Building security system based on infrared induction

Abstract

The invention relates to a building security and protection system based on infrared induction, and the system comprises an infrared induction mechanism which is disposed at a building enclosing wall, and is used for sensing whether a near infrared induction object is close to the building enclosing wall or not, so as to transmit an object induction signal or an object non-induction signal; the security and protection camera shooting mechanism is used for executing a security and protection camera shooting action near a building enclosing wall when receiving the object sensing signal; and the smoothing execution device is used for carrying out smoothing processing on the contrast reserved image by adopting an intelligent matching reference smoothing algorithm so as to obtain an optimized operation picture corresponding to the contrast reserved image. According to the invention, the security camera shooting mechanism can be triggered to execute the security camera shooting action near the building enclosure only when the infrared induction mechanism induces that a relatively close infrared induction object is close to the building enclosure, and more importantly, the smoothing algorithm with the optimal image quality processing effect is matched for different monitoring images; therefore, the quality of the monitoring picture is improved.

Description

Technical Field

[0001] This invention relates to the field of security, and more particularly to a building security system based on infrared sensing. Background Technology

[0002] Digital image processing technology helps people understand the world more objectively and accurately. The human visual system helps us obtain more than three-quarters of the information from the outside world, and images and graphics are the carriers of all visual information. Although the human eye has high discrimination ability and can recognize thousands of colors, in many cases, images are blurry or even invisible to the human eye. Image enhancement technology can make blurry or even invisible images clear and bright. In computers, images can be divided into four basic types according to the amount of color and grayscale: binary images, grayscale images, indexed images, and true-color RGB images. Most image processing software supports these four types of images.

[0003] Existing technology CN116614715A discloses a method for colorizing near-infrared images for scene monitoring. This method uses a Gabor filter bank to extract texture features from both visible light color images and near-infrared grayscale images. The texture features and brightness information are combined to form a feature vector, and K-Means clustering is used to assign category labels to pixels. Then, both the visible light color image and the near-infrared grayscale image are divided into N equal sub-regions horizontally and vertically, and feature lookup tables are constructed for each to find the color mapping relationship between them. Finally, color values ​​are assigned to the corresponding near-infrared grayscale image sub-regions according to the mapping relationship. For those that do not match, color propagation is performed based on the category label relationship to obtain a color near-infrared monitoring image. This invention uses daytime visible light color images as a reference to achieve colorization of nighttime monitoring images, making nighttime monitoring images more consistent with human visual perception, thereby enhancing the functionality of monitoring cameras.

[0004] Currently, security camera systems are widely used, but the 24-hour continuous monitoring mode leads to a large consumption of power and storage space. In fact, monitoring at certain times is meaningless. For example, when no one is near, the monitoring content of the security camera system is almost blank. Therefore, it is necessary to implement intelligent monitoring strategy management for security camera systems. In particular, different smoothing algorithms are required for the monitoring content at different times. Determining the most suitable smoothing algorithm for the monitoring content at different times is also a difficult problem. Summary of the Invention

[0005] The present invention provides a building security system based on infrared sensing, comprising:

[0006] An infrared sensing mechanism is installed at the building perimeter wall to detect whether there are any nearby infrared sensing objects approaching the building perimeter wall, so as to emit an object sensing signal or an object non-sensing signal;

[0007] A security camera mechanism, connected to the infrared sensing mechanism, is used to perform security camera actions near the building perimeter wall when the object sensing signal is received, so as to obtain and output the corresponding security capture images;

[0008] The sequential enhancement mechanism includes a maximum value filtering device, a filtering sharpening device, and a contrast preservation device. The filtering sharpening device is connected to both the maximum value filtering device and the contrast preservation device. The maximum value filtering device is also connected to the security camera mechanism and is used to perform maximum value filtering processing on the received security capture image to obtain and output a corresponding maximum value filtered image. The filtering sharpening device is used to perform high-pass filtering sharpening processing on the received maximum value filtered image to obtain and output a corresponding filtered sharpened image. The contrast preservation device is used to perform processing on the received filtered sharpened image to preserve the boundary between two parts of the image with obvious color or brightness contrast to obtain and output a corresponding contrast preserved image.

[0009] A content determination device, connected to the sequential enhancement mechanism, is used to receive the contrast-preserving image. Based on the pixel value gradient of each pixel, it determines whether each pixel in the contrast-preserving image is an edge pixel. The color channel values ​​corresponding to each edge pixel in the contrast-preserving image, the total number of non-edge pixels in the contrast-preserving image, the sharpness of the contrast-preserving image, the number of pixels in the contrast-preserving image, and the algorithm identifier of the target smoothing algorithm are input into the Hofit neural network after training a set number of times. The Hofit neural network after training a set number of times is run to obtain the signal-to-noise ratio of the image obtained after smoothing the contrast-preserving image using the target smoothing algorithm. The value of the set number of times is inversely related to the numerical mapping relationship between each non-edge pixel in the contrast-preserving image.

