CN107622273A - A kind of target detection and the method and apparatus of identification - Google Patents
A kind of target detection and the method and apparatus of identification Download PDFInfo
- Publication number
- CN107622273A CN107622273A CN201610554579.5A CN201610554579A CN107622273A CN 107622273 A CN107622273 A CN 107622273A CN 201610554579 A CN201610554579 A CN 201610554579A CN 107622273 A CN107622273 A CN 107622273A
- Authority
- CN
- China
- Prior art keywords
- target
- identification
- identified
- classification
- target detection
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The present invention is applied to unmanned air vehicle technique field, there is provided a kind of target detection and the method and apparatus of identification, it is intended to solves the problems, such as the target detection for being not based on unmanned aerial vehicle platform in unmanned plane field in the prior art and identification scheme.Methods described is applied to unmanned aerial vehicle platform, including：Receive the picture signal that the image capture device carried by unmanned plane is shot；Described image signal is detected in real time, judges whether there is target to be identified in described image signal according to default examination criteria；When detecting the target to be identified in described image signal, classification discrimination is carried out to the target to be identified according to the criteria for classification of setting and exports identification result.Technical scheme, by being detected in real time according to default examination criteria to the picture signal of shooting in unmanned aerial vehicle platform, and the target to be identified to detecting carries out classification discrimination according to the criteria for classification of setting, target detection and classification discriminating function based on unmanned aerial vehicle platform are realized.
Description
Technical field
The present invention relates to unmanned air vehicle technique field, more particularly to a kind of target detection and the method and apparatus of identification.
Background technology
Target detection and identification are typically all to take certain feature to describe algorithm, extract the special characteristic of target, and profit
Trained to obtain the grader for this kind of target with certain classifier training framework, can be examined using the grader from video flowing
Survey and identify this kind of target, for example, using color as feature, training the grader come can be used to further judge mesh
Colour type belonging to mark.
Current target detection and identification scheme is all based on computer, mobile phone and other mobile platforms and realized, such as with
Face datection scheme when mobile phone photograph, the real-time scene captured using the cascade classifier of training gained to camera are carried out
Face datection, and according to face location automatic focus adjustable.
In unmanned air vehicle technique field, there is presently no the target detection based on unmanned aerial vehicle platform and identification scheme.
The content of the invention
It is an object of the invention to provide a kind of target detection and the method and apparatus of identification, it is intended to solves in the prior art
The problem of target detection and identification scheme of unmanned aerial vehicle platform are not based in unmanned plane field.
The first aspect of the present invention, there is provided a kind of target detection and the method for identification, methods described are put down applied to unmanned plane
Platform, methods described include：
Receive the picture signal that the image capture device carried by unmanned plane is shot；
Described image signal is detected in real time, judges whether have in described image signal according to default examination criteria
Target to be identified；
When detecting the target to be identified in described image signal, wait to distinguish to described according to the criteria for classification of setting
Know target to carry out classification discrimination and export identification result.
The second aspect of the present invention, there is provided a kind of target detection and the device of identification, described device are put down applied to unmanned plane
Platform, described device include：
Image receiver module, the picture signal shot for receiving the image capture device carried by unmanned plane；
Module of target detection, for being detected in real time to described image signal, institute is judged according to default examination criteria
Whether state has target to be identified in picture signal；
Classification identification module, for when detecting the target to be identified in described image signal, according to setting
Criteria for classification carries out classification discrimination to the target to be identified and exports identification result.
The existing compared with prior art beneficial effect of the present invention is：Pass through the picture signal in unmanned aerial vehicle platform to shooting
Detected in real time according to default examination criteria, and the target to be identified to detecting is divided according to the criteria for classification of setting
Class distinguishes, realizes target detection and classification discriminating function based on unmanned aerial vehicle platform.
Brief description of the drawings
Fig. 1 is the flow chart of a kind of target detection that the embodiment of the present invention one provides and the method for identification；
Fig. 2 is the signal of unmanned plane structure in a kind of target detection that the embodiment of the present invention one provides and the method for identification
Figure；
Fig. 3 is that a kind of target detection that the embodiment of the present invention one provides is shown with first of the application example in the method for identification
It is intended to；
Fig. 4 is that a kind of target detection that the embodiment of the present invention one provides is shown with second of the application example in the method for identification
It is intended to；
Fig. 5 is that a kind of target detection that the embodiment of the present invention one provides is shown with the 3rd of the application example in the method for identification
It is intended to；
Fig. 6 is that a kind of target detection that the embodiment of the present invention one provides is shown with the 4th of the application example in the method for identification
It is intended to；
Fig. 7 is the flow chart of a kind of target detection that the embodiment of the present invention two provides and the method for identification；
Fig. 8 is the structural representation of the device of a kind of target detection that the embodiment of the present invention three provides and identification；
Fig. 9 is the structural representation of the device of a kind of target detection that the embodiment of the present invention four provides and identification.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
It is described in detail below in conjunction with realization of the specific accompanying drawing to the present invention.
