This Japanese IoT company is using computer vision and machine learning to automate daily visual inspections in places without electricity or grid power


Facility management organizations must conduct visual inspections daily, which must dedicate significant time to visiting all inspected sites. These companies want to increase their productivity by adopting IoT devices, but the existing IoT solutions do not meet their needs because most of the sites in the field lack electricity and network access.

LiLz Gauge is a cloud service that enables remote visual inspections of analog gauges using ultra-low power IoT cameras and machine learning. Many machine learning-based systems require extensive data pre-processing beforehand. LiLz Gauge is a deep learning-based computer vision system that does not require consumers to annotate huge volumes of data.

In areas without electricity or grid, LiLz Gauge automates daily eye exams. LiLz Gauge significantly reduces the time required for visual inspections with its LiLz Cam. LiLz Cam are cameras with built-in LTE connectivity, three years of battery life and artificial intelligence algorithms that predict measurement values ​​from acquired photos. It can read circular, semi-circular, and linear gauges, digital and rolling digit or analog displays, and colored warning lights, among others. At no additional cost, a single camera can be used to monitor multiple gauges. Computer vision and machine learning algorithms automatically extract gauge measurements from photographs, and results can be easily validated and corrected if necessary. Captured data can be pushed into current equipment maintenance systems using an API.

This Japanese company recently raised $2.2 million in early 2021. LiLz started with basic building management, but has since expanded to include chemical and industrial plants, construction and manufacturing sites, steel mills, public infrastructure like roads and other areas.

The company continuously updates its technology. They mainly refined the software, making it more easily updatable remotely, improving accuracy and robustness to disturbances, and adding data sharing and other functions. They also develop new products and technologies for functions such as sound search and counting of items in the camera’s field of view, monitoring of floats and level gauges, etc.



About Author

Comments are closed.