Kierdorf Jana, Weber Immanuel, Kicherer Anna, Zabawa Laura, Drees Lukas, Roscher Ribana
Remote Sensing Group, Institute of Geodesy and Geoinformation, University of Bonn, Bonn, Germany.
Application Center for Machine Learning and Sensor Technology, University of Applied Sciences Koblenz, Koblenz, Germany.
Front Artif Intell. 2022 Mar 25;5:830026. doi: 10.3389/frai.2022.830026. eCollection 2022.
The need for accurate yield estimates for viticulture is becoming more important due to increasing competition in the wine market worldwide. One of the most promising methods to estimate the harvest is berry counting, as it can be approached non-destructively, and its process can be automated. In this article, we present a method that addresses the challenge of occluded berries with leaves to obtain a more accurate estimate of the number of berries that will enable a better estimate of the harvest. We use generative adversarial networks, a deep learning-based approach that generates a highly probable scenario behind the leaves exploiting learned patterns from images with non-occluded berries. Our experiments show that the estimate of the number of berries after applying our method is closer to the manually counted reference. In contrast to applying a factor to the berry count, our approach better adapts to local conditions by directly involving the appearance of the visible berries. Furthermore, we show that our approach can identify which areas in the image should be changed by adding new berries without explicitly requiring information about hidden areas.
由于全球葡萄酒市场竞争日益激烈，准确估计葡萄栽培产量的需求变得越来越重要。估计收获量最有前景的方法之一是浆果计数，因为它可以采用非破坏性方式进行，并且其过程可以自动化。在本文中，我们提出了一种方法，该方法解决了叶片遮挡浆果的问题，以获得更准确的浆果数量估计，从而能够更好地估计收获量。我们使用生成对抗网络，这是一种基于深度学习的方法，它利用从无遮挡浆果图像中学习到的模式，生成叶片后面极有可能出现的场景。我们的实验表明，应用我们的方法后对浆果数量的估计更接近人工计数的参考值。与对浆果计数应用一个系数不同，我们的方法通过直接考虑可见浆果的外观，更好地适应了当地条件。此外，我们表明我们的方法可以识别图像中哪些区域需要通过添加新浆果来改变，而无需明确要求关于隐藏区域的信息。
