A method for detecting the opening and closing state of a sliding door based on numerical image processing

What is AI technical title?
AI technical title is built by Patsnap AI team. It summarizes the technical point description of the patent document.
By using numerical image processing methods and monitoring cameras to detect the status of sliding doors, the problems of sensor delay and environmental influences are solved, achieving real-time and accurate detection of sliding door opening and closing, and reducing processor performance requirements.

CN116051510BActive Publication Date: 2026-06-02HANGZHOU SHULAN TECH CO LTD

Patent Information

Authority / Receiving Office: CN · China
Patent Type: Patents(China)
Current Assignee / Owner: HANGZHOU SHULAN TECH CO LTD
Filing Date: 2023-02-02
Publication Date: 2026-06-02

AI Technical Summary

Technical Problem

In existing technologies, there is a delay problem in the sensor sensing of sliding door opening and closing, and the image processing method is greatly affected by environmental changes, making it difficult to achieve real-time and accurate detection of the opening and closing status of the sliding door.

Method used

Numerical image processing methods are used, including perspective transformation, binarization, edge detection, line detection, and pixel matrix variance and mean judgment, to detect the opening and closing status of sliding doors using existing surveillance cameras.

Benefits of technology

It achieves real-time and accurate detection of the opening and closing status of sliding doors, reduces the requirements for processor performance, and features low computational load and fast processing speed.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN116051510B_ABST

Patent Text Reader

Abstract

The application belongs to the technical field of computer vision processing, and provides a method for detecting the opening and closing state of a sliding door based on numerical image processing. The method is simple in numerical image processing, and is used for judging the opening and closing state of the sliding door by perspective transformation, binarization, edge detection, straight line detection, pixel matrix variance and mean value judgment according to the framed door range in the image, so as to realize real-time and accurate detection of the opening and closing state of the sliding door. The opening and closing state of the sliding door can be judged by comparing the pixel mean value and the pixel standard deviation with the corresponding threshold value, and the performance requirement of the processor is low, and the method has the characteristics of low operation amount and fast processing speed.

Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention belongs to the field of computer vision processing technology, and specifically relates to a method for detecting the opening and closing state of a sliding door based on numerical image processing. Background Technology

[0002] For critical locations, such as doors to hazardous chemical warehouses and classified areas, the detection of the opening and closing status of sliding doors requires extremely high accuracy. Common detection methods include sensors and image data. Sensors determine the door's open / closed state based on the door's position, but the sensor's detection and the door's opening / closing are not simultaneous, resulting in significant time delays and hindering rapid and effective detection. Image-based methods are heavily influenced by processor performance and environmental changes, but under certain conditions, they can meet real-time detection requirements. Therefore, how to accurately and in real-time detect the opening and closing status of sliding doors is a key research focus for those skilled in the art. Summary of the Invention

[0003] This invention provides a method for detecting the opening and closing state of a sliding door based on numerical image processing. By using a simple numerical image processing method, for the area of the door defined in the image, perspective transformation, binarization, edge detection, line detection, and judgment of the variance and mean of the pixel matrix are applied to determine whether the sliding door is open or closed, thereby achieving real-time and accurate detection of the opening and closing state of the sliding door.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] This invention provides a method for detecting the opening and closing state of a sliding door based on numerical image processing, the method comprising:

[0006] (1) Based on the images captured by the fixed-point camera, manually select the range of the sliding door;

[0007] (2) Convert the manually selected area of the sliding door into a rectangular area through a transmission transformation;

[0008] (3) Binarize the acquired images captured by the camera;

[0009] (4) Identify the outline of the sliding door using edge detection methods;

[0010] (5) Extract the lines of the door gaps and existing door cutout areas through straight line detection;

[0011] (6) By comparing the length of the straight line extracted by the straight line detection with the height of the sliding door, the lines in the door cutout area are excluded;

[0012] (7) Perform image grayscale conversion and pixel value normalization on the remaining straight line area in step (6);

[0013] (8) By comparing the difference between the mean pixel value and the standard deviation of the pixel value on the left and right sides of the normalized line, the opening and closing status of the sliding door can be determined.

[0014] Furthermore, in step (1), the manual selection of the sliding door is achieved by using four coordinates to select the area of the sliding door in the image captured by the camera.

[0015] Furthermore, in step (4), the edge detection uses edge detection methods such as Canny.

[0016] Furthermore, the line detection employs Huffman line detection.

[0017] Furthermore, in step (5), if the line detection does not detect a line within the rectangular area, it is determined that the sliding door is in a closed state, and the detection ends.

[0018] Furthermore, the specific exclusion criteria in step (6) are as follows:

[0019] If the length of the straight line extracted by the straight line detection is less than 0.8 times the height of the door, then the line in the door's hollow area is identified and excluded.

[0020] Furthermore, in step (8), the pixel mean threshold of the normalized straight line is set to 0.3, and the pixel standard deviation threshold is set to 0.1.

[0021] If both the pixel mean and pixel standard deviation are less than the corresponding threshold, it is considered that the difference in lighting and texture is caused by the NOT gate being open, the gate is in the closed state, and the detection ends.

[0022] If at least one of the pixel mean and pixel standard deviation exceeds the corresponding threshold, it is considered that the difference in lighting and texture on the left and right sides of the door gap is caused by the door being open, the door is in the open state, and the detection ends.

[0023] The present invention has the following beneficial effects:

[0024] (1) This invention utilizes existing surveillance cameras and uses simple numerical image processing methods to determine whether the sliding door is open or closed by perspective transformation, binarization, edge detection, line detection, and pixel matrix variance and mean judgment for the range of the door framed in the image. This enables real-time and accurate detection of the opening and closing state of the sliding door.

