Detail of the student project

Topic:3D object detection
Department: Skupina vizuálního rozpoznávání
Supervisor:Assia Benbihi
Announce as:Diplomová práce, Bakalářská práce, Semestrální projekt
Description:Box detection is a classic task of computer vision consisting in drawing a rectangular box around an object of interest (a car, a cat, a pedestrian). This is one way to represent the location and the nature of an object in the scene. This later allows high-level systems (e.g. autonomous car, ground robot) to understand the layout of the scene it is navigating in.

There is a significant amount of deep learning solutions that work very well (e.g. Faster R-CNN[2]) and they are provided with open source code using easy-to-use libraries (e.g. Pytorch). The most recent advances are related to 3D object detection. Not only the object is detected in the image, but it is also located in the 3D world which is particularly useful for an autonomous system to navigate around.

The project consists in training a state-of-the-art 3D object detector on a novel dataset (we provide access to GPUs) The resulting network will be integrated into our current research project related to visual localization. The student will also get to work in a research environment and interact with other students and researchers. Don't hesitate to write me if you have questions.
Bibliography:[1] DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection?
Responsible person: Petr Pošík