Tag Archives: Dr Grzegorz Cielniak

Computer vision and mobile technology could help blind people ‘see’

Computer scientists are developing new adaptive mobile technology which could enable blind and visually-impaired people to ‘see’ through their smartphone or tablet.

Funded by a Google Faculty Research Award, specialists in computer vision and machine learning based at the University of Lincoln, UK, are aiming to embed a smart vision system in mobile devices to help people with sight problems navigate unfamiliar indoor environments.

Based on preliminary work on assistive technologies done by the Lincoln Centre for Autonomous Systems, the team plans to use colour and depth sensor technology inside new smartphones and tablets, like the recent Project Tango by Google, to enable 3D mapping and localisation, navigation and object recognition. The team will then develop the best interface to relay that to users – whether that is vibrations, sounds or the spoken word.

Project lead Dr Nicola Bellotto, an expert on machine perception and human-centred robotics from Lincoln’s School of Computer Science, said: “This project will build on our previous research to create an interface that can be used to help people with visual impairments.

“There are many visual aids already available, from guide dogs to cameras and wearable sensors. Typical problems with the latter are usability and acceptability. If people were able to use technology embedded in devices such as smartphones, it would not require them to wear extra equipment which could make them feel self-conscious. There are also existing smartphone apps that are able to, for example, recognise an object or speak text to describe places. But the sensors embedded in the device are still not fully exploited. We aim to create a system with ‘human-in-the-loop’ that provides good localisation relevant to visually impaired users and, most importantly, that understands how people observe and recognise particular features of their environment.”

The research team, which includes Dr Oscar Martinez Mozos, a specialist in machine learning and quality of life technologies, and Dr Grzegorz Cielniak, who works in mobile robotics and machine perception, aims to develop a system that will recognise visual clues in the environment. This data would be detected through the device camera and used to identify the type of room as the user moves around the space.

A key aspect of the system will be its capacity to adapt to individual users’ experiences, modifying the guidance it provides as the machine ‘learns’ from its landscape and from the human interaction. So, as the user becomes more accustomed to the technology, the quicker and easier it would be to identify the environment.

The research team will work with a Google sponsor and will be collaborating with specialists at Google throughout the ‘Active Vision with Human-in-the-Loop for the Visually Impaired’ project.

Below is an interview with Dr Bellotto on BBC Radio Lincolnshire:

A PhD position is now available to work on this project. Click here for further details.

The role robotics could play in future food production

A team of computer scientists from the University of Lincoln, UK, is co-organising an international workshop on recent advances in agricultural robotics.

Academics from the Lincoln Centre for Autonomous Systems (L-CAS) will be attending the 13th International Conference on Intelligent Autonomous Systems (IAS-13) from 15th to 19th July, 2014.

Recent results confirm that robots, machines and systems are rapidly achieving intelligence and autonomy, mastering more and more capabilities such as mobility and manipulation, sensing and perception, reasoning and decision making.

The Series of International Conference on Intelligent Autonomous Systems (IAS) founded in 1986 is one of the major events summarising this trend.

As part of this year’s conference Lincoln scientists will be running a workshop with the aim of bringing together both academic and industrial communities to discuss recent advances in robotic applications for agriculture and horticulture.

The world’s rapidly growing population brings new challenges for global food security. To meet the future demand for more, cheaper and better quality food, new and innovative solutions and improvements to current agricultural practices are required. Agricultural robotics is one of the promising technological solutions for addressing these problems.

Dr Grzegorz Cielniak, senior lecturer in the School of Computer Science, said: “The workshop will provide a forum to present the state-of-the-art technical solutions in agricultural robotics and new exciting robotics platforms, but also to encourage future collaborations between the participants.

“Recent examples have shown agricultural robotics autonomously performing a number of different agricultural tasks, from monitoring soil and crop properties and harvesting fruit in orchards, to mechanical weeders eliminating the need for herbicides to produce affordable, safer food. Using teams of small specialised agricultural robots instead of the currently used heavy machinery can result in lower soil compaction leading to energy savings, but also in more robust systems in the case of technical failures. The number of potential new applications is enormous.”

