Visual navigation is developing rapidly and is of great significance to improve agricultural automation. The most important issue involved in visual navigation is extracting a guidance path from agricultural field images. Traditional image segmentation methods may fail to work in paddy field, for the colors of weed, duckweed, and eutrophic water surface are very similar to those of real rice seedings. To deal with these problems, a crop row segmentation and detection algorithm, designed for complex paddy fields, is proposed. Firstly, the original image is transformed to the grayscale image and then the treble-classification Otsu method classifies the pixels in the grayscale image into three clusters according to their gray values. Secondly, the binary image is divided into several horizontal strips, and feature points representing green plants are extracted. Lastly, the proposed double-dimensional adaptive clustering method, which can deal with gaps inside a single crop row and misleading points between real crop rows, is applied to obtain the clusters of real crop rows and the corresponding fitting line. Quantitative validation tests of efficiency and accuracy have proven that the combination of these two methods constitutes a new robust integrated solution, with attitude error and distance error within 0.02° and 10 pixels, respectively. The proposed method achieved better quantitative results than the detection method based on typical Otsu under various conditions.

Soybean variety is connected to stress resistance ability, as well as nutritional and commercial value. Near-infrared hyperspectral imaging was applied to classify three varieties of soybeans (Zhonghuang37, Zhonghuang41, and Zhonghuang55). Pixel-wise spectra were extracted and preprocessed, and average spectra were also obtained. Convolutional neural networks (CNN) using the average spectra and pixel-wise spectra of different numbers of soybeans were built. Pixel-wise CNN models obtained good performance predicting pixel-wise spectra and average spectra. With the increase of soybean numbers, performances were improved, with the classification accuracy of each variety over 90%. Traditionally, the number of samples used for modeling is large. It is time-consuming and requires labor to obtain hyperspectral data from large batches of samples. To explore the possibility of achieving decent identification results with few samples, a majority vote was also applied to the pixel-wise CNN models to identify a single soybean variety. Prediction maps were obtained to present the classification results intuitively. Models using pixel-wise spectra of 60 soybeans showed equivalent performance to those using the average spectra of 810 soybeans, illustrating the possibility of discriminating soybean varieties using few samples by acquiring pixel-wise spectra.