Synthetic Data Generation and Adaption for Object Detection in Smart Vending Machines

TL;DR

This paper introduces an improved synthetic data generation and adaptation method for training deep CNNs to enhance object detection in smart vending machines, addressing challenges of realism and data redundancy.

Contribution

It proposes a novel virtual scene simulation, camera distortion modeling, and generative network post-processing to produce more realistic synthetic images for better training.

Findings

Enhanced detection accuracy with synthetic data

Improved generalization to new environments

Effective reduction of redundant training data

Abstract

This paper presents an improved scheme for the generation and adaption of synthetic images for the training of deep Convolutional Neural Networks(CNNs) to perform the object detection task in smart vending machines. While generating synthetic data has proved to be effective for complementing the training data in supervised learning methods, challenges still exist for generating virtual images which are similar to those of the complex real scenes and minimizing redundant training data. To solve these problems, we consider the simulation of cluttered objects placed in a virtual scene and the wide-angle camera with distortions used to capture the whole scene in the data generation process, and post-processed the generated images with a elaborately-designed generative network to make them more similar to the real images. Various experiments have been conducted to prove the efficiency of using the generated virtual images to enhance the detection precision on existing datasets with limited real training data and the generalization ability of applying the trained network to datasets collected in new environment.