CN116778302B - Object recognition system and portable cloth control box - Google Patents
Object recognition system and portable cloth control box Download PDFInfo
- Publication number
- CN116778302B CN116778302B CN202310574453.4A CN202310574453A CN116778302B CN 116778302 B CN116778302 B CN 116778302B CN 202310574453 A CN202310574453 A CN 202310574453A CN 116778302 B CN116778302 B CN 116778302B
- Authority
- CN
- China
- Prior art keywords
- control box
- portable
- acquisition device
- image acquisition
- 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.)
- Active
Links
- 239000004744 fabric Substances 0.000 title claims abstract description 56
- 238000004891 communication Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000033001 locomotion Effects 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 4
- 229910045601 alloy Inorganic materials 0.000 claims description 4
- 239000000956 alloy Substances 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 4
- 239000011347 resin Substances 0.000 claims description 4
- 229920005989 resin Polymers 0.000 claims description 4
- 238000000034 method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000012015 optical character recognition Methods 0.000 description 3
- 230000036544 posture Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 229910000838 Al alloy Inorganic materials 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000004512 die casting Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/945—User interactive design; Environments; Toolboxes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/96—Management of image or video recognition tasks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The application discloses an object recognition system, including: an image acquisition device and a portable cloth control box; the image acquisition device is used for acquiring an environment image within a preset range from the position of the image acquisition device and sending the environment image to the portable cloth control box; the portable control box is used for analyzing the object in the environment image, and if the object is matched with a preset target object, the portable control box sends out alarm information for indicating that the object in the environment image is matched with the target object; the portable control box is also used for supplying power to the image acquisition device, wherein the image acquisition device is provided with a type selection part, and the photographic parameters and the light source parameters when acquiring the image are correspondingly adjusted according to the type of the object. Because the portable control box can perform object recognition through the portable control box, can supply power to the image acquisition device at the same time, can be free from the limitation of a fixed power supply, and therefore the object recognition system can be portable and movable.
Description
Technical Field
The application relates to the technical field of computers, in particular to an object recognition system and a portable distribution control box.
Background
The traditional object recognition system, especially relates to a face recognition system, an image acquisition device is usually required to be installed near a power supply to supply power to the image acquisition device, limitation exists and the image acquisition device is not easy to move, meanwhile, the face recognition system is usually deployed on a server, a computer or special equipment, the equipment is large in size, the deployment process is complicated, and a worker is required to squat and watch, so that a lot of inconvenience is caused. But in life, sudden events often occur or a temporary set-up and movable object recognition system is required in a specific occasion, such as a concert scene.
Therefore, how to make the object recognition system have the functions of convenient carrying and moving, and also can remotely monitor and reduce the inconvenience of the squatting point on site becomes a problem to be solved by the person skilled in the art.
Disclosure of Invention
The application provides an object recognition system to solve among the prior art object recognition system can't conveniently carry and can not remove, need the problem of scene squatting simultaneously. The application additionally provides a portable cloth control box.
The application provides an object recognition system, comprising: an image acquisition device and a portable cloth control box;
the image acquisition device is used for acquiring an environment image within a preset range from the position of the image acquisition device and sending the environment image to the portable cloth control box;
the portable control box is used for analyzing the object in the environment image, and if the object is matched with a preset target object, the portable control box sends out alarm information for indicating that the object in the environment image is matched with the target object; the portable control box is also used for supplying power to the image acquisition device;
the image acquisition device is provided with a type selection part which is used for selecting and identifying the type of an object in the image, and correspondingly adjusting the shooting parameters when the image is acquired or adjusting the shooting parameters and the light source parameters when the image is acquired according to the type of the object.
Optionally, the image acquisition device may further be provided with a light source and a light source adjusting part, where the light source adjusting part is configured to correspondingly adjust the working parameters of the light source when acquiring the image according to the object type and/or the environment brightness condition.
Optionally, the portable control box comprises a handheld terminal for receiving and displaying alarm information sent by the portable control box.
Optionally, the portable distribution box comprises an object recognition board card stored with an object recognition unit; the object identification board card can be plugged and replaced at any time. Optionally, the objects in the environment image analyzed by the portable control box include at least one of the following: face, vehicle, body, motion, posture, clothing.
Optionally, the portable control box is further configured to send a first instruction for adjusting at least one parameter of a shooting angle and a shooting focal length to the image acquisition device;
the image acquisition device is also used for adjusting at least one parameter of a shooting angle and a shooting focal length of the image acquisition device according to the first instruction.
Optionally, the handheld terminal is further configured to send a second instruction for adjusting at least one parameter of a shooting angle and a shooting focal length of the image acquisition device to the portable fabric control box;
the portable control box is specifically configured to send the first instruction to the image acquisition device according to the second instruction.
Optionally, the portable control box is further used for displaying the alarm information.
Optionally, the handheld terminal is further configured to obtain a first trigger operation for inquiring the alarm information by the user, and send a third instruction for obtaining the alarm information required by the user to the portable fabric control box according to the first trigger operation, so as to obtain the alarm information required by the user provided by the portable fabric control box;
the portable control box is further used for obtaining the third instruction, and providing alarm information required by a user for the handheld terminal aiming at the third instruction.
