Computer Vision Bootcamp | Full 12 hour series | OpenCV, RCNN, UNet, YOLO and Roboflow

Chapters

1. 01Instructor Background and Why Computer Vision Matters21:12
2. 02Industrial Applications of Computer Vision20:45
3. 03Setting Up VS Code, Python and OpenCV23:28
4. 04Drawing and Annotating Shapes on a Canvas36:51
5. 05Detection, Tracking, Counting and Segmentation Concepts32:07
6. 06Counting Objects with YOLO Tracking and IoU17:43
7. 07Tracking People and Vehicles with Centroid Trails22:48
8. 08Instance Segmentation with YOLOv8 and Speed Estimation18:22
9. 09Why Region Proposals: The Idea Behind R-CNN31:31
10. 10Fast R-CNN and Shared Feature Maps32:43
11. 11Faster R-CNN and the Region Proposal Network28:09
12. 12Semantic vs Instance Segmentation and R-CNN Recap36:11
13. 13ROI Pooling vs ROI Align16:32
14. 14How the Region Proposal Network Uses Anchors29:54
15. 15Introduction to U-Net and Semantic Segmentation26:24
16. 16U-Net Decoder, Upsampling and Skip Connections22:08
17. 17Segmentation Loss: Pixel BCE and Dice Loss30:03
18. 18U-Net Variants: U-Net++, Residual and Attention U-Net20:05
19. 19Training U-Net for Concrete Crack Detection37:58
20. 20Deploying a U-Net Gradio App on Hugging Face32:08
21. 21YOLO Motivation, Speed and mAP Comparison27:34
22. 22YOLO Grid Cells and Bounding Box Predictions16:06
23. 23Normalizing Box Coordinates and Confidence Scores26:46
24. 24Confidence at Inference and Class-Specific Scores28:15
25. 25Shoplifting Detection with YOLO and MediaPipe Pose27:55
26. 26Dataset Versions, Augmentation and Model Training23:26
27. 27Building Roboflow Workflows for Segmentation and Pose19:58

About this course

You can also get access to the following if you are part of the PRO version of this bootcamp: 1) Code files 2) Private GitHub repo 3) Hand-written notes 4) Book written by us on the same topic 5) Access to hands-on projects You can register for pro version here: https://hands-on-cv.vizuara.ai/