Z-ENG: Object Detection Using Radar Data Points

Félév: 2024-2025 ősz

Kategória: Nincs megadva

Téma leírása

In the automotive industry, radar devices have been used for decades, emitting radio frequency signals and detecting them to measure the speed and distance of objects ahead of a vehicle. This information is later utilized by driver assistance functions available in modern cars, such as adaptive cruise control, emergency braking assistance, or blind-spot monitoring systems.

Autonomous and driver assistance systems typically associate and fuse signals from radar devices with signals from other sensors of different modalities to obtain redundant information about the current environment state. Radar interface signals span a wide spectrum, ranging from modulated signals detected by individual receiver antennas to pre-processed signals grouped into objects. The process of object detection is multi-step and fundamentally shapes the use of these devices in later driver assistance functions.

The student's task involves the implementation and quantitative evaluation of an algorithm that uses publicly available radar datasets at the lowest possible level to group points and provide object-level output. The task includes reading, processing, grouping, and applying noise filtering to data points within a list of tracked objects in both time and space.

To solve this task, the student will receive assistance from the employees of the Continental AI Development Center.

If you are interested in the topic, be sure to contact Dávid Sik by email before applying, indicating the selected topic, training level, major and the planned project subject.

Külső partner: Continental Autonomous Mobility Hungary

Maximális létszám: 1 fő