Embodiment one：
Fig. 1 be the embodiment of the present invention one provide a kind of target detection and identification method flow chart, this method application
In unmanned aerial vehicle platform, i.e. this method can be effected or carried out on unmanned aerial vehicle platform, specifically include step S101 to S103, be described in detail
It is as follows：
S101, receive the picture signal that the image capture device carried by unmanned plane is shot.
In the unmanned plane structure of Fig. 2 examples, wherein, image capture device 201 includes head and video camera, passes through shooting
The camera of machine is shot, and gathers the picture signal of target, and the picture signal collected is sent into unmanned plane body 203
In image processing equipment 202.
It should be noted that when gathering the picture signal of target, can be with except can be shot by camera
Picture signal is obtained using the mode such as infrared imaging or depth map (Depth Map), wherein depth map is used to indicate that figure
For each pixel relative to the distance of video camera, i.e., each pixel value in depth map represents certain point and shooting in image as in
The distance between machine.
Specifically, the image processing equipment 202 of unmanned plane receives the picture signal shot by image capture device 201.
S102, picture signal is detected in real time, judge whether need in picture signal according to default examination criteria
Recognize target.
Specifically, each frame image signal received is detected in real time, judges whether there is satisfaction in picture signal
The target to be identified of examination criteria, examination criteria can be preset according to identification needs.For example, default examination criteria
The sportsman on football pitch is can be set as, according to the examination criteria, picture signal is detected, whether search has in image
Sportsman to be identified.
It is possible to further using AdaBoosting algorithms, SVMs (Support Vector Machine,
SVM) algorithm and convolutional neural networks (Convolutional Neural Network, CNN) algorithm etc. are carried out to picture signal
Detection in real time.
S103, when detecting target to be identified in picture signal, according to the criteria for classification of setting to target to be identified
Carry out classification discrimination and export identification result.
Specifically, it is right when detecting target to be identified in picture signal according to step S102 real-time testing result
All targets to be identified detected are marked, and according to the criteria for classification of setting, these are marked to be identified
Target carries out classification discrimination, and the identification result of output category identification.
Further, criteria for classification can include one or more the combination in texture, shape and color.
It is possible to further use backpropagation (Back Propagation, BP) neural network algorithm, naive Bayesian
(Naive Bayesian Model, NBM) algorithm, K arest neighbors (k-NearestNeighbor, KNN) algorithm etc. are to mesh to be identified
Mark carries out classification discrimination.
For example, when default examination criteria is the sportsman on football pitch, fortune to be identified is obtained by step S102
Mobilize, criteria for classification is arranged to color, i.e., classified according to the color of clothes, it is assumed that the two couples fortune to be played on court
Red and blueness clothes is worn in mobilization respectively, and after identification is classified in completion, identification result is the sportsman that will wear red clothes
One kind is classified as, the sportsman for wearing blue clothes is classified as another kind of.
It should be noted that except above-mentioned steps directly can be completed by the image processing equipment 202 on unmanned plane
S102 and step S103, the picture signal captured by unmanned plane can also be transmitted to mobile terminal or computer end and be handled,
Complete above-mentioned steps S102 and step S103 detection and discriminating function.
For the ease of understanding the embodiment of the present invention, illustrated below by the application example of a special scenes.
As shown in figure 3, there are unmanned plane A scenes below lasting shooting in the range of a sports ground B；Fig. 4 shows
The image that unmanned plane A image capture device photographs is shown；When default examination criteria is people, Fig. 5 is shown by right
The picture signal that Fig. 4 is shown carries out four target R1, R2, R3 and the R4 to be identified obtained after detecting in real time；When criteria for classification is set
When being set to the color of clothes, it is assumed that wherein R1 and R3 wears white clothes, and R2 and R4 wear black dress, then Fig. 6 is shown by right
The result of the classification identification of this four targets to be identified of R1, R2, R3 and R4, i.e. R1 and R3 are classified as white one kind, and R2 and R4 are classified as
Black is a kind of.
It is real-time by being carried out in unmanned aerial vehicle platform to the picture signal of shooting according to default examination criteria in the present embodiment
Detection, and the target to be identified to detecting carries out classification discrimination according to the criteria for classification of setting, realizes and is put down based on unmanned plane
The target detection and classification discriminating function of platform.