Optionally, the handheld terminal is further configured to obtain a second trigger operation for setting information in the portable fabric control box by a user, and send a fourth instruction for setting information in the portable fabric control box to the portable fabric control box for the second trigger operation;
the portable control box is further used for obtaining the fourth instruction and setting according to setting information contained in the fourth instruction.
Optionally, the handheld terminal is further used for providing the alarm information to other handheld terminals, or the handheld terminal is further used for performing voice communication operation or video communication operation with other handheld terminals.
The application also provides a portable cloth accuse case, include:
an adapter for connecting an image acquisition device, the image acquisition device being a device independent of the portable fabric control box;
an object identifier connected to the adapter for identifying an object in an image of the environment provided by the image acquisition device via the adapter;
the alarm is connected with the object identifier and used for acquiring and prompting alarm information provided by the object identifier, and the alarm information is information used for representing that an object in the environment image is matched with the target object;
a power supply assembly for supplying power; the power supply assembly comprises a power supply adapter, and is connected with the image acquisition device through the power supply adapter to supply power to the image acquisition device.
Optionally, the portable control box is provided with a clamping groove, at least one clamping groove is used for fixing a provided object identification board card, and special information provided for the object identifier is integrated on the object identification board card, wherein the special information comprises an object database used for identifying the object in the environment image or a database used for identifying the object in the environment image and a special program; the application program and the stored database integrated by each of the object recognition boards are specific to a specific recognition object type.
Optionally, the object recognition board corresponds to one of the following recognition object types: face objects, vehicle objects, human body objects, action objects, gesture objects, and clothing objects.
Optionally, a display is also included.
Optionally, an information input device for inputting information is also included.
Optionally, the power supply assembly includes a battery, a power adapter connected with the battery for charging the battery, and a charging interface connected with the power adapter.
Optionally, the portable control box shell is made of PP alloy resin materials.
Optionally, the portable cloth control box comprises an upper cover and a lower cover, and a waterproof rubber ring is arranged at the joint of the upper cover and the lower cover.
Optionally, an anti-unlocking lock catch is arranged outside the portable cloth control box body.
Compared with the prior art, the application has the following advantages:
the application provides an object recognition system, comprising: the portable control box is used for identifying objects in the environment image provided by the image acquisition device through analysis, and generating and sending alarm information if the objects are successfully matched with a preset target object. The portable control box can complete object recognition by itself, so that the portable control box can form a complete object recognition system by combining with the image acquisition device; meanwhile, the portable distribution control box is also provided with a power supply, and can supply power for the portable distribution control box and the image acquisition device, so that the system is not limited by a fixed power supply; the system has the characteristics of complete control function, portability and convenient movement, and meets the requirements of on-site control.
The present application also provides a preferred embodiment of an object recognition system, comprising: the portable control box is used for receiving the alarm information sent by the portable control box, and the portable control box is used for controlling the portable control box to be in a remote state.
Drawings
FIG. 1 is a schematic diagram of an object recognition system provided herein;
FIG. 2 is a schematic structural view of a portable control box provided in the present application;
fig. 3 is a schematic structural diagram of a power supply assembly provided in the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is, however, susceptible of embodiment in many other ways than those herein described and similar generalizations can be made by those skilled in the art without departing from the spirit of the application and the application is therefore not limited to the specific embodiments disclosed below.
For ease of understanding the present application, the object recognition system provided in the first embodiment of the present application is described in detail herein in its entirety. It should be clear that the first embodiment of the present application provides only a preferred solution for protecting the object identifying system, and the specific protection scope of the present application is set forth in the claims, and the protection scope of the present application cannot be limited by the specific content of the embodiment.
The object recognition system provided in the first embodiment of the present application includes a hardware portion constituting the system, and a software portion performing a data processing process by a program configured in hardware and stored data. The two are combined with each other to realize the object recognition system. The function of the object recognition system comprises two aspects, namely, the description of structural connection of a hardware part and the description of data transmission of a software part:
the structural connection is described as follows: firstly, aiming at an object recognition system, an image acquisition device, a portable control box and a handheld terminal are three independent devices, wherein the image acquisition device and the portable control box can be connected in a wired mode or in a wireless mode, and meanwhile the portable control box supplies power to the image acquisition device; secondly, for the portable control box, the portable control box comprises a power supply component, an object identifier, an adapter, an alarm, a display and input equipment, wherein the object identifier can be realized in various modes, and the portable control box is realized by combining a controller with an object identification board card inserted into a clamping groove in the embodiment; the power supply component in the portable control box supplies power for the controller, the adapter and the display module.
