CN114390180A - Desensitization data acquisition method for public venue and desensitization camera - Google Patents
Desensitization data acquisition method for public venue and desensitization camera Download PDFInfo
- Publication number
- CN114390180A CN114390180A CN202210087964.9A CN202210087964A CN114390180A CN 114390180 A CN114390180 A CN 114390180A CN 202210087964 A CN202210087964 A CN 202210087964A CN 114390180 A CN114390180 A CN 114390180A
- Authority
- CN
- China
- Prior art keywords
- desensitization
- camera
- camera body
- identification
- image
- 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
- 238000000586 desensitisation Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 230000006870 function Effects 0.000 claims abstract description 12
- 230000000007 visual effect Effects 0.000 claims abstract description 7
- 230000005540 biological transmission Effects 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 6
- 239000004744 fabric Substances 0.000 claims description 56
- 238000004140 cleaning Methods 0.000 claims description 55
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 53
- 230000004807 localization Effects 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 14
- 239000000463 material Substances 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000000428 dust Substances 0.000 description 4
- 230000017525 heat dissipation Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001125 extrusion Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 241001337998 Machilus Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000007605 air drying Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009736 wetting Methods 0.000 description 1
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
- H04N23/50—Constructional details
- H04N23/52—Elements optimising image sensor operation, e.g. for electromagnetic interference [EMI] protection or temperature control by heat transfer or cooling elements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B1/00—Cleaning by methods involving the use of tools
- B08B1/10—Cleaning by methods involving the use of tools characterised by the type of cleaning tool
- B08B1/14—Wipes; Absorbent members, e.g. swabs or sponges
- B08B1/143—Wipes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B1/00—Cleaning by methods involving the use of tools
- B08B1/30—Cleaning by methods involving the use of tools by movement of cleaning members over a surface
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/617—Upgrading or updating of programs or applications for camera control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Studio Devices (AREA)
Abstract
The invention belongs to the field of cameras, in particular to a desensitization data acquisition method for a public venue and a desensitization camera, wherein the desensitization camera realizes complete localization of visual analysis of the desensitization camera through an identification module of a desensitization camera body, and can meet the requirements of deep analysis of a specified application scene and an identification target; the desensitization camera body only provides desensitization information such as seat-up rate, queuing number and the like for a background, and desensitization original images do not need to be subjected to any local storage, network transmission and rear-end processing, so that the desensitization problem is eliminated on one side of an image identification terminal; the desensitization image information acquired by the desensitization camera is immediately processed only in the random storage of the equipment, and is immediately discarded after identification and analysis, so that burning after reading is realized; by customizing hardware, functions and algorithms, the desensitization camera can realize higher cost performance; the desensitization camera adopts a credible edge computing 'wrapping' mode, so that the running safety of the system can be guaranteed.
Description
Technical Field
The invention relates to the field of cameras, in particular to a desensitization data acquisition method for a public venue and a desensitization camera.
Background
The intelligent recognition of various specified image targets in a public venue, such as recognition of various image targets in a large field of view, a complex environment and a variable scene, has put high demands on the computing performance of a system, and even puts a challenge on the current mainstream algorithm if tiny targets are included.
In order to meet the above requirements as much as possible, the current market mainstream solution for large-field-of-view image target identification is to adopt a system configuration of "front end-middle end-back end", and to give a large amount of calculation to a background process, where a front-end camera is only used for collecting image information, but in each link related to local storage, network transmission, and background process of a private image, the solution inevitably has potential safety hazards in various layers. Therefore, a desensitization data acquisition method and a desensitization camera with high cost performance for a public venue are provided for solving the problems.
In the desensitization intelligent camera system, through customization of hardware, functions and algorithms, target recognition and intelligent analysis are completely completed in the intelligent camera, only information after calculation and desensitization is output externally, and extremely high privacy safety can be realized at a high cost performance.
Disclosure of Invention
In order to make up for the defects of the prior art and solve the problem of potential safety hazards in links related to local storage, network transmission and background processing of private images in a front-end-middle-end-rear-end mode adopted by the mainstream solution of the current market, the invention provides a desensitization data acquisition method and a desensitization camera for a public venue.
