Target Vehicle Recognition Using Boundary Line Deviation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing target vehicle recognition systems inaccurately identify stopped vehicles as targets for steering control, especially when a preceding or oncoming vehicle is turning a curve, due to decreased speed detection accuracy and erroneous boundary line deviations in captured images.
Innovation Solution
A target vehicle recognition apparatus utilizing a front camera and radar sensor to detect stopped vehicles, determine their orientation and boundary line deviations, and accurately recognize them as targets for steering control by analyzing image data and sensor results to prevent false positives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a front camera is used to recognize stopped vehicles, then the system can identify potential target vehicles, but it may erroneously recognize turning vehicles as stopped vehicles due to decreased speed detection accuracy at long distances
Solution Approach 1:
The patent introduces boundary line deviation as an intermediary criterion to mediate between speed detection and target vehicle recognition. By checking whether the vehicle deviates from the travel lane boundary, the system can distinguish between truly stopped vehicles (which may protrude into the lane) and turning vehicles (which temporarily cross the boundary), thereby resolving the contradiction between speed detection accuracy and recognition reliability
Solution Approach 2:
The patent changes the recognition parameters from relying solely on speed detection to combining multiple parameters: speed threshold, boundary line deviation state, and vehicle orientation. This multi-parameter approach allows the system to maintain reliable recognition even when speed detection accuracy decreases at long distances
2Reliability
If the system uses boundary line deviation to identify target vehicles, then it can detect protruding vehicles, but it may cause false positives for vehicles turning curves that temporarily cross the boundary
Solution Approach 1:
The patent performs preliminary checks on vehicle orientation and visible ends before finalizing target vehicle recognition. By examining whether the vehicle is facing forward or backward and whether its ends are visible in the captured image, the system can determine if a boundary line crossing is due to turning (false positive) or actual protrusion (true target), thereby eliminating false positives while maintaining reliable identification
3Area of stationary object
If the system recognizes vehicles based on captured images only, then it can identify vehicle positions, but it cannot accurately determine vehicle orientation and speed at long distances
Solution Approach 1:
The patent makes the recognition system multi-functional by integrating multiple detection capabilities: boundary line deviation detection, vehicle orientation determination, and visible end detection. This universal approach allows the system to maintain accurate target vehicle recognition across various distances and scenarios, compensating for the limitations of single-function detection methods
Data Source
AI summary
A target vehicle recognition apparatus for recognizing a target vehicle as a target to be avoided by steering control of a host vehicle detects a stopped vehicle located in front of the host vehicle, determines whether the stopped vehicle is in a forward-facing state to the host vehicle or a rearward-facing state to the host vehicle, determines whether the stopped vehicle is in a right boundary line deviation state crossing a right boundary line of a travel lane of the host vehicle, a left boundary line deviation state crossing a left boundary line of the travel lane, and recognizes the target vehicle for steering control based on a captured image captured by a front camera of the host vehicle and each of the determination results.