# Kiwifruit detection in challenging conditions

Source: [Kiwifruit detection in challenging conditions](<https://www.sota2.com/research/paper/68fa67ce1e209131cea18969>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:23:05.784Z

Authors: Mahla Nejati, Nicky Penhall, Henry Williams, Jamie Bell, JongYoon Lim, Ho Seok Ahn, Bruce MacDonald

Published: 2020-06-21T07:35:57.000Z

## Abstract

Accurate and reliable kiwifruit detection is one of the biggest challenges in developing a selective fruit harvesting robot. The vision system of an orchard robot faces difficulties such as dynamic lighting conditions and fruit occlusions. This paper presents a semantic segmentation approach with two novel image prepossessing techniques designed to detect kiwifruit under the harsh lighting conditions found in the canopy. The performance of the presented system is evaluated on a 3D real-world image set of kiwifruit under different lighting conditions (typical, glare, and overexposed). Alone the semantic segmentation approach achieves an F1\_score of 0.82 on the typical lighting image set, but struggles with harsh lighting with an F1\_score of 0.13. Utilising the prepossessing techniques the vision system under harsh lighting improves to an F1\_score 0.42. To address the fruit occlusion challenge, the overall approach was found to be capable of detecting 87.0% of non-occluded and 30.0% of occluded kiwifruit across all lighting conditions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2006.11729>)

[PDF](<https://arxiv.org/pdf/2006.11729.pdf>)