CN110059547A - Object detection method and device - Google Patents
Object detection method and device Download PDFInfo
- Publication number
- CN110059547A CN110059547A CN201910176719.3A CN201910176719A CN110059547A CN 110059547 A CN110059547 A CN 110059547A CN 201910176719 A CN201910176719 A CN 201910176719A CN 110059547 A CN110059547 A CN 110059547A
- Authority
- CN
- China
- Prior art keywords
- interest
- region
- candidate frame
- frame
- pedestrian
- 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.)
- Granted
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The present disclosure discloses a kind of object detection method, device, electronic equipment and computer readable storage mediums, wherein the described method includes: returning pedestrian candidate frame according to the first anchor frame and returning the first candidate frame of the region of interest of the pedestrian；The second candidate frame of the region of interest of the pedestrian is returned according to the second anchor frame；Pedestrian detection frame is determined according to the second candidate frame of the pedestrian candidate frame, the first candidate frame of the region of interest and the region of interest.The disclosure returns pedestrian candidate frame and region of interest candidate frame by different anchor frames, can be improved the matching degree of region of interest candidate frame, improves positional accuracy.
Description
Technical field
This disclosure relates to technical field of information processing more particularly to a kind of object detection method, device, electronic equipment and meter
Calculation machine readable storage medium storing program for executing.
Background technique
Pedestrian detection has a wide range of applications in security protection and automatic Pilot field, its object is to pedestrian from background
It detected.The basis of pedestrian detection or a lot of other tasks, such as pedestrian identify again, pedestrian tracking and human body key point
Detection etc..And in security protection and automatic Pilot scene, it is conceived to and solves that pedestrian is crowded and circumstance of occlusion, proposes joint therewith
Pedestrian detecting system, while the region of interest of people and people are detected, the very big precision for improving pedestrian detection.
In the prior art, joint pedestrian detecting system be returned by identical anchor frame people and people region of interest it is inclined
Shifting amount, to obtain corresponding candidate frame.Usually the anchor frame is pre-designed for people's frame, and in this case,
Anchor frame and the region of interest frame of people can mismatch, this region of interest that can greatly increase people returns difficulty, eventually lead to dependent part
Position candidate frame positioning is inaccurate.
Summary of the invention
To overcome the problems in correlation technique, the disclosure provide a kind of object detection method, device, electronic equipment and
Computer readable storage medium.
According to the first aspect of the embodiments of the present disclosure, a kind of object detection method is provided, comprising:
Pedestrian candidate frame is returned according to the first anchor frame and returns the first candidate frame of the region of interest of the pedestrian；
The second candidate frame of the region of interest of the pedestrian is returned according to the second anchor frame；
According to the pedestrian candidate frame, the second candidate frame of the first candidate frame of the region of interest and the region of interest
Determine pedestrian detection frame.
Further, described according to the pedestrian candidate frame, the first candidate frame of the region of interest and the dependent part
Second candidate frame of position determines pedestrian detection frame, comprising:
It is determined according to the first candidate frame of the region of interest and the second candidate frame of the region of interest final related
Position candidate frame；
Pedestrian detection frame is determined according to the pedestrian candidate frame and the final region of interest candidate frame.
Further, described true according to the first candidate frame of the region of interest and the second candidate frame of the region of interest
Fixed final region of interest candidate frame, comprising:
Calculate the friendship of the second candidate frame of the region of interest and the first candidate frame of the region of interest and ratio；
According to the friendship and the region of interest candidate frame more final than determining.
It is further, described according to the friendship and the region of interest candidate frame more final than determining, comprising:
It, will be described if the friendship and than being greater than preset threshold when the second candidate frame of the region of interest is one
Second candidate frame of region of interest is as final region of interest candidate frame；Or,
When the second candidate frame of the region of interest is multiple, it is candidate to choose second handed over and than maximum region of interest
Frame is as region of interest target candidate frame, if described hand over and compare greater than preset threshold, by the region of interest target candidate frame
As final region of interest candidate frame.
Further, described that pedestrian detection is determined according to the pedestrian candidate frame and the final region of interest candidate frame
Frame, comprising:
The first candidate frame that the region of interest is replaced using the final region of interest candidate frame, so that it is determined that pedestrian
Detection block.
