CN109919849B - Bookcase equipment state switching system - Google Patents
Bookcase equipment state switching system Download PDFInfo
- Publication number
- CN109919849B CN109919849B CN201810837087.6A CN201810837087A CN109919849B CN 109919849 B CN109919849 B CN 109919849B CN 201810837087 A CN201810837087 A CN 201810837087A CN 109919849 B CN109919849 B CN 109919849B
- Authority
- CN
- China
- Prior art keywords
- image
- bookcase
- sub
- shielding
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a bookcase equipment state switching system, which comprises: the anti-pinch device is arranged in the bookcase and used for providing anti-pinch measures when a reader takes and delivers books in the bookcase, the anti-pinch device comprises a plurality of isolated vertical plates, and a book is placed between every two isolated vertical plates; the current capture device is used for shooting the opposite side of the bookcase to obtain and output a corresponding image opposite the bookcase; the type analysis equipment is used for inputting the plurality of normalization features into a multi-input single-output deep neural network which is trained and tested in advance, and obtaining the output object type to determine whether a human body exists or not, wherein the number of the normalization features is the same as the number of input parameters of the deep neural network; and the state switching equipment is used for enabling the anti-pinch equipment to enter a working mode from a sleep mode when the type analysis equipment determines that a human body exists. By the aid of the bookcase auxiliary component, unnecessary power consumption is avoided.
Description
Technical Field
The invention relates to the field of intelligent bookcases, in particular to a bookcase equipment state switching system.
Background
The depth of the bookcase bookshelf is the depth of the bookcase bookshelf, and the bookcase bookshelf is mainly used for storing books, so that the depth of the bookcase bookshelf can be determined according to the general book specification. And even the dimension specification of the literature books is not very large. Therefore, the depth size of the bookshelf of the modern bookcase is designed to be between 280mm and 350mm, so that the book collection requirement of most modern people can be met.
The height dimension of the partition board is also designed according to the specification of books. For example, the height of the partition of the bookcase is designed according to the standard size of 16 books, the height of the partition is 280-300 mm, the height of the partition is designed according to the standard size of 32 books, and the height of the partition is 240-260 mm. Some less common larger books are typically over 300mm to 400mm in size, and can be set to a deck height of between 320mm to 420 mm.
Disclosure of Invention
In order to solve the technical problem that the automation level of a bookcase is not high, the invention provides a bookcase equipment state switching system, which is used for performing differential processing on each position of an image and combining results after the differential processing to reconstruct an image which is clearer than an original image; the method comprises the steps of further reducing the range of image recognition by carrying out homomorphic filtering processing, histogram equalization processing and threshold adjustment of each sub-image of image segmentation on an image, and reducing the data volume for subsequent image processing; the method comprises the steps of starting median filtering operation on an image when shielding is not confirmed so as to replace the filtered image with the image for output, and wirelessly sending a shielding alarm signal to a remote management server when shielding is confirmed so as to take remote control measures and overcome the shielding problem on site.