Another aspect is described below for data transmission: firstly, for an object recognition system, an image acquisition device acquires an environment image and sends the environment image to a portable control box, the portable control box recognizes and analyzes an object in the environment image, the object is matched with a target object, alarm information is generated and displayed after the matching is successful, and meanwhile the alarm information is sent to a handheld terminal. Secondly, for the portable control box, the adapter transmits the environment image to the controller in the object identifier, the controller in the object identifier transmits the environment image to the corresponding identification board card in the object identifier, the corresponding identification board card in the object identifier calculates the object through depth and matches with the target object in the corresponding identification board card, the matching result is returned to the controller in the object identifier, the controller in the object identifier generates alarm information according to the result, and the alarm information is transmitted to the display and the alarm, and simultaneously transmitted to the handheld terminal.
The following description of the object recognition system is started to facilitate better understanding of the present solution, and the following description uses face recognition as an example, and fig. 1 is a schematic structural diagram of the object recognition system provided in the present application.
As shown in fig. 1, an object recognition system provided in the present application includes: an image acquisition device 101, a portable control box 102. The image acquisition device 101 is configured to acquire an environmental image within a preset range from a position where the image acquisition device 101 is located, and send the environmental image to the portable control box 102.
It should be noted that, the image acquisition device may be a camera or a video camera, and the application adopts a high-speed intelligent infrared pan-tilt camera, firstly, the camera can be adjusted by 360 degrees in the horizontal and vertical directions, and has a wider monitoring range and a faster cruising speed; secondly, the camera has night vision function, and the maximum distance of the camera can reach 150 meters; finally, the camera adopts a high-strength aluminum alloy die-casting shell, can effectively prevent water and is convenient for outdoor application.
When the acquired image is identified, the identified object may change according to the actual situation, and in order to accurately identify different objects later, the parameters set by the camera are different when the camera acquires the image. For example, if the recognition object is a face and a license plate are different, the recognition of the face requires extraction of feature points and also requires living body detection at the time of performing object recognition. The recognition of license plates generally adopts OCR, and OCR (optical character recognition) character recognition refers to a process that electronic equipment (such as a scanner or a digital camera) checks characters printed on paper and then translates the shapes into computer characters by a character recognition method. Obviously, when the face and the license plate are identified, the collected image information is different in focus.
Therefore, in order to accurately identify the object in the image, a type selection part is arranged at the image acquisition device and used for selecting the type of the object to be identified in the acquired image, and the camera can be in different working modes through the selection of the type selection part, specifically, the parameters of the camera are adjusted to adapt to the type of the object to be identified, so that the camera can accurately acquire image information, and the subsequent identification is facilitated. The type selection part can be designed in various ways, for example, a selection switch with a plurality of gears is adopted, one gear corresponds to one gear, and different gears are provided with different parameters corresponding to the camera. The parameters of the camera can be directly set when leaving the factory, or the parameters can be set or modified according to actual needs after the subsequent installer installs the camera on site, and the parameters are stored through the memory function of the camera and correspond to corresponding gears; the manner of setting the parameters is not particularly limited herein.
In addition, because the types of the identification objects are different, the requirements on the light source conditions are different, or the accuracy of the identification objects can be influenced by the conditions such as ambient brightness, for example, the day or night, the snowing and the raining, and the influence of the weather can also have a certain influence on the identification of the image. Therefore, the light source and the light source adjusting part can be separately arranged at the image acquisition device, and the corresponding light source mode is selected according to the type of the object to be obtained or different environment brightness conditions, so that the working parameters of the light source when the image is acquired are correspondingly adjusted. In one implementation manner, when the type selection part is set, the gear of the type selection part directly corresponds to the light mode, or the gear of the type selection part simultaneously contains the light source selection information, so that when the corresponding object type is selected, the shooting parameter and the light mode corresponding to the object are set at the same time. For example, the type selection unit includes four steps such as "night face recognition", "day face recognition", "night license plate recognition", and "day license plate recognition", and a certain step is selected, and the lighting and photographing parameters may be set. Of course, the above is merely an example, and the specific light setting is not particularly limited herein.
After the shooting parameters and the lamplight are adjusted, the camera can monitor and collect the environment images in the range taking the image acquisition device as the center and taking the preset range as the radius, and the images, such as face environment images, license plates and the like, are obtained by adopting the shooting parameters or the shooting parameters and the lamp light parameters determined by different working modes according to the selected object types, and are directly transmitted to the portable cloth control box through wires or wireless. Since the acquisition of these images has been suitably parameter-selected according to the type of object to be identified, the proportion of subsequent misrecognitions or unrecognizations is significantly reduced. The portable control box 102 is used for receiving the face environment image, analyzing the object in the environment image, and sending alarm information for indicating that the object in the environment image is matched with a preset target object to the handheld terminal 103 if the object is matched with the target object; the portable control box 102 is also used to power the image acquisition device 101.
It should be noted that, in the existing machine learning for acquiring an image, a labeling technology is generally adopted, and because the general labeling technology mainly trains videos through an algorithm based on a convolutional network classification model and a recurrent neural network, the method needs to train continuously accumulated video sample data, occupies more calculation resources, and easily causes model training difficulty due to diversity and subjectivity of video labels, so that the requirement of actual service is difficult to achieve. Therefore, in order to avoid the above problems, the portable fabric control box in the present application is provided with a special object recognition board card; the object identification board card can be plugged and replaced at any time; therefore, the trained model on other equipment can be replaced into a portable cloth control box which needs to be carried out at any time; by the mode, rapid knowledge migration is realized.