According to the second aspect of an embodiment of the present disclosure, a kind of object detecting device is provided, comprising:
Pedestrian's frame determining module, for returning pedestrian candidate frame according to the first anchor frame and returning the region of interest of the pedestrian
The first candidate frame；
Region of interest frame determining module, it is candidate for returning the second of region of interest of the pedestrian according to the second anchor frame
Frame；
Pedestrian detection frame determining module, for according to the first candidate frame of the pedestrian candidate frame, the region of interest and
Second candidate frame of the region of interest determines pedestrian detection frame.
Further, the pedestrian detection frame determining module includes:
Region of interest frame determination unit, for according to the of the first candidate frame of the region of interest and the region of interest
Two candidate frames determine final region of interest candidate frame；
Pedestrian detection frame determination unit, for true according to the pedestrian candidate frame and the final region of interest candidate frame
Determine pedestrian detection frame.
Further, the region of interest frame determination unit is specifically used for: calculating the second candidate frame of the region of interest
Friendship and ratio with the first candidate frame of the region of interest；According to the friendship and the region of interest candidate frame more final than determining.
Further, the region of interest frame determination unit is specifically used for: when the second candidate frame of the region of interest is
At one, if described hand over and compare greater than preset threshold, using the second candidate frame of the region of interest as final dependent part
Position candidate frame；Or, choosing and handing over and than the second of maximum region of interest when the second candidate frame of the region of interest is multiple
Candidate frame is as region of interest target candidate frame, if described hand over and than greater than preset threshold, the region of interest target is waited
Select frame as final region of interest candidate frame.
Further, the pedestrian detection frame determination unit is specifically used for: using the second candidate frame of the region of interest
The first candidate frame of the region of interest is replaced, so that it is determined that pedestrian detection frame.
According to the third aspect of an embodiment of the present disclosure, a kind of electronic equipment is provided, comprising:
Processor；
Memory for storage processor executable instruction；Wherein, the processor is configured to: it is real to execute the present invention
Apply any one object detection method described in example.
According to a fourth aspect of embodiments of the present disclosure, a kind of non-transitorycomputer readable storage medium is provided, when described
When instruction in storage medium is executed by the processor of electronic equipment, so that electronic equipment is able to carry out described in the embodiment of the present invention
Any one object detection method.
The technical scheme provided by this disclosed embodiment can include the following benefits: return row by different anchor frames
People's candidate frame and region of interest candidate frame can be improved the matching degree of region of interest candidate frame, improve positional accuracy.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Fig. 1 is a kind of flow chart for object detection method that the embodiment of the present disclosure one provides.
Fig. 2 is a kind of flow chart for object detection method that the embodiment of the present disclosure two provides.
Fig. 3 a is a kind of flow chart for object detection method that the embodiment of the present disclosure three provides.
Fig. 3 b is the candidate frame signal that first anchor frame determines in a kind of object detection method of the offer of the embodiment of the present disclosure three
Figure.
Fig. 3 c is the candidate frame signal that second anchor frame determines in a kind of object detection method of the offer of the embodiment of the present disclosure three
Figure.
Fig. 3 d is the candidate frame schematic diagram in a kind of object detection method of the offer of the embodiment of the present disclosure three after pedestrian detection.
Fig. 4 is a kind of structural block diagram for object detecting device that the embodiment of the present disclosure four provides.
Fig. 5 is the structural block diagram for a kind of electronic equipment that the embodiment of the present disclosure five provides.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Embodiment one
Fig. 1 is a kind of flow chart for object detection method that the embodiment of the present disclosure one provides, target provided in this embodiment
The executing subject of detection method can be can integrate for the object detecting device that the embodiment of the present disclosure provides, the device in mobile whole
Hold (for example, smart phone, tablet computer etc.), in notebook or fixed terminal (desktop computer), which can be with
Using hardware or software realization.As shown in Figure 1, comprising the following steps:
Step S11, first for returning pedestrian candidate frame according to the first anchor frame and returning the region of interest of the pedestrian are candidate
Frame.
Herein, in order to distinguish different anchor frames, the anchor frame first occurred is known as the first anchor frame here, by subsequent appearance
Anchor frame be known as the second anchor frame.
Wherein, the first anchor frame is the anchor frame being pre-designed for people, for returning pedestrian candidate frame and returning the pedestrian
Region of interest the first candidate frame.
Wherein, pedestrian candidate frame is used to acquire the human body image of pedestrian.
