RadarCat: Object Recognition

Nov 10 2016

Last year, Google demonstrated its ‘Project Soli’ radar technology that identifies subtle finger movements using the built in radar. Scientists at University of St. Andrews have now used the Soli developer kit for creating a device called RadarCat, which can identify different types of objects utilizing the Soli sensor, along with recognition software to train and classify different materials and objects, in real time, with very high accuracy.

Beyond human computer interaction, RadarCat also opens up new opportunities in areas such as navigation and world knowledge (e.g., low vision users), consumer interaction (e.g., checkout scales), industrial automation (e.g., recycling), or laboratory process control (e.g., traceability).


More Details


+ Research Paper: http://dl.acm.org/citation.cfm?id=2984515&CFID=692432805&CFTOKEN=24648509

+ Project researchers include: Hui-Shyong Yeo, Gergely Flamich, Patrick Schrempf, David Harris-Birtill and Aaron Quigley

Additional Coverage

- http://www.theverge.com/2016/11/10/13582700/google-soli-radarcat-object-recognition

- http://www.digitaltrends.com/computing/radarcat-machine-learning-radar-sensor-google-soli/

- http://hackaday.com/2016/10/21/radarcat-gives-computers-a-sense-of-touch/

RadarCat: Object Recognition cover image