在面向对象多光谱图像分割方法中,初始对象特征往往无法反映真实区域的整体特征,从而产生错误的合并结果。针对以上问题,提出采用简单线性迭代聚类(simple linear iterative clustering, SLIC)超像素与结构张量粗分割相结合的方法对其进行改进。先采用SLIC超像素方法产生初始过分割结果,用结构张量产生尺度空间下的粗分割结果,再用粗分割结果指导超像素进行初步合并,使分形网络演化方法(fractal net evolution approach,FNEA)所面向的初始对象能够表达该区域的整体特征,增强后续合并过程对噪声的抗性。将该方法与传统FNEA的分割结果对比表明,该方法具有良好的抗噪能力,对复杂城区高空间分辨率多光谱图像能够得到较好的分割结果。
In the object-oriented multispectral image segmentation, the initial object feature may not reflect the global feature of the whole region and can lead to an incorrect merge. To solve the problem, this paper proposes a method that combines the result of the simple linear iterative clustering(SLIC) super pixel and the rough segmentation result of structure tensor. First, the SLIC process is executed to get an over-segmentation result. Then, make sure the feature of the initial object of the fractal net evolution approach can reflect the real distribution of the whole region, and do the pre-merging between the super pixels under the control of the rough segmentation result of the structure tensor in the scale space. This process can enhance the anti-noise capability of the following merging process. Finally, the final results are given; compared with the results of the traditional fractal net evolution approach(FNEA), the result shows that the method proposed in the paper has better anti-noise capability, and can get better segmentation results even in handling the complex city multispectral images.
Ma Y N, Ming D P, Yang H P . Scale estimation of object-oriented image analysis based on spectral-spatial statistics[J]. Journal of Remote Sensing, 2017,21(4):566-578.
Huang L, Zuo X Q, Feng C , et al. Object-oriented image segmentation based on Canny algorithm[J]. Remote Sensing for Land and Resources, 2011,23(4):26-30.doi: 10.6046/gtzyyg.2011.04.05.
Jia C Y, Li W H, Li X C . High-resolution remote sensing image segmentation based on weight adaptive fractal net evolution approach[J]. Remote Sensing for Land and Resources, 2013,25(4):22-25.doi: 10.6046/gtzyyg.2013.04.04.
[4]
Peng P, Gao W, Liu X G, et al. An improved strategy for object-oriented multi-scale remote sensing imagesegmentation [C]//International Conference on Information Science and Engineering.IEEE, 2010: 1149-1152.
Deng F L, Fan X Y, Wang G , et al. A fast method for creation of the initial objects for FNEA image segmentation[J]. Journal of University of Chinese Academy of Sciences, 2014,31(4):484-491.
Dong Z P, Wang M, Li D R . A high resolution remote sensing image segmentation method by combining superpixels with minimum spanning tree[J]. Acta Geodaeticaet Cartographica Sinica, 2017,46(6):734-742.
[8]
Achanta R, Shaji A, Smith K , et al. SLIC superpixels[EB/OL].
[9]
Achanta R, Shaji A, Smith K , et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(11):2274-2282.
doi: 10.1109/TPAMI.2012.120
pmid: 22641706
[10]
Shi J B, Malik J . Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):888-905.
doi: 10.1109/34.868688
[11]
Veksler O, Boykov Y, Mehrani P. Superpixels and supervoxels in an energy optimization framework [C]//European Conference on Computer Vision, 2010: 211-224.
[12]
Levinshtein A, Stere A, Kutulakos K N , et al. TurboPixels:Fast superpixels using geometric flows[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31(12):2290-2297.
doi: 10.1109/TPAMI.2009.96
pmid: 19834148
[13]
Vedaldi A, Soatto S. Quick shift and kernel methods for mode seeking [C]//European Conference on Computer Vision. 2008: 705-718.
Min Y Z, Cheng T D, Yin C , et al. Texture image segmentation based on GLCM and self-adaptive Gabor filter bank[J]. Computer Engineering, 2017,43(1):280-286.
Cui Z H, Li H J, Li W N , et al. An improved FCM algorithm based on adaptive structure tensor[J]. Journal of Northeastern University (Natural Science), 2013,34(5):637-641.
Zhou S G, Chen C, Yue J P . Extracting roads from high-resolution rs image based on shape priors and GraphCuts[J]. Acta Geodaetica et Cartographica Sinica, 2014,43(1):60-65.
2019, Vol. 31 
