A pipeline for multiple orange detection and tracking with 3-D fruit relocalization and neural-net based yield regression in commercial citrus orchards

TL;DR

This paper presents a comprehensive pipeline combining CNN-based detection, 3-D relocalization, and neural network regression for accurate orange counting and yield estimation in orchards, addressing occlusion and re-entry challenges.

Contribution

It introduces a novel multi-component pipeline for fruit detection, tracking, relocalization, and yield regression, with publicly available datasets for further research.

Findings

Achieves a yield prediction with 0.85 R^2 when 30% of fruits are accurately detected.

Addresses occlusion and re-entry issues with 3-D relocalization.

Provides annotated datasets for orange detection and tracking.

Abstract

Traditionally, sweet orange crop forecasting has involved manually counting fruits from numerous trees, which is a labor-intensive process. Automatic systems for fruit counting, based on proximal imaging, computer vision, and machine learning, have been considered a promising alternative or complement to manual counting. These systems require data association components that prevent multiple counting of the same fruit observed in different images. However, there is a lack of work evaluating the accuracy of multiple fruit counting, especially considering (i) occluded and re-entering green fruits on leafy trees, and (ii) counting ground-truth data measured in the crop field. We propose a non-invasive alternative that utilizes fruit counting from videos, implemented as a pipeline. Firstly, we employ CNNs for the detection of visible fruits. Inter-frame association techniques are then applied to track the fruits across frames. To handle occluded and re-appeared fruit, we introduce a relocalization component that employs 3-D estimation of fruit locations. Finally, a neural network regressor is utilized to estimate the total number of fruit, integrating image-based fruit counting with other tree data such as crop variety and tree size. The results demonstrate that the performance of our approach is closely tied to the quality of the field-collected videos. By ensuring that at least 30% of the fruit is accurately detected, tracked, and counted, our yield regressor achieves an impressive coefficient of determination of 0.85. To the best of our knowledge, this study represents one of the few endeavors in fruit estimation that incorporates manual fruit counting as a reference point for evaluation. We also introduce annotated datasets for multiple orange tracking (MOrangeT) and detection (OranDet), publicly available to foster the development of novel methods for image-based fruit counting.