Achieve actionable insights at scale and speed.
Collect and process visual media at scale with AI. Using AI vastly reduces costs while improving efficiency and outcomes.
Clients & Partners
Scale Processes and Reduce Costs with Machine Learning and AI
We collect and process imagery at scale and speed; extracting objects of interest as well as determining their state. This enables customers to reduce costs, massively scale what they do and unearth hidden insights and knowledge.
Our technology is being used for condition assessment of utility assets, for generating ecological surveys of transport corridors and assuring the outcomes of innovative manufacturing processes.
% Reduction in cost when using our AI for Ecological Surveys
Images processed using the KAI Platform for clients
FEATURED IN:
Recent Solutions
Ecological Surveys
We have developed a vehicle mounted solution for collecting high resolution imagery of roadside vegetation. AI is then used for detecting the presence of invasive plant species or Ash trees.
This provides a rapid, high quality vegetation survey methodology, resulting in cost and time savings for our customers.
Condition Assessment
The Keen AI platform (KAI) extracts key components from footage collected by helicopters or drones and presents them for review to a condition assessment engineer. Reducing assessment time by 66%.
This video shows the application of the background deep learning model used to extract components being applied to a sample video of a single conductor suspension tower in real time.
Corrosion Detection
Corrosion is an ever present issue for electricity transmission and distribution assets. Keen AI combined traditional computer vision techniques and convolutional neural networks in order to identify candidate regions where corrosion maybe present.
Bespoke edge detection algorithms are used in a follow up step identifies regions of the image likely to contain steel and thereby separate background from tower.
Eliminated 25% of towers from the manual review process by marking them as clean.
Manufacturing Quality Assurance
Leaks in a hollow silicon membrane are identified by passing air through the fibre and submerging it. Bubbles appear at the site of an imperfection.
Keen AI developed fast computer vision based tools to highlight areas in the scene where leaks are present and present to a human who can repair the leak. The factory environment is very noisy with the additional complication of uneven lighting.
Increase Efficiency, Improve Outcomes and Reduce Costs with Machine Learning
Our Services
Our technology and expertise to help your organisation use machine vision and artificial intelligence to augment and transform processes.
Engineering Processes to Augment Humans with AI
Many organisations aim to deploy AI and machine learning to augment processes. For this to be successful, processes should be redesigned, taking advantage of the strengths of humans vs. machines, the weaknesses of each and how both can be combined to complement each other. Our team has years of experience of working with organisations and businesses to help them develop and successfully adopt AI augmented processes.
Successfully Incorporating AI into Systems and Processes
Building a proof of concept is achievable in a short timescale. Getting production-ready requires more effort and needs skills outside of traditional Data Science. Keen AI Dev Ops take models and develop applications and the APIs required to use them. We also manage deployments to in-house or cloud infrastructure.
KAI Platform
The vast majority of processes that use visual data or imagery have the same meta-process. Footage is collected, footage is then reviewed by an expert and then the insight generated from the review is shared with other people, processes or systems. Keen AI has created the KAI platform, a flexible cloud-hosted solution for running this meta-process. It’s currently being used for numerous applications, from ecological surveys to condition assessment of powerlines. KAI makes it easy to upload data once it’s been collected, augment human experts with AI (by for example identifying species or components) and continually learns from the actions taken by a human thereby improving over time.
Image Labelling and Synthetic Data Creation
Deep learning relies upon large, representative and well-labelled training data. Keen AI is able to label real data cost-effectively to a very high standard. If insufficient real data is available, we can generate synthetic data from natural scenes.
Model Training and Development
Keen AI has developed deep learning computer vision models for many of our customers. Our team will work with you to create robust models that are able to accurately and reliably perform at the levels required for a successful outcome.
Latest Reads
Join Our Team
Artificial Intelligence and Computer Vision are changing the world at an ever increasing pace. By applying these technologies we help our customers collect, organise, share and understand their visual data . Imagination, skill, hard work and sense of curiousity drive
Creating a Neural Network for Identifying Himalayan Balsam From Roadside Images
At the start of 2020 we didn’t know if it would be possible to collect images of the required quality for an AI based approach to work. What we’ve found is that, yes, it can work. We built a system
Canon and Keen AI work together on AI and Imaging Projects
At Keen AI we create systems which augment process experts, for example ecologists or engineers, with machine learning and AI. Our focus is video or stills processing at scale. At the outset we didn’t intend to collect footage or build
Combining AI with your process expertise can be immensely powerful in delivering efficiencies, improving outcomes and reducing costs.
Talk to us about your business process today and discover how AI can help.
DScience Ltd © 2021 | The Moseley Exchange, 149-153 Alcester Road, Birmingham. B13 8JP