Temporal object detection

Organisatsiooni nimi
Autonomous Driving Lab
Kokkuvõte
Object detection task is commonly formulated within a single image - find all cars or all traffic lights on that image. Single image makes it impossible to classify temporal features of these objects, for example turning signals of the car are blinking or if the current light in the traffic light is blinking. To be able to do that, the neural network performing the detection needs to be temporally aware - it needs to either have multiple video frames as input, use recurrent neural networks to retain history or use a transformer network to attend over previous frames.

Tasks in this project:
* Create a temporal object detection dataset using tools such as Segment Anything.
* Train a Yolo-like neural network to detect temporal features, for example blinker state of cars or blinking traffic lights.

Links:
* https://ai.meta.com/sam2/
* https://github.com/facebookresearch/segment-anything-2
* https://github.com/Guanghan/ROLO
Lõputöö kaitsmise aasta
2024-2025
Juhendaja
Tambet Matiisen
Suhtlemiskeel(ed)
eesti keel, inglise keel
Nõuded kandideerijale
Tase
Magister
Märksõnad

Kandideerimise kontakt

 
Nimi
Tambet Matiisen
Tel
E-mail
tambet.matiisen@ut.ee
Vaata lähemalt
https://adl.cs.ut.ee/