According to an aspect of the present invention, there is provided a bookcase device state switching system, the system comprising:
the anti-pinch device is arranged in the bookcase and used for providing anti-pinch measures when a reader takes and delivers books in the bookcase, the anti-pinch device comprises a plurality of isolated vertical plates, and a book is placed between every two isolated vertical plates; the current capture device is used for shooting the opposite side of the bookcase to obtain and output a corresponding image opposite the bookcase; the homomorphic filtering equipment is connected with the current capturing equipment and used for receiving the image opposite to the bookcase and executing homomorphic filtering processing on the image opposite to the bookcase so as to obtain a corresponding homomorphic filtering image, wherein the higher the noise amplitude of the image opposite to the bookcase is, the higher the intensity of the executed homomorphic filtering processing is; the equalization processing equipment is connected with the homomorphic filtering equipment and used for receiving the homomorphic filtering image and executing histogram equalization processing on the homomorphic filtering image to obtain a corresponding histogram equalization image; the first threshold extraction device is connected with the equalization processing device and used for receiving the histogram equalization image and determining an integral segmentation threshold corresponding to the histogram equalization image based on the distribution condition of the pixel values of all the pixel points in the histogram equalization image; the first parameter analysis equipment is used for receiving the histogram equalization image and carrying out contrast analysis on the histogram equalization image so as to obtain and output corresponding contrast; the first segmentation processing device is connected with the first parameter analysis device and used for receiving the contrast and carrying out image segmentation processing on the histogram equalization image based on the contrast to obtain a plurality of sub-images, wherein the higher the contrast is, the more the number of the obtained sub-images is; the second threshold extraction device is connected with the first segmentation processing device and used for receiving the plurality of sub-images, determining the region segmentation thresholds corresponding to the sub-images based on the distribution condition of the pixel values of all the pixel points in each sub-image, and outputting the region segmentation thresholds corresponding to all the sub-images; the first numerical value adjusting device is respectively connected with the second threshold value extracting device and the first threshold value extracting device, and is used for receiving the overall segmentation threshold value and each region segmentation threshold value, and performing numerical value adjustment on each region segmentation threshold value based on the overall segmentation threshold value to obtain an adjusted region segmentation threshold value to be used as a region adjustment threshold value to be output; in the first numerical adjustment device, numerically adjusting each region segmentation threshold based on the overall segmentation threshold includes: performing numerical adjustment on the region segmentation threshold value based on the difference value from the whole segmentation threshold value to each region segmentation threshold value; in the first numerical adjustment device, numerically adjusting the region division threshold based on the magnitude of the difference from the overall division threshold to each region division threshold includes: the adjusted region segmentation threshold is the sum of the region segmentation threshold and one fourth of the difference; the second segmentation processing device is connected with the first numerical value adjustment device and used for performing segmentation processing on each sub-image by adopting a corresponding region adjustment threshold value so as to obtain a corresponding target sub-image, and combining all the target sub-images so as to obtain and output a combined image; an image distinguishing device, connected to the second segmentation processing device, configured to receive the combined image, perform uniform blocking on the combined image to obtain respective blocked sub-images, perform detection processing on whether an edge line exists for each blocked sub-image, so as to use the blocked sub-image in which the edge line exists as a reference sub-image, use the blocked sub-image in which the edge line does not exist as a non-reference sub-image, use a plurality of sub-images in a neighborhood of each reference sub-image as a plurality of secondary sub-images, output each secondary sub-image in the combined image, and output each reference sub-image in the combined image; the hierarchical processing device is connected with the image distinguishing device and is used for receiving each reference sub-image and each secondary sub-image in the combined image, performing image sharpening processing of primary sharpening strength on each reference sub-image to obtain each reference sharpened sub-image, performing image sharpening processing of secondary sharpening strength on each secondary sub-image to obtain each secondary sharpened sub-image, and combining the reference sharpened sub-images, the secondary sharpened sub-images and non-reference sub-images of the non-secondary sharpened sub-images to obtain a combined image; the characteristic analysis equipment is connected with the hierarchical processing equipment and used for receiving the combined image, acquiring the area of each object pattern in the combined image, taking the object pattern with the area close to the human body area threshold value as a to-be-processed sub-image, carrying out shape analysis on the to-be-processed sub-image to obtain a plurality of geometric characteristics of an object in the to-be-processed sub-image, and respectively carrying out normalization processing on the geometric characteristics to obtain a plurality of normalized characteristics; the type analysis equipment is connected with the feature analysis equipment and used for receiving the plurality of normalized features and inputting the plurality of normalized features into a multi-input single-output deep neural network which is trained and tested in advance to obtain an output object type so as to determine whether a human body exists or not, wherein the number of the plurality of normalized features is the same as the number of input parameters of the deep neural network; and the state switching equipment is respectively connected with the type analysis equipment and the anti-pinch equipment and is used for enabling the anti-pinch equipment to enter a working mode from a sleep mode when the type analysis equipment determines that a human body exists.
More specifically, in the bookcase device state switching system: the state switching equipment is further used for enabling the anti-pinch equipment to enter a sleep mode from a working mode when the type analysis equipment determines that no human body exists.