Specifically, first having to establish the binding relationship of people and region of interest, go to return with identical anchor frame in this step
Different target, such as human body and region of interest.By being then based on identical anchor frame, it can determine that two candidate frames returned out are
There is binding relationship, that is, some position is a part of someone.
Herein, in order to distinguish different region of interest candidate frames, the region of interest candidate frame that will first appear here
Referred to as the first candidate frame of region of interest, the region of interest candidate frame of subsequent appearance are successively known as the second candidate of region of interest
Frame.
Step S12 returns the second candidate frame of the region of interest of the pedestrian according to the second anchor frame.
Wherein, the anchor frame that the second anchor frame is pre-designed for the region of interest of people, the region of interest for returning people are candidate
Frame.
Wherein, region of interest can be the Partial Feature, including the number of people, face, people's leg, people's arm etc. of human body.Dependent part
Position candidate frame is used to acquire the image of region of interest.
Specifically, initially setting up the binding relationship of pedestrian and pedestrian's region of interest, the first anchor frame and is then respectively adopted
Two anchor frames return pedestrian candidate frame and region of interest candidate frame.
Step S13, according to the of the pedestrian candidate frame, the first candidate frame of the region of interest and the region of interest
Two candidate frames determine pedestrian detection frame.
The present embodiment returns pedestrian candidate frame and region of interest candidate frame by different anchor frames, can be improved region of interest
The matching degree of candidate frame improves positional accuracy.
Embodiment two
Fig. 2 is a kind of flow chart for object detection method that the embodiment of the present disclosure two provides, and the present embodiment is in above-mentioned implementation
On the basis of example, partnered matched row to step according to the second candidate frame of the pedestrian candidate frame and the region of interest
The region of interest candidate frame of people and pedestrian advanced optimize, as shown in Fig. 2, specifically including:
Step S21 returns the first candidate frame of pedestrian candidate frame and the region of interest of the pedestrian according to the first anchor frame.
Specifically, first having to establish the binding relationship of pedestrian and pedestrian's region of interest, in this step with identical anchor frame
It goes to return different target, such as human body and region of interest.By being then based on identical anchor frame, two times returned out can be determined
Frame is selected to have binding relationship, that is, some position is a part of some pedestrian.
Step S22 returns the second candidate frame of the region of interest of the pedestrian according to the second anchor frame.
Step S23 is determined most according to the first candidate frame of the region of interest and the second candidate frame of the region of interest
Whole region of interest candidate frame.
In an alternative embodiment, step 23 includes:
Step S231 calculates the friendship of the second candidate frame of the region of interest and the first candidate frame of the region of interest simultaneously
Than.
Wherein, it hands over and ratio is a concept used in target detection, be the second candidate frame and dependent part of region of interest
The overlapping rate of first candidate frame of position, the i.e. ratio of their intersection and union.
Step S232, according to the friendship and the region of interest candidate frame more final than determining.
Further, step S232 includes:
It, will be described if the friendship and than being greater than preset threshold when the second candidate frame of the region of interest is one
Second candidate frame of region of interest is as final region of interest candidate frame；Or, the second candidate frame when the region of interest is
When multiple, choose and hand over and than the second candidate frame of maximum region of interest as region of interest target candidate frame, if the friendship is simultaneously
Than being greater than preset threshold, then using the region of interest target candidate frame as final region of interest candidate frame.
Step S24 determines pedestrian detection frame according to the pedestrian candidate frame and the final region of interest candidate frame.
In an alternative embodiment, step S24 includes:
The first candidate frame that the region of interest is replaced using the final region of interest candidate frame, so that it is determined that pedestrian
Detection block.
The present embodiment returns pedestrian candidate frame and region of interest candidate frame by different anchor frames, can be improved region of interest
The matching degree of candidate frame improves positional accuracy.
Embodiment three
Fig. 3 a is a kind of flow chart for object detection method that the embodiment of the present disclosure three provides, and the present embodiment is specific implementation
Example, for the disclosure to be described in detail.As shown in Figure 3a, comprising the following steps:
Step S31 returns the first candidate frame of pedestrian candidate frame and the region of interest of the pedestrian according to the first anchor frame.
Step S32 returns the second candidate frame of the region of interest of the pedestrian according to the second anchor frame.
