JoVE Journal > Environment
Summary
Abstract
Introduction
Protocol
Risultati
Discussion
Divulgazioni
Acknowledgements
Materials
Riferimenti
Traduzione automatica
Please note that all translations are automatically generated. Click here for the English version.
Ambiente

生态动物的长期视频跟踪: 挪威龙虾 (诺菲氏肾病) 日生物活动的案例研究

Published: April 08, 2019
doi:
10.3791/58515
, , ,
1Universitat Oberta de Catalunya, 2Institute of Marine Sciences,Spanish National Research Council (CSIC), 3Institute for Environmental Protection and Research (ISPRA), 4Department of Biology and Ecology of Fishes,Leibniz-Institute of Freshwater Ecology and Inland Fisheries

Summary

在这里, 我们提出了一个协议, 单独跟踪动物在很长一段时间。它使用计算机视觉方法来识别一组手动构建的标签, 方法是使用一组龙虾作为案例研究, 同时提供有关如何容纳、操纵和标记龙虾的信息。

Abstract

我们提出了一种与基于背景减法和图像阈值的视频跟踪技术相关的协议, 该协议使单独跟踪单独的男女同校动物成为可能。我们用四个共同存放的挪威龙虾 (诺韦吉克斯肾病) 在黑暗的条件下测试了5天的跟踪程序。龙虾已经被单独贴上标签了。实验设置和使用的跟踪技术完全基于开源软件。将跟踪输出与人工检测进行比较后发现, 有69% 的时间正确检测到龙虾。在正确检测到的龙虾中, 99.5% 的时间正确识别了它们的个别标签。考虑到协议中使用的帧速率和龙虾的运动速率, 视频跟踪的性能具有较好的质量, 具有代表性的结果支持了协议在为研究需要生成有价值数据方面的有效性 (个人)。空间占用率或运动活动模式)。这里提出的协议可以很容易地定制, 因此可以转移到其他物种, 在这些物种中, 一个群体中的标本的个别跟踪对回答研究问题很有价值。

Introduction

在过去的几年中, 基于图像的自动跟踪提供了高度精确的数据集, 可用于探索生态学和行为学科1中的基本问题。这些数据集可用于动物行为的定量分析2,3。然而, 用于跟踪动物和行为评估的每一种图像方法都有其优点和局限性。在基于图像的跟踪协议中, 使用电影中以前帧中的空间信息来跟踪动物4、5、6,当两个动物的路径交叉时, 就会引入错误。这些错误通常是不可逆的, 并随着时间的推移而传播。尽管计算方面的进展减少或几乎消除了这个问题5,7, 这些技术仍然需要均匀的实验环境来准确地识别和跟踪动物。

使用可以在动物身上唯一识别的标记可以避免这些错误, 并允许对已识别的个人进行长期跟踪。工业和商业中存在广泛使用的标记 (如条形码和二维码), 可以使用众所周知的计算机视觉技术进行识别, 例如增强现实 (例如 artag8) 和摄像机校准 (例如, caltag9)).标签动物以前曾被用于不同动物物种的高通量行为研究, 例如蚂蚁3或蜜蜂10, 但以前的一些系统没有优化以识别孤立的标记3。

本文提出的跟踪协议特别适用于单通道图像中的动物跟踪, 如红外光或单色光 (特别是蓝光)。因此, 开发的方法不使用颜色提示, 也适用于照明中存在约束的其他设置。此外, 我们还使用定制的标签, 以避免打扰龙虾, 同时, 允许用低成本的相机进行录制。此外, 这里使用的方法是基于独立于框架的标记检测 (即,该算法识别图像中存在的每个标记, 而不管以前的轨迹是什么)。此功能适用于动物可以暂时遮挡或动物轨迹可能相交的应用。

标签设计允许在不同的动物群体中使用。一旦确定了该方法的参数, 就可以将其转移到其他动物跟踪问题上, 而不需要培训特定的分类器 (其他甲壳类动物或腹足类动物)。导出协议的主要限制是标签的大小和对动物的依恋需求 (这使得它不适合小昆虫, 如苍蝇、蜜蜂等) 和动物运动的2D 假设。考虑到所提出的方法假定标记大小保持不变, 此约束非常重要。在3D 环境中自由移动的动物 (例如, 鱼) 会根据其与相机的距离显示不同的标记大小。

