CN113111777A - Indoor personnel density detection system and detection method based on ARM platform - Google Patents
Indoor personnel density detection system and detection method based on ARM platform Download PDFInfo
- Publication number
- CN113111777A CN113111777A CN202110390336.3A CN202110390336A CN113111777A CN 113111777 A CN113111777 A CN 113111777A CN 202110390336 A CN202110390336 A CN 202110390336A CN 113111777 A CN113111777 A CN 113111777A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- platform
- data
- processing
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention discloses an ARM platform-based indoor personnel density detection system and a detection method, and the system comprises a data acquisition platform, a data processing platform, a data analysis platform and a conclusion derivation platform, wherein the data acquisition platform is electrically connected with the data processing platform, the data processing platform is electrically connected with the data analysis platform, the data analysis platform is electrically connected with the conclusion derivation platform, the data acquisition platform comprises a peripheral equipment input module and a real-time analysis module, the data processing platform comprises a feature identification module, a content detection module, an image processing module and an image normalization module, the data analysis module comprises an image gradient arrangement module and an image contrast integration module, and the conclusion derivation platform comprises a histogram combination module, a judgment module and a derivation module. In the invention, each module forms a circuit board, so the module is small in size, convenient to install and free from damaging the existing decoration.
Description
Technical Field
The invention relates to the technical field of population detection, in particular to an indoor personnel density detection system and method based on an ARM platform.
Background
In modern society, because of large population base, the flow of human mouth is difficult to control, people in some activity places need to control at present to prevent exceeding standard, the existing mainstream living body detection schemes are divided into a blocking type (light/wave blocking counting), a gate counting type and an infrared counting type, and the three schemes are all insufficient;
1. blocking type is serious in misalignment of counting in a dense environment of people, and the entering and exiting cannot be judged under a conventional office environment, but simple blocking accumulation is adopted.
2. The gate counter type generally requires large-scale construction for deployment at an entrance and an exit of an office building, and is high in cost and incapable of being deployed for the office due to large size.
3. The infrared counter is too high in deployment cost and narrow in judgment range, and needs to be calculated and analyzed after a user walks a fixed line, so that the infrared counter is mainly used in security environments such as airports and stations and is not suitable for common office scenes.
Disclosure of Invention
Technical problem to be solved
The invention can solve the problems that the existing people number detection is difficult, and the existing people number detection device is large and difficult to deploy.
(II) technical scheme
In order to achieve the above object, the present invention adopts the following technical solutions, wherein the indoor personnel density detection system based on the ARM platform includes a data acquisition platform, a data processing platform, a data analysis platform and a conclusion derivation platform, the data acquisition platform is electrically connected to the data processing platform, the data processing platform is electrically connected to the data analysis platform, and the data analysis platform is electrically connected to the conclusion derivation platform, wherein:
the data acquisition platform comprises a peripheral equipment input module and a real-time analysis module, the peripheral equipment input module is electrically connected with the real-time analysis module, the real-time analysis module comprises a key frame extraction module and a key frame preprocessing module, the peripheral equipment input module is used for inputting video and picture data, and the real-time analysis module is used for analyzing and preprocessing the video and picture data;
the data processing platform comprises a feature recognition module, a content detection module, an image processing module and an image normalization module, wherein the feature recognition module is electrically connected with the content detection module, the image processing module is electrically connected with the content detection module, the image normalization module is electrically connected with the image processing module, the feature recognition module is used for processing and understanding images so as to recognize targets and objects in various different modes, the content detection module is used for retrieving the content of the images and filtering the garbage information in the images, the image processing module is used for cutting the images and processing the images into gray level images, and the image normalization module is used for integrating the images and unifying parameters;
the data analysis module comprises an image gradient arrangement module and an image contrast integration module, the image gradient arrangement module is electrically connected with the image contrast integration module, the image gradient arrangement module comprises an image gradient integration module and an image gradient histogram reprojection module, the image gradient arrangement module is used for calculating and comparing image gradients, and the image contrast integration module is used for normalizing local contrast of an image;
the conclusion exporting platform comprises a histogram combination module, a judgment module and an exporting module, the judgment module is electrically connected with the histogram combination module, the exporting module is electrically connected with the judgment module, the histogram combination module is used for combining histogram vectors in all the blocks to obtain integral feature vectors, the judgment module is used for judging the feature vectors and then obtaining number results, and the exporting module is used for exporting the results to other platforms.