Embodiment two：
Fig. 7 be the embodiment of the present invention two provide a kind of target detection and identification method flow chart, this method application
In unmanned aerial vehicle platform, i.e. this method can be effected or carried out on unmanned aerial vehicle platform, specifically include step S201 to S206, be described in detail
It is as follows：
S201, receive the picture signal that the image capture device carried by unmanned plane is shot.
In the unmanned plane structure of Fig. 2 examples, wherein, image capture device 201 includes head and video camera, passes through shooting
The camera of machine is shot, and gathers the picture signal of target, and the picture signal collected is sent into image processing equipment
202。
It should be noted that when gathering the picture signal of target, can be with except can be shot by camera
Picture signal is obtained using the mode such as infrared imaging or depth map (Depth Map), wherein depth map is used to indicate that figure
For each pixel relative to the distance of video camera, i.e., each pixel value in depth map represents certain point and shooting in image as in
The distance between machine.
Specifically, the image processing equipment 202 of unmanned plane receives the picture signal shot by image capture device 201.
S202, picture signal is detected in real time, judge whether need in picture signal according to default examination criteria
Recognize target.
Specifically, each frame image signal received is detected in real time, judges whether there is satisfaction in picture signal
The target to be identified of examination criteria, examination criteria can be preset according to identification needs.For example, default examination criteria
The sportsman on football pitch is can be set as, according to the examination criteria, picture signal is detected, whether search has in image
Sportsman to be identified.When detecting target to be identified in picture signal, step S203 is continued executing with；When in picture signal
In when being not detected by target to be identified, perform step S207.
It is possible to further using AdaBoosting algorithms, SVMs (Support Vector Machine,
SVM) algorithm and convolutional neural networks (Convolutional Neural Network, CNN) algorithm etc. are carried out to picture signal
Detection in real time.
S203, classification discrimination carried out to target to be identified according to the criteria for classification of setting.Specifically, it is all to what is detected
Target to be identified is marked, and according to the criteria for classification of setting, the target to be identified marked to these is classified
Distinguish.
Further, criteria for classification can include one or more the combination in texture, shape and color.
It is possible to further use backpropagation (Back Propagation, BP) neural network algorithm, naive Bayesian
(Naive Bayesian Model, NBM) algorithm, K arest neighbors (k-NearestNeighbor, KNN) algorithm etc. are to mesh to be identified
Mark carries out classification discrimination.S204, judge that classification recognizes whether success.
Specifically, when classification recognizes successfully, step S205 is continued executing with, otherwise performs step S208.
S205, the identification result of output category identification.
Specifically, the classification identification output identification result completed according to step S203.
For example, when default examination criteria is the sportsman on football pitch, fortune to be identified is obtained by step S202
Mobilize, criteria for classification is arranged to color, i.e., classified according to the color of clothes, it is assumed that the two couples fortune to be played on court
Mobilize dress respectively red and the clothes of blueness, after classification recognize successfully, identification result is will wear the sportsman of red clothes
One kind is classified as, the sportsman for wearing blue clothes is classified as another kind of.
It should be noted that except above-mentioned steps directly can be completed by the image processing equipment 202 on unmanned plane
S202 to step S205, the picture signal captured by unmanned plane can also be transmitted to mobile terminal or computer end and be handled,
Complete detections and identification process of the above-mentioned steps S202 to step S205.
S206, according to identification result to target to be detected carry out UAV Intelligent shooting.
Specifically, the identification result obtained according to step S205, can be by unmanned plane to sorted target to be detected
UAV Intelligent shooting is carried out, and performs step S209.
Further, UAV Intelligent shooting can include UAV Intelligent tracking and UAV Intelligent monitoring.
For example, relay platform and intelligent judgment that can be using unmanned plane as football match, foot be preset as by examination criteria
Sportsman on court, all sportsmen to be identified in image are found by step S202 real-time detection, and to each
Individual sportsman to be identified is marked, while criteria for classification is arranged into color, is completed by step S203 to step S205
Classify after recognizing and exporting identification result, what all sportsmen and sportsman that unmanned plane can be gone out with automatic detection on court were belonged to
Troop, intelligent-tracking can be carried out using unmanned plane on this basis, such as in high-altitude with clapping some specific sportsman, or
Intelligent monitoring is carried out, such as various unnecessary roughnesses are identified when the overall situation is shot, such as offside and dribbling outlet etc..
S207, output detection failure.
Specifically, according to step S202 real-time testing result, when being not detected by target to be identified in picture signal,
Output detection failure, and step S209 is jumped to, exit.
S208, output identification failure.
