No abstract

Abstract:The principle of multiresolution segmentation was represented in detail in this study, and the canny algorithm was applied for edge-detection of a remotely sensed image based on this principle. The target image was divided into regions based on object-oriented multiresolution segmentation and edge-detection. Furthermore, object hierarchy was created, and a series of features (water bodies, vegetation, roads, residential areas, bare land and other information) were extracted by the spectral and geometrical features. The results indicate that the edge-detection has a positive effect on multiresolution segmentation, and overall accuracy of information extraction reaches to 94.6% by the confusion matrix.

Artificial Intelligence (AI) has developed rapidly in recent years, making computer vision a hot spot in recent years. As the core technology of computer vision, semantic segmentation has important theoretical significance and practical application value in the field of computer vision. The research purpose of this technique is to classify each pixel in the image and correctly predict the object category of the pixel, that is, to realize the transformation from pixel to object category. Traditional semantic segmentation algorithms cannot meet the requirements of complex image segmentation, and the requirements of complex image segmentation mechanism are also increasing. Therefore, it is of great significance and application prospect to study semantic segmentation algorithm of image. This paper first introduces the current research status in the field of semantic segmentation at home and abroad, tests and analyzes the CamVid data set with three mainstream algorithms, and finally forecasts the semantic segmentation of images.