The portable control box 102 receives the face environment image transmitted by the image acquisition device, and performs face object recognition on the face environment image by adopting the trained and mature face recognition model carried in by the object recognition board card. When the face object in the recognized face environment image is matched with a preset target object, alarm information is generated and sent to remind on-site staff, and meanwhile the alarm information is sent to the handheld terminal, so that remote monitoring is facilitated. Finally, the portable control box can provide electric energy for the image acquisition device, so that the image acquisition device is not limited by a fixed power supply and is convenient to carry.
Because the object recognition board card contained in the portable control box 102 is configured with a trained and mature deep learning model algorithm, the data in the object recognition board card can be accumulated and parameters can be updated in the working process; since the mature model is configured in advance, the amount of computation for the portable fabric box 102 to further accumulate data and update the deep learning model is not large; in terms of hardware, the device can be plugged and replaced at any time according to the needs, and training results of other devices and increased data volume are introduced; in this way, the mobility of the portable fabric control pod 102 may be effectively increased.
The deep learning algorithm is prior art and is not an important aspect of the improvement of the present application and is not discussed in detail herein. Specifically, a preliminary face recognition model can be designed by adopting a deep learning algorithm principle, then the face recognition model is trained by providing a large number of labeled face images for the face recognition model, and the face recognition model with enough reliability can be obtained after training by a large amount of data.
The application also provides a preferred solution, the object recognition system further comprising: a hand-held terminal 103.
The handheld terminal 103 is configured to receive and display alarm information sent by the portable control box 102. Thus, the staff can select remote monitoring without the need of on-site squatting.
The alarm information comprises alarm voice or alarm music, and the volume and the content of the alarm can be set.
According to the intelligent recognition method and device, different types of recognition boards can be selected according to actual needs of application scenes, intelligent recognition is carried out, and therefore the effects of improving flexibility and expandability of the portable distribution control box are achieved. The application is briefly described in terms of being applicable to the fields of face object recognition and vehicle object recognition; according to the selected recognition field, the object in the environment image analyzed by the portable control box 102 is specifically a face object, or the object in the environment image analyzed by the portable control box 102 is specifically a vehicle object. Of course, the recognition fields in the present application may also include other application fields, and other recognition objects may also include at least one of the following: objects such as a person's body, movements, gestures, and clothing; the identification object can be used as a preliminary screening step before face recognition, for example, in the process of collecting environmental images, the actions, the postures, the clothes and the like of people in the crowd are identified, and key suspected objects are determined. In the crowd with important suspected objects, the face images of the people are further analyzed so as to realize quick and accurate identification. The different recognition objects need to build different recognition models, but the basic principle is consistent.
The following description mainly refers to the field of face recognition.
When portable cloth accuse case installation face identification integrated circuit board, then this system becomes face object recognition system, through the setting of face identification, includes: face size, face pixels, maximum face swaying degree, black and white list, uploading face library and the like, the portable control box can identify face environment images sent by the image acquisition device, the identified face objects are compared and matched with target objects in the face library, alarm information is generated after successful matching, and the alarm information is sent to on-site workers and handheld terminals.
Similarly, the face recognition board card is replaced by the vehicle recognition board card, so that the system becomes a vehicle object recognition system, and accordingly, the vehicle recognition device comprises: vehicle color, vehicle model, license plate, etc. In addition, can also set up different discernment integrated circuit boards for different discernment objects in this application, combine different discernment integrated circuit boards, and then realize improving the effect of accuracy and the efficiency of recognition result. That is, not only the face is recognized, but also the recognition and accumulation of the identification related information can be completed by combining the above-mentioned various recognition boards, so that the key crowd or key figures can be found rapidly. Along with the complex and changeable application scenes, the sequence and the number of the identification boards can also be changed according to the change of the application scenes, and the method is not particularly limited. For example, the face recognition board and the clothing recognition board, or the motion recognition board and the clothing recognition board and the posture recognition board may be combined. Here, a simple explanation will be given of the application of the above scheme in one scene. For example, in daily life, in some cases (where a and B refer to different people), a does something to help B, but a does not want to be known by people but steals away, B needs to find a in order to answer a's enrolment, but B only remembers a's clothing type and face shape. At this time, people with the same type as the clothes A can be determined through the clothes identification board on the road through which the clothes A possibly passes, the first screening is carried out, then the second screening is carried out through the face identification board, and the final personal selection of the clothes A is determined.
In order to enable the image acquisition device to obtain a clearer face environment image, the portable control box 102 is further configured to send a first instruction for adjusting at least one parameter of a shooting angle and a shooting focal length to the image acquisition device 101; the image capturing device 101 is further configured to adjust at least one parameter of a shooting angle and a shooting focal length of the image capturing device 101 according to the first instruction.
