Waste object classification with AI on the edge accelerators

Abstract

The classification of waste with neural networks is already a topic in some scientific papers. An application in the embedded systems area with current AI processors to accelerate the inference has not yet been discussed. Therefore a prototype is created which classifies waste objects and automatically opens the appropriate container for the object. The area of application is in the public space. For the classification a dataset with 25.681 images and 11 classes was created to retrain the CNNs EfficentNet-B0, MobileNet-v2 and NASNet-Mobile. These CNNs run on the current Edge AI -accelerator processors from Google, Intel and Nvidia and are compared for performance, consumption and accuracy. The result of these comparisons and shows the advantages and disadvantages of the respective processors and the CNNs. For the prototype, the most suitable combination of hardware and AI architecture is used and exhibited at the university fair KasetFair2020.