Posture estimation for a canine machine interface based training system

Abstract

Dogs and humans have worked in partnership throughout history thanks to dogs' unique capability of detecting signals in human voices or gestures and learning from human inputs. Traditional canine training methods rely solely on subjective visual observations made by trainers. We propose a canine body-area-network (cBAN) to incorporate context-aware sensing with objective detection algorithms to augment the sensitivity and specificity of human trainer's awareness of the dogs they are training. As an initial effort, we developed a Bluetooth-based wireless infrastructure and tested inertial measurement units as cBAN sensor nodes to electronically assess the posture of the dogs. As a result, we were able to optimize the sensor locations and distinguish different postures using the distinct patterns in the measured angles.

Gestural activity recognition for canine-human communication

“…Activities are non-periodic and short in duration. 4. High reliability is required (no false-positives).…”

“…The first, alluded to earlier, attempted to do this as part of an automated training system [4]. By recognizing the dog's posture, it would be possible for the system to determine if the correct action was performed and whether a reward should be dispensed.…”

“…search & rescue or law enforcement) [5]. The field of dog training has also benefited from advances in wearable computing since passive sensors were used to estimate canine posture [4] during training. We propose a combination of these approaches for enhancing intentional communication between working dogs and their human companions.…”

Wearable wireless biophotonic and biopotential sensors for canine health monitoring

“…With the goal of enhancing human-canine interactions, we have developed a canine-body area network (cBAN) that combines wearable sensing technologies and computational modeling to provide handlers and trainers with an accurate estimation of dog behaviors and emotional state [4][5][6] (Fig. 1).…”

Exploring assistive technology for assistance dog owners in emergency situations

“…Brugarolas et al have worked to develop a "canine body area network" employing motion sensors to provide real time feedback about canine behaviour during training [2]. The authors utilized machine-learning algorithms to identify canine posture through wireless inertial sensing with 3-axis accelerometers and 3-axis gyroscopes, in order to improve the welfare of working dogs by monitoring their behavioral patterns.…”