The handheld terminal 103 is further configured to send a second instruction to the portable fabric control box 102, where the second instruction is used to adjust at least one parameter of a shooting angle and a shooting focal length of the image acquisition device 101; the portable control box 102 is specifically configured to send the first instruction to the image acquisition device 101 according to the second instruction.
It should be noted that, the portable control box can directly set parameters for the image acquisition device, and the handheld terminal can also set parameters for the image acquisition device, only needs to transmit the set information to the portable control box, and the portable control box controls the image acquisition device according to the set information. The above parameters mainly include: shooting angle and shooting focus, wherein, can make image acquisition device can shoot 300 meters outside image after the adjustment focus, shooting angle can make image acquisition device 360 degrees adjustment in vertical, horizontal direction, and the shooting scope is wider.
The portable lockbox 102 is also used to present the alarm information in order to inform field personnel of the alarm condition, while at the same time to reduce field squat to enable remote monitoring.
The handheld terminal 103 is further configured to obtain a first trigger operation for inquiring the alarm information by the user, send a third instruction for obtaining the alarm information required by the user to the portable fabric control box 102 for the first trigger operation, and obtain the alarm information required by the user provided by the portable fabric control box 102; the portable control box 102 is further configured to obtain the third instruction, and provide, for the third instruction, alarm information required by the user to the handheld terminal 103.
The handheld terminal 103 is further configured to provide the alarm information to other handheld terminals, or the handheld terminal 103 is further configured to perform a voice communication operation or a video communication operation with other handheld terminals.
It should be noted that, when the portable control box is successfully matched, corresponding alarm information is generated. The alarm information can be displayed on the screen of the portable distribution control box, so that on-site workers can be conveniently reminded, meanwhile, the alarm information can be sent to the handheld terminal, remote check is convenient, the alarm information can be reduced by combining the alarm information with the handheld terminal, multiple choices are provided for the workers, and the portable distribution control box is more humanized. More importantly, the handheld terminal can also send instructions to the portable cloth control box to enable the portable cloth control box to provide alarm information required by a user.
The portable control box and the handheld terminal are not only limited to display of current alarm information, but also can view historical alarm records and results, field videos, historical videos and the like. In addition, the handheld terminal can also send alarm information to other terminals through voice or video operation, so that message sharing is achieved.
The alarm information content mainly comprises: time, identification object name, degree of similarity, target object picture, etc.
In order to enable a worker to remotely set a message, the handheld terminal 103 is further configured to obtain a second trigger operation for setting information in the portable fabric control box 102 by a user, and send a fourth instruction for setting information in the portable fabric control box 102 to the portable fabric control box 102 for the second trigger operation; the portable control box 102 is further configured to obtain the fourth instruction, and perform setting according to setting information included in the fourth instruction.
It should be noted that, the handheld terminal can set up information to the portable cloth control box, wherein the information mainly includes: alarm personnel related settings, alarm information settings, board related parameter settings, image acquisition device parameter related settings and the like.
Corresponding to the aforementioned object recognition system, the present application further discloses a portable control box, please refer to fig. 2, which is a schematic structural diagram of the portable control box.
The application provides a portable cloth accuse case, include: an adapter 202 for connecting an image acquisition apparatus 101, the image acquisition apparatus 101 being an apparatus independent of the portable fabric control box 102; an object identifier 201 connected to the adapter 202 for identifying an object in an environment image provided by the image acquisition apparatus 101 through the adapter 202;
the adapter transmits the face environment image in the image acquisition device to the object identifier in the portable control box, and the object identifier analyzes and identifies the face environment image.
The adapter is provided with a plurality of connection ports which can be accessed by a plurality of image acquisition devices.
In addition, the image acquisition device and the portable control box can be connected in a wired mode or in a wireless independent mode.
Wherein the object identifier is understood as a functional module formed based on a program run by hardware and supporting data, and comprises two parts on the hardware: the object in the clamping groove is identified to the board card and the controller. The object identifier further comprises a dedicated program (i.e. dedicated software) for implementing the identification algorithm and a required object database, which are stored on the object identification board, or the object identification office has at least a part of the object database stored therein, which dedicated program is installed on the motherboard together with the controller, the dedicated software having to run through the computing power provided by the controller. The operation of the object recognizer for recognizing a face is described below in terms of hardware.
The controller is connected with the adapter, the power supply component, the display, the alarm and the object identification board card. The controller is used to provide the computational power of the core and the transfer of information. The face recognition board is stored with a large amount of face image data and a software or hardware special program of a face recognition model, when the face recognition is carried out, the controller can call and operate the face database stored in the face recognition board and the special program for the face recognition, the controller analyzes and recognizes the environment image through the face recognition model (namely the recognition algorithm) based on the deep learning algorithm, the recognized face object is matched with the target object in the face database, alarm information is generated, and the face recognition model is realized through the execution of the special program by the controller. Simultaneously, the controller sends alarm information to the display and the alarm.
