模拟飞虫复眼视觉的小目标运动检测与跟踪系统研究
Research on Moving Small Target Detection and Tracking System of Simulated Flying Insect Compound Eye Vision
DOI: 10.12677/JISP.2022.113011, PDF,  被引量    科研立项经费支持
作者: 李 柯:南昌理工学院机电工程学院,江西 南昌;沈克永:南昌理工学院计算机信息工程学院,江西 南昌;刘 宝:江西省军工控股集团有限公司,江西 南昌;曹 阳:航空工业洪都集团660研究所,江西 南昌;邱晓健, 陈俊宇:南昌航天广信科技有限责任公司,江西 南昌
关键词: 小目标运动检测杂乱背景昆虫视神经系统神经建模Small Target Motion Detection Cluttered Backgrounds Insect Optic Nervous System Neural Modeling
摘要: 如何准确可靠地辨别嵌入在杂乱移动背景中暗色小物体(小目标)的运动,对于计算机视觉研究领域来说是一个巨大的挑战。自然界中,苍蝇、蜻蜓等一类飞行昆虫在快速飞行过程中准确追踪目标,完成捕食、求偶等却是一种自然特性,受飞虫复眼高适应性和高可靠性地辨别小目标运动的功能优势的启发,本文基于诸如视叶神经纤维网中ON和OFF信号通道、小叶中一类特定小目标运动检测器(STMD)神经元LC11对运动做出精细地选择性响应等昆虫生理学研究的新发现,通过模拟复眼运动视觉信号通路及处理机制,提出一种杂乱移动背景下暗色小目标运动检测与跟踪系统(简称SDC-STMD系统)和相应的算法,实现对杂乱移动背景中小目标运动的解码。多组实验测试表明,所提出的SDC-STMD系统和算法不仅符合当前的昆虫生理学发现,表现了对小目标的运动响应偏好,而且对于在杂乱移动背景下暗色小目标运动检测和跟踪也表现了较高的鲁棒性。
Abstract: It is a huge challenge to accurately and reliably distinguish the movement of darker small objects (i.e., small targets) embedded in cluttered moving backgrounds for computer vision research. In nature, flies, dragonflies and other types of flying insects accurately track targets during fast flight and it is a natural characteristic to complete predation and courtship. Inspired by the advantages of the function of flying insects’ compound eyes to distinguish the movement of small targets with high adaptability and high reliability, this article was based on the new findings of insect physiology, that is, based on the new research findings of the ON and OFF signaling channels in the optic lobe neuropile layers, and a specific type of small target motion detector neurons LC11 in the lobules that make exquisite and selective responses to the movement of small targets, et al. By simulating compound eye’s motion visual signal pathways and processing mechanism, a darker small target motion detection and tracking system (for short SDC-STMD system) and the corresponding algorithm was proposed to decode the motion of translating darker target against cluttered moving backgrounds. Extensive experiment tests showed that the proposed SDC-STMD system and algorithm were not only in accord with current insect physiology findings, i.e., showing its size and motion responsive preferences, but also worked high reliably in detecting the darker small targets against cluttered moving backgrounds.
文章引用:李柯, 沈克永, 刘宝, 曹阳, 邱晓健, 陈俊宇. 模拟飞虫复眼视觉的小目标运动检测与跟踪系统研究[J]. 图像与信号处理, 2022, 11(3): 92-100. https://doi.org/10.12677/JISP.2022.113011

参考文献

[1] Serres, J.R. and Ruffier, F. (2017) Optic Flow-Based Collision-Free Strategies: From Insects to Robots. Arthropod Structure & Development, 46, 703-717.
[Google Scholar] [CrossRef] [PubMed]
[2] Fu, Q.B. and Yue, S.G. (2020) Modelling Drosophila Motion Vision Pathways for Decoding the Direction of Translating Objects against Cluttered Moving Backgrounds. Biological Cybernetics, 114, 443-460.
