A very quick walkthrough on Computer Vision
Download as PPTX, PDF0 likes65 views
Computer vision is a field that teaches computers to understand images and videos in the same way humans do. It aims to automate visual tasks like object recognition, facial recognition, and hand tracking. Some examples include Google's Mediapipe which can track up to two hands with 20 joint points each in 3D space. The presentation provided a quick overview of computer vision and demonstrated a hand tracking demo.
A very quick walkthrough on Computer Vision
- 1. A very, very quick walkthrough on computer vision
- 3. Computer Vision Computer vision is an interdisciplinary scientific field that deals with how computers can gain high-level understanding from digital images or videos. From the perspective of engineering, it seeks to understand and automate tasks that the human visual system can do.
- 7. Common Computer Vision scenarios
- 15. Some demos!
- 16. Google Mediapipe
- 17. Hand Tracking Multi hand support 20 joint points per hand Spatial points (XYZ)
- 18. Let’s play!
- 19. Matías Iacono
Editor's Notes
- #16: MTCNN = https://kpzhang93.github.io/MTCNN_face_detection_alignment/ Pytorch + Facenet = https://github.com/timesler/facenet-pytorch
- #19: MTCNN = https://kpzhang93.github.io/MTCNN_face_detection_alignment/ Pytorch + Facenet = https://github.com/timesler/facenet-pytorch