[0010] The traversal processing device is connected to the content judgment device and is used to take the smoothing algorithm corresponding to the maximum signal-to-noise ratio among the various smoothing algorithms obtained by the Hofit neural network after completing a set number of training cycles as the reference smoothing algorithm.

[0011] A smoothing execution device, connected to the traversal processing device, is used to smooth the contrast-preserving image using a reference smoothing algorithm to obtain an optimized operation screen corresponding to the contrast-preserving image;

[0012] Among them, various smoothing algorithms include the unscaling transformation blur algorithm, the median blur algorithm, the Gaussian blur algorithm, and the bilateral smoothing blur algorithm.

[0013] This invention triggers the security camera to perform security camera action on the vicinity of the building perimeter only when the infrared sensing mechanism detects a nearby infrared sensing object. This reduces the power consumption of the security monitoring system. More importantly, the smoothing algorithm with the highest signal-to-noise ratio among the various smoothing algorithms obtained by the Hofit neural network after completing a set number of training iterations is used as the reference smoothing algorithm. The reference smoothing algorithm is then used to smooth the contrast-preserving image to obtain an optimized operation screen corresponding to the contrast-preserving image, thereby completing the smoothing process with the best smoothing effect customized for the contrast-preserving image. Attached Figure Description

[0014] The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0015] Figure 1 This is a structural block diagram of an infrared sensing-based building security system according to a primary embodiment of the present invention.

[0016] Figure 2 This is a structural block diagram of an infrared sensing-based building security system according to a secondary embodiment of the present invention.

[0017] Figure 3 The following is a structural block diagram of an infrared sensing-based building security system according to a further embodiment of the present invention. Detailed Implementation

[0018] The embodiments of the infrared sensing-based building security system of the present invention will now be described in detail with reference to the accompanying drawings.

[0019] First embodiment

[0020] Figure 1 The above is a structural block diagram of an infrared sensing-based building security system according to a primary embodiment of the present invention. The system includes:

[0021] An infrared sensing mechanism is installed at the building perimeter wall to detect whether there are any nearby infrared sensing objects approaching the building perimeter wall, so as to emit an object sensing signal or an object non-sensing signal;

[0022] For example, an infrared sensing mechanism, installed at the perimeter wall of a building, is used to sense whether there is a nearby infrared sensing object approaching the perimeter wall, so as to emit an object sensing signal or an object non-sensing signal. The infrared sensing mechanism includes an infrared receiving unit and an infrared transmitting unit.

[0023] A security camera mechanism, connected to the infrared sensing mechanism, is used to perform security camera actions near the building perimeter wall when the object sensing signal is received, so as to obtain and output the corresponding security capture images;

[0024] The sequential enhancement mechanism includes a maximum value filtering device, a filtering sharpening device, and a contrast preservation device. The filtering sharpening device is connected to both the maximum value filtering device and the contrast preservation device. The maximum value filtering device is also connected to the security camera mechanism and is used to perform maximum value filtering processing on the received security capture image to obtain and output a corresponding maximum value filtered image. The filtering sharpening device is used to perform high-pass filtering sharpening processing on the received maximum value filtered image to obtain and output a corresponding filtered sharpened image. The contrast preservation device is used to perform processing on the received filtered sharpened image to preserve the boundary between two parts of the image with obvious color or brightness contrast to obtain and output a corresponding contrast preserved image.

[0025] A content determination device, connected to the sequential enhancement mechanism, is used to receive the contrast-preserving image. Based on the pixel value gradient of each pixel, it determines whether each pixel in the contrast-preserving image is an edge pixel. The color channel values ​​corresponding to each edge pixel in the contrast-preserving image, the total number of non-edge pixels in the contrast-preserving image, the sharpness of the contrast-preserving image, the number of pixels in the contrast-preserving image, and the algorithm identifier of the target smoothing algorithm are input into the Hofit neural network after training a set number of times. The Hofit neural network after training a set number of times is run to obtain the signal-to-noise ratio of the image obtained after smoothing the contrast-preserving image using the target smoothing algorithm. The value of the set number of times is inversely related to the numerical mapping relationship between each non-edge pixel in the contrast-preserving image.

[0026] The traversal processing device is connected to the content judgment device and is used to take the smoothing algorithm corresponding to the maximum signal-to-noise ratio among the various smoothing algorithms obtained by the Hofit neural network after completing a set number of training cycles as the reference smoothing algorithm.

