Mobile Object Position Control with Shadow Region Masking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle self-position estimation systems face increased processing load due to the need to generate and correct external edge information for each image frame to account for shadow edges, which are generated by sunlight.
Innovation Solution
A mobile object control device that estimates a shadow region in a captured image based on the self-position and light source position, and masks the shadow region to reduce its influence, thereby reducing processing load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If external edge information is generated and corrected for each image frame to account for shadow edges, then position estimation accuracy is improved, but processing load increases
Solution Approach 1:
The system performs preliminary action by estimating the shadow region before edge detection and position estimation. By calculating where shadows will fall based on light source position and object positions, the system can pre-mask these regions, preventing shadow edges from being detected as false features in subsequent processing steps.
Solution Approach 2:
The system extracts and removes the harmful shadow regions from the image processing pipeline by masking them out before edge detection. This separates the shadow problem from the main edge detection process, allowing standard edge detection algorithms to work only on relevant features without being confounded by shadow artifacts.
2Productivity
If shadow regions are masked based on estimated self-position and light source position, then processing load is reduced, but measurement precision may be affected
Solution Approach 1:
The system performs preliminary action by estimating the shadow region before edge detection and position estimation. By calculating where shadows will fall based on light source position and object positions, the system can pre-mask these regions, preventing shadow edges from being detected as false features in subsequent processing steps.
Solution Approach 2:
The system uses feedback by continuously updating the shadow region estimation based on the estimated self-position and light source position. This creates a closed-loop system where the position estimation improves the shadow masking, which in turn improves the position estimation by eliminating shadow interference.
Data Source
AI summary
A mobile object control device includes: a recognition unit configured to estimate a self-position of a mobile object on the basis of a captured image including a surrounding situation of the mobile object and recognize a surrounding situation of the estimated self-position; a generation unit configured to generate a route from the mobile object to a destination on the basis of the recognized surrounding situation and the destination; and a control unit configured to control the mobile object so that the mobile object moves to the destination along the generated route, wherein the recognition unit estimates a shadow region including a shadow of a specific object in the captured image on the basis of the estimated self-position and a light source position, and masks a portion of the captured image on the basis of a position of the estimated shadow region.