A Comparative Study of 3D Model Acquisition Methods for Synthetic Data Generation of Agricultural Products

TL;DR

This paper compares methods for generating synthetic 3D models to train AI for agricultural object detection, showing that scanned or image-to-3D models improve training, especially when combined with small real datasets.

Contribution

It introduces and evaluates various techniques for creating synthetic datasets from substitute 3D models in agriculture, highlighting the effectiveness of scanned and image-to-3D models.

Findings

Scanned and image-to-3D models enhance synthetic data quality.

Finetuning on small real datasets improves model performance.

Less representative models can still be effective with finetuning.

Abstract

In the manufacturing industry, computer vision systems based on artificial intelligence (AI) are widely used to reduce costs and increase production. Training these AI models requires a large amount of training data that is costly to acquire and annotate, especially in high-variance, low-volume manufacturing environments. A popular approach to reduce the need for real data is the use of synthetic data that is generated by leveraging computer-aided design (CAD) models available in the industry. However, in the agricultural industry these models are not readily available, increasing the difficulty in leveraging synthetic data. In this paper, we present different techniques for substituting CAD files to create synthetic datasets. We measure their relative performance when used to train an AI object detection model to separate stones and potatoes in a bin picking environment. We demonstrate that using highly representative 3D models acquired by scanning or using image-to-3D approaches can be used to generate synthetic data for training object detection models. Finetuning on a small real dataset can significantly improve the performance of the models and even get similar performance when less representative models are used.