[0027] A smoothing execution device, connected to the traversal processing device, is used to smooth the contrast-preserving image using a reference smoothing algorithm to obtain an optimized operation screen corresponding to the contrast-preserving image;

[0028] Among them, various smoothing algorithms include the unscaling transformation blur algorithm, the median blur algorithm, the Gaussian blur algorithm, and the bilateral smoothing blur algorithm;

[0029] The infrared sensing mechanism, installed at the building perimeter wall, is used to sense whether there is a nearby infrared sensing object approaching the building perimeter wall, and to emit an object sensing signal or an object non-sensing signal. This includes: when the infrared sensing mechanism senses that there is a nearby infrared sensing object approaching the building perimeter wall, it emits an object sensing signal.

[0030] Secondary Embodiment

[0031] Figure 2 This is a structural block diagram of an infrared sensing-based building security system according to a secondary embodiment of the present invention.

[0032] Compared to Figure 1 , Figure 2 The infrared-sensing-based building security system may also include:

[0033] A timing server is connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content determination device, respectively, and is used to provide the timing services required by the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content determination device, respectively.

[0034] The timing server is connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, respectively, and is used to provide the timing services required by each of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device. The timing server uses the same timing clock to provide the timing services required by each of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device.

[0035] The timing server device uses the same timing clock to provide the maximum value filtering device, the filtering and sharpening device, the contrast preservation device, and the content judgment device with their respective required timing services, including: the timing server device uses the same timing clock to provide the maximum value filtering device, the filtering and sharpening device, the contrast preservation device, and the content judgment device with reference clock signals of various changing waveforms of the same timing clock.

[0036] Again, examples

[0037] Figure 3 The following is a structural block diagram of an infrared sensing-based building security system according to a further embodiment of the present invention.

[0038] Compared to Figure 1 , Figure 3 The infrared-sensing-based building security system may also include:

[0039] A parallel data bus is connected to the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device, respectively, and is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device;

[0040] The parallel data bus is connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, respectively, and is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, including providing a 64-bit parallel data communication link between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device.

[0041] The parallel data bus is connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, respectively, and is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, including: providing a 32-bit parallel data communication link between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device;

[0042] The parallel data bus is connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, respectively, and is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, including: providing a 16-bit parallel data communication link between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device;

[0043] The parallel data bus, which is connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device respectively, and is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, further includes: the distance between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device is less than or equal to a set distance threshold.

[0044] In addition, in the infrared sensing-based building security system, the infrared sensing mechanism, which is installed at the building perimeter wall, is used to sense whether there is a nearby infrared sensing object approaching the building perimeter wall, so as to emit an object sensing signal or an object not sensing signal. It also includes: when the infrared sensing mechanism senses that there is no nearby infrared sensing object approaching the building perimeter wall, it emits an object not sensing signal.

[0045] Furthermore, the security camera is also used to pause the security camera operation near the building perimeter wall when it receives a non-sensing signal from the object.

[0046] Therefore, it can be seen that the present invention has at least the following main technical features:

[0047] First: Based on the pixel value gradient of each pixel, determine whether each pixel in the contrast-preserving image is an edge pixel. Then, input the color channel values ​​corresponding to each edge pixel in the contrast-preserving image, the total number of non-edge pixels in the contrast-preserving image, the sharpness of the contrast-preserving image, the number of pixels in the contrast-preserving image, and the algorithm identifier of the target smoothing algorithm into the Hofit neural network after it has been trained a set number of times. Run the Hofit neural network after it has been trained a set number of times to obtain the signal-to-noise ratio of the image obtained after smoothing the contrast-preserving image using the target smoothing algorithm. The value of the set number of times is inversely related to the numerical mapping relationship between each non-edge pixel in the contrast-preserving image.

[0048] Secondly: The smoothing algorithm with the largest signal-to-noise ratio among the various smoothing algorithms obtained by the Hofit neural network after completing a set number of training iterations is used as the reference smoothing algorithm. The contrast-preserving image is then smoothed using the reference smoothing algorithm to obtain the optimized operation screen corresponding to the contrast-preserving image, thereby completing the smoothing process with the best smoothing effect customized for the contrast-preserving image.

[0049] Furthermore: The security camera is only triggered to perform security camera actions near the building perimeter when the infrared sensor detects a nearby infrared object approaching, thereby reducing the power consumption of the security monitoring system.

[0050] The infrared sensing-based building security system of this invention addresses the technical problems of high power consumption and difficulty in matching optimal smoothing algorithms to different monitoring images in existing technologies. By only triggering the security camera to perform security camera actions near the building perimeter when the infrared sensing mechanism detects a nearby infrared object, the system simultaneously matches the smoothing algorithm with the best image quality processing effect to different monitoring images, thereby improving the quality of the monitoring images and reducing the power consumption of the monitoring system.

[0051] Although the invention has been specifically shown and described with reference to preferred embodiments thereof, those skilled in the art will understand that various changes in form and detail may be made without departing from the spirit and scope of the invention as set forth in the appended claims. Furthermore, while elements of the invention are described or claimed in the singular, the plural forms are also covered unless expressly stated to be limited to the singular.