More specifically, in the bookcase device state switching system: the size of the filtering window used in the median filtering operation is proportional to the total area of occlusion.
More specifically, in the bookcase device state switching system: in the hierarchical processing device, the image sharpening process of the primary sharpening strength is performed with a sharpening strength greater than that of the secondary sharpening strength.
More specifically, in the bookcase device state switching system, the bookcase device state switching system further comprises:
and the early warning control device is connected with the current capturing device and used for receiving the image opposite to the bookcase, extracting each pixel value of each pixel point in the image opposite to the bookcase, calculating a standard deviation based on each pixel value of each pixel point in the image opposite to the bookcase, sending a shielding early warning signal when the standard deviation exceeds the limit, and sending a non-shielding prompt signal when the standard deviation does not exceed the limit.
More specifically, in the bookcase device state switching system, the bookcase device state switching system further comprises:
and the subimage composition equipment is connected with the early warning control equipment and is used for extracting each brightness value of each pixel point in the image opposite to the bookcase when the shielding early warning signal is received, taking the pixel point with the brightness value smaller than or equal to a preset brightness threshold as a shielding pixel point, removing isolated shielding pixel points in the image opposite to the bookcase and composing each non-isolated shielding pixel point in the image opposite to the bookcase into each shielding subimage.
More specifically, in the bookcase device state switching system, the bookcase device state switching system further comprises:
and the alarm control equipment is connected with the subimage composition equipment and is used for receiving each shielding subimage in the image opposite to the bookcase, calculating the number of pixel points occupied by each shielding subimage to be used as the area of the corresponding shielding subimage, eliminating the shielding subimages with the area smaller than or equal to a preset area threshold value, accumulating the areas of the rest shielding subimages to obtain the total shielding area, sending a shielding alarm signal when the total shielding area exceeds the limit, and sending a shielding unconfirmed signal when the total shielding area does not exceed the limit.
More specifically, in the bookcase device state switching system, the bookcase device state switching system further comprises:
and the decision control device is connected with the alarm control device, is used for starting a median filtering operation on the image opposite to the bookcase when receiving the shielding unconfirmed signal so as to replace the filtered image with the image opposite to the bookcase for output, and is also used for wirelessly sending the shielding alarm signal to a remote management server when receiving the shielding alarm signal.
Drawings
Embodiments of the invention will now be described with reference to the accompanying drawings, in which:
fig. 1 is a schematic structural diagram of a bookcase for which a bookcase device state switching system is shown according to an embodiment of the present invention.
Detailed Description
Embodiments of the bookcase device state switching system of the present invention will be described in detail below with reference to the accompanying drawings.
The size of the bookcase is a concept of full contents, and does not have a uniform standard size. The dimensions of the bookcase include not only the width dimension and the height dimension of the bookcase, but also the external dimensions of the bookcase, namely the depth of the bookcase, the height dimension of the partition boards (the height dimension between layers of the bookcase), the height dimension of the drawers and other local dimensions of the bookcase. Therefore, when the bookcase is customized or purchased, the size of each bookcase is considered in all directions, and the bookcase which is customized or purchased can be properly and harmoniously arranged into a study.
In order to overcome the defects, the invention builds a bookcase equipment state switching system and can solve the corresponding technical problem.
Fig. 1 is a schematic structural diagram of a bookcase for which a bookcase device state switching system is shown according to an embodiment of the present invention. Wherein, 1 is the glass board, 2 is the glass fixed subassembly, and 3 is the side board.
