A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards

TL;DR

This study compares classical and deep learning methods for apple detection and counting, revealing that classical detection outperforms deep learning in detection, while deep learning excels in counting, achieving high yield accuracy in orchard mapping.

Contribution

The paper introduces a comprehensive system for apple detection and counting, and provides a detailed comparison of classical and neural network-based methods across multiple datasets.

Findings

Classical detection methods outperform deep learning in apple detection.

Deep learning methods achieve better accuracy in apple counting.

Combined classical detection with neural counting yields over 95% yield accuracy.

Abstract

We present new methods for apple detection and counting based on recent deep learning approaches and compare them with state-of-the-art results based on classical methods. Our goal is to quantify performance improvements by neural network-based methods compared to methods based on classical approaches. Additionally, we introduce a complete system for counting apples in an entire row. This task is challenging as it requires tracking fruits in images from both sides of the row. We evaluate the performances of three fruit detection methods and two fruit counting methods on six datasets. Results indicate that the classical detection approach still outperforms the deep learning based methods in the majority of the datasets. For fruit counting though, the deep learning based approach performs better for all of the datasets. Combining the classical detection method together with the neural network based counting approach, we achieve remarkable yield accuracies ranging from 95.56% to 97.83%.