Automated long-term tracking and social behavioural phenotyping of animal colonies within a semi-natural environment

Abstract

Social behaviour has a key role in animal survival across species, ranging from insects to primates and humans. However, the biological mechanisms driving natural interactions between multiple animals, over long-term periods, are poorly studied and remain elusive. Rigorous and objective quantification of behavioural parameters within a group poses a major challenge as it requires simultaneous monitoring of the positions of several individuals and comprehensive consideration of many complex factors. Automatic tracking and phenotyping of interacting animals could thus overcome the limitations of manual tracking methods. Here we report a broadly applicable system that automatically tracks the locations of multiple, uniquely identified animals, such as mice, within a semi-natural setting. The system combines video and radio frequency identified tracking data to obtain detailed behavioural profiles of both individuals and groups. We demonstrate the usefulness of these data in characterizing individual phenotypes, interactions between pairs and the collective social organization of groups.

Automated measurement of mouse social behaviors using depth sensing, video tracking, and machine learning

“…This presents a dual challenge to automated behavior classification: first, to accurately extract a representation of an animal's posture from observed data, and second, to map that representation to the correct behavior (24)(25)(26)(27). Current machine vision algorithms that track social interactions in mice mainly use the relative positions of two animals (25,(28)(29)(30); this approach generally cannot discriminate social interactions that involve close proximity and vigorous physical activity, or identify specific behaviors such as aggression and mounting. In addition, existing algorithms that measure social interactions use a set of hardcoded, "hand-crafted" (i.e., predefined) parameters that make them difficult to adapt to new experimental setups and conditions (25,31).…”

Automated image-based tracking and its application in ecology

“…Tracking over short durations (minutes) has aided in our understanding of the genetic basis of social behavior, such as aggression or courtship [8,85], where the high throughput that automation allows provides enhanced power for uncovering patterns in behavioral data [27]. Research over longer times can uncover complex temporal linkages between social behaviors [8,28], and experiments over the order of weeks provide unique insight into the social and behavioral development of individuals in intraspecific groups [31,53,54].…”

“…Another alternative is to use computer vision technologies that detect animals even when their color pattern is statistically indistinguishable from the background, based, for example, on their shape or movement [21]. Finally, it is possible to mark individuals [53] or integrate with other tracking methods such as bio-logging -combining the robustness of bio-loggers for detecting individuals in complex habitat with the high spatiotemporal resolution of imaging [54].…”

“…Fingerprinting allows the addition of habitat structure without increasing assignment errors, as identities are recovered following occlusion [20,21] (Movie S5 in the supplementary material online). Again, use of multiple cameras (Movie S6 in the supplementary material online), marking [53], or integration with bio-logging [54] can enable tracking and identity maintenance during or after occlusions. Some imaging methods can even pass through physical structure, revealing the position of organisms either behind the structure or embedded within it, thus removing the problem of occlusions from physical habitat altogether.…”

Automated Monitoring of Livestock Behavior Using Frequency-Modulated Continuous-Wave Radars

“…Over recent years, advances in quantitative methods for the study of animal behavior have allowed the development of high throughput behavioral analyses (sometimes called ethomics [1], with applications in neurosciences [2], ethology [3], ecology [4], conservation [5], genetics [6], welfare [7], and farming [8]. In agronomy research, analyses of social behavior in livestock are particularly important in order to improve breeding programs.…”