CN109117741A - Offline object identifying method and device to be detected - Google Patents
Offline object identifying method and device to be detected Download PDFInfo
- Publication number
- CN109117741A CN109117741A CN201810804493.2A CN201810804493A CN109117741A CN 109117741 A CN109117741 A CN 109117741A CN 201810804493 A CN201810804493 A CN 201810804493A CN 109117741 A CN109117741 A CN 109117741A
- Authority
- CN
- China
- Prior art keywords
- detected
- objects
- image
- ambient image
- offline
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000010586 diagram Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 9
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 9
- 230000002093 peripheral effect Effects 0.000 description 5
- 230000001815 facial effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
Classifications
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/2149—Restricted operating environment
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of offline object identifying methods and device to be detected, are related to protection and monitor field.The offline object identifying method and device to be detected from the ambient image by extracting characteristics of objects to be detected according to presetting object recognition algorithm model to be detected in local；Then judge whether the characteristics of objects to be detected extracted is contained in pre-stored characteristics of objects library to be detected；Finally when the characteristics of objects to be detected extracted is contained in pre-stored characteristics of objects library to be detected, by include the characteristics of objects to be detected extracted object images to be detected be determined as needed for object images to be detected.The offline object identifying method to be detected and device are not necessarily to for object to be detected to be uploaded to cloud processing, in the case where network limited or unstable networks or data do not allow incoming public network, Object identifying work to be detected locally can be completed, the limitation that not will receive network condition promotes artificial intelligence application more universal.
Description
Technical field
The present invention relates to protection and monitor fields, in particular to a kind of offline object identifying method and device to be detected.
Background technique
Monitoring system is mainly made of headend equipment and rear end equipment this two large divisions, headend equipment usually by video camera,
Manually or electrically the components such as camera lens, holder, shield, monitor, alarm detector and multi-functional decoder form, their each departments
Its duty, and (transmission is contacted by the way that wired, wireless or optical fiber transmission medium are corresponding with the foundation of the various equipment of central control system
Video/audio signal and control, alarm signal).Face recognition and largely to the valuable application of people occur, it is fast and accurate
Object detection system market is also increasingly flourishing.
The mode that artificial intelligence recognition of face at present uses nearly all is with cloud service (ability platform) or large-scale face
The mode of local terminal provides facial recognition capability, and the mode that developer or enterprise's multi-pass cross " cloud " accesses face recognition technology,
I.e. equipment end acquires face picture, then reaches cloud centralized processing, finally returns to equipment end and completes certification.But in some specific fields
Jing Zhong, such as network limited, unstable networks, data do not allow incoming public network, and recognition of face cloud service is obvious " unable to do what one wishes ",
And large-scale face local terminal is not only inconvenient to carry, in the limited situation in space, using also will receive limitation.
Summary of the invention
In view of this, the embodiment of the present invention is designed to provide a kind of offline object identifying method and device to be detected,
To improve above-mentioned problem.
In a first aspect, it is applied to local terminal the embodiment of the invention provides a kind of offline object identifying method to be detected,
The local terminal is connect with image collecting device wire communication, and the offline object identifying method to be detected includes:
Receive the ambient image that image collecting device is sent；
It is to be detected right to extract from the ambient image in local according to presetting object recognition algorithm model to be detected
As feature；
Judge whether the characteristics of objects to be detected extracted is contained in pre-stored characteristics of objects library to be detected；
It will include to mention when the characteristics of objects to be detected extracted is contained in pre-stored characteristics of objects library to be detected
The object images to be detected for the characteristics of objects to be detected got are determined as required object images to be detected.
