In traditional conveyor belt edge detection methods, contact detection methods have a high cost. At the same time noncontact detection methods have low precision, and the methods based on the convolutional neural network are limited by the local operation features of the convolution operation itself, causing problems such as insufficient perception of long-distance and global information. In order to solve the above problems, a dual flow transformer network (DFTNet) integrating global and local information is proposed for belt edge detection. DFTNet could improve belt edge detection accuracy and suppress the interference of belt image noise. In this paper, the authors have merged the advantages of the traditional convolutional neural network's ability to extract local features and the transformer structure's ability to perceive global and long-distance information. Here, the fusion block is designed as a dual flow encoder-decoder structure, which could better integrate global context information and avoid the disadvantages of a transformer structure pretrained on large datasets. Besides, the structure of the fusion block is designed to be flexible and adjustable. After sufficient experiments on the conveyor belt dataset, the comparative results show that DFTNet can effectively balance accuracy and efficiency and has the best overall performance on belt edge detection tasks, outperforming full convolution methods. The processing image frame rate reaches 53.07 fps , which can meet the real-time requirements of the industry. At the same time, DFTNet can deal with belt edge detection problems in various scenarios, which gives it great practical value.

Crop pests and diseases are treated as one of the main factors affecting food production and security. An accurate detection and corresponding precision management to reduce the spread of crop diseases in time and space is an important scientific issue in crop disease control tasks. On the one hand, the development of remote sensing technology provides higher-quality data (high spectral/spatial resolution) for crop disease monitoring. On the other hand, deep learning/machine learning algorithms also provide novel insights for crop disease detection. In this paper, a comprehensive review was conducted to demonstrate various remote sensing platforms (e.g. ground-based, low-attitude and spaceborne scales) and popular sensors (e.g. RGB, multispectral and hyperspectral sensors). In addition, conventional machine learning and deep learning algorithms applied for crop disease monitoring are also reviewed. In the end, considering the crop disease early detection problem which is a challenging problem in this area, self-supervised learning is introduced to motivate future research. It is envisaged that this paper has concluded the recent crop disease monitoring algorithms and provides a novel thought on crop disease early monitoring.