
J.F.P. (Julian) Kooij
J.F.P. (Julian) Kooij
Profiel
Biografie
Julian Kooij (1982) is an Assistant Professor at the
Intelligent Vehicles group, performing research and education on autonomous driving and vehicle perception. The group is part of the
Cognitive Robotics (CoR) department of the 3ME Faculty.
His research interests include statistical machine learning and probabilistic inference for sensor processing (computer vision), environment understanding, and predictive models of Vulnerable Road User (VRU) behavior. Good predictive models of VRU behavior are essential for automated vehicles to guide their decision making and trajectory planning. This is especially true for the challenging urban environment, where interactions with VRUs are frequent.
Before joining 3ME, he was a PostDoc at the
pattern recognition and computer vision lab of the EWI Faculty of TU Delft. In this period, he collaborated on setting up the new
Technology In Motion (TIM) lab at Leiden University Medical Hospital, and developed new signal processing techniques to detect subtle tremors in patients. His PhD at the University of Amsterdam addressed automated analysis of pedestrian tracks, using probabilistic graphical models for unsupervised learning and online predictive Bayesian inference.
In 2013 he interned at Daimler AG in Ulm, Germany. There, he worked on improved pedestrian path prediction for intelligent vehicles, exploiting various contextual cues such as pedestrian head orientation and location relative to the road. During the NWO Cassandra and EU-FP7 ADABTS projects, graphical models were developed for the integration of audio-visual cues, and for anomaly detection, in surveillance applications.
Projecten
Expertise
Publicaties
-
2022
Cross-modal distillation for RGB-depth person re-identification
Frank M. Hafner / Amran Bhuyian / Julian F.P. Kooij / Eric Granger
-
2022
Fast and Compact Image Segmentation using Instance Stixels
Thomas Hehn / Julian F.P. Kooij / Dariu M. Gavrila
-
2022
Multi-class Road User Detection with 3+1D Radar in the View-of-Delft Dataset
Andras Palffy / Ewoud Pool / Srimannarayana Baratam / Julian Kooij / Dariu Gavrila
-
2021
A Joint Extrinsic Calibration Tool for Radar, Camera and Lidar
Joris Domhof / Julian F.P. Kooij / Dariu M. Gavrila
-
2021
Crafted vs. Learned Representations in Predictive Models - A Case Study on Cyclist Path Prediction
Ewoud Pool / Julian F.P. Kooij / Dariu M. Gavrila
-
Onderwijs 2021
Onderwijs 2020
Media
-
2007-09-07
Public talk and discussion on The Automous Vehicle
Verscheen in: Facebook Event page