Detecting pain in cats

Feline Friends grantAnalysing cats’ facial expressions could lead to a major breakthrough in helping to alleviate feline suffering.

Computer vision expert Dr Georgios Tzimiropoulos, from the University of Lincoln, UK, has been pioneering the development of self-learning computer vision systems to aid the automatic detection of facial expressions.

Although the focus has been on humans, the technology will now be used to explore emotional expression in cats.

Derbyshire-based charity Feline Friends donated almost £400,000 for the research, which is aimed at detecting suffering earlier and possibly more subtle signs than has previously been possible, so that owners seek veterinary assistance sooner.

The idea is that by feeding the computer images of cats before and after treatment it will eventually start to pick out the key features that differentiate the two conditions.

Dr Tzimiropoulos will work with leading veterinary behaviourist Professor Daniel Mills, from the School of Life Sciences, who has been developing a clinical technique to help behaviourists identify the emotions of companion animals.

Professor Mills said: “This is a rare opportunity to systematically explore the emotional aspects of suffering in animals in new ways, with a view to developing more efficient early detection mechanisms. The multidisciplinary approach we will be using is ambitious, but has the potential to produce enormous rewards not just for those interested in feline welfare, but also animal welfare more broadly, as the methods we will be developing could be applied to any species.

“The translation of our findings into a usable resource is a major part of the project, so we can maximise the impact of our research. We are delighted that Feline Friends has had the courage and vision to make such a substantial investment in this pioneering work. We anticipate the project will take nearly five years to complete, but hope to be making useful contributions from an early stage within the research.”

Caroline Fawcett, of the charity Feline Friends, added: “Helping owners to better understand their feline companions, and the numerous ailments which beset them, has always been a paramount objective of our charity. Cats are notorious for not showing pain until their suffering becomes unbearable, and this visionary research may open our eyes in such a way that we can take much earlier action to relieve their suffering. The team at the University of Lincoln has demonstrated to us that they really do care about improving the welfare of our cats; and I believe that if anyone can succeed in breaking through the existing barriers to our knowledge then they can.”

Smarter video searching and indexing

Saddam BekhetTyping in text to find a film clip on YouTube often results in diverse (and sometimes unrelated) videos being suggested.

This problem could soon be resolved with the advent of smarter video-search engines that are able to pick and choose the most relevant videos by analysing a tiny fraction of video frames.

Research to create a quick and easy framework that is able to discover semantic similarities between videos without using text-based tags is being carried out at the University of Lincoln, UK.

The volume of video data is rapidly increasing with more than 4 billion hours of video being watched on YouTube each month. The majority of available video data exists in compressed format and the first step towards effective video retrieval is to extract features from these compressed videos.

School of Computer Science PhD student Saddam Bekhet, along with Dr Amr Ahmed and Professor Andrew Hunter, has produced a paper on recent work which suggests a framework towards real-time video matching.

Saddam said: “Everyone uses search engines but currently you are only able to search by text even to search for a video clip, thus some results are far removed from what you were looking for. With the huge volume of data, a smarter video analyser is required to associate semantic tags to the uploaded videos, allowing more efficient indexing and search (including the contents of the video). Being able to enhance the underlying search mechanism (or even input a visual query) would really enhance the likes of YouTube.”

Saddam’s framework relies upon finding similarities between videos using tiny frames instead of using the full-size video frames. Such tiny frames are easily extracted from a compressed video in real-time and able to fully represent video content, without wasting more time in decompressing the video to perform complex computer algorithms.

“I want to discover the semantic similarity between videos using the content only,” he explained. “I adapted some new techniques and found that tiny representative frames could be used to discover similarities. The next stage is to build an effective framework.”

The research follows on from work carried out to provide a framework for automated video analysis and annotation, by Lincoln’s Digital Contents Analysis, Production and Interaction (DCAPI) Group.

The paper ‘Video Matching Using DC-image and Local Features’ was awarded the Best Student Paper Award at the International Conference of Signal and Image Engineering - part of the 2013 World Congress on Engineering.
Organised by the International Association of Engineers (IAENG), the conference focuses on the frontier topics in the theoretical and applied engineering and computer science subjects.

 

Bat vision system could help protect buildings

BatsVital data on bat behaviour is being analysed by a computer vision system developed by the University of Lincoln and Lincolnshire Bat Group.

The technique, which uses a high-speed camera, filming in infra-red, is being developed by academics at the University of Lincoln, UK. It monitors wing beat frequency which might enable the Group to classify species of bat.

Being able to identify individual species would provide extra information on how to effectively manage and protect the buildings they inhabit.

Bat populations frequently roost in buildings, such as churches, which can cause problems in terms of corrosive faeces damaging the structure and valuable artefacts.

As a highly protected species, conservation groups are looking for ways in which to control colonies in a non-invasive way.

PhD student John Atanbori and Dr Patrick Dickinson, from the School of Computer Science, developed the system which has been used by the Lincolnshire Bat Group to collect data on a colony which have been rescued and are being re-habilitated.

John said: “This computer vision technique is able to monitor repeated patterns in wing beat frequency. As specie type can be determined from the way a bat moves its wings this provides vital information not only for conservationists studying the animals, but also building managers and professional ecologists. Wing beat frequency is just one feature that could be monitored to determine species, but the project hopes to eventually encompass other features such as the shape and weight of the bat to provide a faster, more detailed classification. We also hope to transfer this research to birds in the future.”

Data is being collected by the Lincolnshire Bat Group, a local arm of the Bat Conservation Trust.

Dr Peter Cowling, from the Group, which is part of the Bat Conservation Trust, said: “To conserve bats we need to establish the size of current bat populations, working out which bats are where and how they are responding to the threats and pressures they face. By monitoring bats we can discover the factors that are important for their survival. We can identify which species need action now, what areas are important for bats and what threats bats face.”

John presented his research at the National Bat Conference at the University of Warwick in September.

He also presented at CAIP 2013 – an international conference devoted to all aspects of computer vision, image analysis and processing, pattern and recognition.

Funded PhD Position – Cognitive Robotics

Using robots to understand animal social cognition:

We are offering a funded PhD position for an enthusiastic and highly-motivated student to join a thriving and dynamic research environment, and benefit from close associations with both the School of Life Sciences and the School of Computer Science.

The aim of this project is to develop a robot that is able to respond dynamically to the behaviour of the focal animal and use it in a series of cognitive experiments. Bearded dragons (Pogona vitticeps) are an ideal model species for such an endeavour. They are responsive to social cues and show sophisticated social learning abilities. In addition they have relatively simple behavioural repertoires and movement patterns which can be accurately replicated by a robotic simulant.

Contact:

For more information and details on how to apply for this exciting opportunity contact Dr. John Murray (jomurray@lincoln.ac.uk)

University of Lincoln, UK