The technical scheme adopted by the invention for solving the technical problems is as follows: a desensitization data acquisition method for a public venue, comprising the steps of:
s1: the identification module of the desensitization camera body realizes complete localization of visual analysis of the desensitization camera, and can meet the requirements of deep analysis of a specified application scene and an identification target;
s2: the desensitization camera body is used for carrying out image acquisition and intelligent analysis on various targets including tiny targets in the identification area, analyzing and generating user target data such as desensitized attendance rate, queuing number and the like, providing the desensitization information to a background only, and avoiding carrying out any local storage, network transmission and rear-end processing on the desensitization original image information so as to eliminate the personal privacy problem on one side of an image identification terminal;
s3: the desensitization image information acquired by the desensitization camera body is only immediately processed in the random storage device of the equipment, and is immediately discarded after identification and analysis, so that burning after reading is realized; during work, the realization of burning after reading is as follows: (1) after the image is acquired by the camera, the image is stored only in a fixed area of the dynamic random access memory SDRAM of the camera, and the area is called an "image storage area". (2) The system generates a random number between 60-300, called the "coverage amount", denoted by F. (3) The image saving area is divided into an upper half area and a lower half area, when a camera acquires a certain image, the image is saved at the random start (represented by Q) of the upper half area and the lower half area of the image saving area, the image is only written in the position in an overlaying mode for F times, after the F times of overlaying is completed, the previous image area is filled with random numbers, the Q value is updated, and a new image is saved at the start of a new Q value in a circulating mode. (4) The upper half area is initially stored in the forward direction, and the lower half area is initially stored in the reverse direction. The effect thus obtained is: (1) when the next frame of image is obtained, the new image covers the last image storage position, so that the used image can be discarded immediately. (2) The phenomenon that the service life of a certain SDRAM is influenced by repeated reading and writing of a certain SDRAM position is avoided.
S4: by customizing hardware, functions and algorithms suitable for identification requirements, the desensitization camera can realize higher cost performance;
s5: the desensitization camera adopts a credible edge computing 'wrapping' mode to prevent the system program from being attacked in a storage body, during loading and running.
Initial preparation: when closing the hall, call high definition digtal camera to gather high definition image, call the NPU of miniature marginal computing equipment to empty seat and detect the discernment to every seat region is divided automatically, and include the seat and correspond desktop etc. also can carry out manual regulation, with this a plurality of regions of waiting to detect that divide, suppose that a total of generation N seat regions.
And (3) cyclic identification: when the venue is open, call high definition digtal camera to gather high definition image, call the low price NPU of built-in miniature edge computing device, like K210: the total force 1TOPS and the power 0.3W are used for respectively and rapidly identifying N divided visual detection areas, such as the seat areas. The maximum detection image area of the K210 is 224 × 224 pixels, and only a single seat area is detected each time, then the single seat area can be matched with 224 × 5 ten thousand pixels, and the small targets which cannot be detected well under the panoramic picture due to the limitation of the current mainstream target detection algorithm can be detected under the resolution corresponding to the small field of view, so that not only people, notebook computers, books and periodicals and the like can be detected, but also the small targets such as mobile phones, water cups and the like can be identified well, and the small targets such as mobile phones, water cups and the like are also the basis for judging whether the people use the seats or not. The method sequentially carries out cyclic detection on all seat areas, each round of detection time N is subjected to actual measurement, the detection time of a single seat area of the NPU of 1TOPS, such as K210, can be controlled within 100ms, so that the general indoor application scenes, such as 200 seat areas, have the total detection time of 20 seconds per round, and the generation of the seating rate information once in 20 seconds is completely acceptable, and the desensitization camera using the NPU with low price and low power consumption, such as K210, as a main computing power chip has high cost performance, and meanwhile, the volume and the heat productivity can be well controlled, so that large-scale deployment is facilitated.
The desensitization camera adopts a credible edge calculation 'wrapping' mode:
the operating system code of the desensitization camera is solidified in the read-only memory, the code is encrypted, and a completely solidified system loader (comprising encryption, decryption and operation checking functions) is used for checking when the code is loaded and run so as to prevent the system program from being attacked in a memory bank, during loading and running. When the program is abnormal or the intrusion risk is found, the program cannot run, and the system automatically locks and gives a warning. When system level high-risk operation is required, such as on-line firmware updating and system resetting, a local desensitization camera is required to be combined to scan a management two-dimensional code, the management two-dimensional code is randomly generated when the system is firstly operated or reset, can be stored in a screenshot mode at a control end, and can be subjected to system level high-risk operation after passing code scanning authentication of the camera, so that the risk of local attack and remote attack of hackers by non-managers during the operation can be eliminated.
The main computational power chip adopts K210 independently developed by Machilus technology, is a system-level chip integrating machine vision, a convolutional neural network acceleration processor and machine hearing multi-mode recognition, has the capability of seeing and hearing integration, achieves the computational power of 1TOPS, has the power consumption of less than 300mW, uses a 28nm process of power accumulation and ultralow power consumption, has a RISC-V64-bit-based dual-core processor, is internally provided with an independent FPU (field programmable logic unit) in each processing core, and can be widely applied to scenes such as intelligent houses, intelligent parks, intelligent energy consumption, intelligent agriculture and the like.
