华中农业大学在柑橘成熟度预测方面取得重要进展

　　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.