As a preferred technical solution of the present invention, the peripheral device input module is configured as a video capture board card for taking a picture or video and then generating data.
As a preferred technical scheme of the invention, the real-time analysis module adopts an ARM platform terminal computing technology, analyzes and extracts key frame data in a video or a picture in real time and then preprocesses the key frame.
As a preferred technical scheme of the invention, the feature identification module adopts an ARM platform terminal computing technology to identify the feature items in the picture or the video, thereby facilitating the subsequent detection.
As a preferred technical solution of the present invention, the content detection module employs an ARM platform terminal computing technology to detect feature items in a picture, which facilitates subsequent processing, the image processing module employs an ARM platform terminal computing technology to cut a picture, and divides white and black in the picture into a plurality of levels according to a logarithmic relationship, and the image normalization module employs an ARM platform terminal computing technology to perform a series of standard processing transformations on the image, so as to transform the image into a fixed standard form.
As a preferred technical scheme of the invention, the image gradient arrangement module adopts an ARM platform terminal computing technology, and takes an image as a two-dimensional discrete function, and the formula is as follows:
G(x,y)＝dx(i,j)+dy(i,j)；
dx(i,j)＝I(i+1,j)-I(i,j)；
dy(i,j)＝I(i,j+1)-I(i,j)；
wherein, I is the value of the image pixel, and (I, j) is the coordinate of the pixel, and the image contrast integration module adopts ARM platform terminal computing technology to place the gradient of each data in a more standard form, so as to reduce the variation of the model which needs to be considered.
As a preferred technical scheme of the invention, the histogram combination module adopts ARM platform terminal computing technology, runs in a computer and is used for combining histograms in all blocks to obtain an integral feature vector, and the judgment module adopts ARM platform terminal computing technology and is used for judging features in images, removing irrelevant factors and then obtaining the number of people result.
As a preferred technical solution of the present invention, the display device further includes a display module, the display module includes a data line and a display, the data line is electrically connected to the determination module, the display is electrically connected to the data line, the data line is used to import a result to the display, and then the display displays the result.
As a preferred technical scheme of the invention, the data processing platform, the data analysis platform and the conclusion derivation platform are set as ARM platform hosts, so that the structure is small and the installation is convenient.
Meanwhile, the invention also provides an indoor personnel density detection method based on the ARM platform, which specifically comprises the following steps:
s1: acquiring data, acquiring a video or a photo through a video acquisition board card, inputting the video or the photo to a real-time analysis module, separating a background and a target in the photo or the video by using a computer, further analyzing and tracking the target appearing in a camera scene, and preprocessing a key action picture in the movement change of a role or an object;
s2: processing an image, transmitting preprocessed image data into a feature recognition algorithm, processing, analyzing and understanding the image by using a computer to recognize targets and objects in various different modes, detecting the content in the image, primarily cutting the image to make a plurality of images containing data have the same size, and make the image become a gray image, because an initial data image can obtain a plurality of duplicate images after being subjected to some processing or attack, the duplicate images need to be perfectly normalized, and the images can obtain standard images in the same form after being subjected to image normalization processing with the same parameters, so that the images can be conveniently analyzed subsequently;
s3: analyzing the image by using a formula:
G(x,y)＝dx(i,j)+dy(i,j)；
dx(i,j)＝I(i+1,j)-I(i,j)；
dy(i,j)＝I(i,j+1)-I(i,j)；
calculating the gradient of an image, obtaining an image gradient histogram, projecting and comparing the gradient histogram, wherein the gradient strength must be locally normalized in order to explain the change of illumination and contrast, each pixel in each block votes for a direction histogram, the shape of each block can be rectangular or circular, and the direction value of the direction histogram can be 0-180 degrees or 0-360 degrees, which depends on whether the gradient has positive or negative;
s4: and exporting the result, combining histogram vectors in all blocks to obtain an integral feature vector, judging the features by a computer to obtain a specific result, and exporting the result in real time.
(III) advantageous effects
1. According to the indoor personnel density detection system based on the ARM platform, the data acquisition platform can acquire personnel flow in real time and preprocess video pictures in real time, the judgment range is wide, and a user does not need to walk through a fixed route;
2. according to the indoor personnel density detection system based on the ARM platform, the data processing platform can search and cut the image in real time, process the image into a gray image and normalize the image;
3. according to the indoor personnel density detection system based on the ARM platform, the data analysis platform can calculate and compare the gradient of the image in real time, local normalization is carried out on the gradient histogram of the image, and the accuracy is high.
