Elevator Door Sill Obstacle Detection Using Image and Depth Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing elevator systems face safety and reliability issues due to obstacles, such as small and dark-colored foreign objects, that prevent elevator doors from closing properly, leading to potential damage and safety hazards.
Innovation Solution
A system and method for monitoring elevator doors using imaging sensors and data processing devices that collect and analyze image and depth data to detect obstacles, employing color background modeling, foreground detection, and 3D background structural modeling to determine if an obstacle exists, with a combined judgment module for increased accuracy, and triggering alerts or control actions to prevent door movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional obstacle detection methods are used, then the system is simple, but small and dark-colored foreign objects cannot be detected accurately
Solution Approach 1:
The patent combines multiple imaging sensors (color camera and depth sensor) to capture both color and depth information simultaneously. This merging of sensing capabilities enables the system to detect small and dark-colored objects that would be invisible to traditional single-type sensors, resolving the contradiction between detection accuracy and system complexity by integrating complementary sensor types that work together synergistically
Solution Approach 2:
The patent transitions from traditional 2D color-only imaging to 3D imaging by incorporating depth information. This dimensional enhancement allows the system to detect objects based on their spatial position and depth characteristics, enabling accurate detection of small and dark-colored foreign objects that lack color contrast but have distinct depth signatures
2Reliability
If obstacle detection is implemented, then safety is improved, but false alarms increase
Solution Approach 1:
The patent implements a feedback mechanism where detection results from both color and depth analysis are cross-validated. The system uses feedback loops to compare detections from multiple sensor types and processing algorithms, adjusting detection thresholds and parameters based on accumulated data. This feedback approach reduces false alarms by confirming obstacles through multiple independent detection pathways before triggering safety responses
Solution Approach 2:
The patent introduces an intermediary processing layer that mediates between raw sensor data and final detection decisions. This intermediary layer includes algorithms that fuse color and depth information, filter out noise, and resolve ambiguities before generating obstacle detection results. The intermediary processing acts as a buffer that prevents false alarms by thoroughly validating detections before they trigger safety responses
3Loss of time
If real-time monitoring is implemented, then response time is reduced, but computational load increases
Solution Approach 1:
The patent segments the obstacle detection process into distinct stages: color analysis, depth analysis, data fusion, and decision-making. Each stage processes only the necessary information for its specific function, allowing parallel processing of color and depth data streams. This segmentation enables real-time monitoring by breaking down the computational task into manageable, concurrently executable segments that reduce overall processing time and energy consumption
Data Source
AI summary
The present invention relates to a system for monitoring an elevator door, an elevator system, and a method for monitoring an elevator door. The elevator door has an open state or a closed state implemented by moving along an elevator sill. The system for monitoring an elevator door includes: one or more imaging sensors configured to collect image data and depth data of at least one section in the elevator sill that is exposed when the elevator door is in the open state; and a data processing device in communication with the imaging sensor and configured to receive and process the image data and the depth data to determine whether an obstacle preventing the elevator door from entering the closed state exists in the section. By applying the present invention, the safety of the elevator door can be improved effectively, and equipment property losses and personal injuries can be avoided.