SELFY project partners from CEA presented a new lightweight algorithm for detecting dynamic obstacles at IEEE Sensors Conference 2024, held in Kobe, Japan, on October 20-23.
During a session on Data Processing & AI for Automotive Applications, Tiana Rakotovao, from CEA List Fr, presented the paper titled “Low Complexity Dynamic Obstacle Detection for Intelligent Road Infrastructure”, authored by Tiana Rakotovao, Paul Ménard and Carolynn Bernier.
The article showcases a new lightweight algorithm for detecting the points related to dynamic obstacles within LIDAR point clouds. Thanks to its low complexity, the algorithm can be used either to enable near-sensor embedded functionalities or to enhance the capabilities of intelligent infrastructure in the C-ITS context. The approach was evaluated based on a publicly available real-world dataset.
Within the SELFY project, CEA is contributing with the development of several technologies for cooperative driving such as Trust and Data sharing Tools, TDMS architecture definition & Secure and trustworthy communications, Verification and Validation for secure CCAM systems, and RSU centered Tools for Situational Awareness.
IEEE SENSORS 2024, a flagship conference of the IEEE Sensors Council, provided a forum for research scientists, engineers, and practitioners from academia and industry throughout the world to present their latest research findings, ideas, and applications in the areas of sensors and sensing technologies.
