The motivation of this project is to learn and develop a fully capable algorithm that will not only detect the different objects/vehicles in a road, but it will be able to recognise them and segment the image. One application for this project would be its implementation in an antonomous self-driving car. The project will be composed in 5 deliveries (one for each week).
Team name: Deep4Learning
- A. Casadevall, arnau.casadevall.saiz@gmail.com - acasadevall
- S. Castro, sergio.castro.latorre@gmail.com - SCLSCL
- T. Pérez, tonipereztorres@gmail.com - tpereztorres
- A. Salvador, adrisalva122@gmail.com - AdrianSalvador
The report can be found in the following Overleaf project: Visual Recognition for Autonomous Driving
The project presentation can be found in this [link] (https://docs.google.com/presentation/d/1pATMrlv-86Eotm-Z1qS7ohpkkS3RFFPdB2qlYrZ8-4Y/edit?usp=sharing).
- Google slides for Week 1
- Google slides for Week 2 (T.B.A.)
- Google slides for Week 3 (T.B.A.)
- Google slides for Week 4 (T.B.A.)
- Google slides for Week 5 (T.B.A.)
- Google slides for Week 6 (T.B.A.)
- Google slides for Week 7 (T.B.A.)
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. Paper summary
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770-778). Paper summary