The bookcase equipment state switching system shown according to the embodiment of the invention comprises: the anti-pinch device is arranged in the bookcase and used for providing anti-pinch measures when a reader takes and delivers books in the bookcase, the anti-pinch device comprises a plurality of isolated vertical plates, and a book is placed between every two isolated vertical plates;
the current capture device is used for shooting the opposite side of the bookcase to obtain and output a corresponding image opposite the bookcase;
the homomorphic filtering equipment is connected with the current capturing equipment and used for receiving the image opposite to the bookcase and executing homomorphic filtering processing on the image opposite to the bookcase so as to obtain a corresponding homomorphic filtering image, wherein the higher the noise amplitude of the image opposite to the bookcase is, the higher the intensity of the executed homomorphic filtering processing is;
the equalization processing equipment is connected with the homomorphic filtering equipment and used for receiving the homomorphic filtering image and executing histogram equalization processing on the homomorphic filtering image to obtain a corresponding histogram equalization image;
the first threshold extraction device is connected with the equalization processing device and used for receiving the histogram equalization image and determining an integral segmentation threshold corresponding to the histogram equalization image based on the distribution condition of the pixel values of all the pixel points in the histogram equalization image;
the first parameter analysis equipment is used for receiving the histogram equalization image and carrying out contrast analysis on the histogram equalization image so as to obtain and output corresponding contrast;
the first segmentation processing device is connected with the first parameter analysis device and used for receiving the contrast and carrying out image segmentation processing on the histogram equalization image based on the contrast to obtain a plurality of sub-images, wherein the higher the contrast is, the more the number of the obtained sub-images is;
the second threshold extraction device is connected with the first segmentation processing device and used for receiving the plurality of sub-images, determining the region segmentation thresholds corresponding to the sub-images based on the distribution condition of the pixel values of all the pixel points in each sub-image, and outputting the region segmentation thresholds corresponding to all the sub-images;
the first numerical value adjusting device is respectively connected with the second threshold value extracting device and the first threshold value extracting device, and is used for receiving the overall segmentation threshold value and each region segmentation threshold value, and performing numerical value adjustment on each region segmentation threshold value based on the overall segmentation threshold value to obtain an adjusted region segmentation threshold value to be used as a region adjustment threshold value to be output; in the first numerical adjustment device, numerically adjusting each region segmentation threshold based on the overall segmentation threshold includes: performing numerical adjustment on the region segmentation threshold value based on the difference value from the whole segmentation threshold value to each region segmentation threshold value; in the first numerical adjustment device, numerically adjusting the region division threshold based on the magnitude of the difference from the overall division threshold to each region division threshold includes: the adjusted region segmentation threshold is the sum of the region segmentation threshold and one fourth of the difference;
the second segmentation processing device is connected with the first numerical value adjustment device and used for performing segmentation processing on each sub-image by adopting a corresponding region adjustment threshold value so as to obtain a corresponding target sub-image, and combining all the target sub-images so as to obtain and output a combined image;
an image distinguishing device, connected to the second segmentation processing device, configured to receive the combined image, perform uniform blocking on the combined image to obtain respective blocked sub-images, perform detection processing on whether an edge line exists for each blocked sub-image, so as to use the blocked sub-image in which the edge line exists as a reference sub-image, use the blocked sub-image in which the edge line does not exist as a non-reference sub-image, use a plurality of sub-images in a neighborhood of each reference sub-image as a plurality of secondary sub-images, output each secondary sub-image in the combined image, and output each reference sub-image in the combined image;
the hierarchical processing device is connected with the image distinguishing device and is used for receiving each reference sub-image and each secondary sub-image in the combined image, performing image sharpening processing of primary sharpening strength on each reference sub-image to obtain each reference sharpened sub-image, performing image sharpening processing of secondary sharpening strength on each secondary sub-image to obtain each secondary sharpened sub-image, and combining the reference sharpened sub-images, the secondary sharpened sub-images and non-reference sub-images of the non-secondary sharpened sub-images to obtain a combined image;
the characteristic analysis equipment is connected with the hierarchical processing equipment and used for receiving the combined image, acquiring the area of each object pattern in the combined image, taking the object pattern with the area close to the human body area threshold value as a to-be-processed sub-image, carrying out shape analysis on the to-be-processed sub-image to obtain a plurality of geometric characteristics of an object in the to-be-processed sub-image, and respectively carrying out normalization processing on the geometric characteristics to obtain a plurality of normalized characteristics;
the type analysis equipment is connected with the feature analysis equipment and used for receiving the plurality of normalized features and inputting the plurality of normalized features into a multi-input single-output deep neural network which is trained and tested in advance to obtain an output object type so as to determine whether a human body exists or not, wherein the number of the plurality of normalized features is the same as the number of input parameters of the deep neural network;
and the state switching equipment is respectively connected with the type analysis equipment and the anti-pinch equipment and is used for enabling the anti-pinch equipment to enter a working mode from a sleep mode when the type analysis equipment determines that a human body exists.
