Vehicle Door Control with Depth-Aware Partial Intrusion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing door control systems struggle to accurately determine whether a person has intruded into a camera's view, especially when only part of the person is visible, leading to potential safety issues.
Innovation Solution
A door controller utilizing machine learning to analyze imaging-data by recognizing user regions and calculating depth differences between user and intrusion determination regions, enhancing accuracy in determining user intrusion through overlapping and depth analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional imaging detection methods are used to detect intruding objects, then the system can detect objects that fully enter the camera view, but it cannot identify whether an intruding object is a person when only part of the person is visible in the imaging area
Solution Approach 1:
The patent transitions from traditional 2D image analysis to 3D depth-aware analysis by calculating depth differences between the intrusion determination region and detected user regions. This dimensional enhancement allows the system to accurately determine whether a person has intruded even when only partially visible in the camera view, resolving the limitation of traditional methods.
Solution Approach 2:
The system changes the detection parameter from simple presence/absence detection to depth-based intrusion determination. By calculating depth differences and comparing them against threshold values, the system can precisely determine intrusion status based on the spatial relationship between the user and the door, improving detection accuracy without requiring complete object visibility.
2Reliability
If the system restricts door operations when intrusion is detected, then safety is improved, but false restrictions may occur due to inaccurate intrusion detection
Solution Approach 1:
The system implements a feedback mechanism where depth information is continuously calculated and used to adjust door control decisions. By providing accurate depth-based feedback about user position relative to the intrusion zone, the system can make informed decisions about whether to restrict door operations, reducing false restrictions while maintaining safety.
Solution Approach 2:
The patent replaces traditional mechanical or simple sensor-based intrusion detection with a vision-based depth analysis system. This substitution enables more accurate and nuanced intrusion determination, allowing the door control system to distinguish between actual intrusion threats and normal user presence, thereby balancing safety with operational convenience.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
A door controller including an electronic control unit (11) that controls opening and closing of a door (6) based on imaging-data is provided. The electronic control unit (11) is configured to recognize a user region including a user in a frame-image included in the imaging-data; extract an overlapping portion between the user region and an intrusion determination region adjacent to the openable and closable door (6); when a degree of overlapping of the overlapping portion relative to the intrusion determination region becomes equal to or higher than a predetermined degree, calculate a depth difference between the intrusion determination region and the overlapping portion in the frame-image; and when the depth difference is equal to or larger than a threshold value, determine that the user has intruded into the intrusion determination region.