|
|
受生物视觉“图形–背景”分辨机制启发的遥感影像水体信息提取方法
|
Abstract:
蝇类昆虫–果蝇复眼视觉系统的高适应性和高可靠性是一种自然特性，对于视觉杂乱场景中感兴趣目标/区域(统称“图形”)的分辨和飞行追踪过程，在本质上却是良态和适定的。本文针对遥感影像水体信息提取所涉及的图像分割和“图形–背景(figure-backgrounds, FB)”分辨这一逆问题求解存在的病态的(不适定的)本质性困难，基于昆虫生理学研究的新发现，分析果蝇复眼视觉信息加工的神经过程，模拟其无需背景建模、先验信息以及不依赖于样本数据训练隐式模型，所具有的视觉杂乱背景且噪声干扰下“图形–背景”分辨的功能优势，提出一种仿蝇视觉“图形–背景”分辨的遥感影像水体提取方法，通过多组仿真实验，并与标准的归一化差异水体指数NDWI、改进的NDWI (MNDWI)、决策树模型以及SVM分类等方法做了分析对比，验证了新方法的优越性。
The high adaptability and reliability of the compound visual system of flies and drosophila is a natural characteristic, and the identification and flight tracking process of the target/region of interest (general called “graphics”) in the visual clutter scene is essentially well-conditioned and well-adapted. This paper focuses on the ill-posed (not well-posed) inherent difficulties of image segmentation and inverse problem of “figure-backgrounds (FB)” resolution in water extraction from remote sensing images. Based on the new findings of insect physiology, the neural processing of compound visual information in drosophila is analyzed, and the implicit model is trained by simulating modeling without background and prior information, or relying on the sample data, which has the advantages of visual clutter and “figure-backgrounds” resolution under noise interference. A method of water extraction from remote sensing image based on simulating fly’s vision “figure-backgrounds” resolution is proposed. Compared with the standard normalized differential water body index (NDWI), improved NDWI (MNDWI), decision tree model and SVM classification method, the superiority of the new method is verified.
| [1] | 王航, 秦奋. 遥感影像水体提取研究综述[J]. 测绘科学, 2018, 43(5): 23-32. |
| [2] | 李丹, 吴保生, 陈博伟, 薛源, 张翼. 基于卫星遥感的水体信息提取研究进展与展望[J]. 清华大学学报(自然科学版), 2020, 60(2): 147-161. |
| [3] | Paul, A., Tripathi, D. and Dutta, D. (2018) Application and Comparison of Advanced Supervised Classifiers in Extraction of Water Bodies from Remote Sensing Images. Sustainable Water Resources Management, 4, 905-919.
https://doi.org/10.1007/s40899-017-0184-6 |
| [4] | Crasto, N., Hopkinson, C., Forbes, D.L., Lesack, L., Marsh, P., Spooner, I. and van der Sanden, J.J. (2015) ALiDAR-Based Decision-Tree Classification of Open Water Surfaces in an Arctic Delta. Remote Sensing of Environment, 164, 90-102. https://doi.org/10.1016/j.rse.2015.04.011 |
| [5] | 陈前, 郑利娟, 李小娟, 徐崇斌, 吴俣, 谢东海, 刘亮. 基于深度学习的高分遥感影像水体提取模型研究[J]. 地理与地理信息科学, 2019, 35(4): 43-48. |
| [6] | 饶萍, 王建力. 基于中分辨率遥感影像的水体信息精确提取[J]. 贵州大学学报(自然科学版), 2016, 33(5): 17-24. |
| [7] | Paulk, A., Millard, S.S. and van Swinderen, B. (2013) Vision in Drosophila: Seeing the World through a Model’s Eyes. Annual Review of Entomology, 58, 313-332. https://doi.org/10.1146/annurev-ento-120811-153715 |
| [8] | 郭爱克, 彭岳清, 张柯, 奚望. 小虫春秋: 果蝇的视觉学习记忆与认知[J]. 自然杂志, 2009, 31(2): 63-68, 封2. |
| [9] | Neriec, N. and Desplan, C. (2016) From the Eye to the Brain: Development of the Drosophila Visual System. Current Topics in Developmental Biology, 116, 247-271. https://doi.org/10.1016/bs.ctdb.2015.11.032 |
| [10] | Behnia, R. and Desplan, C. (2015) Visual Circuits in Flies: Beginning to See the Whole Picture. Current Opinion in Neurobiology, 34, 125-132. https://doi.org/10.1016/j.conb.2015.03.010 |
| [11] | Takemura, S., Bharioke, A., Lu, Z., Nern, A., Vitaladevuni, S., Rivlin, P.K., Katz, W.T., Olbris, D.J., Plaza, S.M., Winston, P., Zhao, T., Horne, J.A., Fetter, R.D., Takemura, S., Blazek, K., Chang, L., Ogundeyi, O., Saunders, M.A., Shapiro, V., Sigmund, C., Rubin, G.M., Scheffer, L.K., Meinertzhagen, I.A. and Chklovskii, D.B. (2013) A Visual Motion Detection Circuit Suggested by Drosophila Connectomics. Nature, 500, 175-181.
