[1]徐梦溪,施建强,郑胜男,等.模拟复眼视叶神经网的目标运动方向检测模型[J].智能系统学报,2024,19(3):546-555.[doi:10.11992/tis.202203044]
XU Mengxi,SHI Jianqiang,ZHENG Shengnan,et al.Detection model of target motion direction simulating the optic lobe neural network of compound eyes[J].CAAI Transactions on Intelligent Systems,2024,19(3):546-555.[doi:10.11992/tis.202203044]
点击复制
XU Mengxi,SHI Jianqiang,ZHENG Shengnan,et al.Detection model of target motion direction simulating the optic lobe neural network of compound eyes[J].CAAI Transactions on Intelligent Systems,2024,19(3):546-555.[doi:10.11992/tis.202203044]
模拟复眼视叶神经网的目标运动方向检测模型
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第3期
页码:
546-555
栏目:
学术论文—机器学习
出版日期:
2024-05-05
- Title:
- Detection model of target motion direction simulating the optic lobe neural network of compound eyes
- Keywords:
- video; target detection; detection of motion detection; insect’s compound eye; neurocomputing; artificial neural network; multilevel model; optic lobe neural network
- 分类号:
- TP391
- 文献标志码:
- 2023-10-25
- 摘要:
- 如何对杂乱背景中物体（目标）的运动方向做出准确可靠的检测与感知，是计算机视觉研究领域中一个重要问题。自然界中，飞虫（如苍蝇、蜻蜓等）高适应性和高可靠性的感知目标运动是一种自然特性，本文基于飞虫-果蝇视叶神经纤维网最新的生理学研究成果，提出一种基于果蝇视觉感知目标运动方向的多层级检测模型系统。通过对不同场景下拍摄的视频序列样本进行实验和测试，并与2-Q运动检测器模型、基于ON和OFF信号通道处理运动信息的检测模型等进行了对比，验证了其在杂乱背景下对于目标水平和垂直方向运动检测的有效性和鲁棒性。
- Abstract:
- How to detect and perceive the motion direction of objects (targets) in a chaotic background accurately and reliably is an important research area in the field of computer vision. In nature, flying insects (such as flies and dragonflies) can sense the movements of their target with high adaptability and reliability . Based on the latest research results of the physiology of the optic lobe neuropile layer of the flying insect drosophila, a multilevel model system for detecting target motion direction based on visual perception of drosophila is proposed. By shooting the video sequence of samples under different scenarios for experiment and test and comparing with the 2-Q motion detector model based on ON and OFF signal channel processing motion information, the effectiveness and robustness of the proposed system for horizontal and vertical motion detection of video targets under a chaotic background are confirmed.
- 参考文献/References:
-
[1] 郭爱克. 探索自然智慧本质, 照亮类脑智能之路: 果蝇学习记忆与抉择的神经环路机制研究[J]. 中国科学:生命科学, 2019, 49(10): 1354–1374
GUO Aike. A cross-species review of cognitive neural circuits to illuminate the way to brain-inspired intelligence[J]. Scientia sinica (vitae), 2019, 49(10): 1354–1374
[2] PAULK A, MILLARD S S, VAN SWINDEREN B. Vision in Drosophila: seeing the world through a model’s eyes[J]. Annual review of entomology, 2013, 58: 313–332.
[3] WINDING M, PEDIGO B D, BARNES C L, et al. The connectome of an insect brain[J]. Science, 2023, 379(6636): eadd9330.
[4] BORST A, HAAG J, MAUSS A S. How fly neurons compute the direction of visual motion[J]. Journal of comparative physiology A, neuroethology, sensory, neural, and behavioral physiology, 2020, 206(2): 109–124.
[5] 章盛, 沈洁, 郑胜男, 等. 类果蝇复眼视觉神经计算建模及仿生应用研究综述[J]. 红外技术, 2023, 45(3): 229–240
ZHANG Sheng, SHEN Jie, ZHENG Shengnan, et al. Research review of drosophila-like compound eye visual neural computational modeling and bionic applications[J]. Infrared technology, 2023, 45(3): 229–240
[6] 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
XU Mengxi, SHI Jianqiang. Bionic compound eye based multi-source monitoring data fusion and thematic information extraction[J]. Water resources informatization, 2021(1): 71–75
[7] 胡雪蕾, 高明, 陈阳. 大视场曲面仿生复眼光学系统设计[J]. 红外与激光工程, 2020, 49(1): 0114002
HU Xuelei, GAO Ming, CHEN Yang. Design of curved bionic compound eye optical system with large field of view[J]. Infrared and laser engineering, 2020, 49(1): 0114002
[8] 王申奥, 王汉熙. “人造复眼” 英文学术文献展现的学术研究整体态势[J]. 武汉理工大学学报, 2020, 42(2): 90–102
WANG Shen’ao, WANG Hanxi. Academic research situation and development direction of the “artificial compound eyes” in English academic literature[J]. Journal of Wuhan University of Technology, 2020, 42(2): 90–102
[9] FU Qinbing, WANG Hongxin, HU Cheng, et al. Towards computational models and applications of insect visual systems for motion perception: a review[J]. Artificial life, 2019, 25(3): 263–311.
