Kawasaki Geological Engineering Co. Ltd. and Fujitsu Limited have announced that Fujitsu’s AI engine is going to be leveraged to develop subsurface cavity survey technology. With the aim to detect underground cavities more accurately, the technology will be rolled out in summer 2017. 

 

Kawasaki Geological Engineering is using Fujitsu’s deep learning platform service to analyze and process the huge volume of radar images collected with underground radar probe equipment. This will increase the efficiency of search for underground cavities which earlier required expert technicians to make visual determinations.

 

 

Moreover, by connecting this technology with Fujitsu’s Traffic & Road Data Service, it would be easy to understand the position of cavities beneath road surfaces. This, in turn, would make the necessity of road repairs clear to the government.

 

In Japan, 3,300 incidents of collapse take place every year due to the cavities found under road surfaces. The primary cause for these collapses is aging sewer pipes located about 3 meters underground. In order to address the issue, Kawasaki has developed underground radar probe equipment that works up to 5 meters deep. This may significantly improve the reliability of cavity explorations beneath road surfaces going forward.

 

The massive volume of radar images taken with Kawasaki Geological Engineering’s world-leading underground cavity detection technology will be analyzed and processed by using image recognition through the Zinrai Deep Learning platform service launched by Fujitsu. The AI will be trained through machine learning on images where changes in radar reflection are displayed as waveforms, and will then determine whether they are cavities or sewer pipes.

 

Fujitsu is the leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions, and services. Approximately 155,000 Fujitsu people support customers in more than 100 countries.