Second aspect, the embodiment of the invention also provides a kind of offline object recognition equipments to be detected, are applied to local whole
End, the local terminal are connect with image collecting device wire communication, and the offline object recognition equipment to be detected includes:
Information receiving unit, for receiving the ambient image of image collecting device transmission；
Feature extraction unit, in local according to presetting object recognition algorithm model to be detected from the environment map
Characteristics of objects to be detected is extracted as in；
Judging unit, for judging whether the characteristics of objects to be detected extracted is contained in pre-stored object to be detected
In feature database；
Object images determination unit, for when the characteristics of objects to be detected that extract be contained in it is pre-stored to be detected right
When as feature database, by include the characteristics of objects to be detected extracted object images to be detected be determined as needed for object to be detected
Image.
Compared with prior art, offline object identifying method and device to be detected provided by the invention, by local according to
Characteristics of objects to be detected is extracted from the ambient image according to presetting object recognition algorithm model to be detected；Then judgement mentions
Whether the characteristics of objects to be detected got is contained in pre-stored characteristics of objects library to be detected；It is finally to be checked when what is extracted
It will include the characteristics of objects to be detected extracted when survey characteristics of objects is contained in pre-stored characteristics of objects library to be detected
Object images to be detected are determined as required object images to be detected.The offline object identifying method to be detected and device are without will be to
Test object is uploaded to cloud processing, in the case where network limited or unstable networks or data do not allow incoming public network,
Object identifying work to be detected locally can be completed, i.e., not will receive the limitation of network condition, promote artificial intelligence application more
It is universal.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.Therefore, below to the reality of the invention provided in the accompanying drawings
The detailed description for applying example is not intended to limit the range of claimed invention, but is merely representative of selected implementation of the invention
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
Every other embodiment, shall fall within the protection scope of the present invention.
Fig. 1 is the interaction schematic diagram of local terminal provided in an embodiment of the present invention and image collecting device；
Fig. 2 is the structural block diagram of local terminal provided in an embodiment of the present invention；
Fig. 3 is the flow chart of offline object identifying method to be detected provided in an embodiment of the present invention；
Fig. 4 is the functional block diagram of offline object recognition equipment to be detected provided in an embodiment of the present invention.
Icon: 100- image collecting device；The local terminal 200-；300- object recognition equipment to be detected offline；101- is deposited
Reservoir；102- storage control；103- processor；104- Peripheral Interface；401- information receiving unit；402- feature extraction list
Member；403- judging unit；404- object images determination unit；405- picture charge pattern unit；406- number recording unit；407- report
Alert instruction generation unit.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Offline object recognition equipment to be detected provided by present pre-ferred embodiments and method can be applied to as shown in Figure 1
Application environment in.As shown in Figure 1, wire communication connects between image collecting device 100, local terminal 200, image collector
It sets 100 and carries out data interaction with local terminal 200.In the embodiment of the present invention, image collecting device 100 can be used but unlimited
In video camera.
As shown in Fig. 2, being the functional block diagram of offline object recognition equipment 300 to be detected provided by the invention.Peace
Local terminal 200 equipped with the offline object recognition equipment 300 to be detected includes memory 101, storage control 102, processing
Device 103 and Peripheral Interface 104.Wherein, memory 101, storage control 102, processor 103, each element of Peripheral Interface 104
It is directly or indirectly electrically connected between each other, to realize the transmission or interaction of data.For example, these elements can lead between each other
It crosses one or more communication bus or signal wire is realized and is electrically connected.Offline object recognition equipment 300 to be detected includes at least one
It is a to be stored in the memory 101 or be solidificated in the local terminal in the form of software or firmware (firmware)
Software function module.Processor 103 is for executing the executable module stored in memory 101, for example, offline object to be detected
The software function module or computer program that identification device 300 includes.
Wherein, memory 101 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Wherein, memory 101 is for storing program, and the processor 103 executes described program after receiving and executing instruction, aforementioned
Method performed by the local terminal that the stream process that any embodiment of the embodiment of the present invention discloses defines can be applied to processor
In 103, or realized by processor 103.
Processor 103 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 103 can
To be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit
(Network Processor, abbreviation NP) etc.；Can also be digital signal processor (DSP), specific integrated circuit (ASIC),
Ready-made programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hard
Part component.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor
It can be microprocessor or the processor 103 be also possible to any conventional processor etc..
