CN114025078A - Binocular three-layer framework - Google Patents
Binocular three-layer framework Download PDFInfo
- Publication number
- CN114025078A CN114025078A CN202111133485.8A CN202111133485A CN114025078A CN 114025078 A CN114025078 A CN 114025078A CN 202111133485 A CN202111133485 A CN 202111133485A CN 114025078 A CN114025078 A CN 114025078A
- Authority
- CN
- China
- Prior art keywords
- visual
- unit
- binocular
- gate
- processing unit
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/95—Computational photography systems, e.g. light-field imaging systems
- H04N23/951—Computational photography systems, e.g. light-field imaging systems by using two or more images to influence resolution, frame rate or aspect ratio
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/38—Individual registration on entry or exit not involving the use of a pass with central registration
Abstract
The invention provides a binocular three-layer architecture, which divides a traffic logic into three independent units, reduces the operation intensity of each unit, ensures that the whole equipment has low manufacturing cost, is quick and efficient in subsequent maintenance, and is convenient for quick update of a subsequent system. The vision sensing unit is a first-layer framework and comprises a binocular camera and a first processor part, wherein RGB images captured by the binocular camera are transmitted into the first processing part, and the first processing part converts the RGB images into depth images and outputs the depth images; the visual processing unit performs operation processing on the depth image transmitted by the visual sensing unit, calculates the length, width, height and three-dimensional size of a target, distinguishes the type of the target, analyzes the motion trend and speed of the target, and finally transmits the obtained information to the visual traffic logic unit; the visual passing logic unit integrates the information fed back by the visual processing unit and preset passing information, carries out the passing operation judgment of the gate machine and determines whether the gate machine opens or closes the gate.
Description
Technical Field
The invention relates to the technical field of gate passing, in particular to a binocular three-layer framework.
Background
With the development of the technology, in the passing process of the gate, the requirement on the passing logic is not the pure infrared dot matrix logic, but the visual technology which is higher in requirement, safer and more reliable is required. The binocular vision technology is a mature technology, but the technology is combined with the traffic logic, and in a groping stage, the existing structure combining the binocular vision technology and the traffic logic directly transmits the pictures shot by vision to the traffic logic module for processing, so that the traffic logic module needs to be configured with a CPU with strong processing capacity, the manufacturing cost of equipment corresponding to the whole framework is high, and when the equipment is assembled, the interfaces of the vision processing module and the CPU must be arranged in a one-to-one correspondence manner, the requirement on the equipment is high, the equipment cannot be suitable for replacing general equipment, and the quick updating of a subsequent system is not facilitated.
Disclosure of Invention
In order to solve the problems, the invention provides a binocular three-layer architecture, which divides a traffic logic into three independent units, reduces the operation intensity of each unit, ensures that the whole equipment has low manufacturing cost, is quick and efficient in subsequent maintenance, and facilitates quick update and update of a subsequent system.
A binocular three-layer architecture, comprising:
a visual sense unit;
a vision processing unit;
a visual pass logic unit;
the vision sensing unit is a first-layer framework and comprises a binocular camera and a first processor part, wherein RGB images captured by the binocular camera are transmitted into the first processor part, and the first processor part converts the RGB images into depth images and outputs the depth images;
the visual processing unit performs operation processing on the depth image transmitted by the visual sensing unit, calculates the length, width, height and three-dimensional size of a target, distinguishes the type of the target, analyzes the motion trend and speed of the target, and finally transmits the obtained information to the visual traffic logic unit;
the visual passing logic unit integrates the information fed back by the visual processing unit and preset passing information, carries out the passing operation judgment of the gate machine and determines whether the gate machine opens or closes the gate.
It is further characterized in that:
the binocular camera and the first processor part corresponding to the vision sensing unit are arranged at the top of the gate;
the vision processing unit is arranged in the gate;
the visual passing logic unit is arranged in the gate;
the communication data interface between the visual sensing unit and the visual processing unit is independently arranged;
the communication interface between the vision processing unit and the vision logic unit is independently arranged.
After the technical scheme is adopted, the visual sensing unit, the visual processing unit and the visual traffic logic unit are respectively and independently arranged, the visual sensing unit converts RGB images into depth images and outputs the depth images to the visual processing unit, the visual processing unit carries out operation processing on the depth images transmitted by the visual sensing unit, calculates the three-dimensional size of the length, the width and the height of a target, distinguishes the type of the target and analyzes the motion trend and the speed of the target, finally transmits the obtained information to the visual traffic logic unit, the visual traffic logic unit integrates the information fed back by the visual processing unit and preset traffic information, carries out operation judgment on the traffic of the gate machine and determines whether the gate machine is opened or closed, the traffic logic is divided into three independent units, the operation intensity of each unit is reduced, the manufacturing cost of the whole equipment is low, the subsequent maintenance is quick and efficient, and the subsequent system can be updated quickly and conveniently.
Drawings
FIG. 1 is a schematic diagram of the logic structure of the present invention;
FIG. 2 is a logic flow diagram for the opening or closing of the gate of the present invention.
Detailed Description
A binocular three-layer architecture is characterized by comprising a vision sensing unit, a vision processing unit and a vision passing logic unit;
the vision sensing unit is a first-layer framework and comprises a binocular camera and a first processor part, wherein RGB images captured by the binocular camera are transmitted into the first processing part, and the first processing part converts the RGB images into depth images and outputs the depth images;
the visual processing unit is a second-layer framework and is used for performing operation processing on the depth image transmitted by the visual sensing unit, calculating the three-dimensional size of the length, the width and the height of the target, distinguishing the type of the target, analyzing the motion trend and the speed of the target and finally transmitting the obtained information to the visual traffic logic unit;
the visual passing logic unit is a third-layer structure and integrates the information fed back by the visual processing unit and preset passing information to carry out the operation judgment of the passing of the gate machine and determine whether the gate machine is opened or closed.
The vision processing unit is arranged in the gate;
the visual passing logic unit is arranged in the gate;
the communication data interface between the visual sensing unit and the visual processing unit is independently arranged;
the communication interface between the vision processing unit and the vision logic unit is independently arranged.
During specific implementation, the binocular camera corresponding to the vision sensing unit and the first processor part are both arranged at the top of the gate, and the installation position of the binocular camera is a height position 2.7-3.1 m away from the ground level;
when the binocular camera is installed, the horizontal angle between the binocular camera and the ground plane is +/-3 degrees, and the binocular camera is arranged towards the area of the gate passage;
the visual sensing unit and the visual processing unit have larger communication data volume and adopt the Ethernet for communication; the communication interface between the vision processing unit and the vision logic unit adopts RS232 and Ethernet to communicate. Standard interfaces can be defined between every two layers of architectures, so that a new binocular three-layer architecture can be formed by later separation or other brands;
the system functional units are effectively divided, each system takes its own role, and problems can be easily found during maintenance to give medicines according to symptoms; the three-tier architecture distributes the computing power of the core processor and allows the current, less expensive CPU to perform each function.
In specific implementation, after the visual logic unit performs logic judgment each time, the next round of information acquisition and judgment are performed again; the logic flow (see fig. 2) is that after the setting is started, the logic judgment of the passing authorization is carried out, when the gate is judged to be capable of passing, the door is opened, then the visual sensing unit carries out visual channel detection, the door opening state is continued under the condition that the passenger does not pass, until the visual channel detects that the passenger passes, the visual logic unit drives the gate to close the door, and then the next round of information acquisition and the judgment are carried out again; when the setting is started and the gate is not opened by the logic judgment gate for passing authorization, resetting and entering the next round of information acquisition and judgment again.
The working principle is as follows: the visual sensing unit, the visual processing unit and the visual traffic logic unit are respectively and independently arranged, the visual sensing unit converts RGB images into depth images and outputs the depth images to the visual processing unit, the visual processing unit performs operation processing on the depth images transmitted by the visual sensing unit, calculates the three-dimensional size of the length, the width and the height of a target, distinguishes the type of the target, analyzes the motion trend and the speed of the target, finally transmits the obtained information to the visual traffic logic unit, the visual traffic logic unit synthesizes the information fed back by the visual processing unit and preset traffic information to perform operation judgment on the traffic of the gate machine and determines whether the gate machine is opened or closed, the traffic logic is divided into three independent units, the operation intensity of each unit is reduced, the manufacturing cost of the whole equipment is low, the subsequent maintenance is quick and efficient, and the subsequent system can be updated quickly and conveniently.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (6)
1. A binocular three-layer architecture, comprising:
a visual sense unit;
a vision processing unit;
a visual pass logic unit;
the vision sensing unit is a first-layer framework and comprises a binocular camera and a first processor part, wherein RGB images captured by the binocular camera are transmitted into the first processor part, and the first processor part converts the RGB images into depth images and outputs the depth images;
the visual processing unit performs operation processing on the depth image transmitted by the visual sensing unit, calculates the length, width, height and three-dimensional size of a target, distinguishes the type of the target, analyzes the motion trend and speed of the target, and finally transmits the obtained information to the visual traffic logic unit;
the visual passing logic unit integrates the information fed back by the visual processing unit and preset passing information, carries out the passing operation judgment of the gate machine and determines whether the gate machine opens or closes the gate.
2. The binocular three-layer architecture of claim 1, wherein: the binocular camera and the first processor part corresponding to the vision sensing unit are arranged at the top of the gate.
3. The binocular three-layer architecture of claim 1, wherein: the vision processing unit is arranged in the gate.
4. The binocular three-layer architecture of claim 1, wherein: the visual passing logic unit is arranged in the gate.
5. The binocular three-layer architecture of claim 1, wherein: and the communication data interface between the visual sensing unit and the visual processing unit is independently arranged.
6. The binocular three-layer architecture of claim 1, wherein: the communication interface between the vision processing unit and the vision logic unit is independently arranged.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111133485.8A CN114025078A (en) | 2021-09-27 | 2021-09-27 | Binocular three-layer framework |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111133485.8A CN114025078A (en) | 2021-09-27 | 2021-09-27 | Binocular three-layer framework |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114025078A true CN114025078A (en) | 2022-02-08 |
Family
ID=80054990
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111133485.8A Pending CN114025078A (en) | 2021-09-27 | 2021-09-27 | Binocular three-layer framework |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114025078A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107274368A (en) * | 2017-06-16 | 2017-10-20 | 大连交通大学 | Compatible vision processing system and method |
US20190007675A1 (en) * | 2017-06-29 | 2019-01-03 | Archermind Technology (Nanjing) Co., Ltd. | Method and apparatus for acquiring three-dimensional image using two cameras |
CN113393603A (en) * | 2020-03-11 | 2021-09-14 | 杭州海康威视数字技术股份有限公司 | Control method and system of channel gate |
-
2021
- 2021-09-27 CN CN202111133485.8A patent/CN114025078A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107274368A (en) * | 2017-06-16 | 2017-10-20 | 大连交通大学 | Compatible vision processing system and method |
US20190007675A1 (en) * | 2017-06-29 | 2019-01-03 | Archermind Technology (Nanjing) Co., Ltd. | Method and apparatus for acquiring three-dimensional image using two cameras |
CN113393603A (en) * | 2020-03-11 | 2021-09-14 | 杭州海康威视数字技术股份有限公司 | Control method and system of channel gate |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104320615B (en) | A kind of intelligent video safety-protection system and its signal processing method | |
CN104270570A (en) | Binocular video camera and image processing method thereof | |
CN103379266A (en) | High-definition web camera with video semantic analysis function | |
CN106485927A (en) | A kind of intelligent transportation violation information harvester and acquisition method | |
CN104157138A (en) | Urban road video monitoring system | |
US11161456B1 (en) | Using the image from a rear view camera in a three-camera electronic mirror system to provide early detection of on-coming cyclists in a bike lane | |
CN105516661B (en) | Principal and subordinate's target monitoring method that fisheye camera is combined with ptz camera | |
US11586843B1 (en) | Generating training data for speed bump detection | |
CN114093142A (en) | Object-aware temperature anomaly monitoring and early warning by combining visual and thermal sensing | |
CN202352075U (en) | Five-in-one electronic police system | |
CN110194107A (en) | A kind of vehicle intelligent back-sight visual system of integrative display and warning function | |
CN108597225A (en) | Intelligent road traffic surveillance and control system and its monitoring method | |
CN110939351A (en) | Visual intelligent control method and visual intelligent control door | |
CN107431747A (en) | Camera device | |
CN112153334A (en) | Intelligent video box equipment for safety management and corresponding intelligent video analysis method | |
CN113012469A (en) | Intelligent traffic early warning system based on target recognition | |
CN107748786B (en) | Warning situation big data management system | |
CN111062319B (en) | Driver call detection method based on active infrared image | |
CN111723708A (en) | Van-type cargo vehicle carriage door state recognition device and system based on deep learning | |
CN203812397U (en) | Urban road video monitor system | |
CN114025078A (en) | Binocular three-layer framework | |
CN110659593A (en) | Urban haze visibility detection method based on improved DiracNet | |
WO2024037408A1 (en) | Underground coal mine pedestrian detection method based on image fusion and feature enhancement | |
CN109602585B (en) | Blind guiding glasses and anti-collision early warning method thereof | |
CN101393602B (en) | Be applied to the eye identifying method for tracing of personnel control |
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 |