Philip Vance

Ulster University · School of Computing and Intelligent Systems

Human activity recognition has been an open problem in computer vision for almost 2 decades. During this time, there have been many approaches proposed to solve this problem, but very few have managed to solve it in a way that is sufficiently computationally efficient for real-time applications. Recently, this has changed, with keypoint-based metho...

Retail shoplifting is one of the most prevalent forms of theft and has accounted for over one billion GBP in losses for UK retailers in 2018. An automated approach to detecting behaviours associated with shoplifting using surveillance footage could help reduce these losses. Until recently, most state-of-the-art vision-based approaches to this probl...

The retina acts as the primary stage for the encoding of visual stimuli in the central nervous system. It is comprised of numerous functionally distinct cells tuned to particular types of visual stimuli. This work presents an analytical approach to identifying contrast-driven retinal cells. Machine learning approaches as well as traditional regress...

Artificial vision using computational models that can mimic biological vision is an area of ongoing research. One of the main themes within this research is the study of the retina and in particular, retinal ganglion cells which are responsible for encoding the visual stimuli. A common approach to modelling the internal processes of retinal ganglio...

Obstacle avoidance is a critical aspect of control for a mobile robot when navigating towards a goal in an unfamiliar environment. Where traditional methods for obstacle avoidance depend heavily on path planning to reach a specific goal location whilst avoiding obstacles, the method proposed uses an adaption of a potential fields algorithm to succe...

Determining the location of individuals within indoor locations can be useful in various scenarios including security, gaming and ambient assisted living for the elderly. Healthcare services globally are seeking to allow people to stay in their familiar home environments longer due to the multitude of benefits associated with living in non-clinical...

This paper describes the application of a Convolutional Neural Network (CNN) in the context of a predator/prey scenario. The CNN is trained and run on data from a Dynamic and Active Pixel Sensor (DAVIS) mounted on a Summit XL robot (the predator), which follows another one (the prey). The CNN is driven by both conventional image frames and dynamic...

The processing capabilities of biological vision systems are still vastly superior to artificial vision, even though this has been an active area of research for over half a century. Current artificial vision techniques integrate many insights from biology yet they remain far-off the capabilities of animals and humans in terms of speed, power, and...

This paper describes the application of a Convolutional Neural Network (CNN) in the context of a predator/prey scenario. The CNN is trained and run on data from a Dynamic and Active Pixel Sensor (DAVIS) mounted on a Summit XL robot (the predator), which follows another one (the prey). The CNN is driven by both conventional image frames and dynamic...

Traditionally, it has been assumed that the important information from a visual scene is encoded within the average firing rate of a retinal ganglion cell. Many modelling techniques thus focus solely on estimating a firing rate rather than a cells temporal response. It has been argued however that the latter is more important, as intricate details...

Determining the structure and size of a retinal ganglion cell’s receptive field is critically important when formulating a computational model to describe the relationship between stimulus and response. This is commonly achieved using a process of reverse correlation through stimulation of the retinal ganglion cell with artificial stimuli (for exam...

Robotic ecologies are networks of heterogeneous robotic devices pervasively embedded in everyday environments, where they cooperate to perform complex tasks. While their potential makes them increasingly popular, one fundamental problem is how to make them both autonomous and adaptive, so as to reduce the amount of preparation, pre-programming and...

Robotic ecologies are systems made out of several robotic devices, including mobile robots, wireless sensors and e�ectors embedded in everyday environments, where they cooperate to achieve complex tasks. This paper demonstrates how endowing robotic ecologies with information processing algorithms such as perception, learning, planning, and novelty...

Current approaches to networked robot systems (or ecology of robots and sensors) in ambient assisted living applications (AAL) rely on pre-programmed models of the environment and do not evolve to address novel states of the environment. Envisaged as part of a robotic ecology in an AAL environment to provide different services based on the events a...

Determining the location of individuals within indoor locations can be useful in various scenarios including security, gaming and ambient assisted living for the elderly. Healthcare services globally are seeking to allow people to stay in their familiar home environments longer due to the multitude of benefits associated with living in non-clinical...

In an ambient assisted living environment, raw data can often be very noisy making is difficulty to interrupt by a decision and reasoning system. To help reduce the effects of noise, we propose a decision and reasoning system which combines an interval fuzzy system and a self-organising fuzzy neural network (SOFNN) is presented in this paper. The m...

Determining the location of individuals 'within indoor locations can be useful in var- ious scenarios including security, gaming and ambient assisted living for the elderly. Healthcare services globally are seeking to allow people to stay in their familiar home environments longer due to the multitude of benefits associated with living in non-clini...

Determining the location of individuals within indoor locations can be useful in various scenarios including security, gaming and ambient assisted living for the elderly. Healthcare services globally are seeking to allow people to stay in their familiar home environments longer due to the multitude of benefits associated with living in non-clinical...

Determining the location of individuals within indoor locations can be useful in various scenarios including security, gaming and home assistance. The domain of home assistance also includes caring for the elderly. Healthcare services globally are seeking to allow people to stay in their familiar home environments longer due to the multitude of ben...

GPS currently provides accurate localisation for external applications however it fails to function internally due to the direct line-of-sight requirement by satellites. This exposes a need to produce a reliable, low cost, accurate system for internal use. As with GPS, internal localisation signals suffer from attenuation, reflection, refraction an...