Various input/output devices are couple processor 103 and memory 101 by Peripheral Interface 104.In some implementations
In example, Peripheral Interface 104, processor 103 and storage control 102 can be realized in one single chip.In some other reality
In example, they can be realized by independent chip respectively.
Referring to Fig. 3, being applied to local terminal the embodiment of the invention provides a kind of offline object identifying method to be detected
200, the local terminal 200 is connect with 100 wire communication of image collecting device, the offline object identifying method packet to be detected
It includes:
Step S301: the ambient image that image collecting device 100 is sent is received.
Image collecting device 100 can be installed on the good position of internal home network environment, it is also possible to be installed on basement or
The position of Outdoor Network environment difference.
Step S302: it is extracted from the ambient image in local according to presetting object recognition algorithm model to be detected
Characteristics of objects to be detected.
In the present embodiment, when characteristics of objects to be detected is real human face feature, step S302 can specifically install as follows
Mode is implemented:
Current RFCN network model classifier and the ambient image based on pre-training obtain the ambient image
Doubtful face characteristic classification, class probability value, target candidate frame position coordinates and fixed position coordinate, wherein it is described
Class probability value is when the ambient image includes doubtful face characteristic, and the doubtful face characteristic belongs to the general of the classification
Rate value；According to ring described in the class probability value, the target candidate frame position coordinates and the fixed position coordinate measurement
Whether border image includes real human face feature corresponding with the classification；When the class probability value is more than or equal to presetting
Probability threshold value, and when the fixed position coordinate is in the target candidate frame, identifies and extract the ambient image packet
The real human face feature corresponding with the classification contained passes through the class probability value and fixed position coordinate of integrated environment image
Determine ambient image whether include the type human face target, not only increase the accuracy of Face detection position, also reduce
False detection rate.
Step S303: judge whether the characteristics of objects to be detected extracted is contained in pre-stored characteristics of objects to be detected
In library；If so, thening follow the steps S304.
Step S304: by include the characteristics of objects to be detected extracted object images to be detected be determined as needed for it is to be checked
Survey object images.
Wherein, when the ambient image is dynamic environment image, the offline object identifying method to be detected further include:
Step S305: the required object images to be detected are tracked in dynamic environment image.
Specifically, the facial image taken in camera can be positioned by image recognition, and commands camera shooting
Head tracks the facial image, and the facial image is allowed to be always held within the scope of camera view.
Step S306: record extracts the number of characteristics of objects to be detected.
When extracting primary characteristics of objects to be detected, can count as a flow of the people, therefore extracted by record
The number of characteristics of objects to be detected can count on the flow of the people of current environment scene within a certain period of time.
When the characteristics of objects to be detected is face characteristic or personal feature, the offline object identifying method to be detected
Further include:
Step S307: judging whether required face characteristic image or required personal characteristic image are blacklist image, if
It is to then follow the steps S308.
Step S308: alarm command is generated.
Alarm command can remind staff in time, carry out live control to blacklist personnel to scene.
Referring to Fig. 4, being applied to local whole the embodiment of the invention also provides a kind of offline object recognition equipment to be detected
End 200.Local terminal 200 is connect with 100 wire communication of image collecting device.It should be noted that provided by the present embodiment
Offline object recognition equipment to be detected, Face datection provided by the technical effect and above-described embodiment of basic principle and generation
Method is identical, and to briefly describe, the present embodiment part does not refer to place, can refer to corresponding contents in the above embodiments.It is described
Offline object recognition equipment to be detected includes information receiving unit 401, feature extraction unit 402, judging unit 403, object diagram
As determination unit 404, picture charge pattern unit 405, number recording unit 406 and alarm command generation unit 407.
Information receiving unit 401 is used to receive the ambient image of the transmission of image collecting device 100.
