Deep learning based camera/radar sensor fusion technology for road side unit (RSU) applications
Summary Based on deep learning camera/radar object detection and tracking technology, the proposed road side unit (RSU) system has achieved over 95% vehicle detection accuracy within 100m detection range in the processing performance of 10fps under nVidia Jetson Xavier platform. Compared to the 32-beam lidar based RSU, the proposed RSU achieves 97% reduction of sensor cost that exhibits high competitiveness in deployment cost. The proposed RSU system has been verified in fields and we are now cooperating with an industry partner to deploy the RSU system in both Tainan and Tao-Yuan cities.

The world first multi-scale deep learning object detection technology together with radar point cloud based dynamic ROI selection and an automatic deep learning model pruning tool (ezModel) enables the unique competitiveness of the proposed embedded RSU system, which achieves 95% detection accuracy within 100m detection range at 10fps processing performance. The cost of the RSU system is about $NTD 50,000, which is much more competitive than the 32-beam lidar RSU that cost about $NTD 500,000.

The proposed technology attracted Wistron to launch a four-year investment with annual amount of 10M NTD to setup Wistron-NCTU embedded artificial intelligence research center in NCTU. At the same time, the proposed technology developed in our MOST project also results 12 industrial projects in a total amount of 27.8M NTD investment from local industry. A new start-up is under cultivation to attract the Angel round investment up to 100M-180M NTD and launched by the end of 2021.
Technical Film
Keyword Smart transportation surveillance system#real-time traffic monitoring
More like this
Provide the latest information of AI research centers and applied industries