Introduction and goals of this thesis

Maps contain important information to navigate and route vehicles. For autonomous vehicles this information about the surrounding has to be highly accurate and current to directly interpret and evaluate the surrounding, measured by sensors. The richer the information is, the better a vehicle can judge the situation, predict next steps and react. The surrounding of the vehicle can significantly influence the driving situation. Which conditions lead to unsafe driving behavior is not always clear. Therefore, it is important to investigate how such situations can be reliably detected, and then search for their triggers. It is conceivable that such insecure situations (e.g near-accidents, u-turns, avoiding obstacles) are reflected, for example, as anomalies in the movement trajectories of road users. Collecting real world traffic data in driving studies is very time consuming and expensive. On the other hand, a lot of roads or public areas are already monitored with video cameras. In addition nowadays more and more of such video data is made publicly available over the internet so that the amount of free but low quality video data is increasing. This research will exploit the use of such kind of opportunistic VGI.

As basis for further research, the aim of this work therefore is to test and evaluate different object detection methods (at least background subtraction, Faster R-CNN) on provided surveillance video data. Afterwards the detections have to be aggregated to road user trajectories (e.g. with an extended kalman filter).

Desirable the methods should be implemented into an already existing processing pipeline to extract road user trajectories from surveillance video da

Tasks

1.   Literature research and introduction into relevant algorithms, the provided data as well as the existing surveillance video pipeline

2.   Optional: Search for or generate own test and evaluation (labeled ground truth) data  

3.   Implement (adapt, tune, train,…) different (at least two) current state of the art object detection methods as well as a tracking algorithm.

4.   Detailed systematic evaluation by comparing the used methods

5.   Documentation and presentation of the results

Tools

►    Surveillance video data of static scenes

►    If required, provision of a (powerful) desktop PC with a GPU

Requirement

►    Programming knowledge (e.g Python)

►    Knowledge in the field of computer vision and machine learning useful

Contact

►    Christian Koetsier (christian.koetsier@ikg.uni-hannover.de, 0511 762-2472)

►    Prof. Dr.-Ing. habil. Monika Sester (monika.sester@ikg.uni-hannover.de, 0511 762- 3588)

►    Institute of Cartography and Geoinformatics, Appelstraße 9a, 30167 Hannover, room 616