Next, the detailed structure of the bookcase device state switching system of the present invention will be further described.
In the bookcase device state switching system: the state switching equipment is further used for enabling the anti-pinch equipment to enter a sleep mode from a working mode when the type analysis equipment determines that no human body exists.
In the bookcase device state switching system: the size of the filtering window used in the median filtering operation is proportional to the total area of occlusion.
In the bookcase device state switching system: in the hierarchical processing device, the image sharpening process of the primary sharpening strength is performed with a sharpening strength greater than that of the secondary sharpening strength.
In the book case equipment state switching system, still include:
and the early warning control device is connected with the current capturing device and used for receiving the image opposite to the bookcase, extracting each pixel value of each pixel point in the image opposite to the bookcase, calculating a standard deviation based on each pixel value of each pixel point in the image opposite to the bookcase, sending a shielding early warning signal when the standard deviation exceeds the limit, and sending a non-shielding prompt signal when the standard deviation does not exceed the limit.
In the book case equipment state switching system, still include:
and the subimage composition equipment is connected with the early warning control equipment and is used for extracting each brightness value of each pixel point in the image opposite to the bookcase when the shielding early warning signal is received, taking the pixel point with the brightness value smaller than or equal to a preset brightness threshold as a shielding pixel point, removing isolated shielding pixel points in the image opposite to the bookcase and composing each non-isolated shielding pixel point in the image opposite to the bookcase into each shielding subimage.
In the book case equipment state switching system, still include:
and the alarm control equipment is connected with the subimage composition equipment and is used for receiving each shielding subimage in the image opposite to the bookcase, calculating the number of pixel points occupied by each shielding subimage to be used as the area of the corresponding shielding subimage, eliminating the shielding subimages with the area smaller than or equal to a preset area threshold value, accumulating the areas of the rest shielding subimages to obtain the total shielding area, sending a shielding alarm signal when the total shielding area exceeds the limit, and sending a shielding unconfirmed signal when the total shielding area does not exceed the limit.
And in the bookcase equipment state switching system, the bookcase equipment state switching system further comprises:
and the decision control device is connected with the alarm control device, is used for starting a median filtering operation on the image opposite to the bookcase when receiving the shielding unconfirmed signal so as to replace the filtered image with the image opposite to the bookcase for output, and is also used for wirelessly sending the shielding alarm signal to a remote management server when receiving the shielding alarm signal.
In addition, the image filtering performed by the homomorphic filtering device suppresses the noise of the target image under the condition of keeping the detail features of the image as much as possible, which is an indispensable operation in image preprocessing, and the effectiveness and reliability of subsequent image processing and analysis are directly affected by the quality of the processing effect.
Due to the imperfections of the imaging system, the transmission medium, and the recording device, the digital images are often contaminated by various noises during the formation, transmission, and recording processes thereof. In addition, noise may also be introduced into the resulting image at some point in the image processing when the input image object is not as expected. These noises often appear as an isolated pixel or block of pixels on the image that causes a strong visual effect. In general, the noise signal is not correlated with the object to be studied-it appears in the form of useless information, disturbing the observable information of the image. For digital image signals, the noise table is more or less extreme values, and the extreme values act on the real gray values of image pixels through addition and subtraction to cause bright and dark point interference on the image, so that the image quality is greatly reduced, and the follow-up work of image restoration, segmentation, feature extraction, image identification and the like is influenced. Two basic issues must be considered to construct an effective noise suppression filter: the noise in the target and the background can be effectively removed; meanwhile, the shape, the size and the specific geometric and topological structure characteristics of the image target can be well protected.
