3results about How to "Reduce misclassification rate" patented technology

This invention discloses a method and apparatus for fine extraction of aquatic vegetation and landscape connectivity assessment in rivers and lakes based on high-resolution remote sensing, belonging to the field of environmental remote sensing monitoring and water ecology assessment technology. It includes: acquiring and preprocessing high-resolution satellite imagery to obtain a standardized remote sensing image dataset; extracting water body masks and aquatic vegetation coverage areas through hierarchical threshold segmentation; constructing a dual-threshold discrimination rule based on the normalized vegetation index and soil-regulated vegetation index to finely divide the distribution areas of floating and submerged plants; constructing a binary raster map of vegetation distribution based on the distribution areas; combining a preset connectivity distance threshold; calculating the landscape connectivity index of vegetation patches based on graph theory; determining the ratio of equivalent connected area to effective connected area; and completing a comprehensive assessment of the ecological effectiveness of the aquatic vegetation community. This invention is mainly used for remote sensing monitoring of aquatic vegetation in urban rivers and lakes and for assessing the effectiveness of water ecology restoration, effectively mitigating spectral interference from complex water body sediment backgrounds.

The present application relates to a kind of bolt nut sorting and conveying equipment for parts processing, belong to parts sorting and conveying equipment technical field.It includes: rack, with first installation area and second installation area;Feeding assembly, installed in the first installation area, including detachable feeding box, feeding table and feeding unit, the feeding unit is provided with single electric drive roller;Material stacking table, is located in the output end of the feeding assembly, and is connected by belt pulley to convey parts;First transfer assembly, is installed in the side of the material stacking table, is equipped with transfer claw;Container feeding assembly, installed in the second installation area, including two staggered lifting units and the limit strip of conveying belt;Second transfer assembly, is erected on the rack, for shifting the output container on sorting platform.The technical problem of low efficiency of parts conveying and sorting in the prior art is solved.

The application belongs to the field of hyperspectral image processing, and discloses a hyperspectral image classification method based on kernel joint sparse representation. The method pre-processes original hyperspectral images, obtains spatial neighborhood and spectral neighborhood information based on a watershed superpixel segmentation and a fuzzy C-means (FCM) clustering, and constructs a double neighborhood constraint structure. The method calculates spatial-spectral similarity based on the constraint neighborhood, constructs adaptive matrix features, measures manifold distance between adaptive matrix features by using Stein divergence, combines the double neighborhood constraint region to construct a constraint neighborhood dictionary, adopts Stein kernel function to construct a kernel joint sparse representation model, and completes classification according to the reconstruction residual of each category sub-dictionary. The application can improve spatial-spectral information fusion capability, and improve classification stability and precision in complex boundary and small sample scenarios.