In order to avoid tedious deployment of the portable control box and realize the function of convenient carrying, the portable control box 102 is provided with a clamping groove 201-3, at least one clamping groove 201-3 is used for fixing a provided object identification board card 201-1, and special information provided for the object identifier 201 is integrated on the object identification board card 201-1, wherein the special information comprises a database for identifying objects in the environment image or a database and a special program for identifying the objects in the environment image; the application programs and the stored databases integrated by each of the object recognition boards 201-1 are specific to a particular recognition object type. The object recognition board 201-1 corresponds to recognizing one of the object types as follows: face objects, vehicle objects, human body objects, action objects, gesture objects, and clothing objects.
It should be noted that, the card slot can replace the corresponding object recognition board card according to the scene requirement; different object databases and application specific programs are provided on different object identification boards. Wherein, the special program is a carrier in the form of software or hardware of a special recognition model designed based on a deep learning algorithm.
In addition, the recognition object mainly includes: face objects and vehicle objects.
In order to facilitate the field staff to receive and view alarm information, the portable control box further comprises an alarm 203 connected with the object identifier 201 and used for acquiring and prompting the alarm information provided by the object identifier 201, wherein the alarm information is information used for indicating that an object in the environment image is matched with the target object; a display 205 is also included.
The object identifier can identify the face environment image sent by the network adapter, analyze the face object and match the face object with the target object, and if the matching is successful, generate alarm information and send the alarm information to the alarm. Meanwhile, the alarm information is displayed on a display, so that the user can check and confirm conveniently. In addition, the display can also view the whole process of shooting by the image acquisition device, historical video, image records and the like in real time.
To facilitate the setup operation of the portable fabric control box, an information input device 206 for inputting information is also included.
It should be noted that, through the input device, including a keyboard, a mouse, etc., the information setting and the message input can be performed on the image acquisition device, the portable control box, and the handheld terminal in the portable control box.
In order to make the portable control box portable and not limited by a fixed power supply, the portable control box further comprises a power supply assembly 204 which is respectively connected with the adapter 202 and the object identifier 201 and is used for supplying power to the adapter 202 and the object identifier 201; the power supply assembly 204 includes a battery 303, a power adapter 302 connected to the battery 303 for charging the battery 303, and a charging interface 301 connected to the power adapter 302.
It should be noted that, the power supply component in the portable control box not only can supply power to the display, the object identifier and the adapter of the portable control box, but also can supply power to the image acquisition device.
The power supply assembly can supply power by replacing a battery and can supply power by adopting a charging mode. The charging mode is mainly that the room electricity is connected with a charging interface of the power supply assembly, and the room electricity is transmitted to the battery through the power supply adapter to achieve the power supply effect.
In order to enable the portable distribution control box to be suitable for outdoor occasions, the whole box body shell of the portable distribution control box is in a buckling mode, and the portable distribution control box shell is made of PP alloy resin materials; the portable cloth control box comprises an upper cover and a lower cover, and a waterproof rubber ring is arranged at the joint of the upper cover and the lower cover; an anti-unlocking lock catch is arranged outside the portable cloth control box body.
The PP alloy resin material adopted by the shell has good waterproof effect, and the waterproof rubber ring is added at the joint of the upper cover and the lower cover, so that the whole distribution control box has good waterproof performance and can be better suitable for outdoor occasions, wherein the lower cover is used for accommodating a main board (comprising a controller, a clamping groove), a keyboard, a power supply assembly and the like, and the upper cover is used for accommodating a display. In addition, the outside of box is equipped with prevents opening the hasp, and factor of safety is higher.
While the preferred embodiment has been described, it is not intended to limit the invention thereto, and any person skilled in the art may make variations and modifications without departing from the spirit and scope of the present invention, so that the scope of the present invention shall be defined by the claims of the present application.
Claims (19)
1. An object recognition system, comprising: an image acquisition device and a portable cloth control box; the image acquisition device is used for acquiring an environment image within a preset range from the position of the image acquisition device and sending the environment image to the portable cloth control box;
the portable control box is used for analyzing the object in the environment image, and if the object is matched with a preset target object, the portable control box sends out alarm information for indicating that the object in the environment image is matched with the target object; the portable control box is also used for supplying power to the image acquisition device;
the image acquisition device is provided with a type selection part which is used for selecting and identifying the type of an object in the image, and correspondingly adjusting the shooting parameters when the image is acquired or adjusting the shooting parameters and the light source parameters when the image is acquired according to the type of the object;
the portable control box is provided with a clamping groove, at least one clamping groove is used for fixing a provided object identification board card, and special information provided for an object identifier is integrated on the object identification board card, wherein the special information comprises an object database used for identifying the object in the environment image or a database used for identifying the object in the environment image and a special program; a special program integrated by each object identification board card and a stored database aim at specific identification object types;
wherein the special program is a carrier in the form of software or hardware of a special recognition model designed based on a deep learning algorithm.
2. The object recognition system according to claim 1, wherein a light source and a light source adjusting part are provided on the image acquisition device, and the light source adjusting part is used for adjusting the working parameters of the light source when acquiring the image according to the object type and/or the environment brightness condition.
