Estimating mango crop yield using image analysis using fruit at 'stone hardening' stage and night time imaging

By A. Payne, Kerry Brian Walsh, P. Subedi, D. Jarvis. 2014

124 citations recorded by the source corpus.

This paper extends a previous study on the use of image analysis to automatically estimate mango crop yield (fruit on tree) (Payne et al., 2013). Images were acquired at night, using artificial lighting of fruit at an earlier stage of maturation ('stone hardening' stage) than for the previous study. Multiple image sets were collected during the 2011 and 2012 seasons. Despite altering the settings of the filters in the algorithm presented in the previous study (based on colour segmentation using RGB and YCbCr, and texture), the less mature fruit were poorly identified, due to a lower extent of red colouration of the skin. The algorithm was altered to reduce its dependence on colour features and to increase its use of texture filtering, hessian filtering in particular, to remove leaves, trunk and stems. Results on a calibration set of images (2011) were significantly improved, with 78.3% of fruit detected, an error rate of 10.6% and an R^2 value (machine vision to manual count) of 0.63. Further application of the approach on validation sets from 2011 and 2012 had mixed results, with issues related to variation in foliage characteristics between sets. It is proposed the detection approaches within both of these algorithms be used as a 'toolkit' for a mango detection system, within an expert system that also uses user input to improve the accuracy of the system.

Subfields: Plant Science

View Paper: https://www.semanticscholar.org/paper/5f0a62af2b4689e7eee5ecd2bcd5feafe843296d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Plant Science

Citations in the corpus

Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards (2016, methodology): “onment or the data gathering operation. For example, pepper detection in Song et al. (2014) is conducted in a greenhouse with controlled illumination conditions. Equivalently, in Nuske et al. (2014); Payne et al. (2014); Font et al. (2015) the data is captured at night using strobes, which signicant”
Deep learning for real-time fruit detection and orchard fruit load estimation: benchmarking of ‘MangoYOLO’ (2019, methodology): “The prediction results of handcrafted algorithms based on colour, texture and shape reported by Payne et al. (2014) and Qureshi et al.”
YOLO-Tomato: A Robust Algorithm for Tomato Detection Based on YOLOv3 (2020, background): “Payne et al. [6] proposed a color and texture-based algorithm to estimate mango crop yield.”
Deep fruit detection in orchards (2016, methodology): “Typically, prior work utilises hand engineered features to encode visual attributes that discriminate fruit from non-fruit regions [2]–[4].”
Sensors and systems for fruit detection and localization: A review (2015, background): “Researchers (Linker et al., 2012; Stajnko et al., 2009, 2007; Dobrusin et al., 1993; Payne et al., 2013, 2014; Plebe and Grasso, 2001; Cakir et al., 2013) have integrated multiple features from two or more feature groups to improve the accuracy and robustness of fruit detection methods.”