近日,华中农业大?a href='//www.sqrdapp.com/news/tag_545.html' class='zdbq' title='柑橘相关食品资讯' target='_blank'>柑橘全程
机械化平台和人工智能与统计学习团队以Predicting and Visualizing Citrus Colour Transformation Using a Deep Mask-Guided Generative Network为题在农艺学领域期刊Plant Phenomics发表研究论文。该研究通过生成式深度学习方法,实现了对柑橘果皮颜色变化的高精度可视化预测、/div>
柑橘果皮颜色是果实发育的良好指标,因此监测和预测其颜色变化可以帮助农作物的管理和收获进行决策。研究观察了107个脐橙样本,在其果皮颜色转变期间采集?535张柑橘图像,构建了首个柑橘转色数据集。研究提出了一种将视觉感知融入深度学习的网络框架,包括分割网络、生成网络和感知损失网络;生成网络中的嵌入层将图像特征和时间信息进行了有效融合,使得该网络模型能够根据输入图像和不同的时间间隔来生成果皮颜色转变的预测图像、/div>
[
食品资讯搜索] [
加入收藏] [
告诉好友] [
打印本文] [
关闭窗口]
为了方便现实场景中的应用,研究团队将该模型移植到了安卓设备APP上,通过手机相机拍摄柑橘图像,并在APP中输入感兴趣的时间间隔即可完成预测。该研究成果预测柑橘果皮颜色的变化并使其可视化,为柑橘果园管理实践提供有效帮助,并为其他水果作物的研究提供了借鉴和扩展的可能性、/div>
我校理学院硕士研究生鲍泽韩和副教授李伟夫为本论文共同第一作者,工学院副研究员陈耀晖和海南大学生物医学工程学院副教授肖驰为共同通讯作者。理学院教授陈洪和日本RIKEN研究所研究员Vijay John参与了论文的研究和指导工作、/div>
【英文摘要【/div>
Citrus rind colour is a good indicator of fruit development, and methods to mo
nitor and predict colour transformation therefore help the decisions of crop management practices and harvest schedules. This work presents the complete workflow to predict and visualize citrus colour transformation in the orchard featuring high accuracy and fidelity. 107 sample Navel oranges were observed during the colour transformation period, resulting in a dataset co
ntaining 7535 citrus images. A f
ramework is proposed that integrates visual saliency into deep learning, and it co
nsists of a segmentation network, a deep mask-guided generative network, and a loss network with manually-designed loss functions. Moreover, the fusion of image features and temporal information enables one single model to predict the rind colour at different time intervals, thus effectively shrinking the number of model parameters. The semantic segmentation network of the f
ramework achieves the mean intersection over unio
n score of 0.9694, and the generative network obtains a peak signal-to-noise ratio of 30.01 and a mean local style loss score of 2.710, which indicate both high quality and similarity of the generated images and are also co
nsistent with human perception. To ease the applications in the real world, the model is ported to an Android-ba
sed application for mobile devices. The methods can be readily expanded to other fruit crops with a colour transformation period. The dataset and the source code are publicly available at Github.
日期9a href="//www.sqrdapp.com/news/2023-06-13.html">2023-06-13
行业相关食品资讯
推荐图文