GeoPython2019

»Spotting Sharks with the TensorFlow Object Detection API«
2019-06-25, 13:30–14:00, Room 1

Object detection is about locating and classifying the objects in an image. In this worked example, we’ll use TensorFlow to build an application that can tell the difference between a sneaky shark and a sunburnt surfer. We’ll demystify the jargon, and learn about R-CNN, Faster R-CNN, YOLO and SSD.

Computer vision technology is rapidly improving and developers now have access to many state of the art computer vision libraries. One of these libraries is the TensorFlow Object Detection API, which makes it easy to train, test and evaluate object detection models.

This talk will start with a jargon busting introduction to the problem of object detection, explaining the different approaches that are available and the benefits and trade-offs that they introduce.

The talk will finish with a worked example of an object detection application that looks to identify marine life in aerial footage, with potential safety and scientific applications.