3. The object recognition system according to claim 1, comprising a handheld terminal for receiving and displaying alarm information sent by the portable control box.
4. The object recognition system according to claim 1, wherein the portable cloth control box includes an object recognition board card storing an object recognition unit; the object identification board card is plugged and replaced at any time.
5. The object recognition system of claim 1, wherein the particular recognition object in the environmental image analyzed by the portable fabric box comprises at least one of:
face, vehicle, body, motion, posture, clothing.
6. The object recognition system according to claim 1 or 3, wherein the portable control box is further configured to issue a first instruction for adjusting at least one parameter of a shooting angle and a shooting focal length to the image acquisition apparatus;
the image acquisition device is also used for adjusting at least one parameter of a shooting angle and a shooting focal length of the image acquisition device according to the first instruction.
7. The object recognition system of claim 3, wherein the handheld terminal is further configured to issue a second instruction to the portable fabric control box for adjusting at least one parameter of a shooting angle and a shooting focal length of the image acquisition device;
the portable control box is specifically used for sending a first instruction to the image acquisition device according to the second instruction.
8. The object recognition system of claim 1, wherein the portable fabric box is further configured to display the alarm information.
9. The object recognition system according to claim 3, wherein the handheld terminal is further configured to obtain a first trigger operation for inquiring about alarm information by a user, send a third instruction for obtaining alarm information required by the user to the portable control box for the first trigger operation, and obtain the alarm information required by the user provided by the portable control box;
the portable control box is further used for obtaining the third instruction, and providing alarm information required by a user for the handheld terminal aiming at the third instruction.
10. The object recognition system of claim 3, wherein the handheld terminal is further configured to obtain a second trigger operation for setting information in the portable fabric control box by a user, and issue a fourth instruction for setting information in the portable fabric control box to the portable fabric control box for the second trigger operation;
the portable control box is further used for obtaining the fourth instruction and setting according to setting information contained in the fourth instruction.
11. The object recognition system of claim 3, wherein the handheld terminal is further configured to provide the alert information to other handheld terminals or the handheld terminal is further configured to perform a voice communication operation or a video communication operation with other handheld terminals.
12. A portable fabric control box, comprising:
an adapter for connecting an image acquisition device, the image acquisition device being a device independent of the portable fabric control box;
an object identifier connected to the adapter for identifying an image of the environment provided by the image acquisition device via the adapter;
the alarm is connected with the object identifier and used for acquiring and prompting alarm information provided by the object identifier, and the alarm information is information used for representing that an object in the environment image is matched with a target object;
a power supply assembly for supplying power; the power supply assembly comprises a power supply adapter, and is connected with the image acquisition device through the power supply adapter to supply power to the image acquisition device;
the portable control box is provided with a clamping groove, at least one clamping groove is used for fixing a provided object identification board card, and special information provided for the object identifier is integrated on the object identification board card, wherein the special information comprises an object database used for identifying the object in the environment image or a database used for identifying the object in the environment image and a special program; a special program integrated by each object identification board card and a stored database aim at specific identification object types;
wherein the special program is a carrier in the form of software or hardware of a special recognition model designed based on a deep learning algorithm.
13. The portable fabric control pod of claim 12, wherein the object recognition card corresponds to one of the following specific recognition object types: face objects, vehicle objects, human body objects, action objects, gesture objects, and clothing objects.
14. The portable fabric control pod of claim 12, further comprising a display.
15. The portable fabric control pod of claim 12, further comprising an information input device for inputting information.
16. The portable fabric control pod of claim 12, wherein the power assembly comprises a battery, a power adapter coupled to the battery to charge the battery, and a charging interface coupled to the power adapter.
17. The portable fabric control box of claim 12, wherein the portable fabric control box housing is made of PP alloy resin material.
18. The portable control box of claim 12, wherein the portable control box comprises an upper cover and a lower cover, and a waterproof rubber ring is arranged at the joint of the upper cover and the lower cover.