Projects involving L-CAS include a 12-month feasibility study, funded by a £132,000 grant from the Technology Strategy Board, to create a system of laser sensors to accurately control agricultural sprayers.

Other tasks include the creation of new multi-purpose imaging technology to undertake quality inspection tasks in the food industry; automatic identification of potato blemishes and improvements in the seal integrity of heat-sealed packaging.

The workshop is supported by IEEE Robotics and Automation Society Technical Committee on Agricultural Robotics & Automation and is a continuation of previous agricultural robotics events held as part of IROS2012 and ICRA2008 conferences.

IAS-13, which is taking place in Padova, Italy, invites researchers, engineers and practitioners to disseminate their achievements and provides them with a forum to exchange their ideas.

Agricultural robotics helping to meet the demand for future food production
Agricultural robotics helping to meet the demand for future food production

New group’s research to improve food production

Safer food, less waste, more efficient food production and better use of natural resources are just some of the goals inspiring the work of a new research group at the University of Lincoln, UK.

The Agri-Food Technology Research Group aims to develop new technological solutions for all stages of food production including cultivation, harvest, processing and packaging.

Agri-food is the largest industry in Lincolnshire and food security is also one of the major challenges identified by the UK Research Councils. Demand for food will grow by 40 per cent by 2030 and 70 per cent by 2050. The challenge is to meet this demand in ways that are environmentally, socially and economically sustainable, and in the face of global climate change.

Research in this area undertaken by Lincoln academics has already resulted in links with local, national and global agri-food industry obtaining more than £500,000 in government and industry support.

Group leader Professor Tom Duckett, from the School of Computer Science, said members would continue to work with industry in tackling challenges faced in the real world.

He said: “Agriculture and food production is not only a major part of our local industry – it’s also vital to the health and happiness of people everywhere. As a young person growing up in Lincolnshire, I worked in various different jobs in fields and food factories, where I learned that the human element of food production is also really important. This technology is not about replacing human workers, but about giving them new tools to help produce more and meet the challenges of feeding a growing population.

In our previous research, we have developed new technologies such as sensory systems that enable robots to build 3D maps of their environments and trainable vision systems for inspecting food products. This new research group is about bringing these cutting edge technologies together and applying them to new areas of food production, especially through our links with the local and international agri-food industry. For instance, many of the sensing technologies that were developed originally for small-scale mobile robots as laboratory prototypes now have the potential to be applied in agricultural vehicles in the real world for improving food cultivation and harvesting.”

Together with colleague Dr Grzegorz Cielniak, Professor Duckett has already begun a 12-month feasibility study, funded by a £132,000 grant from the Technology Strategy Board, to create a system of laser sensors to accurately control agricultural sprayers.

Another project being carried out with the Processors and Growers Research Organisation (PGRO) and Frontier Agriculture aims to analyse field beans for the presence of specific pest and larval damage. The study will review, test and develop computer state of the art vision algorithms suitable for detecting, selecting and classifying the beans most effectively.

Other tasks include the creation of new multi-purpose imaging technology to undertake quality inspection tasks in the food industry; automatic identification of potato blemishes and improvements in the seal integrity of heat-sealed packaging.

More research and development work in the group is focussed at the National Centre for Food Manufacturing (NCFM) – the specialist campus of the University of Lincoln working with food manufacturing businesses. Work at the NCFM includes studies carried out for the Food Standards Agency, DEFRA and WRAP as well as projects for the centre’s partners and clients. The focus of the work is around food safety and shelf life extension as well as processing and packaging systems.

The Agri-Food Technology Research Group is keen to work with local, national and international businesses and organisations to solve problems relevant to them and their industry. They can be contacted by e-mailing tduckett@lincoln.ac.uk