Develop Computer Vision Apps With Go
summary
Built an automated video tagging pipeline in Go that replaces a manual team of five to six people, using GoCV with Haar cascades for face bounding boxes, sending one frame every few seconds to cloud APIs to cut cost, and integrating AWS/Google/Azure vision services plus TensorFlow and YOLO for real-time needs. Notes include celebrity detection failures (Beyoncé misidentified), API rate limits kicking in above ~10 calls/sec, Amazon Rekognition best for celebrities, Azure for OCR, and free tiers of ~5,000 calls/month then ~$1–$1.50 per extra 1k.
AI-written summary · about
chapters (6)
- 0:00Start
- 3:30HUMANS vs MACHINE
- 11:18VIDEO CONTENT
- 12:56BEYONCÉ
- 14:38SPEED/RATE LIMITING
- 16:53GETTING STARTED
related talks
42mComputer Vision Using Go And OpenCV 3
41mComputer Vision with GO and OpenCV
46mBuilding computer vision applications Q&A
01h 33mComputer Vision in Azure
45mA Picture Is Worth More Than 1,000 Lines of Code
46mBuild apps with state-of-the-art computer vision
29mApplied Custom Vision
36mApps That See 👀 Practical AI Vision for Developers