A desensitization camera for a public venue is suitable for the desensitization data acquisition method for the public venue, a light shield is fixedly mounted on the outer surface of a desensitization camera body, a lens is arranged on one side of the desensitization camera body, two connecting rods are fixedly mounted at the bottom end of the desensitization camera body, a bottom plate is fixedly mounted at one end of each connecting rod, two electric push rods are fixedly mounted inside the bottom plate, a signal receiver is fixedly mounted on one side of each electric push rod, a fixing block is fixedly mounted at one end of each electric push rod, a fixing groove is formed in one side of each fixing block, two elastic binding bands are fixedly mounted on the side wall of each fixing groove, and cleaning cloth is arranged inside each fixing groove; the during operation, through two elasticity bandages of pulling fixed block one side, thereby put into the fixed slot of fixed frame with cleaning cloth, loosen the elasticity bandage again, let the elasticity bandage press from both sides cleaning cloth in the fixed slot of fixed block, pass through GSM900MHZ signal transmitter this moment again, the transmitting instruction, let GSM900MHZ signal receiver on the electric putter receive the instruction, and drive electric putter and begin work, electric putter takes fixed block and cleaning cloth to begin to slide, cleaning cloth at this moment is laminated with the camera lens on the desensitization camera body mutually, through the slip cleaning cloth that makes a round trip, make cleaning cloth clean with the camera lens on the desensitization camera body, clean the dust that the camera lens on the function can clear away the desensitization camera body was stained with, avoid influencing the shooting of desensitization camera body.
Preferably, a hook and loop fastener surface is fixedly installed on the inner wall of the fixing groove, and a hook and loop fastener female surface is fixedly installed at one end of the cleaning cloth; during operation, when cleaning cloth gets into in the fixed slot, the primary face of magic subsides on the cleaning cloth can aim at the sub-face of magic subsides in the fixed slot, and then will clean cloth and fix in the fixed slot.
Preferably, a limiting frame is fixedly mounted on one side of the fixing block, a water tank is fixedly mounted on the inner wall of the limiting frame, a water pipe is fixedly mounted on one side of the water tank, and a sliding column is slidably connected to one side of the limiting frame; the during operation, when two fixed blocks move to the direction that is close to each other, two slip posts can meet and extrude, and then promote the slip post to the water tank direction, make the one end extrusion water tank of slip post, water in the water tank can flow into in the fixed slot of fixed block through the water pipe this moment, make the water soak the cleaning cloth in the fixed slot, the camera lens is cleaned more easily to the cleaning cloth after moist, the cleaning cloth adopts the rapid-curing cutback surface fabric, can air-dry fast after moist, after having cleaned camera lens and cleaning cloth and air-drying, start an electric putter, let electric putter take the cleaning cloth that has done to clean the camera lens, thereby dry the moisture content on the camera lens, when starting an electric putter, two slip posts can not extrude each other, therefore the water tank can not go out water.
Preferably, an anti-collision pad is fixedly mounted at one end of the sliding column, and a top plate is fixedly mounted at one end, far away from the anti-collision pad, of the sliding column; the during operation, when two fixed blocks removed to the direction that is close to each other, the crashproof pad on the slip post can contact each other earlier, avoids two slip post direct clashes, because crashproof pad and roof all are the rubber material, so striking many times can not damage, can not produce the damage to the water tank when and the roof extrudees the water tank.
Preferably, the surface of the sliding column is sleeved with a spring, one end of the spring is fixedly installed with the anti-collision pad, and the other end of the spring is fixedly installed with the limiting frame; during operation, when slip post and crash pad no longer receive the extrusion, spring on the spacing frame resumes elasticity, and the spring is taking slip post and roof through the crash pad and is reseing for the roof is no longer extrudeed the water tank and is gone out water.
The invention has the advantages that:
1. according to the invention, through the use of hardware, functions and algorithms of the customized desensitization camera body, complete localization of visual analysis of the desensitization camera is further realized, and higher cost performance is obtained, through intelligent analysis of an application scene image, the desensitization camera carries out desensitization data acquisition on an image target in a desensitization area, only acquires desensitized target data such as seat occupancy and the like, and the desensitized image is incinerated after being read, so that the desensitized image cannot be locally stored and network transmitted, and a rear-end server is not uploaded, thereby eliminating personal privacy problems on one side of an image recognition terminal.
