JCK algorithm team won third place in the AMAP-TECH algorithm competition organized by Alibaba-AutoNavi.

December 2020

Recently, the first AMAP-TECH algorithm competition, which lasted for more than two months, was successfully held by AutoNavi, a subsidiary of Alibaba. The competition questions are derived from real scenes that are based on dynamic road conditions analysis of vehicle video images. The road conditions targeted by the competition affect the user's choice of travel routes and methods, but also have important value for traffic management departments and urban planning departments. The judges of the competition include Cha Hongbin, professor of Peking University and director of the Key Laboratory of Machine Perception and Intelligence of the Ministry of Education, Wang Liang, researcher of the Institute of Automation, Chinese Academy of Sciences, and deputy director of the State Key Laboratory of Pattern Recognition, and Li Xiaolong, chairman of the AutoNavi Map Technology Committee.

JCK team finally won third place in this competition. The team leader Shi Nan, a senior algorithm engineer of JCK, innovatively proposed an algorithm model that combines multi-frame image sequences and video keyframes. The team achieved excellent results in both the preliminary and semi-finals, standing out among 880 participating teams and thousands of players across the country, ranking first and third on the two ranking lists, and finally breaking into the finals. In the final defense session, the team introduced the advantages, originality, and stable performance of their algorithms.