-
Book Overview & Buying
-
Table Of Contents
-
Feedback & Rating

Computer Vision on AWS
By :

You have successfully built a video analysis pipeline for real-time video streams using OpenCV and the RTSP protocol to sample frames from IP cameras. You processed a short recording from my iPhone using the Amazon Rekognition Video API to identify time offsets and PIL to draw bounding boxes around people.
You assembled an (almost) production-ready pipeline that asynchronously processes files and uses a completion notification to avoid pulling for status. This foundational API opens the door to sports highlights, safety systems, and improving building layouts, among other potential scenarios. Suppose a traditional store reviewed the footage and determined that its customers gravitate toward specific areas. In that case, they should place high-margin items in those areas to increase sales.
One of the limitations of our solution is that indexes, not names, reference humans. In the last chapter, you mitigated this issue using Amazon Rekognition’s Face API to build...