https://doi.org/10.1038/nature12450 |
| [12] | Behnia, R., Clark, D.A., Carter, A.G., Clandinin, T.R. and Desplan, C. (2014) Processing Properties of ON and OFF Pathways for Drosophila Motion Detection. Nature, 512, 427-430. https://doi.org/10.1038/nature13427 |
| [13] | Haag, J., Arenz, A., Serbe, E., Gabbiani, F. and Borst, A. (2016) Complementary Mechanisms Create Direction Selectivity in the Fly. eLIFE, 5, 1-15. https://doi.org/10.7554/eLife.17421 |
| [14] | Keles, M.F. and Frye, M.A. (2017) Object-Detecting Neurons in Drosophila. Current Biology, 27, 680-687.
https://doi.org/10.1016/j.cub.2017.01.012 |
| [15] | Egelhaaf, M. (1985) On the Neuronal Basis of Figure-Ground Discrimination by Relative Motion in the Visual System of the Fly. Biological Cybernetics, 52, 267-280. https://doi.org/10.1007/BF00336983 |
| [16] | Wang, H., Peng, J. and Yue, S. (2020) A Directionally Selective Small Target Motion Detecting Visual Neural Network in Cluttered Backgrounds. IEEE Transactions on Cybernetics, 50, 1541-1555.
https://doi.org/10.1109/TCYB.2018.2869384 |
| [17] | 徐梦溪, 施建强. 仿生复眼型多源监测数据融合与专题信息提取[J]. 水利信息化, 2021(1): 71-75. |
| [18] | Borst, A., Haag, J. and Mauss, A.S. (2020) How Fly Neurons Compute the Direction of Visual Motion. Journal of Comparative Physiology A, 206, 109-124. https://doi.org/10.1007/s00359-019-01375-9 |
| [19] | Missler, J.M. and Kamangar, F.A. (1995) A Neural Network for Pursuit Tracking Inspired by the Fly Visual System. Neural Networks, 8, 463-480. https://doi.org/10.1016/0893-6080(94)00105-U |
| [20] | 黄凤辰, 李敏, 石爱业, 汤敏, 徐立中. 受昆虫视觉启发的多光谱遥感影像小目标检测[J]. 通信学报, 2011, 32(9): 88-95. |
| [21] | 徐扬. 基于蝇视觉机制的信息特征提取方法研究[D]: [硕士学位论文]. 南京: 河海大学, 2021. |
| [22] | Wiederman, S.D., Shoemaker, P.A. and O’Carroll, D.C. (2008) A Model for the Detection of Moving Targets in Visual Clutter Inspired by Insect Physiology. PLoS ONE, 3, e2784. https://doi.org/10.1371/journal.pone.0002784 |
| [23] | Watt, R.J. and Phillips, W.A. (2000) The Function of Dynamic Grouping Invision. Trends in Cognitive Sciences, 4, 447-454. https://doi.org/10.1016/S1364-6613(00)01553-9 |
| [24] | 凌静, 徐立中, 石爱业, 黄凤辰, 汤敏. 一种基于Choquet模糊积分小波系数选择的遥感图像融合方法[J]. 遥感学报, 2009, 13(2): 263-268. |