2. According to the desensitizing camera body cleaning device, the cleaning cloth is placed into the fixing groove of the fixing frame by pulling the two elastic binding bands on one side of the fixing block, then the elastic binding bands are loosened, the cleaning cloth is clamped in the fixing groove of the fixing block by the elastic binding bands, at the moment, the GSM900MHZ signal transmitter transmits an instruction, the GSM900MHZ signal receiver on the electric push rod receives the instruction and drives the electric push rod to start working, the electric push rod drives the fixing block and the cleaning cloth to start sliding, the cleaning cloth is attached to the lens on the desensitizing camera body at the moment, the cleaning cloth cleans the lens on the desensitizing camera body by sliding the cleaning cloth back and forth, the cleaning function can remove dust attached to the lens on the desensitizing camera body, and the shooting of the desensitizing camera body is prevented from being influenced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a desensitization data collection method for a public venue according to an embodiment;
fig. 2 is a schematic structural diagram of a desensitization camera body in the first embodiment;
FIG. 3 is a schematic structural diagram of a base plate according to an embodiment;
figure 4 is a schematic view of the structure of the magic tape according to the first embodiment;
figure 5 is a schematic view of the female surface of the magic tape according to the first embodiment;
FIG. 6 is a schematic diagram of a structure at B in FIG. 3 according to a first embodiment;
FIG. 7 is a schematic structural diagram of a position-limiting frame according to an embodiment;
FIG. 8 is a schematic view of the heat dissipation hole in the second embodiment.
In the figure: 1. a desensitization camera body; 2. a lens; 301. a connecting rod; 302. a base plate; 303. a signal receiver; 304. a fixed block; 305. fixing grooves; 306. a cleaning cloth; 307. tightening and loosening the binding band; 308. a magic tape surface; 309. magic tape mother surface; 310. a limiting frame; 311. a water tank; 312. a water pipe; 313. a sliding post; 314. an anti-collision pad; 315. a top plate; 316. a spring; 317. an electric push rod; 4. heat dissipation holes; 5. a light shield.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Referring to fig. 1-7, a desensitization data collection method for public venues includes the following steps:
s1: the visual analysis of the desensitization camera is completely localized through the identification module of the desensitization camera body 1, and the requirements of deep analysis on a specified application scene and an identification target can be met;
s2: various targets including tiny targets in the identification area are subjected to image acquisition and intelligent analysis through the desensitization camera body 1, user target data such as seat-getting rate, queuing number and the like after desensitization are generated through analysis, such desensitization information is only provided for a background, and any local storage, network transmission and rear-end processing are not required to be carried out on desensitization original image information, so that the personal privacy problem is eliminated on one side of an image identification terminal;
s3: the desensitization image information acquired by the desensitization camera body 1 is only immediately processed in the random storage device of the equipment, and is immediately discarded after identification and analysis, so that burning after reading is realized; during work, the realization of burning after reading is as follows: (1) after the image is acquired by the camera, the image is stored only in a fixed area of the dynamic random access memory SDRAM of the camera, and the area is called an "image storage area". (2) The system generates a random number between 60-300, called the "coverage amount", denoted by F. (3) The image saving area is divided into an upper half area and a lower half area, when a camera acquires a certain image, the image is saved at the random start (represented by Q) of the upper half area and the lower half area of the image saving area, the image is only written in the position in an overlaying mode for F times, after the F times of overlaying is completed, the previous image area is filled with random numbers, the Q value is updated, and a new image is saved at the start of a new Q value in a circulating mode. (4) The upper half area is initially stored in the forward direction, and the lower half area is initially stored in the reverse direction. The effect thus obtained is: (1) when the next frame of image is obtained, the new image covers the last image storage position, so that the used image can be discarded immediately. (2) The phenomenon that the service life of a certain SDRAM is influenced by repeated reading and writing of a certain SDRAM position is avoided.
S4: by customizing hardware, functions and algorithms suitable for identification requirements, the desensitization camera can realize higher cost performance;
s5: the desensitization camera adopts a credible edge computing 'wrapping' mode to prevent the system program from being attacked in a storage body, during loading and running.
Initial preparation: when closing the hall, call high definition digtal camera to gather high definition image, call the NPU of miniature marginal computing equipment to empty seat and detect the discernment to every seat region is divided automatically, and include the seat and correspond desktop etc. also can carry out manual regulation, with this a plurality of regions of waiting to detect that divide, suppose that a total of generation N seat regions.
