Computer Vision in Practice
summary
Introduces practical computer vision problems and the state of the art, covering image classification, object detection, image segmentation, and instance segmentation. Explains data acquisition and preprocessing, hardware selection and other practical considerations for running projects, and reviews computer-vision tools and services from Google, Microsoft, and IBM, aimed at developers, project leads, and decision-makers without requiring prior knowledge.
AI-written summary · about
chapters (20)
- 0:00Computer vision intro
- 0:49Vision problems and apps
- 3:33How computers see images
- 5:39CNNs for vision
- 9:12Object detection challenges
- 11:18Vision algorithms history
- 16:29Image segmentation
- 17:32SSD and YOLO: real-time
- 19:17Deep learning impact
- 21:26Build vs buy solutions
- 23:51Data acquisition and labeling
- 26:41Dataset augmentation
- 29:26Model selection and transfer
- 31:12Tools and frameworks
- 32:58Training and hardware
- 34:22Model metrics
- 35:46Project implementation steps
- 36:52Field opportunities
- 37:41Q&A
- 40:10Q&A
related talks
20mComputer Vision: From Facial Recognition to Image Analysis
37mFrom Academia to Industry: Computer Vision with Deep Learning
40mArtificial Intelligence in Computer Vision
33mImage Intelligence Today: Computer Vision
14mA Primer to Modern Day Computer Vision
45mA Picture Is Worth More Than 1,000 Lines of Code
35mBeyond painting buttons: computer vision techniques
01h 29mComputer Vision: An (Un?)Expected Journey, with Keras and Tensorflow