Research on the High Resolution Remote Sensing Image Target Detection Based on Machine Learning

With the development of computer technology and the national aerospace industry, remote sensing satellites have been successively projected into the air, and the resolution of remote sensing images is becoming higher and clearer. The surface information contained in remote sensing images can be used not only in civil fields such as forestry, agriculture, water conservancy, but also in the military and national defense fields. Current target detection technologies have achieved good results in natural image detection, but their performance in remote sensing images is poor. This is due to the high resolution of remote sensing images themselves, the small size of key targets in the image, and the dense distribution in multiple directions, while the background information is very complex and covers the entire range of the image, resulting in low detection accuracy and slow speed issues when using traditional methods for target detection. High resolution remote sensing images have a wide range of utilization scenarios. The traditional remote sensing image target detection based on artificial vision recognition and processing has been difficult to effectively cope with and meet the practical needs of large-scale high-resolution remote sensing impact target recognition. Based on this, this paper first analyzes remote sensing image information extraction methods based on machine learning, then studies high-resolution remote sensing image target detection methods based on machine learning, and finally presents the development trend of high-resolution remote sensing image target detection based on machine learning.