Vehicle Door Control Using Camera-Based Boarding Intent Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems struggle to accurately determine a person's intention to get on a vehicle, such as a bus, leading to incorrect door operations due to factors like waiting passengers or observers, as they primarily rely on foot position changes.
Innovation Solution
A vehicle control system using a vehicle-exterior camera and machine learning model to analyze time-series image data, segmenting images into blocks, calculating motion vectors, and determining getting-on intentions through entrance-directional components, with correction for distance from the entrance, to accurately identify getting-on gestures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the door control system focuses only on foot position changes to determine getting-on intention, then the system is simple to operate, but the determination accuracy is insufficient due to false positives from waiting passengers or observers
Solution Approach 1:
The patent segments the determination process into multiple independent analysis components: foot position change detection, gesture recognition, and machine learning-based intention classification. Each component processes specific features separately, then combines results to improve overall accuracy while maintaining manageable system complexity through modular architecture
Solution Approach 2:
The patent introduces an intermediary machine learning model that acts as a mediator between raw camera data and door control decisions. This model processes and interprets multiple features (foot position, gestures, body orientation) to produce a reliable getting-on intention determination, reducing false positives while keeping the control system architecture organized and maintainable
2Reliability
If the system uses only foot position data to determine getting-on intention, then the device complexity is low, but the reliability of door operation control is insufficient
Solution Approach 1:
The patent merges multiple detection methods (foot position analysis, gesture recognition, body orientation detection) into a unified door control system. By combining these independent detection channels and requiring consistent signals across multiple modalities, the system achieves high reliability in determining getting-on intention while avoiding false triggering from single-source errors
Solution Approach 2:
The system implements feedback mechanisms where the machine learning model continuously refines its determination based on accumulated data from multiple detection sources. The model learns from patterns in foot position changes, gestures, and body orientations over time, improving reliability of door operation control while maintaining a manageable detection system through adaptive intelligence
3Ease of operation
If the system opens the door during closing control when getting-on intention is detected, then the service quality improves, but the risk of incorrect door operations increases without accurate determination
Solution Approach 1:
The patent performs preliminary analysis of multiple features (foot position, gestures, body orientation) and machine learning-based intention classification before executing the door opening action during closing control. This preliminary multi-factor verification ensures that the door is opened only when getting-on intention is confidently determined, improving passenger boarding convenience while preventing incorrect operations through advance verification
Data Source
AI summary
A vehicle control system includes: a vehicle-exterior camera configured to photograph a getting-on area at the vicinity of an entrance; a getting-on intention determination unit determining whether there is a person that is performing a predetermined getting-on intention gesture to a vehicle, based on time-series data of a photographed image of the vehicle-exterior camera, at a time of execution of a closing control of a door; and a door control unit stopping the closing control of the door and open the door, when the getting-on intention determination unit determines that there is the person that is performing the getting-on intention gesture.