Feature extraction unit 402 is used in local according to presetting object recognition algorithm model to be detected from the environment
Characteristics of objects to be detected is extracted in image.
When the characteristics of objects to be detected is real human face feature, the feature extraction unit 402 is specifically used for being based on
It is special that the current RFCN network model classifier of pre-training and the ambient image obtain the doubtful face that the ambient image includes
Classification, class probability value, target candidate frame position coordinates and the fixed position coordinate of sign, wherein the class probability value is
When the ambient image includes doubtful face characteristic, the doubtful face characteristic belongs to the probability value of the classification；According to institute
State whether ambient image described in class probability value, the target candidate frame position coordinates and the fixed position coordinate measurement wraps
Contain real human face feature corresponding with the classification；When the class probability value be greater than or equal to presetting probability threshold value,
And the fixed position coordinate in the target candidate frame when, identify and to extract the ambient image including with the class
Not corresponding real human face feature.
It is pre-stored to be detected right that judging unit 403 is used to judge whether the characteristics of objects to be detected extracted to be contained in
As in feature database.
Object images determination unit 404 be used for when the characteristics of objects to be detected that extract be contained in it is pre-stored to be detected
When characteristics of objects library, by include the characteristics of objects to be detected extracted object images to be detected be determined as needed for it is to be detected right
As image.
When the ambient image is dynamic environment image, picture charge pattern unit 405 is for right in dynamic environment image
Object images to be detected needed for described are tracked.
When the ambient image is dynamic environment image, it is to be detected right that number recording unit 406 is extracted for record
As the number of feature.
When the characteristics of objects to be detected is face characteristic or personal feature, if alarm command generation unit 407 is used for
When required face characteristic image or required personal characteristic image are blacklist image, alarm command is generated.
In conclusion offline object identifying method and device to be detected provided by the invention, by default in local foundation
Fixed object recognition algorithm model to be detected extracts characteristics of objects to be detected from the ambient image；Then judgement is extracted
Whether characteristics of objects to be detected is contained in pre-stored characteristics of objects library to be detected；Finally when the object to be detected extracted
It will include the to be detected of the characteristics of objects to be detected extracted when feature is contained in pre-stored characteristics of objects library to be detected
Object images are determined as required object images to be detected.The offline object identifying method to be detected is not necessarily to device will be to be detected right
As being uploaded to cloud processing, in the case where network limited or unstable networks or data do not allow incoming public network, locally it is being
Achievable Object identifying work to be detected, i.e., not will receive the limitation of network condition, promote artificial intelligence application more universal.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, local terminal or network equipment etc.) execute all or part of step of each embodiment the method for the present invention
Suddenly.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), deposits at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic or disk.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to an entity or behaviour
Make with another entity or operate distinguish, without necessarily requiring or implying between these entities or operation there are it is any this
The actual relationship of kind or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to nonexcludability
Include so that include a series of elements process, method, article or equipment not only include those elements, but also
Including other elements that are not explicitly listed, or further include for this process, method, article or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method, article or equipment of element.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
Claims (10)
1. a kind of offline object identifying method to be detected, which is characterized in that be applied to local terminal, the local terminal and image
Acquisition device wire communication connection, the offline object identifying method to be detected include:
Receive the ambient image that image collecting device is sent；
Object spy to be detected is extracted from the ambient image according to presetting object recognition algorithm model to be detected in local
Sign；
Judge whether the characteristics of objects to be detected extracted is contained in pre-stored characteristics of objects library to be detected；
It will include to extract when the characteristics of objects to be detected extracted is contained in pre-stored characteristics of objects library to be detected
Characteristics of objects to be detected object images to be detected be determined as needed for object images to be detected.
2. offline object identifying method to be detected according to claim 1, which is characterized in that the ambient image is dynamic
Ambient image, the offline object identifying method to be detected further include:
The required object images to be detected are tracked in dynamic environment image.