[10] 黄凤辰, 李敏, 石爱业, 等. 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
HUANG Fengchen, LI Min, SHI Aiye, et al. Insect visual system inspired small target detection for multi-spectral remotely sensed images[J]. Journal on communications, 2011, 32(9): 88–95
[11] JOESCH M, SCHNELL B, RAGHU S V, et al. ON and OFF pathways in Drosophila motion vision[J]. Nature, 2010, 468(7321): 300–304.
[12] KELE? M F, FRYE M A. Object-detecting neurons in drosophila[J]. Current biology:CB, 2017, 27(5): 680–687.
[13] HAAG J, ARENZ A, SERBE E, et al. Complementary mechanisms create direction selectivity in the fly[J]. eLife, 2016, 5: e17421.
[14] STROTHER J A, WU S T, WONG A M, et al. The emergence of directional selectivity in the visual motion pathway of drosophila[J]. Neuron, 2017, 94(1): 168–182.
[15] FISHER Y E, LEONG J C S, SPORAR K, et al. A class of visual neurons with wide-field properties is required for local motion detection[J]. Current biology: CB, 2015, 25(24): 3178–3189.
[16] EICHNER H, JOESCH M, SCHNELL B, et al. Internal structure of the fly elementary motion detector[J]. Neuron, 2011, 70(6): 1155–1164.
[17] HENNIG P, EGELHAAF M. Neuronal encoding of object and distance information: a model simulation study on naturalistic optic flow processing[J]. Frontiers in neural circuits, 2012, 6: 14.
[18] WIEDERMAN S D, O’CARROLL D C. Biologically inspired feature detection using cascaded correlations of off and on channels[J]. Journal of artificial intelligence and soft computing research, 2013, 3(1): 5–14.
[19] YUE Shigang, FU Qinbing. Modeling direction selective visual neural network with ON and OFF pathways for extracting motion cues from cluttered background[C]//2017 International Joint Conference on Neural Networks. Anchorage: IEEE, 2017: 831-838.
[20] FU Qinbing, YUE Shigang. Modelling Drosophila motion vision pathways for decoding the direction of translating objects against cluttered moving backgrounds[J]. Biological cybernetics, 2020, 114(4/5): 443–460.
[21] 李柯, 沈克永, 刘宝, 等. 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
LI Ke, SHEN Keyong, LIU Bao, et al. Research on moving small target detection and tracking system of simulated flying insect compound eye vision[J]. Journal of image and signal processing, 2022, 11(3): 92–100
[22] 施建强, 徐扬, 徐梦溪, 等. 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]// 2021年中国仪器仪表学会学术年会. 上海: 中国仪器仪表学会, 2021: 1-4.
SHI Jianqiang, XU Yang, XU Mmengxi, et al. An artificial neural network model simulating fly vision for sensing target motion direction[C]//2021 Annual Conference of China Instrument and Control Society. Shanghai: China Instrument and Control Society, 2021: 1-4.
[23] SHEN Keyong, YANG Yang, LIANG Yuying, et al. Modeling Drosophila vision neural pathways to detect weak moving targets from cluttered backgrounds[J]. Computers and electrical engineering, 2022, 99: 107678.
[24] BORST A, EGELHAAF M. Principles of visual motion detection[J]. Trends in neurosciences, 1989, 12(8): 297–306.
[25] FRANCESCHINI N, RIEHLE A, LE NESTOUR A. Directionally selective motion detection by insect neurons[C]//Facets of Vision. Heidelberg: Springer, 1989: 360-390.
- 相似文献/References:
-
[1]刘 清,吴志刚,窦 琴,等.粒子滤波的视频目标跟踪算法研究[J].智能系统学报,2009,4(6):538.[doi:10.3969/j.issn.1673-4785.2009.06.012]
LIU Qing,WU Zhi-gang,DOU Qin,et al.A particle filtering algorithm for tracking moving objects in videos[J].CAAI Transactions on Intelligent Systems,2009,4():538.[doi:10.3969/j.issn.1673-4785.2009.06.012]
[2]胡光龙,秦世引.动态成像条件下基于SURF和Mean shift的运动目标高精度检测[J].智能系统学报,2012,7(1):61.
