{"id":19735,"date":"2024-09-26T12:31:00","date_gmt":"2024-09-26T12:31:00","guid":{"rendered":"https:\/\/dataforpublicgood.org.in\/?p=19735"},"modified":"2025-02-06T14:21:36","modified_gmt":"2025-02-06T14:21:36","slug":"winners-announced-for-the-2024-bengaluru-mobility-challenge-2024","status":"publish","type":"post","link":"https:\/\/dataforpublicgood.org.in\/cdpg\/media-releases\/winners-announced-for-the-2024-bengaluru-mobility-challenge-2024\/","title":{"rendered":"Winners Announced for the 2024 \u2018Bengaluru Mobility Challenge -2024\u2019"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t
\n\t\t\t\t

<\/p>\n

Bengaluru, India \u2013September 26, 2024:<\/strong> The highly anticipated 2024 Bengaluru Mobility Challenge<\/a> concluded successfully at the Symposium on Data for Public Good, 2nd Edition<\/a>, with innovative teams from across the country showcasing data-driven solutions to improve urban mobility in Bengaluru. \u00a0<\/p>\n

The two-phase competition was organised jointly by Bengaluru Traffic Police<\/a> (BTP) and Centre of Data for Public Good (CDPG)<\/a>, which is part of IISc\u2019s Foundation of Science Innovation and Technology. It attracted top talent from universities, startups, and research institutions. The event was part of the IEEE Dataport Competitions<\/strong>, the challenge focused on solving problems related to traffic congestion, improving public transit, and enhancing the overall urban mobility experience in one of India\u2019s largest and most dynamic cities. Participants were tasked with analyzing real-world video data from traffic and Safe City cameras provided by the BTP to solve the following problems.<\/p>\n

In Phase 1, using historical video feeds from 23 Safe City cameras located at junctions in northern Bengaluru as training data, the participants were asked to estimate the cumulative counts of vehicles (by vehicle class and by turning pattern at the junction) in a given 30-minute video clip to the end of the clip and also predict cumulative counts of vehicles by vehicle class from the end time of the clip up to 30 minutes into the future. In Phase 2, using the same training data set, the participants were asked to identify vehicles that originally appeared in one camera and then later appeared in a different camera.<\/p>\n

The competition was hosted on IEEE Dataport<\/a>, while the prizes were sponsored by IEEE Foundation. Some of the statistics related to the hackathon are below:<\/p>\n

\n
\n

Phase 1<\/strong>:<\/p>\n