Step S33 calculates the friendship of the second candidate frame of the region of interest and the first candidate frame of the region of interest simultaneously
Than.
Step S34, if described hand over and than replacing institute using the second candidate frame of the region of interest greater than preset threshold
The first candidate frame of region of interest is stated, so that it is determined that pedestrian detection frame.
The present embodiment is illustrated below based on joint pedestrian detecting system, each is set in advance for people
First anchor frame of meter, joint pedestrian detecting system return the region of interest of pedestrian and pedestrian to the first anchor frame simultaneously, finally obtain
The first candidate frame of the region of interest of pedestrian and pedestrian is obtained, as shown in Figure 3b.At the same time, it in addition increases in the present embodiment
The region of interest detection branches of pedestrian, single class object detection system of the branch based on basis.Specifically, first to the phase of pedestrian
It closes position and is pre-designed matched second anchor frame, then return the second candidate frame of the region of interest of pedestrian to the second anchor frame, lead to
The region of interest candidate frame that this method obtains the pedestrian of accurate positioning is crossed, as shown in Figure 3c.Finally, being produced to above-mentioned two branch
Raw candidate frame uses replacement policy, as shown in Figure 3d, candidate according to pedestrian candidate frame and corresponding replaced region of interest
Frame determines pedestrian detection frame.
Example IV
Fig. 4 is a kind of object detecting device block diagram that the embodiment of the present disclosure four provides.The device can integrate in mobile whole
Hold (for example, smart phone, tablet computer etc.), in notebook or fixed terminal (desktop computer), which can be with
Using hardware or software realization.Referring to Fig. 4, which includes pedestrian's frame determining module 41,42 and of region of interest frame determining module
Pedestrian detection frame determining module 43；Wherein,
Pedestrian's frame determining module 41 is used to return pedestrian candidate frame according to the first anchor frame and returns the dependent part of the pedestrian
First candidate frame of position；
Region of interest frame determining module 42 is used to return the second candidate of the region of interest of the pedestrian according to the second anchor frame
Frame；
Pedestrian detection frame determining module 43 be used for according to the pedestrian candidate frame, the region of interest the first candidate frame and
Second candidate frame of the region of interest determines pedestrian detection frame.
Further, the pedestrian detection frame determining module 43 includes: region of interest frame determination unit 431 and pedestrian detection
Frame determination unit 432；Wherein,
Region of interest frame determination unit 431 is used for according to the first candidate frame of the region of interest and the region of interest
Second candidate frame determines final region of interest candidate frame；
Pedestrian detection frame determination unit 432 is used for according to the pedestrian candidate frame and the final region of interest candidate frame
Determine pedestrian detection frame.
Further, the region of interest frame determination unit 431 is specifically used for: calculate the region of interest second is candidate
Friendship and ratio of the frame with the first candidate frame of the region of interest；According to the friendship and the region of interest candidate frame more final than determining.
Further, the region of interest frame determination unit 431 is specifically used for: when the second candidate frame of the region of interest
When being one, if described hand over and compare greater than preset threshold, using the second candidate frame of the region of interest as final correlation
Position candidate frame；Or, choosing and handing over and than the of maximum region of interest when the second candidate frame of the region of interest is multiple
Two candidate frames are as region of interest target candidate frame, if described hand over and compare greater than preset threshold, by the region of interest target
Candidate frame is as final region of interest candidate frame.
Further, the pedestrian detection frame determination unit 432 is specifically used for: candidate using the second of the region of interest
Frame replaces the first candidate frame of the region of interest, so that it is determined that pedestrian detection frame.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Embodiment five
The embodiment of the present disclosure provides a kind of electronic equipment, comprising:
Processor；
Memory for storage processor executable instruction；Wherein, processor is configured as:
Pedestrian candidate frame is returned according to the first anchor frame and returns the first candidate frame of the region of interest of the pedestrian；
The second candidate frame of the region of interest of the pedestrian is returned according to the second anchor frame；
According to the pedestrian candidate frame, the second candidate frame of the first candidate frame of the region of interest and the region of interest
Determine pedestrian detection frame.
Further, described according to the pedestrian candidate frame, the first candidate frame of the region of interest and the dependent part
Second candidate frame of position determines pedestrian detection frame, comprising:
It is determined according to the first candidate frame of the region of interest and the second candidate frame of the region of interest final related
Position candidate frame；
Pedestrian detection frame is determined according to the pedestrian candidate frame and the final region of interest candidate frame.