HU Guanglong,QIN Shiyin.High precision detection of a mobile object under dynamic imaging based on SURF and Mean shift[J].CAAI Transactions on Intelligent Systems,2012,7():61.
[3]韩峥,刘华平,黄文炳,等.基于Kinect的机械臂目标抓取[J].智能系统学报,2013,8(2):149.[doi:10.3969/j.issn.1673-4785.201212038]
HAN Zheng,LIU Huaping,HUANG Wenbing,et al.Kinect-based object grasping by manipulator[J].CAAI Transactions on Intelligent Systems,2013,8():149.[doi:10.3969/j.issn.1673-4785.201212038]
[4]韩延彬,郭晓鹏,魏延文,等.RGB和HSI颜色空间的一种改进的阴影消除算法[J].智能系统学报,2015,10(5):769.[doi:10.11992/tis.201410010]
HAN Yanbin,GUO Xiaopeng,WEI Yanwen,et al.An improved shadow removal algorithm based on RGB and HSI color spaces[J].CAAI Transactions on Intelligent Systems,2015,10():769.[doi:10.11992/tis.201410010]
[5]曾宪华,易荣辉,何姗姗.流形排序的交互式图像分割[J].智能系统学报,2016,11(1):117.[doi:10.11992/tis.201505037]
ZENG Xianhua,YI Ronghui,HE Shanshan.Interactive image segmentation based on manifold ranking[J].CAAI Transactions on Intelligent Systems,2016,11():117.[doi:10.11992/tis.201505037]
[6]葛园园,许有疆,赵帅,等.自动驾驶场景下小且密集的交通标志检测[J].智能系统学报,2018,13(3):366.[doi:10.11992/tis.201706040]
GE Yuanyuan,XU Youjiang,ZHAO Shuai,et al.Detection of small and dense traffic signs in self-driving scenarios[J].CAAI Transactions on Intelligent Systems,2018,13():366.[doi:10.11992/tis.201706040]
[7]王鈃润,聂秀山,杨帆,等.基于排序学习的视频摘要[J].智能系统学报,2018,13(6):921.[doi:10.11992/tis.201806013]
WANG Xingrun,NIE Xiushan,YANG Fan,et al.Video summarization based on learning to rank[J].CAAI Transactions on Intelligent Systems,2018,13():921.[doi:10.11992/tis.201806013]
[8]莫宏伟,汪海波.基于Faster R-CNN的人体行为检测研究[J].智能系统学报,2018,13(6):967.[doi:10.11992/tis.201801025]
MO Hongwei,WANG Haibo.Research on human behavior detection based on Faster R-CNN[J].CAAI Transactions on Intelligent Systems,2018,13():967.[doi:10.11992/tis.201801025]
[9]宁欣,李卫军,田伟娟,等.一种自适应模板更新的判别式KCF跟踪方法[J].智能系统学报,2019,14(1):121.[doi:10.11992/tis.201806038]
NING Xin,LI Weijun,TIAN Weijuan,et al.Adaptive template update of discriminant KCF for visual tracking[J].CAAI Transactions on Intelligent Systems,2019,14():121.[doi:10.11992/tis.201806038]
[10]伍鹏瑛,张建明,彭建,等.多层卷积特征的真实场景下行人检测研究[J].智能系统学报,2019,14(2):306.[doi:10.11992/tis.201710019]
WU Pengying,ZHANG Jianming,PENG Jian,et al.Research on pedestrian detection based on multi-layer convolution feature in real scene[J].CAAI Transactions on Intelligent Systems,2019,14():306.[doi:10.11992/tis.201710019]
备注/Memo
收稿日期:2022-03-23。
基金项目:江苏省自然科学基金项目（BK20221399）.
作者简介:徐梦溪，博士，教授。主要研究方向为图像处理、多媒体系统与应用软件。主持和参与国家自然科学基金项目和省部级科技计划项目8项，获省部级科技进步奖3项，获发明专利授权10余项，发表学术论文30余篇，出版专著及教材3部。E-mail：xumx@njit. edu.cn;施建强，教授级高级工程师。主要研究方向为电力系统仿真、自动化检测技术、信息系统集成与应用。E-mail：shijq@njit.edu.cn;郑胜男，高级实验师。主要研究方向为图像处理、智能信息处理。E-mail：zhengsn@njit.edu.cn
通讯作者:徐梦溪. E-mail：xumx@njit.edu.cn
更新日期/Last Update:
1900-01-01