This article first appeared in Digital Edge, The Edge Malaysia Weekly on December 28, 2020 - January 3, 2021
When Inference Tech Sdn Bhd started out close to two years ago, it focused on providing facial recognition technology solutions in Malaysia. But at that time, bigger and more established players in China were gearing up to enter the local market.
Inference Tech’s CEO Izad Che Muda tells Digital Edge that the company hit a roadblock because it was having trouble selling its facial recognition technology solutions locally. “China, being a surveillance state, perfected the technology and it was hard for a start-up like us to compete with them from a technological standpoint and commercial pricing.”
At that time, the company had a health and safety pilot project that was running at Petronas sites called Eyesite. This was a video monitoring technology that had been designed to identify and alert the person in charge when a worker at a specific site is breaking safety rules. For example, at a construction site, Eyesite can detect if a worker is not wearing a helmet or gloves.
Fast forward to early this year when Covid-19 hit and borders were shut. That presented the company with a second chance to make its mark in the local market, thanks to Eyesite.
“Before Covid-19, Eyesite had some traction but the moment Covid-19 hit, the traction increased tenfold because [monitoring systems] became relevant. Facial recognition for attendance purposes was our flagship product, but we pivoted and positioned Eyesite as our flagship product instead.
At the time, the Movement Control Order (MCO) was being lifted and companies were putting in place standard operating procedures (SOPs) to restart operations. Inference Tech decided to extend Eyesite to include a Covid-19 module. Izad says that within two weeks, the team developed a module that was able to detect the usage of face masks, whether people were socially distancing and even temperature checks.
With these features, Izad says the technology can help construction sites monitor and control the situation in the event a Covid-19 outbreak happens onsite. For example, if a large development has 20 blocks under construction and a Covid-19 outbreak happens at only two blocks, the construction company will only need to stop work at those particular blocks, provided that it has proof, which can be obtained by Eyesite.
The company later developed a two-in-one thermal and facial recognition scanner so that companies can record a person’s attendance and temperature simultaneously when they enter the workplace.
“Eyesite is definitely the most in demand this year because of Covid-19,” Izad says.
“Hopefully, our clients will see that AI [artificial intelligence] drones and CCTV cameras will help them reduce risks at worksites and eliminate or reduce work stoppage in the post-Covid-19 world.”
Izad adds that Petronas has continued to show its support for Inference Tech as it is looking to deploy Eyesite at other Petronas sites. This is because Eyesite is able to shave about 10% off Petronas’ budget for safety solutions.
Over the last few months, Inference Tech has been working with Petronas to test out new solutions. The most recent is an automated AI-driven drone surveillance to complement and augment security guards and safety officers on site.
This security-focused solution was put in place to reduce the security guards’ exposure to other people and Covid-19. With the drone, security guards can carry out surveillance and monitoring routines in the safety of their guardhouses.
“With AI, not only can we detect SOP violations but we can help minimise the amount of work security guards and safety officers have to do. For example, if a safety officer’s job requires them to go to the site to detect violations, with our solution, we can minimise or totally eliminate the need to go to the site,” says Izad.
“The end result is twofold. One, they get automated reporting of the violation, and two, they can minimise their risk of contracting Covid-19. This applies to the security guards as well.”
The drone surveillance space has potential, says Izad. The company is currently venturing into CCTV and drone surveillance for private residences and will be carrying out a pilot project to test out the system in this setting.
The company has developed another solution, Cityscape, a smart city and infrastructure management solution. Inference Tech is working with Menteri Besar Selangor (Inc) (MBI Selangor) to modernise and automate Selangor’s road inspection and maintenance workflow.
The systems used by local councils are disjointed and non-centralised, says Izad, and so it adapted Cityscape to InfraSEL [the Selangor infrastructure solution], which will enable the local council workers to detect potholes and other road defects through a dashcam as well as to carry out traffic monitoring.
The system leverages AI, data science, and the internet of things (IoT) to help local councils do their work faster and more cost-effectively. Inference Tech has digitised the processes, starting with the process of collecting or gathering reports from road users.
User complaints via the app and hotlines are collected through Cityscapes. It also scours social media, picking up keywords, location tags and images of complaints.
The next step was to make things easier for the local council workers to identify potholes using a dashcam, says Izad. Inference Tech uses drones and dashcams with its software to identify road defects. The system is automated and will detect and geotag potholes, with a very slim possibility of missing defects.
Izad says following its pilot project, the Selangor government has taken on the company to begin work on 4,000km worth of Selangor state roads in February 2021. A command centre for this initiative has been built in the Selangor State Secretary building.
Izad says he noticed a significant increase in awareness when it comes to AI, machine learning and other deep tech jargon. He says private companies and government bodies are more receptive to fancy, but somewhat unproven technologies. This rise in technological literacy, he believes, is thanks to the pandemic.
“With Petronas specifically, it is receptive because we have established a track record and with that, we can easily approach other units of Petronas. And other companies are more receptive because of our success with Petronas. But more importantly, people are more receptive and know more about AI.
“I notice it in the line of questioning. Instead of the typical ‘What is AI’ query, we get questions like, ‘How much will it cost us to deploy seven drones and five cameras?’ The tech awareness is significantly more noticeable this year and that is a great thing.”
Save by subscribing to us for your print and/or digital copy.