And (3) cyclic identification: when the venue is open, call high definition digtal camera to gather high definition image, call the low price NPU of built-in miniature edge computing device, like K210: the total force 1TOPS and the power 0.3W are used for respectively and rapidly identifying N divided visual detection areas, such as the seat areas. The maximum detection image area of the K210 is 224 × 224 pixels, and only a single seat area is detected each time, then the single seat area can be matched with 224 × 5 ten thousand pixels, and a small target which cannot be detected well under a panoramic picture due to the limitation of a current mainstream target detection algorithm can be detected under the resolution corresponding to the small field of view, so that not only people, notebook computers, books and periodicals and the like can be detected, but also small targets such as mobile phones, water cups and the like can be identified well, and the small targets such as the mobile phones, the water cups and the like are also the basis for judging whether the people use the seats. The method sequentially carries out cyclic detection on all seat areas, each round of detection time N is subjected to actual measurement, the detection time of a single seat area of the NPU of 1TOPS, such as K210, can be controlled within 100ms, so that the general indoor application scenes, such as 200 seat areas, have the total detection time of 20 seconds per round, and the generation of the seating rate information once in 20 seconds is completely acceptable, and the desensitization camera using the NPU with low price and low power consumption, such as K210, as a main computing power chip has high cost performance, and meanwhile, the volume and the heat productivity can be well controlled, so that large-scale deployment is facilitated.
The desensitization camera adopts a credible edge calculation 'wrapping' mode:
the operating system code of the desensitization camera is solidified in the read-only memory, the code is encrypted, and a completely solidified system loader (comprising encryption, decryption and operation checking functions) is used for checking when the code is loaded and run so as to prevent the system program from being attacked in a memory bank, during loading and running. When the program is abnormal or the intrusion risk is found, the program cannot run, and the system automatically locks and gives a warning. When system level high-risk operation is required, such as on-line firmware updating and system resetting, a local desensitization camera is required to be combined to scan a management two-dimensional code, the management two-dimensional code is randomly generated when the system is firstly operated or reset, can be stored in a screenshot mode at a control end, and can be subjected to system level high-risk operation after passing code scanning authentication of the camera, so that the risk of local attack and remote attack of hackers by non-managers during the operation can be eliminated.
The desensitization camera for the public venue is suitable for the desensitization data acquisition method for the public venue, a light shield 5 is fixedly mounted on the outer surface of a desensitization camera body 1, a lens 2 is arranged on one side of the desensitization camera body 1, two connecting rods 301 are fixedly mounted at the bottom end of the desensitization camera body 1, a bottom plate 302 is fixedly mounted at one end of each connecting rod 301, two electric push rods 317 are fixedly mounted in the bottom plate 302, a signal receiver 303 is fixedly mounted on one side of each electric push rod 317, a fixing block 304 is fixedly mounted at one end of each electric push rod 317, a fixing groove 305 is formed in one side of each fixing block 304, two loosening straps 307 are fixedly mounted on the side wall of each fixing groove 305, and a cleaning cloth 306 is arranged in each fixing groove 305; during operation, the cleaning cloth 306 is placed in the fixing groove 305 of the fixing frame by pulling the two elastic binding bands 307 on one side of the fixing block 304, then the elastic binding bands 307 are loosened, the cleaning cloth 306 is clamped in the fixing groove 305 of the fixing block 304 by the elastic binding bands 307, at the moment, the instruction is transmitted by the GSM900MHZ signal transmitter, the GSM900MHZ signal receiver 303 on the electric push rod 317 receives the instruction and drives the electric push rod 317 to start to work, the electric push rod 317 drives the fixing block 304 and the cleaning cloth 306 to start to slide, the cleaning cloth 306 is attached to the lens 2 on the desensitization camera body 1 at the moment, the cleaning cloth 306 is enabled to wipe the lens 2 on the desensitization camera body 1 through the back-and-forth sliding of the cleaning cloth 306, dust attached to the lens 2 on the desensitization camera body 1 can be removed through the wiping function, and the shooting of the desensitization camera body 1 is prevented from being influenced.
A magic tape surface 308 is fixedly installed on the inner wall of the fixing groove 305, and a magic tape female surface 309 is fixedly installed at one end of the cleaning cloth 306; in operation, when the cleaning cloth 306 enters the fixing groove 305, the female surface 309 of the hook and loop fastener on the cleaning cloth 306 is aligned with the sub-surface of the hook and loop fastener in the fixing groove 305, so as to fix the cleaning cloth 306 in the fixing groove 305.
