Aerial Object Detection via Multi-Feature Metadata Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer-implemented tools for detecting objects in aerial images are time-consuming, labor-intensive, and error-prone, failing to provide the necessary quality and accuracy for object detection and classification.
Innovation Solution
A method and system that manipulate and process aerial image metadata and features, such as color and height, to select and combine relevant pixels, creating a graphic representation of objects by applying pre-configured rules and metadata handling to enhance object detection and classification accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual object detection is used in aerial images, then detection accuracy can be maintained, but the process becomes time-consuming and labor-intensive
Solution Approach 1:
The patent replaces manual mechanical detection with an automated computer-implemented system that processes aerial images through multiple digital steps including color space conversion, feature extraction, and automated classification algorithms to identify objects without human intervention
Solution Approach 2:
The detection process is divided into distinct sequential stages: converting images to HSV color space, extracting specific color features, identifying geometric features, and performing classification. This segmentation allows each stage to be optimized independently while maintaining overall accuracy
2Productivity
If existing computer-implemented tools are used for object detection, then time consumption is reduced, but detection quality and accuracy are insufficient
Solution Approach 1:
The system combines multiple detection approaches and feature types (color features from HSV space, geometric features, texture features) into a composite detection framework, where each feature type contributes to the overall detection accuracy, creating a more robust system than single-feature methods
Solution Approach 2:
The patent transforms images into different color spaces (HSV) and extracts multiple parameters including hue, saturation, value, and various geometric features. By changing the parameter representation and using multiple parameters simultaneously, the system achieves both efficiency and high accuracy
3Measurement precision
If multiple features are processed according to metadata and rules, then object classification accuracy improves, but system complexity increases
Solution Approach 1:
The system performs preliminary processing steps before main classification, including converting all images to HSV color space upfront, pre-defining color ranges for different object types, and pre-configuring detection rules. This preliminary preparation simplifies the subsequent classification process despite the multiple features involved
Data Source
AI summary
A method for detecting objects of a specified class in an aerial image of an area, including manipulating first and second features related to each element of the image according to image metadata and pre-configured rules, selecting a first group of elements complying with a first condition related to the first feature, the first condition based on the image metadata and the pre-configured rules, selecting a second group of elements complying with a second condition related to the second feature, the second condition based on the image metadata and the pre-configured rules, and creating a representation of the area from elements common to the first group and the second group, the representation including elements belonging to the objects of the specified class.