Kernelized structural classification for 3D dogs body parts detection

Despite pattern recognition methods for human behavioral analysis has flourished in the last decade, animal behavioral analysis has been almost neglected. Those few approaches are mostly focused on preserving livestock economic value while attention on the welfare of companion animals, like dogs, is now emerging as a social need. In this work, following the analogy with human behavior recognition, we propose a system for recognizing body parts of dogs kept in pens. We decide to adopt both 2D and 3D features in order to obtain a rich description of the dog model. Images are acquired using the Microsoft Kinect to capture the depth map images of the dog. Upon depth maps a Structural Support Vector Machine (SSVM) is employed to identify the body parts using both 3D features and 2D images. The proposal relies on a kernelized discriminative structural classificator specifically tailored for dogs independently from the size and breed. The classification is performed in an online fashion using the LaRank optimization technique to obtaining real time performances. Promising results have emerged during the experimental evaluation carried out at a dog shelter, managed by IZSAM, in Teramo, Italy.

The effect of preferential paw usage on dogs' (Canis familiaris) performance in a manipulative problem-solving task

In a number of species, individuals showing lateralized hand/paw usage (i.e. the preferential use of either the right or left paw) compared to ambilateral individuals have been shown to be more proactive in novel situations. In the current study we used an established test to assess preferential paw usage in dogs (the Kong test) and then compared the performance of ambilateral and lateralized dogs as well as left- vs. right-pawed dogs in a novel manipulative problem solving task. Results showed an equal proportion of ambilateral and lateralized dogs but contrary to predictions non-lateralized dogs were faster at accessing the apparatus in test trials. No differences emerged between right- and left-pawed dogs. Results are discussed in relation to previous studies on lateralization. © 2013 Elsevier B.V.

Behavioural and physiological responses of shelter dogs to long-term confinement

In Italy, National Law (281/1991) prohibits euthanasia of shelter dogs if they are not dangerous or suffering seriously. Adoption rates in rescue shelters are often lower than entrance rates, leading inevitably to overcrowded facilities where animals are likely to spend the rest of their lives in kennels. In this situation, housing conditions (i.e. space provided, environmental, and social stimulation) may have an impact on canine welfare. In this research project, the effects of two different forms of housing (group- and pair housing) on long-term shelter dogs were compared using behavioural and physiological parameters. Observational data and saliva samples were collected from dogs exposed to both experimental settings; behaviour and cortisol concentration levels were used as welfare indicators. Pair housing offered fewer social and environmental stimuli and behavioural analysis showed a significant decrease in locomotor, exploratory, and social behaviour. Cortisol levels show that this parameter varied independently of housing conditions. Although this study found no evidence suggesting that one form of confinement reduced animal welfare more than the other (e.g. in terms of abnormal behaviour, or higher cortisol concentrations), the type of confinement did affect the expression of a variety of behaviours and these variations should not be ignored with respect to housing decisions for long-term shelter dogs.

Temperament test for re-homed dogs validated through direct behavioral observation in shelter and home environment

This study was the first attempt to carry out a validation of a temperament test (TT) for shelter dogs that addressed the topics of inter- and intra-raters agreements, test-retest reliability, and validity. The TT consisted of 22 subtests. Each dog was approached and handled by an unfamiliar person and made to interact with a same- and an opposite-gender conspecific. Dogs were tested twice in the shelter and once in their new homes 4 months after adoption to evaluate consistency in behavioral assessment. Playfulness, trainability, problem solving abilities, food possessiveness, and reactivity to sudden stimuli were also evaluated. Testers scored dogs' responses in terms of confidence, fearfulness, and aggressiveness. Results highlighted strengths and limits of this TT that was devised to help shelter staff in matching dogs' personality and owners' expectations. Methodological constraints when working with sheltered dogs are unavoidable; however, the test proved to be overall feasible, reliable, and valid although further studies are needed to address the critical issues that emerged. © 2011 Elsevier Inc.

Agility and search and rescue training differently affects pet dogs' behaviour in socio-cognitive tasks

Both genetic factors and life experiences appear to be important in shaping dogs' responses in a test situation. One potentially highly relevant life experience may be the dog's training history, however few studies have investigated this aspect so far. This paper briefly reviews studies focusing on the effects of training on dogs' performance in cognitive tasks, and presents new, preliminary evidence on trained and untrained pet dogs' performance in an 'unsolvable task'. Thirty-nine adult dogs: 13 trained for search and rescue activities (S&R group), 13 for agility competition (Agility group) and 13 untrained pets (Pet group) were tested. Three 'solvable' trials in which dogs could obtain the food by manipulating a plastic container were followed by an 'unsolvable' trial in which obtaining the food became impossible. The dogs' behaviours towards the apparatus and the people present (owner and researcher) were analysed. Both in the first 'solvable' and in the 'unsolvable' trial the groups were comparable on actions towards the apparatus, however differences emerged in their human-directed gazing behaviour. In fact, results in the 'solvable' trial, showed fewer S&R dogs looking back at a person compared to agility dogs, and the latter alternating their gaze between person and apparatus more frequently than pet dogs. In the unsolvable trial no difference between groups emerged in the latency to look at the person however agility dogs looked longer at the owner than both pet and S&R dogs; whereas S&R dogs exhibited significantly more barking (always occurring concurrently to looking at the person or the apparatus) than both other groups. Furthermore, S&R dogs alternated their gaze between person and apparatus more than untrained pet dogs, with agility dogs falling in between these two groups. Thus overall, it seems that the dogs' human-directed communicative behaviours are significantly influenced by their individual training experiences. © 2009 Elsevier B.V. All rights reserved.

Comparing lateral bias in dogs and humans using the KongTM ball test

The KongTM ball test has been used extensively to assess lateral bias in the domestic dog. Implicit in this challenge is the assumption that dogs use their dominant paw to stabilise the ball. This study examined whether or not this is the case. A comparative approach was adopted, exploring limb use in dogs and humans. In Experiment 1, the paw preference of 48 dogs was assessed on the KongTM ball test. Analysis revealed an equal distribution of paw use, although significantly more dogs were paw-preferent than ambilateral. Significantly more male dogs were classified as right-pawed, while more females were ambilateral. There was no significant effect of canine sex or castration status on the dogs’ paw preferences. In Experiment 2, 94 adult humans were assessed on their ability to remove a piece of paper from a KongTM ball with their mouth, using their left, right or both hands to stabilise the ball. 76% of the right-handed people used their left hand, and 82% of the left-handed participants used their right hand, to hold the KongTM steady. It is concluded that dogs, like humans, are most likely using their non-dominant limb to stabilise the KongTM ball and their dominant side for postural support. This has potential applied implications from an animal welfare perspective.