Claims

1. A building security system based on infrared sensing, characterized in that, The system includes: An infrared sensing mechanism is installed at the building perimeter wall to detect whether there are any nearby infrared sensing objects approaching the building perimeter wall, so as to emit an object sensing signal or an object non-sensing signal; A security camera mechanism, connected to the infrared sensing mechanism, is used to perform security camera actions near the building perimeter wall when the object sensing signal is received, so as to obtain and output the corresponding security capture images; The sequential enhancement mechanism includes a maximum value filtering device, a filtering sharpening device, and a contrast preservation device. The filtering sharpening device is connected to both the maximum value filtering device and the contrast preservation device. The maximum value filtering device is also connected to the security camera mechanism and is used to perform maximum value filtering processing on the received security capture image to obtain and output a corresponding maximum value filtered image. The filtering sharpening device is used to perform high-pass filtering sharpening processing on the received maximum value filtered image to obtain and output a corresponding filtered sharpened image. The contrast preservation device is used to perform processing on the received filtered sharpened image to preserve the boundary between two parts of the image with obvious color or brightness contrast to obtain and output a corresponding contrast preserved image. A content determination device, connected to the sequential enhancement mechanism, is used to receive the contrast-preserving image. Based on the pixel value gradient of each pixel, it determines whether each pixel in the contrast-preserving image is an edge pixel. The color channel values ​​corresponding to each edge pixel in the contrast-preserving image, the total number of non-edge pixels in the contrast-preserving image, the sharpness of the contrast-preserving image, the number of pixels in the contrast-preserving image, and the algorithm identifier of the target smoothing algorithm are input into the Hofit neural network after training a set number of times. The Hofit neural network after training a set number of times is run to obtain the signal-to-noise ratio of the image obtained after smoothing the contrast-preserving image using the target smoothing algorithm. The value of the set number of times is inversely related to the numerical mapping relationship between each non-edge pixel in the contrast-preserving image. The traversal processing device is connected to the content judgment device and is used to take the smoothing algorithm corresponding to the maximum signal-to-noise ratio among the various smoothing algorithms obtained by the Hofit neural network after completing a set number of training cycles as the reference smoothing algorithm. A smoothing execution device, connected to the traversal processing device, is used to smooth the contrast-preserving image using a reference smoothing algorithm to obtain an optimized operation screen corresponding to the contrast-preserving image; Among them, various smoothing algorithms include the unscaling transformation blur algorithm, the median blur algorithm, the Gaussian blur algorithm, and the bilateral smoothing blur algorithm.

2. The building security system based on infrared sensing as described in claim 1, characterized in that: An infrared sensing mechanism, installed at the building perimeter wall, is used to sense whether there is a nearby infrared sensing object approaching the building perimeter wall, and to emit an object sensing signal or an object non-sensing signal. The infrared sensing mechanism emits an object sensing signal when it senses that there is a nearby infrared sensing object approaching the building perimeter wall.

3. The building security system based on infrared sensing as described in claim 2, characterized in that, The system also includes: A timing server is connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content determination device, respectively, and is used to provide the timing services required by the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content determination device, respectively. The timing server is connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, respectively, and is used to provide the timing services required by the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device respectively. The timing server uses the same timing clock to provide the timing services required by the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device respectively.

4. The building security system based on infrared sensing as described in claim 3, characterized in that: The timing server uses the same timing clock to provide the maximum value filtering device, the filtering and sharpening device, the contrast preservation device, and the content determination device with their respective required timing services, including: the timing server uses the same timing clock to provide the maximum value filtering device, the filtering and sharpening device, the contrast preservation device, and the content determination device with reference clock signals of various changing waveforms of the same timing clock.

5. The building security system based on infrared sensing as described in claim 3, characterized in that, The system also includes: A parallel data bus is connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device, respectively, and is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device.

6. The building security system based on infrared sensing as described in claim 5, characterized in that: A parallel data bus, connected to the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device respectively, is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device, including: providing a 64-bit parallel data communication link between each pair of the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device.

7. The building security system based on infrared sensing as described in claim 5, characterized in that: A parallel data bus, connected to the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device respectively, is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device, including: providing a 32-bit parallel data communication link between each pair of the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device.

8. The building security system based on infrared sensing as described in claim 5, characterized in that: A parallel data bus, connected to the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device respectively, is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device, including: providing a 16-bit parallel data communication link between each pair of the maximum value filtering device, the filtering sharpening device, the contrast retention device, and the content judgment device.

9. The building security system based on infrared sensing as described in claim 5, characterized in that: A parallel data bus, connected to the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device respectively, is used to provide parallel data communication links between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device. The bus further includes a distance between each pair of the maximum value filtering device, the filtering and sharpening device, the contrast retention device, and the content judgment device that is less than or equal to a set distance threshold.

Images