Henan University (20240242477). REMOTE SENSING CLASSIFICATION METHOD BASED ON RELATIVE ENTROPY simplified abstract
Contents
REMOTE SENSING CLASSIFICATION METHOD BASED ON RELATIVE ENTROPY
Organization Name
Inventor(s)
REMOTE SENSING CLASSIFICATION METHOD BASED ON RELATIVE ENTROPY - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240242477 titled 'REMOTE SENSING CLASSIFICATION METHOD BASED ON RELATIVE ENTROPY
The abstract of the patent application describes a remote sensing classification method based on relative entropy. This method involves determining sample points of different types of ground objects in a study area, extracting remote sensing parameter values to form standard time series plots, calculating KL values using a KL-divergence formula, and classifying pixels based on the minimum KL value.
- Determining sample points of ground objects and remote sensing parameters
- Extracting remote sensing parameter values to form standard time series plots
- Calculating KL values using a KL-divergence formula
- Classifying pixels based on the minimum KL value
- Utilizing variation characteristics of ground objects in series
- Tight integration with KL-divergence for measuring probability distribution similarity
Potential Applications: - Environmental monitoring - Agricultural management - Urban planning - Disaster response - Forestry management
Problems Solved: - Improved classification accuracy of ground objects - Better recognition of ground object types - Enhanced remote sensing data analysis
Benefits: - Increased efficiency in ground object classification - Enhanced decision-making in various industries - Improved accuracy in remote sensing applications
Commercial Applications: Title: "Enhanced Remote Sensing Classification Method for Ground Objects" This technology can be used in industries such as agriculture, environmental monitoring, urban planning, and disaster response to improve data analysis and decision-making processes.
Questions about the technology: 1. How does this method improve the accuracy of ground object classification? 2. What are the key advantages of using relative entropy in remote sensing classification?
Original Abstract Submitted
a remote sensing classification method based on relative entropy includes: determining sample points of n types of ground objects in a study area and determining series remote sensing parameters; extracting, based on the sample points, remote sensing parameter values to form standard time series plots as a first distribution; taking remote sensing parameter values of to-be-classified pixels as a second distribution, determining, based on the second distribution and the first distribution, kl values of the to-be-classified pixels by using a kl-divergence formula, then obtaining n kl layers; and comparing n kl values of each to-be-classified pixel to classify it to be a type of ground objects with a minimum kl value. the method utilizes variation characteristics of ground objects in series and tightly combines with kl-divergence possessing obvious advantages in measuring probability distribution similarity, thereby achieving better classification and recognition on ground object types and improving classification accuracy.
