Parking Lot Recognition for False Power Reduction Prevention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driving power reduction systems erroneously activate when a vehicle is on an ordinary road due to misinterpretation of road markings as parking lot lines, leading to unnecessary power reduction.
Innovation Solution
A driving assistance system that detects parking slots and parked vehicles using image data to recognize parking rows and determine if the vehicle is in a parking lot, then checks for erroneous accelerator operations to accurately prevent unnecessary power reduction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If driving power reduction control is enabled when the vehicle is detected to be in a parking lot, then unnecessary power reduction is prevented on ordinary roads, but the system may still erroneously detect road markings as parking slot lines leading to false activation
Solution Approach 1:
The patent introduces an image recognition system as an intermediary between the accelerator operation detection and the driving power reduction control. The image recognition section captures images of road markings and uses pattern recognition to distinguish actual parking slot lines from ordinary road markings, providing more reliable location information to the control section and preventing false activation.
Solution Approach 2:
The patent replaces the simple presence/absence detection of parking slots with an image-based recognition system. Instead of relying solely on sensor data or simple line detection, the system uses camera images and image processing algorithms to visually identify and verify parking slot characteristics, thereby improving detection accuracy.
2Ease of manufacture
If the system detects parking slots using simple line detection, then the system is simple to implement, but road markings such as stop lines and pedestrian crossings are erroneously detected as parking slot lines
Solution Approach 1:
The patent segments the line detection process into multiple stages: first detecting all linear features in the image, then analyzing their geometric characteristics (spacing, length, orientation), and finally synthesizing this information to identify parking slots. This multi-stage segmentation allows the system to distinguish parking slot lines from other road markings by comparing their specific geometric patterns.
Solution Approach 2:
The patent changes the detection parameters from simple line presence to multiple geometric parameters including line spacing, line length, orientation angles, and relative positions. By analyzing multiple parameters simultaneously and comparing them against predefined parking slot characteristics, the system achieves more precise detection while maintaining reasonable complexity.
Data Source
AI summary
A driving assistant apparatus 1 includes a parking row recognition section 11, 12, 13A which recognizes a parking slot(s) PL and/or a parked vehicle(s) VL around an own vehicle 100 and recognizes a parking row PR in which the number of the recognized successive parking slot(s) PL and/or parked vehicle(s) VL is equal to or greater than a predetermined first threshold number, a parking lot staying determination section 16 which determines whether or not the own vehicle 100 is present in a parking lot P having the parking row PR, an erroneous operation determination section 17 which obtains an operation state of an acceleration operation element and determines, on the basis of the operation state, whether or not an occupant has performed an erroneous operation of erroneously stepping on the acceleration operation element, and a control section 18 which executes driving power reduction control of reducing driving power of the own vehicle 100 when the parking lot staying determination section 16 determines that the own vehicle 100 is present in the parking lot P and the erroneous operation determination section 17 determines that the occupant has performed the erroneous operation.