基于超像素和超度量轮廓图的无人机图像分割算法
|
摘要
为精确地分割高分辨率无人机航拍图像中的不同地物,提出一种基于超像素和超度量轮廓图的无人机图像分割算法.首先对图像进行线性谱聚类,生成超像素;然后根据HSV颜色空间的直方图特征计算超像素区域间的不相似度;再结合层次分割思想得到可表示边缘强度的超度量轮廓图并将其归一化;最后利用合适的阈值删除边缘强度低于该阈值的轮廓,并将所对应的区域进行合并得到分割后的图像.与ISODATA,FCM和gPb-OWT-UCM算法比较的实验结果表明,该算法图像分割准确率较高,对初始参数的依赖性小,且计算复杂度低.
An image segmentation algorithm based on superpixel and ultrametric contour map is proposed to accurately segment different images captured in the high-resolution unmanned aerial vehicle(UAV). Firstly, the image was segmented into superpixels by linear spectral clustering. Secondly, the dissimilarity between superpixels was calculated according to the histogram features in the Hue, Saturation and Value(HSV) color space. The ultrametric contour map which can represent the strength of the corresponding contour was obtained with the idea of hierarchical segmentation and then normalized. Finally, using the appropriate threshold value, the contours with lower weights than the threshold were deleted and the regions with higher similarity were merged to obtain the segmented result.Compared with segmentation algorithms including Iterative self-organizing data analysis algorithm(ISODATA), fuzzy c-means(FCM) and globalized probability of boundary, oriented watershed transform and ultrametric contour map(gPb-OWT-UCM), the experimental results show that the presented algorithm has higher accuracy and lower computational complexity and less dependence on the initialized values.
An image segmentation algorithm based on superpixel and ultrametric contour map is proposed to accurately segment different images captured in the high-resolution unmanned aerial vehicle(UAV). Firstly, the image was segmented into superpixels by linear spectral clustering. Secondly, the dissimilarity between superpixels was calculated according to the histogram features in the Hue, Saturation and Value(HSV) color space. The ultrametric contour map which can represent the strength of the corresponding contour was obtained with the idea of hierarchical segmentation and then normalized. Finally, using the appropriate threshold value, the contours with lower weights than the threshold were deleted and the regions with higher similarity were merged to obtain the segmented result.Compared with segmentation algorithms including Iterative self-organizing data analysis algorithm(ISODATA), fuzzy c-means(FCM) and globalized probability of boundary, oriented watershed transform and ultrametric contour map(gPb-OWT-UCM), the experimental results show that the presented algorithm has higher accuracy and lower computational complexity and less dependence on the initialized values.
引文
[1] Pajares G. Overview and current status of remote sensing applications based on unmanned aerial vehicles(UAVs)[J].Photogrammetric Engineering&Remote Sensing, 2015,81(4):281-329
[2] Li Y. Vehicle extraction using histogram and genetic algorithm based fuzzy image segmentation from high resolution UAV aerial imagery[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2008, XXXVII(B3b):529-534
[3] Ma C H, Dai Q, Liu S B. A hybrid PSO-ISODATA algorithm for remote sensing image segmentation[C]//Proceedings of International Conference on Industrial Control and Electronics Engineering. Los Alamitos:IEEE Computer Society Press, 2012:1371-1375
[4] Huang C L, Chen J J, Chen C J, et al. Geological segmentation on UAV aerial image using shape-based LSM with dominant color[C]//Proceedings of the 30th International Conference on Advanced Information Networking and Applications Workshops. Los Alamitos:IEEE Computer Society Press, 2016:928-933
[5] Zhong T Y, Liu W P, Luo Y Q, et al. A new type-2 fuzzy algorithm for unmanned aerial vehicle image segmentation[J].International Journal of Multimedia and Ubiquitous Engineering, 2017, 12(5):75-90
[6] Subudhi B N, Patwa I, Ghosh A, et al. Edge preserving region growing for aerial color image segmentation[C]//Proceedings of Intelligent Computing, Communication and Devices. Heidelberg:Springer, 2015:481-488
[7] Chen Z Y, Wang C, Wen C L, et al. Vehicle detection in high-resolution aerial images via sparse representation and superpixels[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(1):103-116
[8] Li H G, Shi Y, Zhang B C, et al. Superpixel-based feature for aerial image scene recognition[J]. Sensors, 2018, 18(1):156
[9] Chen J S, Li Z Q, Huang B. Linear spectral clustering superpixel[J]. IEEE Transactions on Image Processing, 2017,26(7):3317-3330
[10] Arbelaez P. Boundary extraction in natural images using ultrametric contour maps[C]//Proceedings of the Conference on Computer Vision and Pattern Recognition Workshop. Los Alamitos:IEEE Computer Society Press, 2006:182
[11] Arbelaez P, Maire M, Fowlkes C, et al. Contour detection and hierarchical image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5):898-916.