Further, described true according to the first candidate frame of the region of interest and the second candidate frame of the region of interest
Fixed final region of interest candidate frame, comprising:
Calculate the friendship of the second candidate frame of the region of interest and the first candidate frame of the region of interest and ratio；
According to the friendship and the region of interest candidate frame more final than determining.
It is further, described according to the friendship and the region of interest candidate frame more final than determining, comprising:
It, will be described if the friendship and than being greater than preset threshold when the second candidate frame of the region of interest is one
Second candidate frame of region of interest is as final region of interest candidate frame；Or,
When the second candidate frame of the region of interest is multiple, it is candidate to choose second handed over and than maximum region of interest
Frame is as region of interest target candidate frame, if described hand over and compare greater than preset threshold, by the region of interest target candidate frame
As final region of interest candidate frame.
Further, described that pedestrian detection is determined according to the pedestrian candidate frame and the final region of interest candidate frame
Frame, comprising:
The first candidate frame that the region of interest is replaced using the final region of interest candidate frame, so that it is determined that pedestrian
Detection block.
Wherein, Fig. 5 is the block diagram for a kind of electronic equipment that the embodiment of the present disclosure provides.For example, the electronic equipment can be
Mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, Medical Devices, body-building are set
It is standby, personal digital assistant etc..
Referring to Fig. 5, which may include following one or more components: processing component 502, memory 504, electricity
Power component 506, multimedia component 508, audio component 510, the interface 512 of input/output (I/O), sensor module 514, with
And communication component 516.
The integrated operation of the usual controlling electronic devices of processing component 502, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 502 may include that one or more processors 520 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 502 may include one or more modules, just
Interaction between processing component 502 and other assemblies.For example, processing component 502 may include multi-media module, it is more to facilitate
Interaction between media component 508 and processing component 502.
Memory 504 is configured as storing various types of data to support the operation in electronic equipment.These data
Example includes the instruction of any application or method for operating on an electronic device, contact data, telephone book data,
Message, picture, video etc..Memory 504 can by any kind of volatibility or non-volatile memory device or they
Combination is realized, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), it is erasable can
Program read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memory
Reservoir, disk or CD.
Power supply module 506 provides electric power for the various assemblies of electronic equipment.Power supply module 506 may include power management system
System, one or more power supplys and other with for electronic equipment generate, manage, and distribute the associated component of electric power.
Multimedia component 508 includes the screen of one output interface of offer between the electronic equipment and user.?
In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel,
Screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes that one or more touch passes
Sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding is dynamic
The boundary of work, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more
Media component 508 includes a front camera and/or rear camera.When electronic equipment is in operation mode, as shot mould
When formula or video mode, front camera and/or rear camera can receive external multi-medium data.Each preposition camera shooting
Head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 510 is configured as output and/or input audio signal.For example, audio component 510 includes a Mike
Wind (MIC), when electronic equipment is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to reception external audio signal.The received audio signal can be further stored in memory 504 or via communication set
Part 516 is sent.In some embodiments, audio component 510 further includes a loudspeaker, is used for output audio signal.
I/O interface 512 provides interface between processing component 502 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 514 includes one or more sensors, and the state for providing various aspects for electronic equipment is commented
Estimate.For example, sensor module 514 can detecte the state that opens/closes of electronic equipment, the relative positioning of component, such as institute
The display and keypad that component is electronic equipment are stated, sensor module 514 can also detect electronic equipment or electronic equipment one
The position change of a component, the existence or non-existence that user contacts with electronic equipment, electronic equipment orientation or acceleration/deceleration and electricity
The temperature change of sub- equipment.Sensor module 514 may include proximity sensor, be configured to connect in not any physics
It is detected the presence of nearby objects when touching.Sensor module 514 can also include optical sensor, such as CMOS or ccd image sensor,
For being used in imaging applications.In some embodiments, which can also include acceleration transducer, top
Spiral shell instrument sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 516 is configured to facilitate the communication of wired or wireless way between electronic equipment and other equipment.Electricity
Sub- equipment can access the wireless network based on communication standard, such as WiFi, carrier network (such as 2G, 3G, 4G or 3G) or they
Combination.In one exemplary embodiment, communication component 516 is received via broadcast channel from external broadcasting management system
Broadcast singal or broadcast related information.In one exemplary embodiment, the communication component 516 further includes near-field communication
(NFC) module, to promote short range communication.For example, radio frequency identification (RFID) technology, Infrared Data Association can be based in NFC module
(IrDA) technology, ultra wide band (UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, electronic equipment can be by one or more application specific integrated circuit (ASIC), number
Signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 504 of instruction, above-metioned instruction can be executed by the processor 520 of electronic equipment to complete the above method.For example,
The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk
With optical data storage devices etc..
