Although health and safety in the workplace has improved over the years, there are still a large number of workplace accidents happening in the UK and Europe every year.

Most of these accidents can be avoided with the help of AI and computer vision.

In the UK, for example, 1.4 million people suffer from a work-related illness, according to Health and Safety Executive. A total of 111 workers were killed at work in 2019/2020.

581,000 working people sustained an injury at work, according to the Labour Force Survey.

69,208 injuries to employees were reported under RIDDOR.

28.2 million working days were lost due to work-related illness and workplace injury.

AI-based computer vision solutions such as IRIS can help track and predict workplace accidents and thus prevent them from happening.

AI computer vision use cases

Fork lift safety, prediction and prevention of fork lift accidents

Forklift and pedestrian-related risks are identified as one of the major concerns for manufacturing premises, warehouses, yards, depots, etc. Using computer vision, AI algorithm helps observe forklift movement in the defined area. Alarms are raised for incidents and accidents like speeding, movements in the wrong direction, parking in the movement area, pedestrians not using sidewalks, and any other instances of non-compliance that can lead to accidents.

Forklifts alone accounted for 1,300 UK employees being hospitalized last year with serious injuries. Unfortunately, the number is rising due to significant growth in e-commerce, and warehouse space, across the UK and Europe.

Lifting equipment

Computer vision systems can detect the type of lifting equipment used, and identify different types of loads. They can monitor the work the lifting equipment is used for, and provide real time warnings for employees walking/standing under suspended load.

Work at height

AI and computer vision systems can monitor loads on an elevated platform. They can detect PPE and correct equipment usage, over-crowding on scaffolding, and even falling objects. These systems can also monitor entry into exclusion zones.

Fire and thermal injuries and accidents

Computer vision fire detection models are trained to detect fire at an early stage, within 10-15 seconds. Real-time alarms can be integrated with local buzzers, PA systems, display systems, email, SMS, and push notifications. These systems can also detect people stuck in different areas of the site during a fire.

Machine security and safety

Computer vision and AI systems can detect employees in the hazardous zone and provide real-time warnings. The warnings could also be provided to machine operators in case an employee is detected near the machine. AI systems can monitor the level of maintenance, reducing the chance of breakdowns and accidents. The system could also provide real time alerts in case of accidents, reducing the time to provide medical help.

Monitoring use of PPE

Employers have duties concerning the provision and use of personal protective equipment (PPE) at work. AI and computer vision systems can measure compliance and ensure the right PPE equipment is used to protect the user against health or safety risks at work. This includes safety helmets, gloves, eye protection, high-visibility clothing, safety footwear, and safety harnesses. The same systems can monitor the use of respiratory protective equipment, such as masks.

Cost and timelines for deployment

Most workplaces have existing CCTV infrastructure in place. AI and computer vision solutions can be easy and quick to deploy as they can get the feed from existing CCTV cameras. This makes the system a low cost solution with little capital investment.

Subhash is focussed on Artificial Intelligence and Computer Vision. His mission is to get businesses to adopt AI to make workplace safer and efficient. He is doing this by helping companies to leverage their existing CCTV infrastructure and using IRIS, an AI solution to achieve exceptional business insights and outcomes.