A vehicle recognition technology for traffic surveillance developed by South Korea's Electronics and Telecommunications Research Institute (ETRI) won an international contest. ETRI announced that its researchers ranked first and third respectively, in the vehicle detection section of the international competition hosted by Advanced Video and Signal-based Surveillance (AVSS), the world's largest video security conference. The event was held in Auckland, New Zealand, for four days starting from November 27, 2018.
AVSS is the premier annual international conference in the field of video and signal-based surveillance that brings together experts from academia, industry, and government. AVSS is sponsored by the Institute of Electrical and Electronics Engineers (IEEE), in particular the IEEE Signal Processing Society (IVMSP TC) and the IEEE Computer Society (PAMI TC).
The system developed by ETRI utilizes deep learning technology, resulting in an 85.67 percent mean average precision (mAP) rate in recognizing cars on the road. By applying this technology, predicting the direction of vehicles became easier, optimizing traffic signal mechanism. As a result, this technology can dramatically improve the traffic congestion in urban areas.
Aside from winning the AVSS 2018 Challenge, Jong Taek Lee, ETRI's senior researcher, presented a paper on deep learning-based vehicle detection technology at AVSS 2018's IWT4S, attracting significant attention from researchers in relevant fields. The technology introduced in the paper concerned a new method in video analysis environment, which contributed to achieving best record in the competition.
###
About Electronics and Telecommunications Research Institute (ETRI)
ETRI is a non-profit government-funded research institute.
Since its foundation in 1976, ETRI, a global ICT research institute, has been making its immense effort to provide Korea a remarkable growth in the field of ICT industry.
ETRI delivers Korea as one of the top ICT nations in the World, by unceasingly developing world's first and best technologies.