Difference between revisions of "Object Tracking and Anticipation"

Revision as of 11:04, 23 September 2024

Title	Object Tracking and Anticipation
Summary	The thesis presents an experimental study of different object-tracking and trajectory anticipation algorithms in the context of autonomous driving. The student will analyze how different tracking and anticipation algorithms in scenes with falling snowflakes. Given the detected object bounding boxes, the student will experiment with Kalman Filtering, Extended Kalman Filtering, Particle Filtering, and Deep Learning-based tracking methods.
Keywords
TimeFrame
References
Prerequisites	A solid background in Python and Machine Learning.
Author
Supervisor	Eren Aksoy
Level	Master
Status	Open

@@ Line 1: / Line 1: @@
 {{StudentProjectTemplate
-|Summary=The thesis presents an experimental study of different object-tracking and trajectory anticipation algorithms in the context of autonomous driving. The student will analyze how different tracking and anticipation algorithms in scenes with falling snowflakes. Given the detected object bounding boxes, the student will experiment with Kalman Filtering, Extended Kalman Filtering, Particle Filtering, and Deep Learning-based tracking methods. As a dataset, the student will use CADC together with a custom object detection method. The thesis will be carried out as part of an EU project ROADVIEW.
+|Summary=The thesis presents an experimental study of different object-tracking and trajectory anticipation algorithms in the context of autonomous driving. The student will analyze how different tracking and anticipation algorithms in scenes with falling snowflakes. Given the detected object bounding boxes, the student will experiment with Kalman Filtering, Extended Kalman Filtering, Particle Filtering, and Deep Learning-based tracking methods.
 |Prerequisites=A solid background in Python
 and Machine Learning.