Key Performance Indicators (KPIs) are crucial in measuring the effectiveness of an organization's occupational health and safety (OHS) management system. In recent years, computer vision (CV) technology has revolutionized the way OHS KPIs are measured and reported. In this article, we will discuss how CV can be used to measure KPIs more accurately and in real-time, providing data-driven insights that can help organizations improve workplace safety and reduce the number of workplace accidents.
Measurable values, known as Key Performance Indicators (KPIs), are utilized to track progress towards specific business objectives. KPIs are often compared against metrics such as headcount, such as events per 100,000 people, or working hours, such as per one million hours worked, enabling comparison between various organizations or parts of the same organization over time. In a survey of 600 safety specialists, reported accidents and injuries were found to be the most commonly measured safety KPI. However, this is a reactive or lagging measure as it only indicates when something has already gone wrong. Despite this, it remains the most popular KPI as it is easy to measure using traditional methods. With the aid of artificial intelligence, particularly computer vision monitoring of CCTV, it is possible to establish more proactive KPIs that prevent accidents and injuries from occurring in the first place.
According to a recent survey, the second most common KPI in OHS management systems is scores from audits and inspections. However, audits are labor-intensive, and organizations tend to use them infrequently, perhaps once or twice a year. Inspections might be required more often, but they can result in a tick-box exercise – a process to get out of the way on Friday afternoon before you go home.
CV can monitor some items that audits and inspections would look at, but more accurately and in real-time, every day of the year. For example, CV can be configured to identify obstacles in walkways or doors left open. When you do an annual audit, you can compare the data from CV to assess the accuracy of the auditing process.
Counting near misses is another popular form of KPI in OHS management systems. Near miss schemes rely on people to identify and then report things that might have resulted in an accident or injury but did not. However, people often do not report the same near miss repeatedly. Therefore, CV can be consistent and objective about reporting near misses. As well as providing a more accurate KPI, it provides better information for fixing the problem, for example, developing training programmes, improved signage, or altered routes.
According to the Australian Bureau of Statistics, in 2020, the agriculture, forestry, and fishing industry had the highest rate of work-related injury and disease (5,760 per 100,000 workers). The construction industry had the second-highest rate (3,520 per 100,000 workers), followed by the manufacturing industry (2,190 per 100,000 workers). CV technology can be used to improve workplace safety in these industries by providing real-time insights into potential hazards and near misses.
CV can also be used to monitor and measure the effectiveness of safe operating procedures and method statements. By identifying critical points in these steps, organizations can measure these as an early indicator of safe operations. For example, CV could report how often the correct PPE is being worn in the location required, and QR codes linked to a job management system could report on the tools being used. This would provide a leading KPI, indicating how often there was a measurable deviation from the procedure.
A smaller but still substantial number of organizations use the number of employees receiving safety training as a KPI. While training is essential for OHS, attending a training course does not prove someone will apply their learning on the job. A training KPI could be supported by CV. For example, from observation, a safety manager notices some workers over-reach rather than move. Movement ranges are defined, and CV is used to count how often workers over-reach. The problem is widespread. Training is provided. After the training, the over-reaching reduces on the day shift, but not on the night shift. Discussion with the workers identifies that the day-supervisor is supporting the new way of working, while the night-supervisor is still emphasizing speed over caution. The CV provides the information needed to make the training more effective.
In conclusion, poorly set KPIs can have unintended consequences, such as pointless activities or under-reporting of incidents to achieve the right numbers without making the workplace any safer or healthier.
Automated supervision, monitoring and risk prediction in areas of safety, quality and productivity.