In the exemplary embodiment, a kind of application program is additionally provided, the memory 504 for example including instruction, above-mentioned finger
Enabling can be executed by the processor 520 of electronic equipment to complete the above method.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (8)
1. a kind of object detection method characterized by comprising
Pedestrian candidate frame is returned according to the first anchor frame and returns the first candidate frame of the region of interest of the pedestrian；
The second candidate frame of the region of interest of the pedestrian is returned according to the second anchor frame；
It is determined according to the second candidate frame of the pedestrian candidate frame, the first candidate frame of the region of interest and the region of interest
Pedestrian detection frame.
2. object detection method according to claim 1, which is characterized in that it is described according to the pedestrian candidate frame, it is described
First candidate frame of region of interest and the second candidate frame of the region of interest determine pedestrian detection frame, comprising:
Final region of interest is determined according to the second candidate frame of the first candidate frame of the region of interest and the region of interest
Candidate frame；
Pedestrian detection frame is determined according to the pedestrian candidate frame and the final region of interest candidate frame.
3. object detection method according to claim 2, which is characterized in that described to be waited according to the first of the region of interest
Frame and the second candidate frame of the region of interest is selected to determine final region of interest candidate frame, comprising:
Calculate the friendship of the second candidate frame of the region of interest and the first candidate frame of the region of interest and ratio；
According to the friendship and the region of interest candidate frame more final than determining.
4. object detection method according to claim 3, which is characterized in that described according to the friendship and more final than determination
Region of interest candidate frame, comprising:
When the second candidate frame of the region of interest is one, if described hand over and compare greater than preset threshold, by the correlation
Second candidate frame at position is as final region of interest candidate frame；Or,
When the second candidate frame of the region of interest is multiple, chooses and hand over and make than the second candidate frame of maximum region of interest
For region of interest target candidate frame, if the friendship and than being greater than preset threshold, using the region of interest target candidate frame as
Final region of interest candidate frame.
5. according to the described in any item object detection methods of claim 2-4, which is characterized in that described according to the pedestrian candidate
Frame and the final region of interest candidate frame determine pedestrian detection frame, comprising:
The first candidate frame that the region of interest is replaced using the final region of interest candidate frame, so that it is determined that pedestrian detection
Frame.
6. a kind of object detecting device characterized by comprising
Pedestrian's frame determining module, for pedestrian candidate frame is returned according to the first anchor frame and return the pedestrian region of interest the
One candidate frame；
Region of interest frame determining module, the second candidate frame of the region of interest for returning the pedestrian according to the second anchor frame；
Pedestrian detection frame determining module, for according to the first candidate frame of the pedestrian candidate frame, the region of interest and described
Second candidate frame of region of interest determines pedestrian detection frame.
7. a kind of electronic equipment characterized by comprising
Processor；
Memory for storage processor executable instruction；Wherein, the processor is configured to: perform claim require 1-5
Described in any item object detection methods.
