BioSense: Real-Time Object Tracking for Animal Movement and Behavior Research

Segmenting and tracking of objects in video is of great importance for video-based encoding, surveillance, and retrieval. However, the inherent difficulty of object segmentation and tracking is to distinguish changes in the displacement of objects from disturbing effects such as noise and illumination changes. Therefore, in this paper, we formulate a color-based deformable model which is robust against noisy data and changing illumination. Computational methods are presented to measure color constant gradients. Further, a model is given to estimate the amount of sensor noise through these color constant gradients. The obtained uncertainty is subsequently used as a weighting term in the deformation process. Experiments are conducted on image sequences recorded from three-dimensional scenes. From the experimental results, it is shown that the proposed color constant deformable method successfully finds object contours robust against illumination, and noisy, but homogeneous regions.

Video object segmentation and tracking are two essential building blocks of smart surveillance systems. However, there are several issues that need to be resolved. Threshold decision is a difficult problem for video object segmentation with a multi-background model. In addition, some conditions make robust video object tracking difficult. These conditions include nonrigid object motion, target appearance variations due to changes in illumination, and background clutter. In this paper, a video object segmentation and tracking framework is proposed for smart cameras in visual surveillance networks with two major contributions. First, we propose a robust threshold decision algorithm for video object segmentation with a multi-background model. Second, we propose a video object tracking framework based on a particle filter with the likelihood function composed of diffusion distance for measuring color histogram similarity and motion clue from video object segmentation. The proposed framework can track nonrigid moving objects under drastic changes in illumination and background clutter. Experimental results show that the presented algorithms perform well for several challenging sequences, and our proposed methods are effective for the aforementioned issues.

Classification of farm animal behaviors are based upon oral or written descriptions of the activity that an animal is engaged in. The quantification of animal behavior for research requires that an individual recognize and code the behavior of the animal under study. The classification of these behaviors can be subjective and may differ among observers. Illustrated guides to animal behavior do not convey the motion associated with most behaviors. Video based guides offer a subjective method of quantifying behaviors with real time demonstrations of the components that make up a behavior. In this paper, we propose an animal behavior video database system which can automatically extract animal motion information from the input animal activity video clip by a multi-object tracking and reasoning system. The extracted information is then analyzed and described using a set of standard animal behavior terms we are developing. The behavior description is used to automatically annotate the given video clip, and serves as the content-based index. The user of the system is able to use a keywork description of the behavior to retrieve the corresponding video object. The intended applications of the system are animal and veterinary science education, and animal behavior research. The prototype system is built for swine and will be extended to other farm animal species.

In this article, we introduce the optical motion capture system and its application in animal behavior research, and track its development direction. Optical motion capture system has only been in existence for decades, but it has developed very rapidly. By virtue of its own advantages, it provides a new perspective in the study of animal behavior. It can allow biologists to obtain more specific details of animal movements, and can also establish links between human diseases and animal models. Combined with modern computer technology, optical motion capture systems will play a greater role in animal behavior research.

While most animal behavior researchers have mastered the process of knowledge creation, generating knowledge that can readily be applied requires a different set of skills. The process and timeframe of fundamental scientific knowledge production is often not relevant to those who might apply it, such as conservation or wildlife managers. Additionally, the complex challenges that policy makers, managers and practitioners face are often not adequately communicated to and among scientists. This mutual disconnect in discourse, relationships, common terms, and practices is especially apparent when animal behavior researchers seek to have applied impact. We argue that bridging the complex implementation gap in animal behavior requires a formalized vision for change. We turn to change model theory, a tool commonly used in other fields for identifying the links between actions and outcomes necessary for enacting large-scale change. We focus on the subfield of conservation behavior with a change model that outlines specific ways to improve collaboration and coordination between animal behavior science and conservation practice. We present this targeted change model, review each strategy the model outlines, and highlight pressing actions that people from various career stages and backgrounds can take. We encourage researchers to further the alignment of science with management needs by developing the proper communication mechanisms for improved cultural exchange and plan future change model efforts directly targeting managers. Beyond the conservation behavior change model we present, we also discuss the broad applicability of change models to enhance the application of academic research to other fields. Fundamental science researchers are increasingly required to show impact of their work on society; the change model process we describe here can enable further impact.

To identify trends in research on pure ethology (fundamental issues in animal behaviour) in New Zealand, we combined manual and database searches of the five ethological journals with the greatest impact factors (Animal Behaviour, Behavioral Ecology, Behavioral Ecology and Sociobiology, Ethology and Behaviour) published from 1937 to (and including) 2007. We counted all articles giving a New Zealand address for the first‐listed and/or reprint author. Our analyses showed (1) a total of 131 articles in the five journals, with Animal Behaviour, the journal of preference, containing nearly half of the articles collected; (2) a sharp and steady increase in articles published per year; (3) all four of Tinbergen's questions received attention, with mechanistic and functional studies being more common than studies of development and evolutionary history; (4) a recent resurgence of mechanistic research, representing 67% of all studies in the period from 2003–07; (5) a balance in research focusing on the proximate and ultimate causes of behaviour, shifting towards proximate research in the early 1990s; (6) many New Zealand institutions published papers in the five journals, although universities were the main contributors; (7) only a small subset of the research (28.8%) was done with overseas collaboration; (8) a total of 139 authors were involved in the research reviewed (when all authors for each paper were considered without taking address into account); (9) a maturation of the sampled research by the early 1990s (i.e., when “descriptive” and “explanatory” papers were supplemented with “synthesis” papers); and (10) a large number of investigations (55%) used birds as the study subject. Ethology inNew Zealand, as represented in the five leading animal behaviour journals, was found to be a diverse, dynamic and growing field.

Simple SummaryOur research team has developed an automated computer system that uses convolutional neural networks (CNNs) to monitor and analyse the sleep patterns of dogs. Traditional methods of recording animal behaviour, such as direct observations (of sleep) of either live behaviour or recorded behaviour, can be time-consuming and error-prone, making it difficult to replicate studies. Sleep may be a crucial indicator of an animal’s well-being, but it has been overlooked in animal welfare research due to the time-consuming nature of measuring sleep. Compared to direct behavioural observations from the same videos, our system achieved an 89% similarity score in automatically detecting and quantifying sleep duration and fragmentation in dogs. Although there were no significant differences in the time percentage of sleep observed, the system recorded more total sleep time than human observers making direct observations on the same data sources. The automated system used could become a valuable tool for animal behaviour and welfare research.Although direct behavioural observations are widely used, they are time-consuming, prone to error, require knowledge of the observed species, and depend on intra/inter-observer consistency. As a result, they pose challenges to the reliability and repeatability of studies. Automated video analysis is becoming popular for behavioural observations. Sleep is a biological metric that has the potential to become a reliable broad-spectrum metric that can indicate the quality of life and understanding sleep patterns can contribute to identifying and addressing potential welfare concerns, such as stress, discomfort, or health issues, thus promoting the overall welfare of animals; however, due to the laborious process of quantifying sleep patterns, it has been overlooked in animal welfare research. This study presents a system comparing convolutional neural networks (CNNs) with direct behavioural observation methods for the same data to detect and quantify dogs’ sleeping patterns. A total of 13,688 videos were used to develop and train the model to quantify sleep duration and sleep fragmentation in dogs. To evaluate its similarity to the direct behavioural observations made by a single human observer, 6000 previously unseen frames were used. The system successfully classified 5430 frames, scoring a similarity rate of 89% when compared to the manually recorded observations. There was no significant difference in the percentage of time observed between the system and the human observer (p > 0.05). However, a significant difference was found in total sleep time recorded, where the automated system captured more hours than the observer (p < 0.05). This highlights the potential of using a CNN-based system to study animal welfare and behaviour research.

Animal behaviour can be explained from several complementary perspectives, and these explanations can be formally categorized into "levels of analysis." Recognizing levels of analysis may prevent unnecessary conflict between complementary explanations and promote the understanding of behaviour from all possible perspectives. However, there is considerable room for debate as to the best framework of levels. The current framework is based on the concept of "proximate and ultimate causes," which merges the functional consequences of a behaviour with its evolutionary causes. Consequently, the use of this framework leads to confusion between causes and effects of behaviours, and leaves no room for studies of the effects of a behaviour other than those with adaptive significance for the animal performing it. A more balanced approach can be encouraged by considering questions about causes and effects of behaviours to be in separate categories, with their own analytical levels. Causes of behaviours can be explained by processes on at least four levels: evolution, ontogeny, fluctuations in an animal's state, and occurrence of behaviour-eliciting stimuli. Effects of behaviour may also occur on several levels, but the levels will depend on what is being affected (i.e., the animal performing the behaviour, other organisms, or the physical environment). The causes of behaviours can be influenced by their effects through feedback mechanisms such as reinforcement and natural selection. However, we should not assume such feedback mechanisms to be important in the causation of all behaviours. If we use the effects of behaviours to explain why they occur, it is important to explicitly recognize the feedback mechanism(s) invoked.

Integrating diverse concepts from animal behavior, movement ecology, and machine learning, we develop an overview of the ecology of learning and animal movement. Learning-based movement is clearly relevant to ecological problems, but the subject is rooted firmly in psychology, including a distinct terminology. We contrast this psychological origin of learning with the task-oriented perspective on learning that has emerged from the field of machine learning. We review conceptual frameworks that characterize the role of learning in movement, discuss emerging trends, and summarize recent developments in the analysis of movement data. We also discuss the relative advantages of different modeling approaches for exploring the learning-movement interface. We explore in depth how individual and social modalities of learning can matter to the ecology of animal movement, and highlight how diverse kinds of field studies, ranging from translocation efforts to manipulative experiments, can provide critical insight into the learning process in animal movement.

Studying animal behaviour allows us to understand how different species and individuals navigate their physical and social worlds. Video coding of behaviour is considered a gold standard: allowing researchers to extract rich nuanced behavioural datasets, validate their reliability, and for research to be replicated. However, in practice, videos are only useful if data can be efficiently extracted. Manually locating relevant footage in 10,000 s of hours is extremely time-consuming, as is the manual coding of animal behaviour, which requires extensive training to achieve reliability. Machine learning approaches are used to automate the recognition of patterns within data, considerably reducing the time taken to extract data and improving reliability. However, tracking visual information to recognise nuanced behaviour is a challenging problem and, to date, the tracking and pose-estimation tools used to detect behaviour are typically applied where the visual environment is highly controlled. Animal behaviour researchers are interested in applying these tools to the study of wild animals, but it is not clear to what extent doing so is currently possible, or which tools are most suited to particular problems. To address this gap in knowledge, we describe the new tools available in this rapidly evolving landscape, suggest guidance for tool selection, provide a worked demonstration of the use of machine learning to track movement in video data of wild apes, and make our base models available for use. We use a pose-estimation tool, DeepLabCut, to demonstrate successful training of two pilot models of an extremely challenging pose estimate and tracking problem: multi-animal wild forest-living chimpanzees and bonobos across behavioural contexts from hand-held video footage. With DeepWild we show that, without requiring specific expertise in machine learning, pose estimation and movement tracking of free-living wild primates in visually complex environments is an attainable goal for behavioural researchers.

This chapter relates to the emerging field of evolutionary psychology. Building on past research understanding of the mechanisms underlying animal behavior is presented. Current researches in this field offer many insights into the development of social behaviours displayed among humans. The contribution of animal behaviour research to unravel the evolution of individual and social behaviours including foraging strategies, reproductive systems, social behaviour, dominance hierarchies, social communication, parental investment patterns, evolution of eusociality, among others, are highlighted. Finally, the applications of animal behaviour studies in the area of wildlife such as conservation, management of national parks, and zoo management are indicated. It may be noted that the developments in the area of animal behavior are impressive and are perhaps as good as noted in allied disciplines of anthropology and zoology. However, animal behaviour research is currently an underdeveloped field of psychology. India could perhaps rejuvenate its close association with animal world and nature, a main part of its mythology and real life, by developing this area.

Book Review| October 01 2013 Animals Animal Wise: The Thoughts and Emotions of Our Fellow Creatures. By Virginia Morell. 2013. Crown Publishers. (ISBN 9780307461445). 291 pp. Hardback. $26.00. [Due out in paperback in early 2014.] Gail Baker Gail Baker 1Lane Community College, Eugene, OR 97405 bakerg@lanecc.edu Search for other works by this author on: This Site PubMed Google Scholar The American Biology Teacher (2013) 75 (8): 591–592. https://doi.org/10.1525/abt.2013.75.8.13 Views Icon Views Article contents Figures & tables Video Audio Supplementary Data Peer Review Share Icon Share Twitter LinkedIn Tools Icon Tools Get Permissions Cite Icon Cite Search Site Citation Gail Baker; Animals. The American Biology Teacher 1 October 2013; 75 (8): 591–592. doi: https://doi.org/10.1525/abt.2013.75.8.13 Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentThe American Biology Teacher Search “The question now is not ‘Do animals think?’ It’s ‘How and what do they think?’” With this statement, Virginia Morell sets the theme of her book and the path of inquiry explored by the scientists she interviewed. To answer the latter question, researchers study ants, fish, birds, rats, elephants, dolphins, chimpanzees, dogs, and wolves. Each chapter introduces us to an animal group and associated cognitive studies. We also meet the scientists and learn about the challenges and controversies with which they grapple. It takes creativity, passion, and dedication to the years of observation required to design and implement compelling scientific studies about cognition. We have to be satisfied with the journey of discovery in this field because there are only tentative emerging answers to the how and maybe the what of animal thought. Two other interesting themes in this book are how changes and biases in the process of scientific... You do not currently have access to this content.