3. offline object identifying method to be detected according to claim 1, which is characterized in that the ambient image is dynamic
Ambient image, the offline object identifying method to be detected further include:
Record extracts the number of characteristics of objects to be detected.
4. offline object identifying method to be detected according to claim 1, which is characterized in that the characteristics of objects to be detected
For face characteristic or personal feature, the offline object identifying method to be detected further include:
If required face characteristic image or required personal characteristic image are blacklist image, alarm command is generated.
5. offline object identifying method to be detected according to claim 1, which is characterized in that the characteristics of objects to be detected
For real human face feature, local according to presetting object recognition algorithm model to be detected extracted from the ambient image to
The step of test object feature includes:
What current RFCN network model classifier and the ambient image based on pre-training obtained that the ambient image includes doubts
Like the classification of face characteristic, class probability value, target candidate frame position coordinates and fixed position coordinate, wherein the classification
Probability value is when the ambient image includes doubtful face characteristic, and the doubtful face characteristic belongs to the probability of the classification
Value；
According to environment described in the class probability value, the target candidate frame position coordinates and the fixed position coordinate measurement
Whether image includes real human face feature corresponding with the classification；
When the class probability value is greater than or equal to presetting probability threshold value, and the fixed position coordinate is waited in the target
When selecting in frame, the real human face feature corresponding with the classification that the ambient image includes is identified and extracted.
6. a kind of offline object recognition equipment to be detected, which is characterized in that be applied to local terminal, the local terminal and image
Acquisition device wire communication connection, the offline object recognition equipment to be detected include:
Information receiving unit, for receiving the ambient image of image collecting device transmission；
Feature extraction unit, for local according to presetting object recognition algorithm model to be detected from the ambient image
Extract characteristics of objects to be detected；
Judging unit, for judging whether the characteristics of objects to be detected extracted is contained in pre-stored characteristics of objects to be detected
In library；
Object images determination unit, for being contained in pre-stored object to be detected spy when the characteristics of objects to be detected extracted
Levy library when, by include the characteristics of objects to be detected extracted object images to be detected be determined as needed for object diagram to be detected
Picture.
7. offline object recognition equipment to be detected according to claim 6, which is characterized in that the ambient image is dynamic
Ambient image, the offline object recognition equipment to be detected further include:
Picture charge pattern unit, for being tracked in dynamic environment image to the required object images to be detected.
8. offline object recognition equipment to be detected according to claim 6, which is characterized in that the ambient image is dynamic
Ambient image, the offline object recognition equipment to be detected further include:
Number recording unit, for recording the number for extracting characteristics of objects to be detected.
9. offline object recognition equipment to be detected according to claim 6, which is characterized in that the characteristics of objects to be detected
For face characteristic or personal feature, the offline object recognition equipment to be detected further include:
Alarm command generation unit, if be blacklist image for required face characteristic image or required personal characteristic image,
Generate alarm command.