One of the commonly used image filtering modes is a non-linear filter, generally speaking, when the signal spectrum and the noise spectrum are mixed or when the signal contains non-superimposed noise, such as noise caused by system nonlinearity or the presence of non-gaussian noise, etc.), the conventional linear filtering techniques, such as fourier transform, while filtering out noise, always blur the image details (such as edges, etc.) in some way, thereby causing the positioning accuracy of the image linear features and the extractability of the features to be reduced. The nonlinear filter is based on a nonlinear mapping relation of an input signal, a specific noise can be mapped to be zero approximately, the main characteristic of the signal is reserved, and therefore the nonlinear filter can overcome the defects of the linear filter to a certain extent.
By adopting the state switching system of the bookcase equipment, aiming at the technical problem of low intelligent degree of the bookcase in the prior art, the image is reconstructed to be clearer than the original image by performing the differential processing on each position of the image and combining the results after the differential processing; the method comprises the steps of further reducing the range of image recognition by carrying out homomorphic filtering processing, histogram equalization processing and threshold adjustment of each sub-image of image segmentation on an image, and reducing the data volume for subsequent image processing; the method comprises the steps of starting median filtering operation on an image to replace the filtered image with the image for output when the shielding is not confirmed, and wirelessly sending a shielding alarm signal to a remote management server when the shielding is confirmed so as to take remote control measures and overcome the shielding problem on site.
It is to be understood that while the present invention has been described in conjunction with the preferred embodiments thereof, it is not intended to limit the invention to those embodiments. It will be apparent to those skilled in the art from this disclosure that many changes and modifications can be made, or equivalents modified, in the embodiments of the invention without departing from the scope of the invention. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (7)
1. A bookcase device state switching system, comprising:
the anti-pinch device is arranged in the bookcase and used for providing anti-pinch measures when a reader takes and delivers books in the bookcase, the anti-pinch device comprises a plurality of isolated vertical plates, and a book is placed between every two isolated vertical plates;
the current capture device is used for shooting the opposite side of the bookcase to obtain and output a corresponding image opposite the bookcase;
the homomorphic filtering equipment is connected with the current capturing equipment and used for receiving the image opposite to the bookcase and executing homomorphic filtering processing on the image opposite to the bookcase so as to obtain a corresponding homomorphic filtering image, wherein the higher the noise amplitude of the image opposite to the bookcase is, the higher the intensity of the executed homomorphic filtering processing is;
the equalization processing equipment is connected with the homomorphic filtering equipment and used for receiving the homomorphic filtering image and executing histogram equalization processing on the homomorphic filtering image to obtain a corresponding histogram equalization image;
the first threshold extraction device is connected with the equalization processing device and used for receiving the histogram equalization image and determining an integral segmentation threshold corresponding to the histogram equalization image based on the distribution condition of the pixel values of all the pixel points in the histogram equalization image;
the first parameter analysis equipment is used for receiving the histogram equalization image and carrying out contrast analysis on the histogram equalization image so as to obtain and output corresponding contrast;
the first segmentation processing device is connected with the first parameter analysis device and used for receiving the contrast and carrying out image segmentation processing on the histogram equalization image based on the contrast to obtain a plurality of sub-images, wherein the higher the contrast is, the more the number of the obtained sub-images is;
the second threshold extraction device is connected with the first segmentation processing device and used for receiving the plurality of sub-images, determining the region segmentation thresholds corresponding to the sub-images based on the distribution condition of the pixel values of all the pixel points in each sub-image, and outputting the region segmentation thresholds corresponding to all the sub-images;
the first numerical value adjusting device is respectively connected with the second threshold value extracting device and the first threshold value extracting device, and is used for receiving the overall segmentation threshold value and each region segmentation threshold value, and performing numerical value adjustment on each region segmentation threshold value based on the overall segmentation threshold value to obtain an adjusted region segmentation threshold value to be used as a region adjustment threshold value to be output; in the first numerical adjustment device, numerically adjusting each region segmentation threshold based on the overall segmentation threshold includes: performing numerical adjustment on the region segmentation threshold value based on the difference value from the whole segmentation threshold value to each region segmentation threshold value; in the first numerical adjustment device, numerically adjusting the region division threshold based on the magnitude of the difference from the overall division threshold to each region division threshold includes: the adjusted region segmentation threshold is the sum of the region segmentation threshold and one fourth of the difference;