本协议的目的是提供一种用户友好的方法, 以便在2D 上下文中长时间 (即几天或几周) 跟踪多个标记动物。方法方法是基于使用开源软件和硬件。自由和开源软件允许调整、修改和自由再分发;因此, 生成的软件在每一步11,12上都得到了改进。

这里介绍的协议侧重于为跟踪和评估四个水生动物在水箱中的运动活动而设立的实验室, 为期5天。视频文件从1秒图像中录制, 并以每秒20帧的速度在视频中进行编译 (1个录制日占用约1小时的视频)。所有的视频录制都会自动进行后处理, 以获得动物的位置, 并应用计算机视觉方法和算法。该协议允许获取大量的跟踪数据, 避免了它们的人工注释, 这在以前的实验论文13中已经证明是耗时和费力的。

我们使用挪威龙虾 (诺维吉克斯的尼弗罗斯) 进行案例研究;因此, 我们提供特定物种的实验室条件来维护它们。龙虾执行经过充分研究的洞穴出现节奏, 这些节奏是在生物钟14、15 的控制下, 当它们共同居住时, 它们形成了 16,17的优势等级。因此, 这里介绍的模型是一个很好的例子, 研究人员感兴趣的行为的社会调制, 特别是关注生理节律。

这里提出的方法很容易复制, 如果有可能区分有个别标签的动物, 可以适用于其他物种。在实验室复制这种方法的最低要求是: (一) 实验装置的等温室;(ii) 连续供水;(三) 水温控制机制;(iv) 灯光控制系统;(v) USB 摄像机和标准计算机。

在本协议中, 我们使用 Python18和 opencv19 (开源计算机视觉库)。我们依靠快速和通用的操作 (在实现和执行方面), 如背景减法20和图像阈值21,22。

Protocol

本研究中使用的物种不是濒危物种或受保护物种。取样和实验室实验遵循了西班牙关于动物福利的立法和内部机构 (icm-csic) 条例。动物取样是在地方当局 (加泰罗尼亚地区政府) 允许的情况下进行的。 1. 动物维护和取样 请注意:下面的协议是基于这样的假设, 即研究人员可以在夜间在野外对诺维皮斯进行采样, 以避免对光感受器<sup class="xre…

Representative Results

我们手动构造了实验数据的子集来验证自动视频分析。一个样本大小为 1, 308 帧, 置信度为 99% (这是一种安全度量, 显示样本是否在其误差范围内准确地反映了总体情况) 和误差幅度为 4% (这是描述关闭程度的百分比)。样本给出的响应是对总体中的实际值的响应) 是随机选择的, 并对正确识别 Roi 和每个 ROI 中的标记的正确标识进行了手动注释。请注意, 单个帧可能包含一个未?…

Discussion

视频跟踪协议的性能和代表性结果证实了其在动物行为领域应用研究中的有效性, 重点是被关押动物的社会调制和生理节律。动物检测的效率 (69%)和标签区分的准确性 (99.5%)再加上这里使用的目标物种的行为特征 (即运动率), 这个协议是长期实验试验 (例如, 几天和几周) 的完美解决方案。此外, 该协议还提供了一个基本优势, 即在开发和定制方面更易于使用, 并且速度更快, 而其他技术, 如自动学习算…

Divulgazioni

The authors have nothing to disclose.

Acknowledgements

作者感谢为出版这项工作提供资金的 Joan B. company。此外, 作者还感谢巴塞罗那海洋科学研究所 (ICM-CSIC) 实验水族馆区的技术人员在实验工作中提供的帮助。

这项工作得到了 RITFIM 项目 (CTM2010-16274; 首席调查员: J. aguzzi) 的支持, 以及西班牙经济和竞争力部设立的 TIN2015-66951-C2-2-r 赠款。

Materials

Tripod 475 Manfrotto A0673528 Discontinued
Articulated Arm 143 Manfrotto D0057824 Discontinued
Camera USB 2.0 uEye LE iDS UI-1545LE-M https://en.ids-imaging.com/store/products/cameras/usb-2-0-cameras/ueye-le.html
Fish Eye Len C-mount f=6mm/F1.4 Infaimon Standard Optical  https://www.infaimon.com/es/estandar-6mm
Glass Fiber Tank 1500x700x300 mm
Black Felt Fabric
Wood Structure Tank 5 Wood Strips 50x50x250 mm
Wood Structure Felt Fabric 10 Wood Strips 25x25x250 mm
Stainless Steel Screws As many as necessary for fix wood strips structures
PC 2-cores CPU, 4GB RAM, 1 GB Graphics, 500 GB HD
External Storage HDD 2 TB capacity desirable
iSPY Sotfware for Windows PC iSPY https://www.ispyconnect.com/download.aspx
Zoneminder Software Linux PC Zoneminder https://zoneminder.com/
OpenCV 2.4.13.6 Library OpenCV https://opencv.org/
Python 2.4 Python https://www.python.org/
Camping Icebox
Plastic Tray
Cyanocrylate Gel To glue tag’s 
1 black PVC plastic sheet (1 mm thickness) Tag's construction
1 white PVC plastic sheet (1 mm thickness) Tag's construction
4 Tag’s Ø 40 mm Maked with black & white PVC plastic sheet
3 m Blue Strid Led Ligts (480 nm) Waterproof as desirable
3 m IR Strid Led Ligts (850 nm) Waterproof as desirable
6m  Methacrylate Pipes Ø 15 mm Enclosed Strid Led
4 PVC Elbow  45o Ø 63 mm Burrow construction
3 m Flexible PVC Pipe Ø 63 mm Burrow construction
4 PVC Screwcap Ø 63 mm Burrow construction
4 O-ring Ø 63 mm Burrow construction
4 Female PVC socket glue / thread Ø 63 mm Burrow construction
10 m DC 12V Electric Cable Light Control Mechanism
Ligt Power Supply DC 12V 300 w Light Control Mechanism
MOSFET, RFD14N05L, N-Canal, 14 A, 50 V, 3-Pin, IPAK (TO-251) RS Components 325-7580 Light Control Mechanism
Diode, 1N4004-E3/54, 1A, 400V, DO-204AL, 2-Pines RS Components 628-9029 Light Control Mechanism
Fuse Holder RS Components 336-7851 Light Control Mechanism
2 Way Power Terminal 3.81mm RS Components 220-4658 Light Control Mechanism
Capacitor 220 µF 200 V RS Components 440-6761 Light Control Mechanism
Resistance 2K2 7W RS Components 485-3038 Light Control Mechanism
Fuse 6.3x32mm 3A RS Components 413-210 Light Control Mechanism
Arduino Uno Atmel Atmega 328 MCU board RS Components 715-4081 Light Control Mechanism
Prototipe Board CEM3,3 orific.,RE310S2 RS Components 728-8737 Light Control Mechanism
DC/DC converter,12Vin,+/-5Vout 100mA 1W RS Components 689-5179 Light Control Mechanism
2 SERA T8 blue moonlight fluorescent bulb 36 watts SERA Discontinued / Light isolated facility
DOWNLOAD MATERIALS LIST