[0025] (2) This invention can determine the opening and closing status of a sliding door simply by comparing the pixel mean and pixel standard deviation, which are both less than the corresponding threshold. It has low requirements for processor performance and features low computational load and fast processing speed. Attached Figure Description

[0026] Figure 1 This is a flowchart of the detection method of the present invention. Detailed Implementation

[0027] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments are only specific illustrations of the invention and should not be regarded as limitations on the invention. The purpose of the embodiments is to enable those skilled in the art to better understand and reproduce the technical solution of the present invention. The scope of protection of the present invention should still be determined by the scope defined in the claims.

[0028] like Figure 1 As shown, the present invention provides a method for detecting the opening and closing state of a sliding door based on numerical image processing, the method comprising:

[0029] S1, based on the image captured by the fixed-point camera, manually select the range of the sliding door; the manual selection of the sliding door is achieved by using four coordinates to select the area of the sliding door in the image captured by the camera.

[0030] S2, transforms the manually selected area of the sliding door into a rectangular area through a transmission transformation;

[0031] S3, perform binarization processing on the acquired camera images;

[0032] S4. The outline of the sliding door is identified through edge detection methods; the edge detection uses edge detection methods such as Canny.

[0033] S5, extract the lines of the door gap and the existing door cutout area through line detection; the line detection adopts Huffman line detection.

[0034] If the line detection does not detect a line within the rectangular area, the sliding door is determined to be closed, and the detection ends.

[0035] S6. By comparing the length of the straight line extracted by the straight line detection with the height of the sliding door, lines in the door's hollow area are excluded; if the length of the straight line extracted by the straight line detection is less than 0.8 times the height of the door, then the lines in the door's hollow area are identified and excluded.

[0036] S7, perform image grayscale conversion and pixel value normalization on the remaining straight line area in step S6.

[0037] S8 determines the opening / closing status of the sliding door by comparing the difference between the mean pixel value and the standard deviation of the pixel value on both sides of the normalized straight line.

[0038] The threshold values for the pixel mean of the normalized straight line are set to 0.3, and the threshold values for the pixel standard deviation are set to 0.1.

[0039] If both the pixel mean and pixel standard deviation are less than the corresponding threshold, it is considered that the difference in lighting and texture is caused by the NOT gate being open, the gate is in the closed state, and the detection ends.

[0040] If at least one of the pixel mean and pixel standard deviation exceeds the corresponding threshold, it is considered that the difference in lighting and texture on the left and right sides of the door gap is caused by the door being open, the door is in the open state, and the detection ends.

[0041] This invention utilizes existing surveillance cameras and employs simple numerical image processing methods. Within a defined area of the door in the image, perspective transformation, binarization, edge detection, line detection, and pixel matrix variance and mean are used to determine whether the sliding door is open or closed. This achieves real-time and accurate detection of the sliding door's opening and closing status. Furthermore, this invention determines the door's opening and closing status simply by comparing the pixel mean and pixel standard deviation, which are both less than corresponding thresholds. It has low processor performance requirements and is characterized by low computational load and fast processing speed.

[0042] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

Claims

1. A method for detecting the opening and closing state of a sliding door based on numerical image processing, characterized in that, The method includes: (1) Based on the images captured by the fixed-point camera, manually select the range of the sliding door; (2) Transform the manually selected area of the sliding door into a rectangular area using perspective transformation; (3) Binarize the acquired images captured by the camera; (4) Identify the outline of the sliding door using edge detection methods; (5) Extract the lines of the door seam and the existing door cutout area through straight line detection; (6) By comparing the length of the straight line extracted by the straight line detection with the height of the sliding door, the lines in the door's hollow area are excluded; (7) Perform image grayscale conversion and pixel value normalization on the remaining straight line area in step (6); (8) By comparing the difference between the mean of pixels on the left and right sides of the normalized line and the standard deviation of pixels, the opening and closing status of the sliding door can be determined.

2. The method for detecting the opening and closing state of a sliding door based on numerical image processing according to claim 1, characterized in that, In step (1), the manual selection of the sliding door is achieved by using four coordinates to select the area of the sliding door in the image captured by the camera.

3. The method for detecting the opening and closing state of a sliding door based on numerical image processing according to claim 1, characterized in that, In step (4), the edge detection uses Canny edge detection.

4. The method for detecting the opening and closing state of a sliding door based on numerical image processing according to claim 1, characterized in that, The line detection employs Huffman line detection.

5. The method for detecting the opening and closing state of a sliding door based on numerical image processing according to claim 1, characterized in that, In step (5), if the line detection does not detect a line within the rectangular area, it is determined that the sliding door is in a closed state, and the detection ends.

6. The method for detecting the opening and closing state of a sliding door based on numerical image processing according to claim 1, characterized in that, The specific exclusion criteria in step (6) are as follows: If the length of the straight line extracted by the straight line detection is less than 0.8 times the height of the door, then the line in the door's hollow area is identified and excluded.

7. The method for detecting the opening and closing state of a sliding door based on numerical image processing according to claim 1, characterized in that, In step (8), the pixel mean threshold of the normalized straight line is set to 0.3 and the pixel standard deviation threshold is set to 0.

1. If both the pixel mean and pixel standard deviation are less than the corresponding threshold, it is considered that the difference in lighting and texture is caused by the NOT gate being open, the gate is in the closed state, and the detection ends. If at least one of the pixel mean and pixel standard deviation exceeds the corresponding threshold, it is considered that the difference in lighting and texture on the left and right sides of the door gap is caused by the door being open, the door is in the open state, and the detection ends.