4. According to the indoor personnel density detection system based on the ARM platform, the conclusion derivation platform can provide interface support for multiple systems, and data access support is conveniently provided for other systems.
5. According to the indoor personnel density detection system based on the ARM platform, the circuit board is formed by all the modules, the size is small, the installation is convenient, and the existing decoration is not damaged.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic block diagram of an indoor personnel density detection system based on an ARM platform according to the present invention;
FIG. 2 is a schematic block diagram of specific modules of the indoor personnel density detection system based on the ARM platform according to the present invention;
FIG. 3 is a schematic block diagram of a flow of the indoor personnel density detection method based on the ARM platform.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it is to be understood that the terms "longitudinal", "upper", "lower", "left", "right", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
As shown in fig. 1-2, the system for detecting indoor personnel density based on the ARM platform includes a data acquisition platform, a data processing platform, a data analysis platform and a conclusion derivation platform, wherein the data acquisition platform is electrically connected to the data processing platform, the data processing platform is electrically connected to the data analysis platform, and the data analysis platform is electrically connected to the conclusion derivation platform, wherein:
the data acquisition platform comprises a peripheral equipment input module and a real-time analysis module, the peripheral equipment input module is electrically connected with the real-time analysis module, the real-time analysis module comprises a key frame extraction module and a key frame preprocessing module, the key frame extraction module is used for extracting key frames, the specific positions of the key frames are the frames where key actions are located in indoor roles or object motion changes, then the key frames are preprocessed, the data processing platform is convenient to process, the calculation amount on an image level is reduced, the key frame extraction time is shortened, the peripheral equipment input module is used for inputting video and picture data, and the real-time analysis module is used for extracting and preprocessing the video and picture data;
the data processing platform comprises a feature identification module, a content detection module, an image processing module and an image normalization module, the feature recognition module is electrically connected with the content detection module, the image processing module is electrically connected with the content detection module, the image normalization module is electrically connected with the image processing module, the feature recognition module is used for processing and understanding the image, to identify various different modes of objects and objects, e.g., static objects and dynamic objects, a content detection module to retrieve content of the picture, filter spam in the picture, for example, a table or a chair, the image processing module is configured to crop a picture and process the picture into a grayscale picture, specifically, process the grayscale picture into an image with only one sampling color per pixel, and the image normalization module is configured to integrate the picture and unify parameters;
the data analysis module comprises an image gradient arrangement module and an image contrast integration module, the image gradient arrangement module is electrically connected with the image contrast integration module, the image gradient arrangement module comprises an image gradient integration module and an image gradient histogram reprojection module, the image gradient arrangement module is used for calculating and comparing image gradients, and the image contrast integration module is used for normalizing local contrast of an image;
the conclusion exporting platform comprises a histogram combination module, a judgment module and an exporting module, the judgment module is electrically connected with the histogram combination module, the exporting module is electrically connected with the judgment module, the histogram combination module is used for combining histogram vectors in all the modules to obtain an integral feature vector, the judgment module is used for judging the feature vector and then obtaining a number result, and the exporting module is used for exporting the result to other platforms, for example: display, cell-phone and computer.
Specifically, the peripheral device input module is configured as a video acquisition board card for shooting a picture or video and then generating data.
Specifically, the real-time analysis module analyzes and extracts key frame data in a video or a picture in real time by adopting an ARM platform terminal computing technology and then preprocesses a key frame, wherein the key frame is specifically the frame where a key action is located in the motion change of an indoor role or object.
Specifically, the feature identification module adopts an ARM platform terminal computing technology to identify feature items in the picture or the video, so that subsequent detection is facilitated.
Specifically, the content detection module adopts an ARM platform terminal computing technology to detect characteristic items in the picture, so that subsequent processing is facilitated, the image processing module adopts the ARM platform terminal computing technology to cut the picture and divide white and black in the picture into a plurality of grades according to a logarithmic relation, and the image normalization module adopts the ARM platform terminal computing technology to perform a series of standard processing transformation on the picture and enable the image to be transformed into a fixed standard form.
Specifically, the image gradient arrangement module adopts an ARM platform terminal computing technology to view an image as a two-dimensional discrete function, and the formula is as follows:
G(x,y)＝dx(i,j)+dy(i,j)；
dx(i,j)＝I(i+1,j)-I(i,j)；
dy(i,j)＝I(i,j+1)-I(i,j)；
wherein, I is the value of the image pixel, and (I, j) is the coordinate of the pixel, and the image contrast integration module adopts ARM platform terminal computing technology to place the gradient of each data in a more standard form, so as to reduce the variation of the model which needs to be considered.
Specifically, the histogram combination module adopts an ARM platform terminal computing technology, operates in a computer, and is used for combining histograms in all blocks to obtain an integral feature vector, and the judgment module adopts an ARM platform terminal computing technology and is used for judging features in an image, removing irrelevant factors, and then obtaining a number result.
Specifically, the display device further comprises a display module, wherein the display module comprises a data line and a display, the data line is electrically connected with the judging module, the display is electrically connected with the data line, the data line is used for leading the result into the display, and then the display displays the result.
Specifically, the data processing platform, the data analysis platform and the data export platform are set as ARM platform hosts, so that the data processing platform is small in structure, convenient to install, suitable for indoor places and small in influence on existing decoration.
As shown in fig. 3, the present invention further provides an indoor personnel density detection method based on the ARM platform, which specifically includes the following steps:
s1: acquiring data, acquiring a video or a photo through a video acquisition board card, inputting the video or the photo to a real-time analysis module, separating a background and a target in the photo or the video by using a computer, further analyzing and tracking the target appearing in a camera scene, and preprocessing a key action picture in the movement change of a role or an object;
s2: processing an image, transmitting preprocessed image data into a feature recognition algorithm, processing, analyzing and understanding the image by using a computer to recognize targets and objects in various different modes, detecting the content in the image, primarily cutting the image to make a plurality of images containing data have the same size, and make the image become a gray image, because an initial data image can obtain a plurality of duplicate images after being subjected to some processing or attack, the duplicate images need to be perfectly normalized, and the images can obtain standard images in the same form after being subjected to image normalization processing with the same parameters, so that the images can be conveniently analyzed subsequently;
s3: analyzing the image by using a formula:
G(x,y)＝dx(i,j)+dy(i,j)；
dx(i,j)＝I(i+1,j)-I(i,j)；
dy(i,j)＝I(i,j+1)-I(i,j)；
calculating the gradient of an image, obtaining an image gradient histogram, projecting and comparing the gradient histogram, wherein the gradient strength must be locally normalized in order to explain the change of illumination and contrast, each pixel in each block votes for a direction histogram, the shape of each block can be rectangular or circular, and the direction value of the direction histogram can be 0-180 degrees or 0-360 degrees, which depends on whether the gradient has positive or negative;
s4: and exporting the result, combining histogram vectors in all blocks to obtain an integral feature vector, judging the features by a computer to obtain a specific result, and exporting the result in real time.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. Indoor personnel density detecting system based on ARM platform, including data acquisition platform, data processing platform, data analysis platform and conclusion derivation platform, its characterized in that, data acquisition platform with data processing platform electric connection, data processing platform with data analysis platform electric connection, data analysis platform with conclusion derivation platform electric connection, wherein:
the data acquisition platform comprises a peripheral equipment input module and a real-time analysis module, the peripheral equipment input module is electrically connected with the real-time analysis module, the real-time analysis module comprises a key frame extraction module and a key frame preprocessing module, the peripheral equipment input module is used for inputting video and picture data, and the real-time analysis module is used for analyzing and preprocessing the video and picture data;
the data processing platform comprises a feature recognition module, a content detection module, an image processing module and an image normalization module, wherein the feature recognition module is electrically connected with the content detection module, the image processing module is electrically connected with the content detection module, the image normalization module is electrically connected with the image processing module, the feature recognition module is used for processing and understanding images so as to recognize targets and objects in various different modes, the content detection module is used for retrieving the content of the images and filtering the garbage information in the images, the image processing module is used for cutting the images and processing the images into gray level images, and the image normalization module is used for integrating the images and unifying parameters;
the data analysis module comprises an image gradient arrangement module and an image contrast integration module, the image gradient arrangement module is electrically connected with the image contrast integration module, the image gradient arrangement module comprises an image gradient integration module and an image gradient histogram reprojection module, the image gradient arrangement module is used for calculating and comparing image gradients, and the image contrast integration module is used for normalizing local contrast of an image;
the conclusion exporting platform comprises a histogram combination module, a judgment module and an exporting module, the judgment module is electrically connected with the histogram combination module, the exporting module is electrically connected with the judgment module, the histogram combination module is used for combining histogram vectors in all the modules to obtain integral feature vectors, the judgment module is used for judging the feature vectors and then obtaining number results, and the exporting module is used for exporting the results to other platforms.
2. The ARM platform based indoor people density detection system of claim 1, wherein the peripheral device input module is configured as a video capture board card for taking pictures or videos and then generating data.
3. The ARM platform based indoor personnel density detection system of claim 1, wherein the real-time analysis module adopts ARM platform terminal computing technology, analyzes and extracts keyframe data in a video or a picture in real time and then preprocesses the keyframe.
4. The ARM platform based indoor personnel density detection system of claim 1, wherein the feature recognition module uses ARM platform terminal computing technology to recognize feature items in pictures or videos for subsequent detection.
5. The system of claim 1, wherein the content detection module employs an ARM platform terminal computing technology to detect feature items in the picture for subsequent processing, the image processing module employs an ARM platform terminal computing technology to crop the picture and divide the white and black colors of the picture into several levels according to a logarithmic relationship, and the image normalization module employs an ARM platform terminal computing technology to perform a series of standard processing transformations on the image to a fixed standard form.
6. The ARM platform based indoor people density detection system of claim 4, wherein the image gradient arrangement module adopts ARM platform terminal computing technology to view an image as a two-dimensional discrete function, and the formula is as follows:
G(x,y)＝dx(i,j)+dy(i,j)；
dx(i,j)＝I(i+1,j)-I(i,j)；
dy(i,j)＝I(i,j+1)-I(i,j)；
wherein, I is the value of the image pixel, and (I, j) is the coordinate of the pixel, and the image contrast integration module adopts ARM platform terminal computing technology to place the gradient of each data in a more standard form, so as to reduce the variation of the model which needs to be considered.
7. The ARM platform based indoor personnel density detection system of claim 1, wherein the histogram combination module adopts ARM platform terminal computing technology, operates in a computer and is used for combining histograms in all blocks to obtain an integral feature vector, and the judgment module adopts ARM platform terminal computing technology and is used for judging features in an image, removing irrelevant factors and then obtaining a personnel number result.
8. The ARM platform based indoor personnel density detection system of claim 1, further comprising a plurality of display modules, wherein the display modules comprise data lines and a display, the data lines are electrically connected with the determination module, the display is electrically connected with the data lines, the data lines are used for leading results to the display, and then the display displays the results.
9. The ARM platform based indoor people density detection system of claim 1, wherein the data processing platform, the data analysis platform and the data export platform are configured as an ARM platform host.
10. The indoor personnel density detection method based on the ARM platform is characterized by comprising the following steps:
s1: acquiring data, acquiring a video or a photo through a video acquisition board card, inputting the video or the photo to a real-time analysis module, separating a background and a target in the photo or the video by using a computer, further analyzing and tracking the target appearing in a camera scene, and preprocessing a key action picture in the movement change of a role or an object;
s2: processing an image, transmitting preprocessed image data into a feature recognition algorithm, processing, analyzing and understanding the image by using a computer to recognize targets and objects in various different modes, detecting the content in the image, primarily cutting the image to make a plurality of images containing data have the same size, and make the image become a gray image, because an initial data image can obtain a plurality of duplicate images after being subjected to some processing or attack, the duplicate images need to be perfectly normalized, and the images can obtain standard images in the same form after being subjected to image normalization processing with the same parameters, so that the images can be conveniently analyzed subsequently;
s3: analyzing the image by using a formula:
G(x,y)＝dx(i,j)+dy(i,j)；
dx(i,j)＝I(i+1,j)-I(i,j)；
dy(i,j)＝I(i,j+1)-I(i,j)；
calculating the gradient of an image, obtaining an image gradient histogram, projecting and comparing the gradient histogram, wherein the gradient strength must be locally normalized in order to explain the change of illumination and contrast, each pixel in each block votes for a direction histogram, the shape of each block can be rectangular or circular, and the direction value of the direction histogram can be 0-180 degrees or 0-360 degrees, which depends on whether the gradient has positive or negative;
s4: and exporting the result, combining histogram vectors in all blocks to obtain an integral feature vector, judging the features by a computer to obtain a specific result, and exporting the result in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110390336.3A CN113111777A (en) | 2021-04-12 | 2021-04-12 | Indoor personnel density detection system and detection method based on ARM platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110390336.3A CN113111777A (en) | 2021-04-12 | 2021-04-12 | Indoor personnel density detection system and detection method based on ARM platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113111777A true CN113111777A (en) | 2021-07-13 |
Family
ID=76715766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110390336.3A Pending CN113111777A (en) | 2021-04-12 | 2021-04-12 | Indoor personnel density detection system and detection method based on ARM platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111777A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113762289A (en) * | 2021-09-30 | 2021-12-07 | 广州理工学院 | Image matching system based on ORB algorithm and matching method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170017846A1 (en) * | 2015-07-15 | 2017-01-19 | Umm Al-Qura University | Crowd and traffic monitoring apparatus and method |
| CN106382718A (en) * | 2016-08-30 | 2017-02-08 | 广州穗剑实验室科技有限公司 | Ventilation and air-conditioning control system based on real-time video analysis |
| CN106548158A (en) * | 2016-11-07 | 2017-03-29 | 华南理工大学 | Crowd density intelligent monitor system and method based on machine vision |
| CN108564008A (en) * | 2018-03-28 | 2018-09-21 | 厦门瑞为信息技术有限公司 | A kind of real-time pedestrian and method for detecting human face based on ZYNQ |
| CN109905675A (en) * | 2019-03-13 | 2019-06-18 | 武汉大学 | A kind of mine personnel monitoring system based on computer vision and method |
-
2021
- 2021-04-12 CN CN202110390336.3A patent/CN113111777A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170017846A1 (en) * | 2015-07-15 | 2017-01-19 | Umm Al-Qura University | Crowd and traffic monitoring apparatus and method |
| CN106382718A (en) * | 2016-08-30 | 2017-02-08 | 广州穗剑实验室科技有限公司 | Ventilation and air-conditioning control system based on real-time video analysis |
| CN106548158A (en) * | 2016-11-07 | 2017-03-29 | 华南理工大学 | Crowd density intelligent monitor system and method based on machine vision |
| CN108564008A (en) * | 2018-03-28 | 2018-09-21 | 厦门瑞为信息技术有限公司 | A kind of real-time pedestrian and method for detecting human face based on ZYNQ |
| CN109905675A (en) * | 2019-03-13 | 2019-06-18 | 武汉大学 | A kind of mine personnel monitoring system based on computer vision and method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113762289A (en) * | 2021-09-30 | 2021-12-07 | 广州理工学院 | Image matching system based on ORB algorithm and matching method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109819208B (en) | Intensive population security monitoring management method based on artificial intelligence dynamic monitoring | |
| US7003135B2 (en) | System and method for rapidly tracking multiple faces | |
| CN105701467B (en) | A kind of more people's abnormal behaviour recognition methods based on human figure feature | |
| US20130163822A1 (en) | Airborne Image Capture and Recognition System | |
| US20120183212A1 (en) | Identifying descriptor for person or object in an image | |
| US20130170711A1 (en) | Edge detection image capture and recognition system | |
| US20080187172A1 (en) | Tracking Apparatus And Tracking Method | |
| CN109918971B (en) | Method and device for detecting number of people in monitoring video | |
| CN108960067A (en) | Real-time train driver motion recognition system and method based on deep learning | |
| CN109359577B (en) | System for detecting number of people under complex background based on machine learning | |
| CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
| CN113269091A (en) | Personnel trajectory analysis method, equipment and medium for intelligent park | |
| WO2023165616A1 (en) | Method and system for detecting concealed backdoor of image model, storage medium, and terminal | |
| CN111582118A (en) | Face recognition method and device | |
| WO2019088333A1 (en) | Method for recognizing human body activity on basis of depth map information and apparatus therefor | |
| CN114511592A (en) | Personnel trajectory tracking method and system based on RGBD camera and BIM system | |
| CN113111777A (en) | Indoor personnel density detection system and detection method based on ARM platform | |
| CN114067396A (en) | Vision learning-based digital management system and method for live-in project field test | |
| CN117475353A (en) | Video-based abnormal smoke identification method and system | |
| CN112183287A (en) | People counting method of mobile robot under complex background | |
| Solina et al. | 15 seconds of fame-an interactive, computer-vision based art installation | |
| CN113743380B (en) | Active tracking method based on video image dynamic monitoring | |
| TWI777689B (en) | Method of object identification and temperature measurement | |
| US20220036114A1 (en) | Edge detection image capture and recognition system | |
| CN210442821U (en) | Face recognition device |
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 |