Riferimenti

  1. Dell, A. I., et al. Automated image-based tracking and its application in ecology. Trends in Ecology & Evolution. 29 (7), 417-428 (2014).
  2. Berman, G. J., Choi, D. M., Bialek, W., Shaevitz, J. W. Mapping the stereotyped behaviour of freely moving fruit flies. Journal of The Royal Society Interface. 11 (99), (2014).
  3. Mersch, D. P., Crespi, A., Keller, L. Tracking Individuals Shows Spatial Fidelity Is a Key Regulator of Ant Social Organization. Science. 340 (6136), 1090 (2013).
  4. Tyson, L. Hedrick Software techniques for two- and three-dimensional kinematic measurements of biological and biomimetic systems. Bioinspiration & Biomimetics. 3 (3), 034001 (2008).
  5. Branson, K., Robie, A. A., Bender, J., Perona, P., Dickinson, M. H. High-throughput ethomics in large groups of Drosophila. Nature Methods. 6 (6), 451-457 (2009).
  6. de Chaumont, F., et al. Computerized video analysis of social interactions in mice. Nature Methods. 9, 410 (2012).
  7. Pérez-Escudero, A., Vicente-Page, J., Hinz, R. C., Arganda, S., de Polavieja, G. G. idTracker: tracking individuals in a group by automatic identification of unmarked animals. Nature Methods. 11 (7), 743-748 (2014).
  8. Fiala, M. ARTag, a fiducial marker system using digital techniques. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05). 2, 590-596 (2005).
  9. Koch, R., Kolb, A., Rezk-Salama, C., Koch, R., Kolb, A., Rezk-salama, C. . CALTag: High Precision Fiducial Markers for Camera Calibration. , (2010).
  10. Crall, J. D., Gravish, N., Mountcastle, A. M., Combes, S. A. BEEtag: A Low-Cost, Image-Based Tracking System for the Study of Animal Behavior and Locomotion. PLOS ONE. 10 (9), e0136487 (2015).
  11. Charpentier, R. Free and Open Source Software: Overview and Preliminary Guidelines for the Government of Canada. Open Source Business Resource. , (2008).
  12. Crowston, K., Wei, K., Howison, J. Free/Libre Open Source Software Development: What We Know and What We Do Not Know. ACM Computing Surveys. 37, (2012).
  13. Edmonds, N. J., Riley, W. D., Maxwell, D. L. Predation by Pacifastacus leniusculus on the intra-gravel embryos and emerging fry of Salmo salar. Fisheries Management and Ecology. 18 (6), 521-524 (2011).
  14. Sbragaglia, V., et al. Identification, Characterization, and Diel Pattern of Expression of Canonical Clock Genes in Nephrops norvegicus (Crustacea: Decapoda) Eyestalk. PLOS ONE. 10 (11), e0141893 (2015).
  15. Sbragaglia, V., et al. Dusk but not dawn burrow emergence rhythms of Nephrops norvegicus (Crustacea: Decapoda). Scientia Marina. 77 (4), 641-647 (2013).
  16. Katoh, E., Sbragaglia, V., Aguzzi, J., Breithaupt, T. Sensory Biology and Behaviour of Nephrops norvegicus. Advances in Marine Biology. 64, 65-106 (2013).
  17. Sbragaglia, V., Leiva, D., Arias, A., Antonio García, J., Aguzzi, J., Breithaupt, T. Fighting over burrows: the emergence of dominance hierarchies in the Norway lobster (Nephrops norvegicus). The Journal of Experimental Biology. 220 (24), 4624-4633 (2017).
  18. . Welcome to Python.org Available from: https://www.python.org/ (2018)
  19. Bradski, G. . OpenCV Library. Dr. Dobb’s Journal of Software Tools. , (2000).
  20. Piccardi, M. Background subtraction techniques: a review. 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583). 4, 3099-3104 (2004).
  21. Sankur, B. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging. 13 (1), 146 (2004).
  22. Lai, Y. K., Rosin, P. L. Efficient Circular Thresholding. IEEE Transactions on Image Processing. 23 (3), 992-1001 (2014).
  23. Gaten, E. Light‐induced damage to the dioptric apparatus of Nephrops norvegicus (L.) and the quantitative assessment of the damage. Marine Behaviour and Physiology. 13 (2), 169-183 (1988).
  24. Sbragaglia, V., et al. An automated multi-flume actograph for the study of behavioral rhythms of burrowing organisms. Journal of Experimental Marine Biology and Ecology. 446, 177-186 (2013).
  25. Johnson, M. L., Gaten, E., Shelton, P. M. J. Spectral sensitivities of five marine decapod crustaceans and a review of spectral sensitivity variation in relation to habitat. Journal of the Marine Biological Association of the United Kingdom. 82 (5), 835-842 (2002).
  26. Markager, S., Vincent, W. F. Spectral light attenuation and the absorption of UV and blue light in natural waters. Limnology and Oceanography. 45 (3), 642-650 (2000).
