edge Detection； Computer Vision
摘要: 针对较为复杂的光伏电站场景中的图像中光伏板边缘提取问题，本文提出了一种精细检测方法。所提出的方法首先引入多尺度的图像特征，通过鼓励网络不同层输出的特征表示检测对应该层尺度的图像边缘，进而充分融合不同尺度特征中所包含的丰富信息，使得对于不同尺度物体边缘的检测都能够更加精细；其次，本方法利用多任务学习结构，通过挖掘语义分割和边缘检测两个任务之间的相关性与互补性，使得图像特征更加聚焦于待提取边缘的物体，排除场景中无关物体或噪声的干扰，从而生成更加合理的图像边缘。量化的实验结果与可视化结果均表明，本方法能够获得更加精准的图像边缘检测效果。
Abstract: Aimed at edge extraction of photovoltaic panels in the complicated photovoltaic power stations, this paper puts forward a precise detection method. For the proposed method, first, multi-dimensional image features are introduced. The feature representations from different layers of network detect image edge correspond to the dimension of this layer. The plenty of information in different dimension features is fully integrated to make the edge detection of object with different dimensions be more precise. Second, this method makes use of multi-task learning structure and digs out the correlation and complementarity between semantic segmentation and edge detection to make low-level features of image more concentrate on the object edge to be extracted and eliminate the interference of irrelevant objects or noise in the scene, thereby generating a more ideal image edge. Both quantitative experimental result and visualization result show that this method can acquire more precise image edge detection effect.
文章引用：李金中, 左宇晨, 汪玉, 王子磊. 一种面向复杂场景的图像边缘检测方法[J]. 计算机科学与应用, 2021, 11(11): 2599-2608. https://doi.org/10.12677/CSA.2021.1111263

参考文献

[1] 陶洪久, 柳健, 田金文. 基于小波变换和数学形态学的遥感图像边缘检测[J]. 红外与激光工程, 2002, 31(2): 154-157.
[2] 王鸿娟. 边缘检测在医学图像处理中的应用研究[J]. 自动化与仪器仪表, 2017(5): 140-141.
[3] 赖思渝, 王宇峰, 王娟. 一种基于边缘检测的医学图像增强方法[J]. 电脑与信息技术, 2013(2): 17-20.
[4] 霍桂利. 基于智能控制算法的自动驾驶系统优化研究[J]. 现代电子技术, 2019, 42(20): 177-180.
[5] 俞涛. 基于深度学习的图像语义分割在自动驾驶中的应用[D]: [硕士学位论文]. 武汉: 华中科技大学, 2018.
[6] Canny, J.F. (1987) A Computational Approach to Edge Detection. In: Readings in Computer Vision, Elsevier, Amsterdam, 184-203. [Google Scholar] [CrossRef] 
[7] Taira, R.K., Iglesias, J.E. and Jahanshad, N. (2010) Characterizing Imaging Data. Springer US, Berlin. [Google Scholar] [CrossRef] 
[8] Xie, S. and Tu, Z. (2015) Holistically-Nested Edge Detection. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1395-1403. [Google Scholar] [CrossRef] 
[9] He, J., Zhang, S., Yang, M., et al. (2020) Bi-Directional Cascade Network for Perceptual Edge Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 3823-3832. [Google Scholar] [CrossRef] 
[10] Hu, Z., Zhen, M., Bai, X., et al. (2020) JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds. European Conference on Computer Vision, Heraklion, 5-11 September 2020, 222-239. [Google Scholar] [CrossRef] 
[11] Liu, S., Johns, E. and Davison, A.J. (2018) End-to-End Mul-ti-Task Learning with Attention. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 1871-1880. [Google Scholar] [CrossRef] 
[12] Misra, I., Shrivastava, A., Gupta, A., et al. (2016) Cross-Stitch Networks for Multi-Task Learning. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 3994-4003. [Google Scholar] [CrossRef] 
[13] Liu, Y., et al. (2018) Richer Convolutional Features for Edge Detec-tion. IEEE Transactions on Pattern Analysis & Machine Intelligence, 41, 1939-1946.
[14] Soria, X., Riba, E. and Sappa, A. (2020) Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection. 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), Snowmass, 1-5 March 2020, 1923-1932. [Google Scholar] [CrossRef] 
[15] Yu, Z., Feng, C., Liu, M.Y., et al. (2017) CASENet: Deep Category-Aware Semantic Edge Detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 5964-5973. [Google Scholar] [CrossRef] 
[16] Simonyan, K. and Zisserman, A. (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition.
[17] Chen, L.C., Papandreou, G., Schroff, F., et al. (2017) Rethinking Atrous Convolution for Semantic Image Segmentation.