Introduction to Pixano: an Open Source Tool to Assist Annotation of Image Databases
summary
Pixano is an open source, browser-based annotation tool released in 2020 and built over two years to speed labeling for detection, tracking, segmentation and LiDAR point clouds. It ships as a web component and on npm/GitHub, supports polygons, semantic and instance masks, and 3D point-cloud boxes. Interactive modules convert boxes to precise masks automatically and claim to generalize to unseen objects (example: a tomato). The code is modular and ready for integration.
AI-written summary · about
chapters (8)
- 0:00Introduction to computer vision
- 3:36Pixano: Smart annotation tool
- 8:01Features of Pixano
- 13:11Demonstrations and deployment
- 17:10Panel discussion wrap-up
- 20:04Explainable AI in practice
- 25:06AI for EU and pilot cases
- 28:00AI resources and closing
related talks
52mIntroducing Apache Annotator (Incubating)
18mCustomizable Computer Vision Expands Data Access Without Compromising Privacy
34mThe Recipe for Perfect Annotation in Computer Vision
43mPANOPTES: Open Source Exoplanet Discovery
36mOpenbytes Builds Open Dataset Standards and Schema Aiming to Bring Transformational Changes to AI by Making Open Datasets More Available and Accessible
25mPersonalizing Your Images with AI-Powered Features
52mUsing Open Source Tech to Unearth the Stories of the Panama Papers
26mFrom Panoramic Vision to Lightweight 3D Worlds for Semantic Visual Tracking