Canine Pose Estimation: A Computing for Public Safety Solution

Abstract

In this paper we discuss determining canine pose in the context of common poses observed in Urban Search and Rescue dogs through the use a sensor network made up of accelerometers. We discuss the use of the Canine Pose Estimation System in a disaster environment, and propose techniques for determining canine pose. In addition we discuss the challenges with this approach in such environments. This paper presents the experimental results obtained from the Heavy Urban Search and Rescue disaster simulation, where experiments were conducted using multiple canines, which show that angles can be derived from acceleration readings. Our experiments show that similar angles were measured for each of the poses, even when measured on multiple USAR canines of varying size. We also developed an algorithm to determine poses and display the current canine pose to the screen of a laptop. The algorithm was successful in determining some poses and had difficulty with others. These results are presented and discussed in this paper.

Real-Time Detection of the Activity of a Dog

“…We can clearly see differences on frequency on the gyroscope. It confirms the Ribeiro et al [6] hypothesis: result are (highly) dependent on the placement of the sensor. It is difficult to place the sensor at the same position on dogs that have different size and morphology.…”

“…We rapidly decided to use a smartphone on the dog. It has numerous advantages: it is embed a small and powerful processor that already have many built-in devices, like GPS, camera, speaker, sensors, and communication capacities GSM, Bluetooth, Wi-Fi… So unlike Ribeiro et al [6], which use two 1-axis accelerometer , we decided to take advantage of the sensor of the phone, in our case: 3-axis accelerometer, 3-axis gyroscope, 3-axis magnetometer. Figure 2 describe the data flowchart of the presented method.…”

“…We will certainly use GPS on our device but we chose to start with the detection of the activity of the dog. Ribeiro et al [6] proposed a method to detect the pose of USAR dogs. It uses two 1-axis accelerometer to find the poses of USAR dogs.…”

Wearable wireless biophotonic and biopotential sensors for canine health monitoring

“…The use of IMUs combined with GPS has been used for localization and estimation of animal behavior and activity levels in companion animals and livestock [7,8]. These attempts are limited in the set of behaviors that can be detected and none of them offer simultaneous monitoring of vital signs.…”

An assessment of a Wireless Mesh Network performance for Urban Search and Rescue task

“…The CPE device collects acceleration readings and then wirelessly transmits this data to a CPE processor [1,3,4]. Once the data is successfully received by the CPE processor, the CPE algorithm is used to estimate the canine's pose and this is shown to the handler.…”