RoboK


NEWS


Cambridge start-up receives $2.1M for AI industrial computer vision


C


ambridge-based start-up RoboK has received $2.1m funding


to develop its industrial computer vision solutions. Te Cambridge University


spin-out applies artificial intelligence in CCTV cameras to help logistics operators, such as large ports, warehouses, and sortation hubs, to prevent safety hazards and delays, as well as making operations more efficient inside facilities. By turning passive video into


actionable intelligence, the firm says it can enhance safety and efficiency at large-scale infrastructure sites. Te series A investment


round brings the firm’s total funding to $4m to date, and will help it connect to sites such as ports and other industrial infrastructure. RoboK also plans


to hire additional commercial and product roles to support its growth plans. “Our technology has the


potential to revolutionise the entire infrastructure industry and we are starting with ports,” said Hao Zheng, co-founder and CEO at RoboK. “Tis is especially significant for the UK, as 95% of all UK imports and exports are transported by sea. We are committed to making it accessible to as many workplaces with existing industrial CCTV cameras as possible. “Supported by strong research


expertise, our solution stands out in our ability to provide accurate and robust AI insights at scale and cost-effectively. Our team has built an easily configurable solution that can address the many key challenges of our customers and we are


Today’s Machine Vision News: CoaXPress supports fiber BitFlow announces the Claxon-Fiber


Hao Zheng, co-founder and CEO of RoboK


excited to use this funding to continue our journey of making industrial workplaces safer and more efficient.” Te Bristol Port Company, one of RoboK’s customers, said it saw a reduction of more than 90% in potential safety incidents after three months. David Brown, CEO of the Bristol Port


Company, said: “I have been extremely impressed by the insights, data and detail we have gained from this cutting-edge technology. Tere are clearly huge opportunities for all UK ports to collaborate and benefit from what we have learned; without question we now run a safer operation.”


AI vision software helps fight wildfires


A Silicon Valley-based start-up has developed a tool that uses artificial intelligence (AI) to help fight wildfires. By linking its fire detection


software to a camera network used in California for wildfire detection, Chooch – a vision software provider – said it reduced false positives from 2,000 a week to eight. False positives can be


caused by fog, rain, and smudges on the lenses of the camera network, but as the new generative AI model analyses snapshots every 15 minutes, it can more accurately identify signs of smoke or fire. In the California wildfires of 2020, almost 10,000 wildfires burned through 4.3m acres of forest.


• Four fiber optic links, each carrying 12.5 Gb/S • Supports one to four cameras • CoaXPress 2.0 compliant • Standard QSFP+ cage • PCIe x8 Gen3


www.bitflow.com “With the 2020 wildfires,


it became very personal, so we asked fire officials how we could help,” said Emrah Gultekin, CEO of Chooch. Michael Lou, President of Chooch, added: “Fire chiefs were excited about launching the technology in their


monitoring centres and what it could achieve.” Stopping just one fire from


spreading out of control would pay for the wildfire detection system for 50 years, Chooch estimates. For reference, the California wildfires caused $19bn in losses in 2020. The AI tool gives firefighters


in California’s Kern County a dashboard on their smartphones and PCs, populated in real time with alerts, so they can detect wildfires quickly. “The fusion of large language models and computer vision will bring about even more powerful and accurate products that are easier to deploy,” said Gultekin. The company has its eye


on other applications too. For example, the software can be connected to drones and fixed cameras to detect corrosion on capacitors or vegetation encroaching on power lines. One manufacturer also uses its models to detect product defects, Chooch said.


@imveurope | www.imveurope.com


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32