Supporting animal welfare with automatic tracking of giraffes with thermal cameras

Externally observing of animal behaviour is an essential method for understanding and improving captive animal welfare, but is limited by observer subjectivity and high-labour costs, and is not embedded in day-to-day care. In this paper, we present a solution via a system that utilizes a single thermal camera to automatically locate giraffes within their enclosure, matching human estimation accuracy. We present an account of the development of this system, our approach, and an evaluation through focus-group interviews with zoo-keepers which provide insight into the most appropriate visualisation methods, and the future opportunities for automatic tracking technologies to support husbandry practices, zoo visitor experiences, and conservation education.

[1]  Patricia Pons,et al.  Envisioning Future Playful Interactive Environments for Animals , 2015 .

[2]  Marcus Carter,et al.  Interactive technology and human-animal encounters at the zoo , 2017, Int. J. Hum. Comput. Stud..

[3]  Oskar Juhlin,et al.  Animal-Computer Interaction: The emergence of a discipline , 2017, Int. J. Hum. Comput. Stud..

[4]  Matthew J. Anderson,et al.  The effects of GPS collars on African elephant (Loxodonta africana) behavior at the San Diego Zoo Safari Park , 2012 .

[5]  Heli Väätäjä,et al.  Don't cut to the chase: hunting experiences for zoo animals and visitors , 2016, ACI.

[6]  Steve North,et al.  HABIT: Horse Automated Behaviour Identification Tool - a position paper , 2015 .

[7]  King-Sun Fu,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Roland Kays,et al.  Observing the unwatchable through acceleration logging of animal behavior , 2013, Animal Biotelemetry.

[9]  Irenilza de Alencar Nääs,et al.  Image analysis for assessing broiler breeder behavior response to thermal environment , 2012 .

[10]  D Marr,et al.  Bandpass channels, zero-crossings, and early visual information processing. , 1979, Journal of the Optical Society of America.

[11]  Peter L. Tyack,et al.  A digital acoustic recording tag for measuring the response of wild marine mammals to sound , 2003 .

[12]  Sarah E. Ritvo,et al.  Music as enrichment for Sumatran orangutans (Pongo abelii) , 2016 .

[13]  W. H. Gispen,et al.  Classification of rat behavior with an image-processing method and a neural network , 2000, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[14]  Clara Mancini,et al.  Animal-computer interaction: a manifesto , 2011, INTR.

[15]  Marcus Carter,et al.  Naturalism and ACI: augmenting zoo enclosures with digital technology , 2015, Advances in Computer Entertainment.

[16]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[17]  Mansi Parikh,et al.  Animal Detection Using Template Matching Algorithm , 2013 .

[18]  Charalampos Z. Patrikakis,et al.  A complete farm management system based on animal identification using RFID technology , 2010 .

[19]  Javier Jaén Martínez,et al.  Sound to your objects: a novel design approach to evaluate orangutans' interest in sound-based stimuli , 2016, ACI.

[20]  Hans-Hellmut Nagel,et al.  Volumetric model and 3D trajectory of a moving car derived from monocular TV frame sequences of a street scene , 1981, Comput. Graph. Image Process..

[21]  Manuela M. Veloso,et al.  Automatically tracking and analyzing the behavior of live insect colonies , 2001, AGENTS '01.

[22]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[24]  Yuichi Nakamura,et al.  Application of a computer vision technique to animal-borne video data: extraction of head movement to understand sea turtles’ visual assessment of surroundings , 2015, Animal Biotelemetry.

[25]  Tomaso A. Poggio,et al.  A general framework for object detection , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[26]  Marcus Carter,et al.  Kinecting with Orangutans: Zoo Visitors' Empathetic Responses to Animals' Use of Interactive Technology , 2017, CHI.

[27]  Ian D. Reid,et al.  Stable multi-target tracking in real-time surveillance video , 2011, CVPR 2011.

[28]  M. Dawkins,et al.  Using behaviour to assess animal welfare , 2004, Animal Welfare.

[29]  K. Horback,et al.  GPS technology as a proxy tool for determining relationships in social animals: An example with African elephants , 2015 .

[30]  Kenton O'Hara,et al.  Collecting and Sharing Location-based Content on Mobile Phones in a Zoo Visitor Experience , 2007, Computer Supported Cooperative Work (CSCW).

[31]  Graham Mitchell,et al.  Giraffe Thermoregulation: a review , 2004 .

[32]  Takeo Kanade,et al.  Vision and Navigation for the Carnegie-Mellon Navlab , 1987 .

[33]  Peter Carr,et al.  Monitoring Giraffe Behavior in Thermal Video , 2015, 2015 IEEE Winter Applications and Computer Vision Workshops.

[34]  Han Wang,et al.  Gray Level Corner Detection , 1998, MVA.