the second segmentation processing device is connected with the first numerical value adjustment device and used for performing segmentation processing on each sub-image by adopting a corresponding region adjustment threshold value so as to obtain a corresponding target sub-image, and combining all the target sub-images so as to obtain and output a combined image;
an image distinguishing device, connected to the second segmentation processing device, configured to receive the combined image, perform uniform blocking on the combined image to obtain respective blocked sub-images, perform detection processing on whether an edge line exists for each blocked sub-image, so as to use the blocked sub-image in which the edge line exists as a reference sub-image, use the blocked sub-image in which the edge line does not exist as a non-reference sub-image, use a plurality of sub-images in a neighborhood of each reference sub-image as a plurality of secondary sub-images, output each secondary sub-image in the combined image, and output each reference sub-image in the combined image;
the hierarchical processing device is connected with the image distinguishing device and is used for receiving each reference sub-image and each secondary sub-image in the combined image, performing image sharpening processing of primary sharpening strength on each reference sub-image to obtain each reference sharpened sub-image, performing image sharpening processing of secondary sharpening strength on each secondary sub-image to obtain each secondary sharpened sub-image, and combining the reference sharpened sub-images, the secondary sharpened sub-images and non-reference sub-images of the non-secondary sharpened sub-images to obtain a combined image;
the characteristic analysis equipment is connected with the hierarchical processing equipment and used for receiving the combined image, acquiring the area of each object pattern in the combined image, taking the object pattern with the area close to the human body area threshold value as a to-be-processed sub-image, carrying out shape analysis on the to-be-processed sub-image to obtain a plurality of geometric characteristics of an object in the to-be-processed sub-image, and respectively carrying out normalization processing on the geometric characteristics to obtain a plurality of normalized characteristics;
the type analysis equipment is connected with the feature analysis equipment and used for receiving the plurality of normalized features and inputting the plurality of normalized features into a multi-input single-output deep neural network which is trained and tested in advance to obtain an output object type so as to determine whether a human body exists or not, wherein the number of the plurality of normalized features is the same as the number of input parameters of the deep neural network;
and the state switching equipment is respectively connected with the type analysis equipment and the anti-pinch equipment and is used for enabling the anti-pinch equipment to enter a working mode from a sleep mode when the type analysis equipment determines that a human body exists.
2. The bookcase device state switching system of claim 1, wherein:
the state switching equipment is further used for enabling the anti-pinch equipment to enter a sleep mode from a working mode when the type analysis equipment determines that no human body exists.
3. The bookcase device state switching system of claim 2, wherein:
in the hierarchical processing device, the image sharpening process of the primary sharpening strength is performed with a sharpening strength greater than that of the secondary sharpening strength.
4. The bookcase device state switching system of claim 3, further comprising:
and the early warning control device is connected with the current capturing device and used for receiving the image opposite to the bookcase, extracting each pixel value of each pixel point in the image opposite to the bookcase, calculating a standard deviation based on each pixel value of each pixel point in the image opposite to the bookcase, sending a shielding early warning signal when the standard deviation exceeds the limit, and sending a non-shielding prompt signal when the standard deviation does not exceed the limit.
5. The bookcase device state switching system of claim 4, further comprising:
and the subimage composition equipment is connected with the early warning control equipment and is used for extracting each brightness value of each pixel point in the image opposite to the bookcase when the shielding early warning signal is received, taking the pixel point with the brightness value smaller than or equal to a preset brightness threshold as a shielding pixel point, removing isolated shielding pixel points in the image opposite to the bookcase and composing each non-isolated shielding pixel point in the image opposite to the bookcase into each shielding subimage.
6. The bookcase device state switching system of claim 5, further comprising:
and the alarm control equipment is connected with the subimage composition equipment and is used for receiving each shielding subimage in the image opposite to the bookcase, calculating the number of pixel points occupied by each shielding subimage to be used as the area of the corresponding shielding subimage, eliminating the shielding subimages with the area smaller than or equal to a preset area threshold value, accumulating the areas of the rest shielding subimages to obtain the total shielding area, sending a shielding alarm signal when the total shielding area exceeds the limit, and sending a shielding unconfirmed signal when the total shielding area does not exceed the limit.
