Precise LINDAR data ground object classification method based on adaptive characteristic weight synthesis

Abstract

The invention, which belongs to the remote sensing data ground object classification field, particularly relates to a precise LINDAR data ground object classification method based on adaptive characteristic weight synthesis. According to the invention, full feature information extraction is carried out on an experiment image, elevation, spectrum, intensity, and texture feature subsets are constructed based on the physical significance of the feature and a difference including ground object information; importance differences of different feature subsets during the ground object classification process are analyzed under a random forest frame, importance measures of all feature subsets are calculated, and class memberships of pixels to all kinds of ground objects are obtained; with comprehensive utilization of the importance measures of the feature subsets as well as an evidence-conflict-calculation-based weight coefficient, synthesis of multiple evidence sources formed by all feature subsets is carried out; and according to the synthesis result, precise ground object classification is realized by using a voting-based decision making rule and a preliminary classification result is optimized by employing an effective space limitation strategy.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This patented technology allows an aircraft's radar sensor (LIDAR) can detect more accurate distance from targets than previous systems without sacrificing resolution or sensitivity. It uses this knowledge to create models called fuzzy sets which represent potential threatening scenarios while reducing their impact on overall performance. By selecting representative sample parts at random, we aim to reduce redundancy by replacing only certain ones rather than all them altogether. Additionally, our method optimizes weights used during analysis to improve object recognition results through correlations among various factors like altitude and target position. Overall, these technical improvements help prevent collateral damage caused by unintended detection events such as missiles or bomb attacks.

Problems solved by technology

This patented technical problem addressed in this patents relates to accurately identifying and categorizing ground materials due to their complex nature. Ground object recognition systems use laser radar imagery collected at multiple locations around the world's area to extract detailed spatially distributed reflectance values called aerial depth maps (ALSM). These map measurements help improve understanding terrain characteristics during autonomous driving operations like road safety monitoring and environmental pollution assessment. However, existing methods often neglect relevant factors involved in each measurement, leading to errors when selecting representative samples. Additionally, current techniques require extensive analysis effort because they cannot fully utilize all available sources of data.

Images