8. a kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processor of electronic equipment
When execution, so that electronic equipment is able to carry out the described in any item object detection methods of claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910176719.3A CN110059547B (en) | 2019-03-08 | 2019-03-08 | Target detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910176719.3A CN110059547B (en) | 2019-03-08 | 2019-03-08 | Target detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110059547A true CN110059547A (en) | 2019-07-26 |
| CN110059547B CN110059547B (en) | 2021-06-25 |
Family
ID=67316107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910176719.3A Active CN110059547B (en) | 2019-03-08 | 2019-03-08 | Target detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059547B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110532985A (en) * | 2019-09-02 | 2019-12-03 | 北京迈格威科技有限公司 | Object detection method, apparatus and system |
| CN111178126A (en) * | 2019-11-20 | 2020-05-19 | 北京迈格威科技有限公司 | Target detection method, target detection device, computer equipment and storage medium |
| CN111275002A (en) * | 2020-02-18 | 2020-06-12 | 上海商汤临港智能科技有限公司 | Image processing method and device and electronic equipment |
| WO2021169964A1 (en) * | 2020-02-24 | 2021-09-02 | 华为技术有限公司 | Target detection method and related device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169421A (en) * | 2017-04-20 | 2017-09-15 | 华南理工大学 | A kind of car steering scene objects detection method based on depth convolutional neural networks |
| CN107403141A (en) * | 2017-07-05 | 2017-11-28 | 中国科学院自动化研究所 | Method for detecting human face and device, computer-readable recording medium, equipment |
| WO2018029670A1 (en) * | 2016-08-10 | 2018-02-15 | Zeekit Online Shopping Ltd. | System, device, and method of virtual dressing utilizing image processing, machine learning, and computer vision |
| CN108629354A (en) * | 2017-03-17 | 2018-10-09 | 杭州海康威视数字技术股份有限公司 | Object detection method and device |
-
2019
- 2019-03-08 CN CN201910176719.3A patent/CN110059547B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018029670A1 (en) * | 2016-08-10 | 2018-02-15 | Zeekit Online Shopping Ltd. | System, device, and method of virtual dressing utilizing image processing, machine learning, and computer vision |
| CN108629354A (en) * | 2017-03-17 | 2018-10-09 | 杭州海康威视数字技术股份有限公司 | Object detection method and device |
| CN107169421A (en) * | 2017-04-20 | 2017-09-15 | 华南理工大学 | A kind of car steering scene objects detection method based on depth convolutional neural networks |
| CN107403141A (en) * | 2017-07-05 | 2017-11-28 | 中国科学院自动化研究所 | Method for detecting human face and device, computer-readable recording medium, equipment |
Non-Patent Citations (2)
| Title |
|---|
| MULIN CHEN等: "Anchor-based group detection in crowd scenes", 《IEEE》 * |
| 李耀斌: "面向真实场景的行人检测技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110532985A (en) * | 2019-09-02 | 2019-12-03 | 北京迈格威科技有限公司 | Object detection method, apparatus and system |
| CN110532985B (en) * | 2019-09-02 | 2022-07-22 | 北京迈格威科技有限公司 | Target detection method, device and system |
| CN111178126A (en) * | 2019-11-20 | 2020-05-19 | 北京迈格威科技有限公司 | Target detection method, target detection device, computer equipment and storage medium |
| CN111275002A (en) * | 2020-02-18 | 2020-06-12 | 上海商汤临港智能科技有限公司 | Image processing method and device and electronic equipment |
| WO2021169964A1 (en) * | 2020-02-24 | 2021-09-02 | 华为技术有限公司 | Target detection method and related device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110059547B (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106454336B (en) | The method and device and terminal that detection terminal camera is blocked | |
| CN110059547A (en) | Object detection method and device | |
| CN106547663B (en) | Key management method and device | |
| CN105487863A (en) | Interface setting method and device based on scene | |
| CN106484199B (en) | Thresholding setting method and device | |
| KR20180043147A (en) | Method and device for generating instruction | |
| CN104156947A (en) | Image segmentation method, mechanism and device | |
| CN104598111A (en) | Display mode switching method and display mode switching device | |
| CN105224171B (en) | Icon display method, device and terminal | |
| CN103995666A (en) | Method and device for setting work mode | |
| CN104636453A (en) | Illegal user data identification method and device | |
| CN104243829A (en) | Self-shooting method and self-shooting device | |
| CN107092359A (en) | Virtual reality visual angle method for relocating, device and terminal | |
| CN113138701A (en) | Icon position interchange method and device | |
| CN105100193A (en) | Cloud business card recommendation method and device | |
| CN106469265A (en) | Electronic equipment awakening method, device and electronic equipment | |
| CN105242837A (en) | Application page acquisition method and terminal | |
| CN105188027A (en) | Nearby user searching method and device | |
| CN110059548A (en) | Object detection method and device | |
| CN104636064A (en) | Gesture generating method and device | |
| CN106775240B (en) | Triggering method, device and the terminal of application program | |
| CN105487774A (en) | Image grouping method and device | |
| CN105677215A (en) | Application control method and apparatus | |
| CN106126050B (en) | Menu display method and device | |
| CN104539497A (en) | Network connecting 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |