Worksite Semantic Segmentation Using DSM Elevation And Slope
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for identifying and classifying elements at worksites, such as those described by Luo, have limited accuracy in evaluating data types beyond color images, which can affect the precision of object classifications in dynamic environments.
Innovation Solution
A computer-implemented method using a semantic segmentation model that integrates image data with digital surface models (DSM) to derive slope values, enabling accurate identification and tracking of elements at worksites by generating semantic segmentation data based on image data, elevation values, and slope values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only color image data is used for semantic segmentation, then the system complexity is low, but the measurement precision of element identification deteriorates
Solution Approach 1:
The patent combines multiple data types (color image data, digital surface model data, and slope data) into a unified semantic segmentation framework. This merging of diverse data sources enables more accurate element identification by leveraging complementary information from each data type, resolving the contradiction between maintaining low system complexity and achieving high measurement precision.
Solution Approach 2:
The semantic segmentation model is designed to process multiple types of input data (RGB images, DSM, slope information) simultaneously, making it a multi-functional system. This universal approach allows the same model architecture to handle various data formats and extract meaningful features for accurate element classification without requiring separate specialized systems for each data type.
2Measurement precision
If multiple data types are integrated for semantic segmentation, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent segments the complex task of element identification into distinct processing stages: color image processing, digital surface model processing, slope calculation, and final semantic segmentation. By dividing the overall system into modular components, each handling a specific data type or processing function, the system achieves high measurement precision through comprehensive data integration while managing complexity through structured organization and independent processing modules.
Data Source
AI summary
A semantic segmentation model generates semantic segmentation data indicating locations and types of elements at a worksite. The semantic segmentation model generates the semantic segmentation data based on an image depicting the worksite, elevation data indicated by a digital surface model of the worksite, and slope data derived from the digital surface model. Post-processing may enhance the generated semantic segmentation data based on image processing techniques and contextual information indicated by telematics data associated with operations at the worksite.