[12] Gajic L. On ultrametric space[J]. Novi Sad Journal of Mathematics, 2001, 31(2):69-71
[13] Memarsadeghi N, Mount D M, Netanyahu N S, et al. A fast implementation of the ISODATA clustering algorithm[J].International Journal of Computational Geometry&Applications, 2007, 17(1):71-103
[14] Cai W L, Chen S C, Zhang D Q. Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation[J]. Pattern Recognition,2007, 40(3):825-838
[15] Cui Tianyi, Liu Wenping, Zhang Ning. Algorithms and performance comparison of automatic thresholding segmentation for forest regions in remote sensing image[J].Journal of Computer Applications, 2010, 30(12):3269-3273(in Chinese)(崔天意,刘文萍,张宁.遥感图像林区自动阈值分割算法及性能比较[J].计算机应用, 2010, 30(12):3269-3273)
[16] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos:IEEE Computer Society Press, 2015:3431-3440
[17] Zhang Yujin. A classification and comparison of evaluation techniques for image segmentation[J]. China Journal of Image and Graphics, 1996,1(2):151-158(in Chinese)(章毓晋.图象分割评价技术分类和比较[J].中国图象图形学报, 1996, 1(2):151-158)
[2] Li Y. Vehicle extraction using histogram and genetic algorithm based fuzzy image segmentation from high resolution UAV aerial imagery[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2008, XXXVII(B3b):529-534
[3] Ma C H, Dai Q, Liu S B. A hybrid PSO-ISODATA algorithm for remote sensing image segmentation[C]//Proceedings of International Conference on Industrial Control and Electronics Engineering. Los Alamitos:IEEE Computer Society Press, 2012:1371-1375
[4] Huang C L, Chen J J, Chen C J, et al. Geological segmentation on UAV aerial image using shape-based LSM with dominant color[C]//Proceedings of the 30th International Conference on Advanced Information Networking and Applications Workshops. Los Alamitos:IEEE Computer Society Press, 2016:928-933
[5] Zhong T Y, Liu W P, Luo Y Q, et al. A new type-2 fuzzy algorithm for unmanned aerial vehicle image segmentation[J].International Journal of Multimedia and Ubiquitous Engineering, 2017, 12(5):75-90
[6] Subudhi B N, Patwa I, Ghosh A, et al. Edge preserving region growing for aerial color image segmentation[C]//Proceedings of Intelligent Computing, Communication and Devices. Heidelberg:Springer, 2015:481-488
[7] Chen Z Y, Wang C, Wen C L, et al. Vehicle detection in high-resolution aerial images via sparse representation and superpixels[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(1):103-116
[8] Li H G, Shi Y, Zhang B C, et al. Superpixel-based feature for aerial image scene recognition[J]. Sensors, 2018, 18(1):156
[9] Chen J S, Li Z Q, Huang B. Linear spectral clustering superpixel[J]. IEEE Transactions on Image Processing, 2017,26(7):3317-3330
[10] Arbelaez P. Boundary extraction in natural images using ultrametric contour maps[C]//Proceedings of the Conference on Computer Vision and Pattern Recognition Workshop. Los Alamitos:IEEE Computer Society Press, 2006:182
[11] Arbelaez P, Maire M, Fowlkes C, et al. Contour detection and hierarchical image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5):898-916.
[12] Gajic L. On ultrametric space[J]. Novi Sad Journal of Mathematics, 2001, 31(2):69-71
[13] Memarsadeghi N, Mount D M, Netanyahu N S, et al. A fast implementation of the ISODATA clustering algorithm[J].International Journal of Computational Geometry&Applications, 2007, 17(1):71-103
[14] Cai W L, Chen S C, Zhang D Q. Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation[J]. Pattern Recognition,2007, 40(3):825-838
[15] Cui Tianyi, Liu Wenping, Zhang Ning. Algorithms and performance comparison of automatic thresholding segmentation for forest regions in remote sensing image[J].Journal of Computer Applications, 2010, 30(12):3269-3273(in Chinese)(崔天意,刘文萍,张宁.遥感图像林区自动阈值分割算法及性能比较[J].计算机应用, 2010, 30(12):3269-3273)
[16] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos:IEEE Computer Society Press, 2015:3431-3440
[17] Zhang Yujin. A classification and comparison of evaluation techniques for image segmentation[J]. China Journal of Image and Graphics, 1996,1(2):151-158(in Chinese)(章毓晋.图象分割评价技术分类和比较[J].中国图象图形学报, 1996, 1(2):151-158)