7. The bookcase device state switching system of claim 6, further comprising:
and the decision control device is connected with the alarm control device, is used for starting a median filtering operation on the image opposite to the bookcase when receiving the shielding unconfirmed signal so as to replace the filtered image with the image opposite to the bookcase for output, and is also used for wirelessly sending the shielding alarm signal to a remote management server when receiving the shielding alarm signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810837087.6A CN109919849B (en) | 2018-07-26 | 2018-07-26 | Bookcase equipment state switching system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810837087.6A CN109919849B (en) | 2018-07-26 | 2018-07-26 | Bookcase equipment state switching system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109919849A CN109919849A (en) | 2019-06-21 |
CN109919849B true CN109919849B (en) | 2021-03-05 |
Family
ID=66959677
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810837087.6A Active CN109919849B (en) | 2018-07-26 | 2018-07-26 | Bookcase equipment state switching system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109919849B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201238782Y (en) * | 2008-07-25 | 2009-05-20 | 徐霁畅 | Bookcase with adjustable baffle |
CN102342671A (en) * | 2010-08-03 | 2012-02-08 | 张屹翔 | Bookcase |
-
2018
- 2018-07-26 CN CN201810837087.6A patent/CN109919849B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201238782Y (en) * | 2008-07-25 | 2009-05-20 | 徐霁畅 | Bookcase with adjustable baffle |
CN102342671A (en) * | 2010-08-03 | 2012-02-08 | 张屹翔 | Bookcase |
Also Published As
Publication number | Publication date |
---|---|
CN109919849A (en) | 2019-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108714003B (en) | Fixed desktop maintenance system based on gray measurement | |
Russo | A method for estimation and filtering of Gaussian noise in images | |
US4691366A (en) | Image enhancement | |
CN102479383B (en) | Method and device for removing salt and pepper noise | |
CN112184639B (en) | Round hole detection method and device, electronic equipment and storage medium | |
EP2202684A1 (en) | Image processing device and program | |
CN109584198B (en) | Method and device for evaluating quality of face image and computer readable storage medium | |
Zhang et al. | Decision-based non-local means filter for removing impulse noise from digital images | |
CN110796615A (en) | Image denoising method and device and storage medium | |
CN108198198A (en) | Single frames infrared small target detection method based on wavelet transformation and Steerable filter | |
CN101980521A (en) | Image sharpening method and related device | |
CN107170002B (en) | Automatic image focusing method and device | |
CN109919849B (en) | Bookcase equipment state switching system | |
Irum et al. | A noise adaptive approach to impulse noise detection and reduction | |
CN112884662A (en) | Three-dimensional digital map image processing method based on aerial image of aircraft | |
JP2611723B2 (en) | Image sharpness measuring device | |
Mittal et al. | Enhancement and removal of noise from medical images by wavelet transform method | |
Sreeja et al. | A New Switching Median Filter for Impulse Noise Removal from Corrupted Images | |
RU2405200C2 (en) | Method and device for fast noise filtration in digital images | |
CN110522349B (en) | Fixed desktop maintenance method based on gray level measurement | |
CN110378907B (en) | Method for processing image in intelligent refrigerator, computer equipment and storage medium | |
CN112614100A (en) | Ocean plankton image segmentation method | |
CN115393247A (en) | Image processing method, base station feeder line detection method and related device | |
Reddy et al. | Guided image filtering for image enhancement | |
Langampol et al. | Applied Switching Bilateral Filter for Color Images under Mixed Noise |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210209 Address after: 350300 Yuxi town industrial community, Fuqing City, Fuzhou City, Fujian Province Applicant after: HONGSHENG FURNITURE (FUJIAN) Co.,Ltd. Address before: 321300 unit 2, building 43, Sunshine City Garden community, Dongcheng Street, Yongkang City, Jinhua City, Zhejiang Province Applicant before: YONGKANG CHAIDI TRADING Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |