Abstract

Automation is fundamentally changing many industries and retail is no exception. Moonshop is a South African venture trying to solve the problem of autonomous grocery stores using cameras and computer vision. This project is the continuation of a hackathon held to explore different methods for Human Action Recognition in Moonshop’s stores. Throughout the project a pipeline for data processing has been developed and two types of Graph-Convolutional Networks, CTR-GCN and ST-GCN, have been implemented and evaluated on the data produced by this pipeline. The resulting scores aren’t good enough to call it a success. However, this is not necessarily a fault of the models. Rather, there wasn’t enough data to train on and the existing data was of varying to low quality. This makes it complicated to justly judge the models’ performances. In the future, more resources should be spent on generating more and better data in order to really evaluate the feasibility of using Human Action Recognition and Graph-Convolutional Networks at Moonshop.