  27. Aguzzi, J., et al. A New Laboratory Radio Frequency Identification (RFID) System for Behavioural Tracking of Marine Organisms. Sensors. 11 (10), 9532-9548 (2011).
  28. Audin, M. . Geometry [Electronic Resource. , (2003).
  29. . . OpenCV Team Structural Analysis and Shape Descriptors – OpenCV 2.4.13.7 documentation. , (2018).
  30. Slabaugh, G. G. . Computing Euler angles from a rotation matrix. 7, (1999).
  31. Zhang, Z. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence. 22 (11), 1330-1334 (2000).
  32. . www.FOURCC.org – Video Codecs and Pixel Formats Available from: https://www.fourcc.org/ (2018)
  33. Suzuki, S., be, K. Topological structural analysis of digitized binary images by border following. Computer Vision, Graphics, and Image Processing. 30 (1), 32-46 (1985).
  34. Sklansky, J. Finding the convex hull of a simple polygon. Pattern Recognition Letters. 1 (2), 79-83 (1982).
  35. Fitzgibbon, A., Fisher, R. . A Buyer’s Guide to Conic Fitting. , 51.1-51.10 (1995).
  36. Otsu, N. A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man, and Cybernetics. 9 (1), 62-66 (1979).
  37. Hu, M. K. Visual pattern recognition by moment invariants. IRE Transactions on Information Theory. 8 (2), 179-187 (1962).
  38. . Structural Analysis and Shape Descriptors – OpenCV 2.4.13.6 documentation Available from: https://docs.opencv.org/2.4/modules/imgproc/doc/structural_analysis_and_shape_descriptors.html?highlight=cvmatchshapes#humoments (2018)
  39. Douglas, D. H., Peucker, T. K. Algorithms for the Reduction of the Number of Points Required to Represent a Digitized Line or its Caricature. Cartographica: The International Journal for Geographic Information and Geovisualization. 10 (2), 112-122 (1973).
  40. Vanajakshi, B., Krishna, K. S. R. Classification of boundary and region shapes using Hu-moment invariants. Indian Journal of Computer Science and Engineering. 3, 386-393 (2012).
  41. Kahle, D., Wickham, H. ggmap : Spatial Visualization with ggplot2. The R Journal. , 144-162 (2013).
  42. Venables, W. N., Ripley, B. D. . Modern Applied Statistics with S. , (2010).
  43. Abbas, Q., Ibrahim, M. E. A., Jaffar, M. A. A comprehensive review of recent advances on deep vision systems. Artificial Intelligence Review. , (2018).
  44. Menesatti, P., Aguzzi, J., Costa, C., García, J. A., Sardà, F. A new morphometric implemented video-image analysis protocol for the study of social modulation in activity rhythms of marine organisms. Journal of Neuroscience Methods. 184 (1), 161-168 (2009).
  45. Chapman, C. J., Shelton, P. M. J., Shanks, A. M., Gaten, E. Survival and growth of the Norway lobster Nephrops norvegicus in relation to light-induced eye damage. Marine Biology. 136 (2), 233-241 (2000).
  46. . Video tracking software | EthoVision XT Available from: https://www.noldus.com/animal-behavior-research/products/ethovision-xt (2018)
  47. Correll, N., Sempo, G., Meneses, Y. L. D., Halloy, J., Deneubourg, J., Martinoli, A. SwisTrack: A Tracking Tool for Multi-Unit Robotic and Biological Systems. 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems. , 2185-2191 (2006).
  48. . . MATLAB – MathWorks. , (2018).
  49. Leggat, P. A., Smith, D. R., Kedjarune, U. Surgical Applications of Cyanoacrylate Adhesives: A Review of Toxicity. ANZ Journal of Surgery. 77 (4), 209-213 (2007).
  50. Dizon, R. M., Edwards, A. J., Gomez, E. D. Comparison of three types of adhesives in attaching coral transplants to clam shell substrates. Aquatic Conservation: Marine and Freshwater Ecosystems. 18 (7), 1140-1148 (2008).
  51. Cary, R. . Methyl cyanoacrylate and ethyl cyanoacrylate. , (2001).
  52. Krizhevsky, A., Sutskever, I., Hinton, G. E. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. , 1097-1105 (2012).

Tags

Keywords: Video TrackingCohoused Aquatic AnimalsNorway LobsterNephrops NorvegicusLocomotor ActivityAutomationAnimal IDTag DetectionVideo AnalysisChronobiologyEcologyViral ResearchNeuroscienzeHardware DesignOpen Source ProgrammingPythonTag ConstructionInfrared LightingBlue LightPhoto PeriodChilled SeawaterVideo RecordingBehavioral Scoring
check_url/it/58515?article_type=t

Play Video
PDF
DOI
DOWNLOAD MATERIALS LIST
Citazione di questo articolo
Garcia, J. A., Sbragaglia, V., Masip, D., Aguzzi, J. Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus). J. Vis. Exp. (146), e58515, doi:10.3791/58515 (2019).
Scarica citazione
Ristampe e autorizzazioni

View Video

✖

To prove you're not a robot, please enter the text in the image below

CAPTCHA Image
Play CAPTCHA Audio
Refresh Image