Maheswari Prabhakar, Raja Purushothaman, Apolo-Apolo Orly Enrique, Pérez-Ruiz Manuel
School of Mechanical Engineering, SASTRA Deemed University, Thanjavur, India.
Departamento de Ingeniería Aeroespacial y Mecánica de Fluidos, Área de Ingeniería Agroforestal, Universidad de Sevilla, Seville, Spain.
Front Plant Sci. 2021 Jun 25;12:684328. doi: 10.3389/fpls.2021.684328. eCollection 2021.
Smart farming employs intelligent systems for every domain of agriculture to obtain sustainable economic growth with the available resources using advanced technologies. Deep Learning (DL) is a sophisticated artificial neural network architecture that provides state-of-the-art results in smart farming applications. One of the main tasks in this domain is yield estimation. Manual yield estimation undergoes many hurdles such as labor-intensive, time-consuming, imprecise results, etc. These issues motivate the development of an intelligent fruit yield estimation system that offers more benefits to the farmers in deciding harvesting, marketing, etc. Semantic segmentation combined with DL adds promising results in fruit detection and localization by performing pixel-based prediction. This paper reviews the different literature employing various techniques for fruit yield estimation using DL-based semantic segmentation architectures. It also discusses the challenging issues that occur during intelligent fruit yield estimation such as sampling, collection, annotation and data augmentation, fruit detection, and counting. Results show that the fruit yield estimation employing DL-based semantic segmentation techniques yields better performance than earlier techniques because of human cognition incorporated into the architecture. Future directions like customization of DL architecture for smart-phone applications to predict the yield, development of more comprehensive model encompassing challenging situations like occlusion, overlapping and illumination variation, etc., were also discussed.
智能农业在农业的各个领域采用智能系统，以利用先进技术通过可用资源实现可持续的经济增长。深度学习（DL）是一种复杂的人工神经网络架构，在智能农业应用中提供了最先进的成果。该领域的主要任务之一是产量估计。人工产量估计面临诸多障碍，如劳动强度大、耗时、结果不准确等。这些问题促使开发一种智能水果产量估计系统，该系统在帮助农民决定收获、销售等方面能提供更多益处。语义分割与深度学习相结合，通过执行基于像素的预测，在水果检测和定位方面取得了有前景的成果。本文综述了利用基于深度学习的语义分割架构采用各种技术进行水果产量估计的不同文献。它还讨论了智能水果产量估计过程中出现的具有挑战性的问题，如采样、收集、标注和数据增强、水果检测和计数等。结果表明，由于架构中融入了人类认知，采用基于深度学习的语义分割技术进行水果产量估计比早期技术具有更好的性能。还讨论了未来的发展方向，如为智能手机应用定制深度学习架构以预测产量，开发更全面的模型以涵盖遮挡、重叠和光照变化等具有挑战性的情况等。
