UWE Bristol’s Centre for Machine Vision (CMV) are the academic partner on an innovative project with Hoofcount to detect early signs of digital dermatitis lesions and lameness within dairy cattle.
Hoofcount is a 10-year-old family business, focusing on how to keep cows’ hoofs clean and healthy. The project is aimed at using machine vision to develop an early detection lameness monitoring system. It has won funding from UK Research and Innovation (UKRI), part of Defra’s Farming Innovation Programme, for feasibility studies combining innovation with research and collaboration with farmers and growers.
Hoof health is a prevalent issue in agriculture, particularly in the dairy industry, as it is one of the main factors leading to poor milk production. Dairy cows are susceptible to a range of hoof issues including Digital dermatitis, sole ulcers, white line disease and overgrown hooves. These generally show a visual change in the underside and back of the hoof. These issues can develop initially without the animal showing visual signs in its gait.
The researcher working on the project is Dr Chollette Olisah, Research Fellow in Computer Vision and Machine Learning in the CMV.
John Hardiman, Software Engineer at Hoofcount explained:
“Lameness is a key issue in dairy herds, with conservative estimates of 25% of dairy cattle suffering from lameness and each lame cow costing more than £300 in loss of production and treatment. The Hoofcount footbath is trusted and recommended by farmers vets and hoof trimmers internationally as they are seeing a continuous fall in lameness on farms using the Hoofcount Automatic Footbath.”
Detecting and treating these issues at an early stage is beneficial to the animal in keeping the hooves healthy and preventing severe lameness which leads to a lower production, increased veterinary and treatment costs, reduced animal welfare, a higher Carbon footprint, and many other issues.
Developing a system that can visualise these changes daily and detect any potential issues early will be of huge benefit to the national herd. Utilising computer vision and machine learning is Hoofcount’s preferred method for monitoring and detecting these issues.
“Collaboration with farmers is core to Hoofcount’s continued innovation and leading reputation in reliable foot-bathing for heard hoof health. Agri-EPI Centre has bolstered our collaboration, with the introduction of The Centre for Machine Vision (CMV) at UWE Bristol and successful application for Innovate UK funding (IUK). CMV has a track record of successful computer vision within agriculture. Agri-EPI has been instrumental in the project funding application and continues to support the project organisation with its network of research farms.”
“As with our automatic footbaths, we know that we will never get rid of Digital dermatitis and hoof health issues completely, however we want to do everything we can to minimise the effects of them and reduce the spread.”
Agri-EPI’s Head of Dairy, Duncan Forbes said:
“This is a great example of the sort of practical collaborations we seek to create, bringing together innovative companies like Hoofcount with leading research experts like the team at CMV at UWE Bristol. Early detection of lameness is vital to meeting the challenge of delivering a substantial reduction in lameness prevalence in dairy herds. UK milk producers will very much welcome the benefits to cow welfare and cost reduction that this emerging technical solution will deliver.”
Wenhao Zhang, Senior Lecturer in Machine Vision at UWE Bristol commented:
“Unique challenges arising from a realistic environment, such as a farm, are often underestimated when developing machine vision solutions to real-world problems. The large set of uncontrollable and dynamic variables in complex scenes cannot be tackled by simply applying tweaks to existing offerings.
Development of on-farm technology needs to be driven by fundamental research examining practical constraints in a bespoke way, in order to produce an innovative approach that is reliable, robust, and practicable. In this project, to solve the problem of object detection and classification ‘in the wild’, the opportunity to co-create this technology with different stakeholders and to informed design choices with the best farming practices and a wealth of inter-disciplinary knowledge is truly invaluable.”
The Centre for Machine Vision (CMV) is part of the Bristol Robotics Laboratory. They solve real-world practical computer vision problems. Their particular excellence lies in three-dimensional reconstruction and surface inspection.