19. The portable fabric control box of claim 12, wherein the portable fabric control box body is provided with an anti-unlocking lock catch.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310574453.4A CN116778302B (en) | 2023-05-19 | 2023-05-19 | Object recognition system and portable cloth control box |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310574453.4A CN116778302B (en) | 2023-05-19 | 2023-05-19 | Object recognition system and portable cloth control box |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116778302A CN116778302A (en) | 2023-09-19 |
| CN116778302B true CN116778302B (en) | 2024-03-26 |
Family
ID=87988639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310574453.4A Active CN116778302B (en) | 2023-05-19 | 2023-05-19 | Object recognition system and portable cloth control box |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116778302B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101635834A (en) * | 2008-07-21 | 2010-01-27 | 侯荣琴 | Automatic tracing identification system for artificial neural control |
| CN105825568A (en) * | 2016-03-16 | 2016-08-03 | 广东威创视讯科技股份有限公司 | Portable intelligent interactive equipment |
| CN106548161A (en) * | 2016-11-23 | 2017-03-29 | 上海成业智能科技股份有限公司 | The collection of face recognition features' code and knowledge method for distinguishing under the conditions of disturbing for outdoor or light |
| CN108268850A (en) * | 2018-01-24 | 2018-07-10 | 成都鼎智汇科技有限公司 | A kind of big data processing method based on image |
| CN108320735A (en) * | 2018-01-23 | 2018-07-24 | 北京易智能科技有限公司 | A kind of emotion identification method and system of multi-data fusion |
| CN110188658A (en) * | 2019-05-27 | 2019-08-30 | Oppo广东移动通信有限公司 | Personal identification method, device, electronic equipment and storage medium |
| CN210015451U (en) * | 2019-06-03 | 2020-02-04 | 中国电子进出口有限公司 | Embedded portable face cloth accuse case device |
| CN114581998A (en) * | 2022-03-14 | 2022-06-03 | 重庆紫光华山智安科技有限公司 | Deployment and control method, system, equipment and medium based on target object association feature fusion |
| CN114937095A (en) * | 2022-06-16 | 2022-08-23 | 京东方科技集团股份有限公司 | Camera control method, device, system, analysis equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8036425B2 (en) * | 2008-06-26 | 2011-10-11 | Billy Hou | Neural network-controlled automatic tracking and recognizing system and method |
-
2023
- 2023-05-19 CN CN202310574453.4A patent/CN116778302B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101635834A (en) * | 2008-07-21 | 2010-01-27 | 侯荣琴 | Automatic tracing identification system for artificial neural control |
| CN105825568A (en) * | 2016-03-16 | 2016-08-03 | 广东威创视讯科技股份有限公司 | Portable intelligent interactive equipment |
| CN106548161A (en) * | 2016-11-23 | 2017-03-29 | 上海成业智能科技股份有限公司 | The collection of face recognition features' code and knowledge method for distinguishing under the conditions of disturbing for outdoor or light |
| CN108320735A (en) * | 2018-01-23 | 2018-07-24 | 北京易智能科技有限公司 | A kind of emotion identification method and system of multi-data fusion |
| CN108268850A (en) * | 2018-01-24 | 2018-07-10 | 成都鼎智汇科技有限公司 | A kind of big data processing method based on image |
| CN110188658A (en) * | 2019-05-27 | 2019-08-30 | Oppo广东移动通信有限公司 | Personal identification method, device, electronic equipment and storage medium |
| CN210015451U (en) * | 2019-06-03 | 2020-02-04 | 中国电子进出口有限公司 | Embedded portable face cloth accuse case device |
| CN114581998A (en) * | 2022-03-14 | 2022-06-03 | 重庆紫光华山智安科技有限公司 | Deployment and control method, system, equipment and medium based on target object association feature fusion |
| CN114937095A (en) * | 2022-06-16 | 2022-08-23 | 京东方科技集团股份有限公司 | Camera control method, device, system, analysis equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116778302A (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107660039B (en) | A kind of lamp control system of identification dynamic gesture | |
| CN105100724B (en) | A kind of smart home telesecurity monitoring method of view-based access control model analysis | |
| US20160065828A1 (en) | Method for controlling electronic device using ip camera having function of wireless remote controller | |
| CN108200334A (en) | Image capturing method, device, storage medium and electronic equipment | |
| CN111327829B (en) | Composition guiding method, composition guiding device, electronic equipment and storage medium | |
| CN108961497A (en) | A kind of door-locking system with warning function | |
| CN109542233A (en) | A kind of lamp control system based on dynamic gesture and recognition of face | |
| CN110458794B (en) | Quality detection method and device for accessories of rail train | |
| KR20210004162A (en) | Automatic Data Set Generation Device and SW and their Control Method for AI Machine Learning Learning | |
| CN111726921A (en) | Somatosensory interactive light control system | |
| CN115480923B (en) | Multi-mode intelligent classroom edge computing control system | |
| CN109945976B (en) | Binocular imaging detection device and detection method | |
| CN111783674A (en) | Face recognition method and system based on AR glasses | |
| CN116778302B (en) | Object recognition system and portable cloth control box | |
| CN110958322A (en) | Wireless communication system for implementing attendance based on two-dimensional code scanning | |
| CN105872115A (en) | Remote monitoring system based on cloud computing | |
| JP2000214945A (en) | User specification system, device and method for transmition, device and method for information processing, device and method for data providing and providing medium | |
| CN116246200A (en) | Screen display information candid photographing detection method and system based on visual identification | |
| CN205486162U (en) | Stealthy image anti -fake detection equipment based on bluetooth | |
| CN114520902A (en) | Privacy protection-based smart home projection method and system | |
| CN114283278A (en) | Infectious disease prevention and control device and method | |
| KR102211734B1 (en) | Video surveillance device using image correction filter | |
| RU2710951C1 (en) | Self-contained mobile personal identification system | |
| CN218471337U (en) | AI intelligent content recognition device | |
| Garcia et al. | AI Smart Security Camera for Person Detection, Face Recognition, Tracking and Logging |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |