Final Presentation
Final Report
You can access the gifs we created from this link.
- Mert Yazan
- Berkay Arpacı
- Marcos Conde
| Members | Github |
|---|---|
| Mert Yazan | myazann |
| Berkay Arpacı | BBAKY |
| Marcos Conde | mv-lab |
Each week's work is put into its own folder. Check the folders for more detailed information about the code.
Implement and use mAP for the object detection of a video, find error in optical flow, visualize the flow.Tasks:
- Bounding box detection by adding noise to ground truth
- Calculation of mAP for YOLO3, MaskRCNN, SSD
- Optical flow visualization
- MSEN and PPEN calculation
Tasks:
- Gaussian model for Background Segmentation
- Adaptive Gaussian
- Trying SOTA Background segmentation approaches
- Effect of different color spaces in Gaussian
Tasks:
- Try pretrained networks for Object Detection
- Finetune a network on our dataset
- Object Tracking with Maximum Overlap
- Object Tracking with Kalman Filter
Tasks:
- Optical Flow with Block Matcing
- Off-the-shelf Optical Flow
- MTSC (Multi Track Single Camera)
Tasks:
- Improve the MTSC tracking approach done in the previous week
- Implement MTMC tracking
- https://github.com/mcv-m6-video/class2021 by Masters in Computer Vision, @xavigiro
- https://github.com/mcv-m6-video/mcv-m6-2021-team3 by Gemma Alaix, Josep Brugués, Clara Garcia, Aitor Sánchez
- https://github.com/mcv-m6-video/mcv-m6-2021-team2 by Ruben Bagan, Joan Fontanals, Vernon Stanley and Pablo Domingo
- https://github.com/mcv-m6-video/mcv-m6-2021-team1 by Aditya Rana, German Barquero, Carmen García and Juan Chaves
- https://github.com/mcv-m6-video/mcv-m6-2021-team8 by Yu Pang, Khanh Nguyen, Siddhant Bhambri and Dhananjay Nahata
- AI City Challenge