A limiting frame 310 is fixedly mounted on one side of the fixing block 304, a water tank 311 is fixedly mounted on the inner wall of the limiting frame 310, a water pipe 312 is fixedly mounted on one side of the water tank 311, and a sliding column 313 is slidably connected to one side of the limiting frame 310; when the cleaning device works, when the two fixing blocks 304 move towards the direction close to each other, the two sliding columns 313 are connected and extruded, and then the sliding columns 313 are pushed towards the water tank 311, so that one ends of the sliding columns 313 extrude the water tank 311, at the moment, water in the water tank 311 flows into the fixing grooves 305 of the fixing blocks 304 through the water pipes 312, so that the cleaning cloth 306 in the fixing grooves 305 is wetted by the water, the wetted cleaning cloth 306 can wipe the lens 2 more easily, the cleaning cloth 306 is made of quick-drying fabric, the cleaning cloth can be dried quickly after wetting, after the lens 2 is wiped and the cleaning cloth 306 is dried, an electric push rod 317 is started, the electric push rod 317 carries the dried cleaning cloth 306 to wipe the lens 2, so that the water on the lens 2 is wiped, and when the electric push rod 317 is started, the two sliding columns 313 cannot be extruded mutually, so that the water cannot flow out from the water tank 311.
One end of the sliding column 313 is fixedly provided with an anti-collision pad 314, and one end of the sliding column 313 far away from the anti-collision pad 314 is fixedly provided with a top plate 315; during operation, when two fixed blocks 304 move to the direction that is close to each other, crashproof pad 314 on the sliding post 313 can contact each other earlier, avoids two sliding post 313 direct clashes, because crashproof pad 314 and roof 315 are all rubber material, so striking can not damage many times, and can not produce the damage to water tank 311 when roof 315 extrudes water tank 311.
A spring 316 is sleeved on the surface of the sliding column 313, one end of the spring 316 is fixedly installed with the anti-collision pad 314, and the other end of the spring 316 is fixedly installed with the limiting frame 310; in operation, when the sliding column 313 and the crash pad 314 are not squeezed any more, the spring 316 on the limiting frame 310 recovers the elastic force, and the spring 316 drives the sliding column 313 and the top plate 315 to reset through the crash pad 314, so that the top plate 315 does not squeeze the water tank 311 any more to discharge water.
Example two
Referring to fig. 8, in a first comparative example, as another embodiment of the present invention, heat dissipation holes 4 are formed on two sides of the light shield 5; the during operation, when desensitization camera body 1 after long-time work, the inside of desensitization camera body 1 can produce the heat, just in time dispel the heat this moment, and the heat through louvre 4 on the lens hood 5 in with desensitization camera body 1 is discharged, and then reduces the temperature in the desensitization camera body 1, avoids the high temperature in the desensitization camera body 1, influences the normal use of components and parts in the desensitization camera body 1.
The working principle is that the cleaning cloth 306 is placed in the fixing groove 305 of the fixing frame by pulling the two elastic belts 307 on one side of the fixing block 304, then the elastic belts 307 are loosened, the cleaning cloth 306 is clamped in the fixing groove 305 of the fixing block 304 by the elastic belts 307, the female surface 309 of the magic tape on the cleaning cloth 306 is aligned with the sub-surface of the magic tape in the fixing groove 305, further the cleaning cloth 306 is fixed in the fixing groove 305, at the moment, the GSM900MHZ signal transmitter transmits an instruction, the GSM900MHZ signal receiver 303 on the electric push rod 317 receives the instruction and drives the electric push rod 317 to work, the electric push rod 317 drives the fixing block 304 and the cleaning cloth 306 to start sliding, the cleaning cloth 306 at the moment is attached to the lens 2 on the desensitizing camera body 1, when the two fixing blocks 304 move towards the direction close to each other, the two sliding columns 313 are connected and pressed, when the two fixing blocks 304 move towards the direction close to each other, the anti-collision pads 314 on the sliding columns 313 are contacted with each other firstly, so that the two sliding columns 313 are prevented from being directly impacted, the anti-collision pads 314 and the top plate 315 are made of rubber materials, so that the anti-collision pads are not damaged by multiple times of impact, the water tank 311 is not damaged when the top plate 315 extrudes the water tank 311, the sliding columns 313 are further pushed towards the water tank 311, one end of each sliding column 313 extrudes the water tank 311, at the moment, water in the water tank 311 flows into the fixing grooves 305 of the fixing blocks 304 through the water pipes 312, so that the cleaning cloth 306 in the fixing grooves 305 is wetted by the water, the lens 2 on the desensitization camera body 1 is wiped cleanly by the cleaning cloth 306 through back-and-forth sliding, when the sliding columns 313 and the anti-collision pads 314 are not extruded any more, the springs 316 on the limiting frames 310 recover elasticity, the springs 316 drive the sliding columns 313 and the top plate 315 to reset through the anti-collision pads 314, so that the top plate 315 does not extrude the water tank 311 any more to discharge water, cleaning cloth 306 adopts the rapid-curing cutback surface fabric, can air-dry fast after moist, after having cleaned camera lens 2 and cleaning cloth 306 air-dry, start an electric putter 317, let electric putter 317 take cleaning cloth 306 that has done to clean camera lens 2, thereby wipe the water on the camera lens 2 futilely, when starting an electric putter 317, two sliding column 313 can not extrude each other, therefore the water tank 311 can not go out water, the dust that camera lens 2 on the desensitization camera body 1 was stained with can be clear away to the wiping function, avoid influencing the shooting of desensitization camera body 1.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed.
Claims (6)
1. A desensitization data acquisition method for a public venue, comprising: the method comprises the following steps:
s1: the visual analysis of the desensitization camera is completely localized through the identification module of the desensitization camera body (1), and the requirements of deep analysis on a specified application scene and an identification target can be met;
s2: various targets in the identification area, including tiny targets, are subjected to image acquisition and intelligent analysis through the desensitization camera body (1), user target data such as seat attendance rate, queuing number and the like after desensitization are generated through analysis, desensitization information is only provided for a background, and any local storage, network transmission and rear-end processing are not required to be carried out on desensitization original image information, so that the personal privacy problem is eliminated on one side of an image identification terminal;
s3: sensitive image information acquired by the desensitization camera body (1) is immediately processed only in the random storage device of the equipment, and is immediately discarded after identification and analysis are completed, so that burning after reading is realized;
s4: by customizing hardware, functions and algorithms suitable for identification requirements, the desensitization camera can realize higher cost performance;
s5: the desensitization camera adopts a credible edge computing 'wrapping' mode to prevent the system program from being attacked in a storage body, during loading and running.
2. A desensitization camera for a public venue, comprising: the apparatus is suitable for use in a public venue desensitization data acquisition method as claimed in claim 1, a light shield (5) is fixedly arranged on the outer surface of the desensitization camera body (1), one side of the desensitization camera body (1) is provided with a lens (2), the bottom end of the desensitization camera body (1) is fixedly provided with two connecting rods (301), one end of the connecting rod (301) is fixedly provided with a bottom plate (302), two electric push rods (317) are fixedly arranged inside the bottom plate (302), a signal receiver (303) is fixedly arranged on one side of the electric push rod (317), one end of the electric push rod (317) is fixedly provided with a fixed block (304), one side of the fixed block (304) is provided with a fixed groove (305), two elastic binding bands (307) are fixedly mounted on the side wall of the fixing groove (305), and cleaning cloth (306) is arranged inside the fixing groove (305).
3. A desensitizing camera for public venues according to claim 2, wherein: the inner wall fixed mounting of fixed slot (305) has magic subsides son face (308), the one end fixed mounting of cleaning cloth (306) has magic subsides mother face (309).
4. A desensitizing camera for public venues according to claim 3, wherein: one side fixed mounting of fixed block (304) has spacing frame (310), the inner wall fixed mounting of spacing frame (310) has water tank (311), one side fixed mounting of water tank (311) has water pipe (312), one side sliding connection of spacing frame (310) has sliding column (313).
5. Desensitizing camera according to claim 4, in a public venue, characterized by: one end of the sliding column (313) is fixedly provided with an anti-collision pad (314), and one end of the sliding column (313) far away from the anti-collision pad (314) is fixedly provided with a top plate (315).
6. Desensitizing camera according to claim 5, in a public venue, characterized by: the surface of the sliding column (313) is sleeved with a spring (316), one end of the spring (316) is fixedly installed with the anti-collision pad (314), and the other end of the spring (316) is fixedly installed with the limiting frame (310).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210087964.9A CN114390180A (en) | 2022-01-25 | 2022-01-25 | Desensitization data acquisition method for public venue and desensitization camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210087964.9A CN114390180A (en) | 2022-01-25 | 2022-01-25 | Desensitization data acquisition method for public venue and desensitization camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114390180A true CN114390180A (en) | 2022-04-22 |
Family
ID=81203309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210087964.9A Pending CN114390180A (en) | 2022-01-25 | 2022-01-25 | Desensitization data acquisition method for public venue and desensitization camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114390180A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990008399U (en) * | 1997-08-02 | 1999-03-05 | 홍종만 | Cleaning device for car rear view cameras. |
| CN110958397A (en) * | 2019-12-27 | 2020-04-03 | 青岛海信智慧家居***股份有限公司 | Method and device for controlling intelligent camera |
| CN111429330A (en) * | 2020-03-31 | 2020-07-17 | 上海兑观信息科技技术有限公司 | Method and system for protecting privacy of monitoring video |
| CN112150688A (en) * | 2020-08-20 | 2020-12-29 | 优学汇信息科技(广东)有限公司 | Entrance guard monitoring device and method for face recognition |
| CN112157005A (en) * | 2020-07-06 | 2021-01-01 | 南京迈科拓信息科技有限公司 | Automatic cleaning device of surveillance camera head |
| CN213162060U (en) * | 2020-08-07 | 2021-05-11 | 国网河南省电力公司偃师市供电公司 | Camera lens cleaning device |
| CN213194681U (en) * | 2020-08-28 | 2021-05-14 | 广东众科智能科技股份有限公司 | Dustproof surveillance camera head in wisdom city |
| CN112800467A (en) * | 2021-02-18 | 2021-05-14 | 支付宝(杭州)信息技术有限公司 | Online model training method, device and equipment based on data privacy protection |
| CN215420477U (en) * | 2021-08-04 | 2022-01-04 | 南京林业大学 | Security device for smart home |
| CN113918990A (en) * | 2021-09-30 | 2022-01-11 | 北京地平线信息技术有限公司 | Data desensitization processing method and device |
-
2022
- 2022-01-25 CN CN202210087964.9A patent/CN114390180A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990008399U (en) * | 1997-08-02 | 1999-03-05 | 홍종만 | Cleaning device for car rear view cameras. |
| CN110958397A (en) * | 2019-12-27 | 2020-04-03 | 青岛海信智慧家居***股份有限公司 | Method and device for controlling intelligent camera |
| CN111429330A (en) * | 2020-03-31 | 2020-07-17 | 上海兑观信息科技技术有限公司 | Method and system for protecting privacy of monitoring video |
| CN112157005A (en) * | 2020-07-06 | 2021-01-01 | 南京迈科拓信息科技有限公司 | Automatic cleaning device of surveillance camera head |
| CN213162060U (en) * | 2020-08-07 | 2021-05-11 | 国网河南省电力公司偃师市供电公司 | Camera lens cleaning device |
| CN112150688A (en) * | 2020-08-20 | 2020-12-29 | 优学汇信息科技(广东)有限公司 | Entrance guard monitoring device and method for face recognition |
| CN213194681U (en) * | 2020-08-28 | 2021-05-14 | 广东众科智能科技股份有限公司 | Dustproof surveillance camera head in wisdom city |
| CN112800467A (en) * | 2021-02-18 | 2021-05-14 | 支付宝(杭州)信息技术有限公司 | Online model training method, device and equipment based on data privacy protection |
| CN215420477U (en) * | 2021-08-04 | 2022-01-04 | 南京林业大学 | Security device for smart home |
| CN113918990A (en) * | 2021-09-30 | 2022-01-11 | 北京地平线信息技术有限公司 | Data desensitization processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5444562B2 (en) | Digital camera that captures and organizes images before and after shutter signals | |
| US11676390B2 (en) | Machine-learning model, methods and systems for removal of unwanted people from photographs | |
| CN108419012A (en) | Photographic method, device, storage medium and electronic equipment | |
| CN108093158B (en) | Image blurring processing method and device, mobile device and computer readable medium | |
| CN107888822A (en) | Image pickup method, device, terminal and readable storage medium storing program for executing | |
| CN104469229A (en) | Video data storing method and device | |
| CN106713768A (en) | Person-scenery image synthesis method and system, and computer device | |
| CN109672819A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN112351280B (en) | Video encoding method, video encoding device, electronic equipment and readable storage medium | |
| JP4265919B2 (en) | Tracking cooperative monitoring system and imaging apparatus | |
| Guo et al. | Dense123'color enhancement dehazing network | |
| CN113111823A (en) | Abnormal behavior detection method and related device for building construction site | |
| CN108055431A (en) | Real-time field image capturing system and method | |
| CN106325520A (en) | Photographing method and device and mobile terminal | |
| CN101021668B (en) | Method and device for exposure and reconstituting initial image | |
| CN112954212A (en) | Video generation method, device and equipment | |
| KR20160131882A (en) | Electronic apparatus and operating method thereof | |
| CN114390180A (en) | Desensitization data acquisition method for public venue and desensitization camera | |
| CN113422982B (en) | Data processing method, device, equipment and storage medium | |
| CN112738394B (en) | Linkage method and device of radar and camera equipment and storage medium | |
| CN104539851B (en) | A kind of high speed imaging system and method based on the exposure of pixel Optimized Coding Based | |
| CN110796068A (en) | Drowning detection method and system for community swimming pool | |
| CN103339978A (en) | Method and device for providing improved perpetrator imaging | |
| US20220301278A1 (en) | Image processing method and apparatus, storage medium, and electronic device | |
| CN115346150A (en) | Violent behavior detection method and system based on edge calculation |
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 |