autonomous vehicles

Autonomous Vehicles and Sensor Fusion

Topics Cooperative radar-video tracking of pedestrians from a moving vehicle Multimodal vision Radar pedestrian detection using deep learning Low level point cloud processing Object detection and tracking Liborg - Lidar based mapping LIDAR based odometry Automotive occupancy mapping High dynamic range video capture Monocular visual odometry Obstacle detection based on 3D imaging Cooperative radar-video tracking of pedestrians from a moving vehicle Click here for a video by IPI researcher David Van Hamme explaining Cooperative sensor fusion for detection and tracking Click here for an article by IPI researchers David Van Hamme and Jan Aelterman: I Can See Clearly Now! Advanced pedestrian detection using radar-video sensor fusion and automatic tone mapping Autonomous vehicles need to be able to detect other road users and roadside hazards at all times and in all conditions. No single sensor is dependable enough for this task, hence sensor fusion is required.

IPI research on cooperative sensor fusion featured in EOS Science Special on Innovation and Sustainability

Advanced sensor systems bring a future with zero road casualties

Sensor Fusion course at Autosens Academy

IPI contributes a course on Sensor Fusion to AutoSens Academy, the world’s leading community for ADAS and autonomous vehicle technology development

IPI research on automotive vision featured in FierceElectronics

Bringing pedestrian detection for autos to the next level: cooperative sensor fusion and automatic tone mapping

Prof. Wilfried Philips gives a keynote speech at AutoSens in Brussels

Keynote at AutoSens 2019

Information feedback loop for improved pedestrian detection in an autonomous perception system

Environmental perception systems for autonomousvehicles are often built using heterogeneous technologies thatoperate in a sequential manner. In the task of object trackingin particular, where the classical detector-tracker interactionis a serial …

Learning morphological operators for depth completion

Depth images generated by direct projection of LiDAR point clouds on the image plane suffer from a great level of sparsity which is difficult to interpret by classical computer vision algorithms. We propose a method for completing sparse depth images …