10. offline object recognition equipment to be detected according to claim 6, which is characterized in that the object to be detected is special
Sign is real human face feature, the feature extraction unit be specifically used for current RFCN network model classifier based on pre-training and
The ambient image obtains the classification, class probability value, target candidate frame position for the doubtful face characteristic that the ambient image includes
Set coordinate and fixed position coordinate, wherein the class probability value be the ambient image include doubtful face characteristic when,
The doubtful face characteristic belongs to the probability value of the classification；
According to environment described in the class probability value, the target candidate frame position coordinates and the fixed position coordinate measurement
Whether image includes real human face feature corresponding with the classification；
When the class probability value is greater than or equal to presetting probability threshold value, and the fixed position coordinate is waited in the target
When selecting in frame, the real human face feature corresponding with the classification that the ambient image includes is identified and extracted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810804493.2A CN109117741A (en) | 2018-07-20 | 2018-07-20 | Offline object identifying method and device to be detected |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810804493.2A CN109117741A (en) | 2018-07-20 | 2018-07-20 | Offline object identifying method and device to be detected |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109117741A true CN109117741A (en) | 2019-01-01 |
Family
ID=64863223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810804493.2A Pending CN109117741A (en) | 2018-07-20 | 2018-07-20 | Offline object identifying method and device to be detected |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109117741A (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404107A (en) * | 2008-11-19 | 2009-04-08 | 公安部第三研究所 | Internet bar monitoring and warning system based on human face recognition technology |
| CN103020706A (en) * | 2011-09-20 | 2013-04-03 | 佳都新太科技股份有限公司 | Visitors flow rate statistic algorithm based on moving target detection and Haar characteristics |
| CN105354902A (en) * | 2015-11-10 | 2016-02-24 | 深圳市商汤科技有限公司 | Security management method and system based on face identification |
| CN105631406A (en) * | 2015-12-18 | 2016-06-01 | 小米科技有限责任公司 | Method and device for recognizing and processing image |
| CN105740751A (en) * | 2014-12-11 | 2016-07-06 | 深圳市赛为智能股份有限公司 | Object detection and identification method and system |
| CN106650581A (en) * | 2016-09-27 | 2017-05-10 | 腾讯科技（深圳）有限公司 | Visitor flow rate statistics method and device |
| CN106709468A (en) * | 2016-12-31 | 2017-05-24 | 北京中科天云科技有限公司 | City region surveillance system and device |
| CN106780612A (en) * | 2016-12-29 | 2017-05-31 | 浙江大华技术股份有限公司 | Object detecting method and device in a kind of image |
| CN106998444A (en) * | 2017-02-14 | 2017-08-01 | 北京中科天云科技有限公司 | A kind of big data face monitoring system and device |
| CN107368770A (en) * | 2016-05-12 | 2017-11-21 | 深圳市维杰乐思科技有限公司 | A kind of frequent customer's automatic identifying method and system |
| CN107563350A (en) * | 2017-09-21 | 2018-01-09 | 深圳市唯特视科技有限公司 | A kind of method for detecting human face for suggesting network based on yardstick |
| CN107578014A (en) * | 2017-09-06 | 2018-01-12 | 上海寒武纪信息科技有限公司 | Information processor and method |
| US20180068198A1 (en) * | 2016-09-06 | 2018-03-08 | Carnegie Mellon University | Methods and Software for Detecting Objects in an Image Using Contextual Multiscale Fast Region-Based Convolutional Neural Network |
| CN107818343A (en) * | 2017-10-30 | 2018-03-20 | 中国科学院计算技术研究所 | Method of counting and device |
| CN108171207A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Face identification method and device based on video sequence |
-
2018
- 2018-07-20 CN CN201810804493.2A patent/CN109117741A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404107A (en) * | 2008-11-19 | 2009-04-08 | 公安部第三研究所 | Internet bar monitoring and warning system based on human face recognition technology |
| CN103020706A (en) * | 2011-09-20 | 2013-04-03 | 佳都新太科技股份有限公司 | Visitors flow rate statistic algorithm based on moving target detection and Haar characteristics |
| CN105740751A (en) * | 2014-12-11 | 2016-07-06 | 深圳市赛为智能股份有限公司 | Object detection and identification method and system |
