Johan Gelinder

Real Time Object Detection

This is a result of me experimenting with Google’s TensorFlow.
The application is detecting objects using OpenCV in real-time and the neural network is trained on a very large dataset of common object called the COCO data set, which stands for Common Objects in Context. It has 80 classes, 80,000 training images and 40,000 validation images.
The application It detects objects, and is then trying to predict what it “sees”.