Humans differ in how they perceive, assess, and measure animal behaviour. This is problematic because strong observer bias can reduce statistical power, accuracy of scientific inference, and in the worst cases, lead to spurious results. Unfortunately, reports and studies of measurement reliability in animal behaviour studies are rare. Here, we investigated two aspects of measurement reliability in working dogs: inter‐observer agreement and criterion validity (comparing novice ratings with those given by experts). Here, we extend for the first time a powerful framework used in human psychological studies to investigate three potential aspects of (dis)agreement in nonhuman animal behaviour research: (a) that some behaviours are easier to observe than others; (b) that some subjects are easier to observe than others; and (c) that observers with different levels of experience with the subject animal give the same or different ratings. We found that novice observers with the same level of experience agreed upon measures of a wide range of behaviours. We found no evidence that age of the dogs affected agreement between these same novice observers. However, when observers with different levels of experience (i.e., novices vs. a working dog expert) assessed the same dogs, agreement appeared to be strongly affected by the measurement instrument used to assess behaviour. Given that animal behaviour research often utilizes different observers with different levels of experience, our results suggest that further tests of how different observers may measure behaviour in different ways are needed across a wider variety of organisms and measurement instruments.

Animal movement and behaviour is fundamental for ecosystem functioning. The process of seed dispersal by frugivorous animals is a showcase for this paradigm since their behaviour shapes the spatial patterns of the earliest stage of plant regeneration. However, we still lack a general understanding of how intrinsic (frugivore and plant species traits) and extrinsic (landscape features) factors interact to determine how seeds of a given species are more likely to be deposited in some places more than in others. We develop a multi-species mechanistic model of seed dispersal based on frugivore behavioural responses to landscape heterogeneity. The model was fitted to data from three-years of spatially-explicit field observations on the behaviour of six frugivorous thrushes and the fruiting patterns of three fleshy-fruited trees in a secondary forest of the Cantabrian range (N Spain). With such model we explore how seed rain patterns arise from the interaction between animal behaviour and landscape heterogeneity. We show that different species of thrushes respond differently to landscape heterogeneity even though they belong to the same genus, and that provide complementary seed dispersal functions. Simulated seed rain patterns are only realistic when at least some landscape heterogeneity (forest cover and fruit abundance) is taken into account. The common and simple approach of re-sampling movement data to quantify seed dispersal produces biases in both the distance and the habitat at which seeds arrive. Movement behaviour not only affects dispersal distance and seed rain patterns but also can affect frugivore diet composition even if there is no built-in preference for fruiting species. In summary, the fate of seeds produced by a given plant species is strongly affected by both the composition of the frugivore assemblage and the landscape-scale context of the plant location, including the presence of fruits from other plants (from the same or different species).

&lt;p&gt;The ultimate goal of this study is to afford enhanced video object detection and tracking by eliminating the limitations which are existing nowadays. Although high performance ratio for video object detection and tracking is achieved in the earlier work it takes more time for computation. Consequently we are in need to propose a novel video object detection and tracking technique so as to minimize the computational complexity. Our proposed technique covers five stages they are preprocessing, segmentation, feature extraction, background subtraction and hole filling. Originally the video clip in the database is split into frames. Then preprocessing is performed so as to get rid of noise, an adaptive median filter is used in this stage to eliminate the noise. The preprocessed image then undergoes segmentation by means of modified region growing algorithm. The segmented image is subjected to feature extraction phase so as to extract the multi features from the segmented image and the background image, the feature value thus obtained are compared so as to attain optimal value, consequently a foreground image is attained in this stage. The foreground image is then subjected to morphological operations of erosion and dilation so as to fill the holes and to get the object accurately as these foreground image contains holes and discontinuities. Thus the moving object is tracked in this stage. This method will be employed in MATLAB platform and the outcomes will be studied and compared with the existing techniques so as to reveal the performance of the novel video object detection and tracking technique.&nbsp;&lt;/p&gt;