基于HSV-Edgeboxes航拍图像玻璃绝缘子候选区域定位
Locating Glass Insulator Region Proposals of Aerial Images Based on HSV-EdgeBoxes
DOI: 10.12677/CSA.2019.911233, PDF,    国家科技经费支持
作者: 栾 乐*, 罗思敏：广州供电局电力试验研究院，广东 广州
关键词: EdgeBoxes；HSV；候选区域；绝缘子检测；EdgeBoxes； HSV； Region Proposals； Insulator Detection
摘要: 本文提出了HSV-EdgeBoxes可以用于定位航拍图像中玻璃绝缘子的位置。首先将航拍图像由RGB空间转化为HSV空间，根据每个窗口感兴趣颜色区域的面积，计算每个窗口的颜色得分。然后采用结构化的边缘检测和非最大值抑制算法，生成航拍图像的边缘图像。通过统计每个窗口总共包含的边缘数，计算每个窗口的边缘得分。最后，结合颜色得分和边缘得分获得每个窗口的最后得分，选择包含得分高的窗口作为候选区域。实验结果证明了该算法的有效性。
Abstract: HSV-EdgeBoxes is proposed in this paper to locate the glass insulators of aerial images. First, the aerial image is converted to the HSV pace from the RGB space, and the color score of a window is assessed by the area of region of color interest in the box. Then, the edge response map of the aerial image is computed using Structured Edge detector and Non-Maximal Suppression. The edge score of a box is computed by measuring the number of contours that are totally contained. The final score of a box is calculated by color score and edge score jointly. The windows with higher scores are chosen as insulator proposals. The experimental results verify the effectiveness of the proposed method.
文章引用：栾乐, 罗思敏. 基于HSV-Edgeboxes航拍图像玻璃绝缘子候选区域定位[J]. 计算机科学与应用, 2019, 9(11): 2077-2083. https://doi.org/10.12677/CSA.2019.911233

参考文献

[1] 林聚财, 韩军, 陈舫明, 等. 基于彩色图像的玻璃绝缘子缺陷诊断[J]. 电网技术, 2011(1): 127-133.
[2] 张达, 金立军, 胡娟, 等. 基于图像信息融合的绝缘子污秽状态识别[J]. 系统仿真学报, 2013, 25(9): 244-249+257.
[3] 赵振兵, 崔雅萍, 戚银城, 等. 基于改进的R-FCN航拍巡线图像中的绝缘子检测方法[J]. 计算机科学, 2019, 46(3): 165-169.
[4] 杨蔚, 李陈, 杨生兰, 等. 航拍宽幅图像的玻璃绝缘子定位研究[J]. 电子测试, 2016(15): 23-26.
[5] 虢韬, 杨恒, 时磊, 等. 基于Faster RCNN的绝缘子自爆缺陷识别[J]. 电瓷避雷器, 2019(3): 183-189.
[6] Hosang, J., Benenson, R., Dollár, P., et al. (2015) What Makes for Effective Detection Proposals? IEEE Transactions on Pattern Analysis & Machine Intelligence, 38, 814. [Google Scholar] [CrossRef] 
[7] Li, Y., Lu, H., Zhang, L., et al. (2012) An Automatic Image Segmentation Algorithm Based on Weighting Fuzzy C-Means Clustering. In: Luo, J., Ed., Soft Computing in Information Communication Technology, Springer, Berlin, 27-32. [Google Scholar] [CrossRef] 
[8] Felzenszwalb, P.F. and Huttenlocher, D.P. (2004) Efficient Graph-Based Image Segmentation. International Journal of Computer Vision, 59, 167-181. [Google Scholar] [CrossRef] 
[9] Arbelaez, P., Maire, M., Fowlkes, C., et al. (2011) Contour Detection and Hierarchical Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelli-gence, 33, 898-916. [Google Scholar] [CrossRef] 
[10] 王春哲, 安军社, 姜秀杰, 等. 基于颜色距离与Edge Boxes候选区域算法[J]. 液晶与显示, 2019, 34(7): 698-707.
[11] Uijlings, J.R.R., van de Sande, K.E.A., et al. (2013) Selective Search for Object Recognition. International Journal of Computer Vision, 104, 154-171. [Google Scholar] [CrossRef] 
[12] Pont-Tuset, J., Arbelaez, P., Barron, J., et al. (2016) Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation. IEEE Transactions on Pattern Analy-sis and Machine Intelligence, 39, 128-140. [Google Scholar] [CrossRef] 
[13] Humayun, A., Li, F. and Rehg, J.M. (2014) RIGOR: Reusing Inference in Graph Cuts for Generating Object Regions. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 336-343. [Google Scholar] [CrossRef] 
[14] Zitnick, C.L. and Dollár, P. (2014) Edge Boxes: Locating Object Pro-posals from Edges. European Conference on Computer Vision, Zurich, 6-12 September 2014, 391-405. [Google Scholar] [CrossRef] 
[15] Dollár, P. and Zitnick, C.L. (2014) Fast Edge Detection Using Structured Forests. IEEE Transactions on Pattern Analysis & Machine Intelligence, 37, 1558-1570. [Google Scholar] [CrossRef]