| CN105354902A (en) * | 2015-11-10 | 2016-02-24 | 深圳市商汤科技有限公司 | Security management method and system based on face identification |
| CN105631406A (en) * | 2015-12-18 | 2016-06-01 | 小米科技有限责任公司 | Method and device for recognizing and processing image |
| CN107368770A (en) * | 2016-05-12 | 2017-11-21 | 深圳市维杰乐思科技有限公司 | A kind of frequent customer's automatic identifying method and system |
| US20180068198A1 (en) * | 2016-09-06 | 2018-03-08 | Carnegie Mellon University | Methods and Software for Detecting Objects in an Image Using Contextual Multiscale Fast Region-Based Convolutional Neural Network |
| CN106650581A (en) * | 2016-09-27 | 2017-05-10 | 腾讯科技（深圳）有限公司 | Visitor flow rate statistics method and device |
| CN106780612A (en) * | 2016-12-29 | 2017-05-31 | 浙江大华技术股份有限公司 | Object detecting method and device in a kind of image |
| CN106709468A (en) * | 2016-12-31 | 2017-05-24 | 北京中科天云科技有限公司 | City region surveillance system and device |
| CN106998444A (en) * | 2017-02-14 | 2017-08-01 | 北京中科天云科技有限公司 | A kind of big data face monitoring system and device |
| CN107578014A (en) * | 2017-09-06 | 2018-01-12 | 上海寒武纪信息科技有限公司 | Information processor and method |
| CN107563350A (en) * | 2017-09-21 | 2018-01-09 | 深圳市唯特视科技有限公司 | A kind of method for detecting human face for suggesting network based on yardstick |
| CN107818343A (en) * | 2017-10-30 | 2018-03-20 | 中国科学院计算技术研究所 | Method of counting and device |
| CN108171207A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Face identification method and device based on video sequence |
Non-Patent Citations (4)
| Title |
|---|
| JIFENG DAI 等: "R-FCN: Object Detection via Region-based Fully Convolutional Networks", pages 1 - 11 * |
| YITONG WANG 等: "Detecting Faces Using Region-based Fully Convolutional Networks", pages 1 - 10 * |
| 凌明 等主编: ""纵海杯"东南大学第二届嵌入式***设计大赛获奖作品设计报告", 东南大学出版社, pages: 96 * |
| 卫露宁: "基于全卷积神经网络的人脸检测算法研究", vol. 2018, no. 2018, pages 138 - 1243 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858371B (en) | Face recognition method and device | |
| CN104813339A (en) | Methods, devices and systems for detecting objects in a video | |
| CN106295598A (en) | A kind of across photographic head method for tracking target and device | |
| CN108563651B (en) | Multi-video target searching method, device and equipment | |
| CN110516707B (en) | Image labeling method and device and storage medium thereof | |
| CN112422909B (en) | Video behavior analysis management system based on artificial intelligence | |
| CN112153373A (en) | Fault identification method and device for bright kitchen range equipment and storage medium | |
| CN111401239B (en) | Video analysis method, device, system, equipment and storage medium | |
| CN111666821A (en) | Personnel gathering detection method, device and equipment | |
| CN110879986A (en) | Face recognition method, apparatus and computer-readable storage medium | |
| CN116129328A (en) | Method, device, equipment and storage medium for detecting carryover | |
| CN111881740A (en) | Face recognition method, face recognition device, electronic equipment and medium | |
| CN113920585A (en) | Behavior recognition method and device, equipment and storage medium | |
| Zeng et al. | Extended scale invariant local binary pattern for background subtraction | |
| CN113313084A (en) | Sleeping post detection method based on deep learning | |
| JP2012049774A (en) | Video monitoring device | |
| CN109117741A (en) | Offline object identifying method and device to be detected | |
| Zeng et al. | Effectively linking persons on cameras and mobile devices on networks | |
| CN114782883A (en) | Abnormal behavior detection method, device and equipment based on group intelligence | |
| CN111881787A (en) | Camera-based store illegal operation behavior identification method and system | |
| CN113469138A (en) | Object detection method and device, storage medium and electronic equipment | |
| CN113158933A (en) | Method, system, device and storage medium for identifying lost personnel | |
| JPWO2016136214A1 (en) | Discriminator learning apparatus, stagnant object detection system, discriminator learning method, stagnant object detection method, and program | |
| Shekhawat et al. | Realization of Smart and Highly Efficient IoTbased Surveillance System using Facial Recognition on FPGA | |
| CN103777954A (en) | Information processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ning Hao Inventor after: Xu Qing Inventor after: Zhang Lei Inventor after: Zheng Bo Inventor before: Ning Hao Inventor before: Xu Qing Inventor before: Zhang Lei Inventor before: Deng Bo |