“3D Pedestrian Tracking”
Supervisor: Martin Moder (main supervisor), Markus Bock
(Chair of Intelligent Systems http://www.is.uni-due.de/ )
martin.moder@uni-due.de
Appointment: expected each Wednesday morning
Room: BC 422
Description:
in summer semester 2020 we offer the master project "Intelligent Systems" with the focus on " Cognitive Robot Systems". The information event will take place on April 22, 2020 at 16:00 online. Access to the stream will be announced via Moodle.
Autonomous (self-driving) vehicles are increasingly being tested on highways and city streets. But there is also a need for robots that can navigate through environments like sidewalks, buildings, and hallways. In these situations, the robots must interact and cooperate with pedestrians in a socially acceptable manner. The "rules of the road" no longer apply – there are no lanes or street signs, and pedestrians don’t use turn signals when cutting through crowds. Here the perception of pedestrians by using selected sensors plays a major role.
The goal of the project is the realization of a pedestrian detection and tracking system with the help of a 3D camera (probably Intel RealSense) and a 2D lidar sensor. The information of both sensors shall be fused, so that pedestrians can be detected and tracked over time in space with the highest possible confidence.
Participating students should show great commitment and enthusiasm for the project idea and enjoy experimenting with different hardware and developing innovative software solutions. The various tasks and questions are worked on in teams.
Conditions of Participation:
The project is aimed at Master students of Applied Computer Science (PO 12, PO 19), Applied Cognitive and Media Science. (PO 14, PO 19) and ISE Computer Engineering (PO 15, PO 19). Programming knowledge (Python, C++) is required. A high degree of self-motivation is required to familiarize oneself with new programming languages and technologies, e.g. ROS (Robot Operating System). Participation in the courses "Cognitive Robot System", "Computer Robot Vision" and " Neurocomputing" is also of great advantage. A high level of commitment and dedication are of great importance for the success of the project.
The number of participants in the practical project is limited to 12 students.