Vehicle Image Scanning for Real-Time Object Ground Contact Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems face challenges in accurately recognizing the position of objects in images due to high processing loads, which can degrade positional accuracy and compromise traffic safety.
Innovation Solution
A vehicle control device that includes an imager, a recognizer, a driving controller, and a controller. The controller performs scanning on objects around the host vehicle on a two-dimensional image at a predetermined angle, setting the point first coming into contact with the object as a ground contact point, to improve object recognition and driving control accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If variance calculation is performed to determine cut-in determination, then object position recognition accuracy is improved, but processing load increases and real-time control capability deteriorates
Solution Approach 1:
The patent extracts only the essential information needed for cut-in determination from the image data. Instead of performing comprehensive variance calculations on all image pixels, the system selectively processes only relevant regions and features, thereby maintaining recognition accuracy while significantly reducing processing load and enabling real-time control.
Solution Approach 2:
The patent divides the image processing task into segmented steps: first identifying candidate regions, then performing focused analysis on those regions, and finally synthesizing the results for cut-in determination. This segmentation allows the system to achieve accurate object position recognition without the computational burden of processing the entire image at high resolution.
2Productivity
If variance calculation is simplified to reduce processing load, then real-time control capability is improved, but object position recognition accuracy deteriorates
Solution Approach 1:
The patent performs preliminary actions by pre-identifying potential cut-in regions and preparing processing pipelines before actual cut-in events occur. This allows the system to have simplified processing during real-time operation while maintaining accuracy through pre-computed reference data and pre-configured analysis parameters for different scenario types.
3Reliability
If comprehensive processing is performed to ensure traffic safety, then object position recognition accuracy is improved, but device complexity increases
Solution Approach 1:
The patent implements dynamic processing complexity adjustment based on operational context. The system adapts its processing depth and methodology according to factors such as vehicle speed, environmental conditions, and detected risk levels, thereby ensuring traffic safety through comprehensive processing when needed while reducing device complexity during normal operating conditions.
Data Source
AI summary
A vehicle control device according to an embodiment includes an imager configured to image surroundings of a host vehicle, a recognizer configured to recognize a surroundings situation of the host vehicle, a driving controller configured to control one or both of speed and steering of the host vehicle on the basis of a result of the recognition of the recognizer, and a controller configured to control the driving controller on the basis of imaging content of the imager, and the controller performs scanning on an object present around the host vehicle on a two-dimensional image captured by the imager at an angle serving as a predetermined angle upward from left and right lower ends of the two-dimensional image, and sets a point first coming in contact with the object as a ground contact point of the object.