Satellite Imagery River Recognition Based on Agricultural Planting Environment

  • Yong Hu


Automatic recognition of satellite images is a combination of artificial intelligence and digital image processing technology. The geographic data of rivers has become a key link in automatic identification and extraction. In recent years, through the joint efforts of scholars at home and abroad, some progress has been made in the identification and extraction of river information. However, in the research of river recognition rate, recognition accuracy, automation level and operability, the theory and application of map information recognition and extraction technology are still the problems to be solved. In this paper, the recognition and extraction methods of river information in satellite map are studied, and a river extraction method based on gray image is proposed according to the characteristics of river. The gray level processing, mathematical morphology, binarization, thinning and vectorization of the image are also introduced. Finally, the convolution neural network algorithm is applied to river image recognition. The experimental results show that the river extraction method proposed in this paper is effective and can obtain better extraction results.