[Google Scholar] [CrossRef] [PubMed]
[3] Cheng, Y., Cao, J., Zhang, Y.K. and Hao, Q. (2019) Review of State-of-the-Art Artificial Compound Eye Imaging Systems. Bioinspiration & Biomimetics, 14, Article ID: 031002.
[Google Scholar] [CrossRef] [PubMed]
[4] Xu, M.X., Wu, X.B., Zhang, Z. and Lu, Y.Y. (2021) Compound-Eye Imaging Imitation-Based Whole-Field Flow Measurement. Computers and Electrical Engineering, 92, Article ID: 107141.
[Google Scholar] [CrossRef
[5] 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.
[6] 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.
[Google Scholar] [CrossRef] [PubMed]
[7] Fu, Q.B., Wang, H.X., Hu, C. and Yue, S.G. (2019) Towards Computational Models and Applications of Insect Visual Systems for Motion Perception: A Review. Artificial Life, 25, 263-311.
[Google Scholar] [CrossRef] [PubMed]
[8] Hassenstein, B. and Reichardt, W. (1956) Systemtheoretische Analyse der Zeit-, Reihenfolgen- und Vorzeichenauswertung bei der Bewegungsperzeption des Rüsselkäfers Chlorophanus. Zeitschrift für Naturforschung B, 11, 513-524.
[Google Scholar] [CrossRef
[9] 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.
[Google Scholar] [CrossRef] [PubMed]
[10] 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.
[Google Scholar] [CrossRef] [PubMed]
[11] Joesch, M., Schnell, B., Raghu, S.V., Reiff, D.F. and Borst, A. (2010) ON and OFF Pathways in Drosophila Motion Vision. Nature, 468, 300-304.
[Google Scholar] [CrossRef] [PubMed]
[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.
[Google Scholar] [CrossRef] [PubMed]
[13] Keles, M.F. and Frye, M.A. (2017) Object-Detecting Neurons in Drosophila. Current Biology, 27, 680-687.
[Google Scholar] [CrossRef] [PubMed]
[14] Mehmet, F.K., Ben, J.H. and Carola, S. (2020) Inhibitory Interactions and Columnar Inputs to an Object Motion Detector in Drosophila. Cell Reports, 30, 2115-2124.E5.
[Google Scholar] [CrossRef] [PubMed]
[15] 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.
[Google Scholar] [CrossRef] [PubMed]
[16] Eichner, H., Joesch, M., Schnell, B., Reiff, D.F. and Borst, A. (2011) Internal Structure of the Fly Elementary Motion Detector. Neuron, 70, 1155-1164.
[Google Scholar] [CrossRef] [PubMed]
[17] Clark, D.A., Bursztyn, L., Horowitz, M.A., Schnitzer, M.J. and Clandinin, T.R. (2011) Defining the Computational Structure of the Motion Detector in Drosophila. Neuron, 70, 1165-1177.
[Google Scholar] [CrossRef] [PubMed]
[18] 施建强, 徐扬, 徐梦溪, 郑胜男. 一种用于感知目标运动方向的人工苍蝇视觉神经网络模型[C]//中国仪器仪表学会. 2021论文集(上册)中国仪器仪表学会学术年会. 上海: 中国仪器仪表学会, 2021: 1-2.
[19] Shen, K.Y., Yang, Y., Liang, Y.Y. and Xu, L.Z. (2021) Modeling Drosophila Vision Neural Pathways to Detect Weak Moving Targets from Cluttered Backgrounds. Computers and Electrical Engineering, 99, Article ID: 107678.
[Google Scholar] [CrossRef
[20] 徐立中, 陈俊宇, 沈克永, 杨扬, 梁玉英. 一种基于STMD的人工复眼视神经计算模型[C]//中国仪器仪表学会. 2021论文集(上册)中国仪器仪表学会学术年会. 上海: 中国仪器仪表学会, 2021: 148-149.
[21] Nordström, K., Barnett, P.D. and O’Carroll, D.C. (2006) Insect Detection of Small Targets Moving in Visual Clutter Art. PLOS Biology, 4, e54.
[Google Scholar] [CrossRef] [PubMed]