A Look Behind the Scenes of Yandex.Maps: From Raw Satellite Data to Clear Images
summary
A behind-the-scenes look at how raw satellite imagery is processed for Yandex.Maps, covering the pipeline from initial satellite data through geospatial processing and image enhancement to produce clear map images. The talk focuses on the high-throughput systems and techniques used for handling, processing and serving large volumes of satellite data in a production mapping service.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 2:19Image positioning problem
- 5:15Satellite data format
- 9:30Image projection conversion
- 15:10Terrain issues and solutions
- 18:01Neural network final approach
- 21:38Image publishing preparation
- 23:47User optimization
- 25:10Q&A
related talks
21mPreparing Yandex search data — the library and processes we built
05mAlex Kudriashova Interview
43mBackend Architecture of sputnik.ru Maps
29mSpeeding Up Image Preview Rendering in Yandex.Disk
14mSatellite data monitoring for analytical models
39mHow Data Delivery Evolved for Yandex’s Ad Engine
39mSatellite Imagery to Machine-Readable Intelligence
40mStorage Architecture for Yandex.Direct Advertising Objects