Specifically, when the classification that step S203 is carried out recognizes failure, output identification failure.
S209, exit.
It is real-time by being carried out in unmanned aerial vehicle platform to the picture signal of shooting according to default examination criteria in the present embodiment
Detection, and the target to be identified to detecting carries out classification discrimination according to the criteria for classification of setting, realizes and is put down based on unmanned plane
The target detection and classification discriminating function of platform, and on this basis, unmanned plane is carried out to target to be detected according to identification result
Intelligence shooting, unmanned plane is utilized to complete the intelligent works such as various intelligent-trackings and intelligent monitoring so as to realize.
Embodiment three：
Fig. 8 is the structural representation of the device of a kind of target detection that the embodiment of the present invention three provides and identification, in order to just
In explanation, the part related to the embodiment of the present invention illustrate only.A kind of target detections of Fig. 8 examples and the device of identification can be with
It is the executive agent of a kind of target detection and the method for identification that previous embodiment one provides, it can be the image on unmanned plane
Processing equipment.A kind of target detection of Fig. 8 examples and the device of identification are applied to unmanned aerial vehicle platform, and the device mainly includes：Figure
As receiving module 31, module of target detection 32 and classification identification module 33.Each functional module describes in detail as follows：
Image receiver module 31, the picture signal shot for receiving the image capture device carried by unmanned plane；
Module of target detection 32, for being detected in real time to picture signal, image is judged according to default examination criteria
Whether to be identified target is had in signal；
Classification identification module 33, for when detecting target to be identified in picture signal, according to the contingency table of setting
It is accurate that classification discrimination is carried out to target to be identified and exports identification result.
Each module realizes the process of respective function in a kind of target detection and the device of identification that the present embodiment provides, specifically
The description of foregoing embodiment illustrated in fig. 1 is referred to, here is omitted.
It was found from a kind of target detection of above-mentioned Fig. 8 examples and the device of identification, in the present embodiment, by being put down in unmanned plane
Platform is detected in real time to the picture signal of shooting according to default examination criteria, and the target to be identified to detecting is according to setting
The criteria for classification put carries out classification discrimination, realizes target detection and classification discriminating function based on unmanned aerial vehicle platform.
Example IV：
Fig. 9 is the structural representation of the device of a kind of target detection that the embodiment of the present invention four provides and identification, in order to just
In explanation, the part related to the embodiment of the present invention illustrate only.A kind of target detections of Fig. 9 examples and the device of identification can be with
It is the executive agent of a kind of target detection and the method for identification that previous embodiment two provides, it can be the image on unmanned plane
Processing equipment.A kind of target detection of Fig. 9 examples and the device of identification are applied to unmanned aerial vehicle platform, and the device mainly includes：Figure
As receiving module 41, module of target detection 42 and classification identification module 43.Each functional module describes in detail as follows：
Image receiver module 41, the picture signal shot for receiving the image capture device carried by unmanned plane；
Module of target detection 42, for being detected in real time to picture signal, image is judged according to default examination criteria
Whether to be identified target is had in signal；
Classification identification module 43, for when detecting target to be identified in picture signal, according to the contingency table of setting
It is accurate that classification discrimination is carried out to target to be identified and exports identification result.
Further, criteria for classification includes the combination of one or more of texture, shape and color.
Further, the device also includes：
Detection failure module 44, for when being not detected by target to be identified in picture signal, output detection to fail；
Intelligent-tracking module 45, for carrying out UAV Intelligent shooting to target to be detected according to identification result.
Further, the device also includes：
Identification failure module 46, for distinguishing failure when the criteria for classification according to setting carries out classification to target to be identified
When, output identification failure.
Further, UAV Intelligent shooting includes UAV Intelligent tracking and UAV Intelligent monitoring.
Each module realizes the process of respective function in a kind of target detection and the device of identification that the present embodiment provides, specifically
The description of foregoing embodiment illustrated in fig. 7 is referred to, here is omitted.
It was found from a kind of target detection of above-mentioned Fig. 9 examples and the device of identification, in the present embodiment, by being put down in unmanned plane
Platform is detected in real time to the picture signal of shooting according to default examination criteria, and the target to be identified to detecting is according to setting
The criteria for classification put carries out classification discrimination, realizes target detection based on unmanned aerial vehicle platform and classification discriminating function, and
On the basis of this, UAV Intelligent shooting is carried out to target to be detected according to identification result, utilizes unmanned plane complete so as to realize
Into the intelligent work such as various intelligent-trackings and intelligent monitoring.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment
What is stressed is all the difference with other embodiment, between each embodiment same or similar part mutually referring to
.For device class embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, it is related
Part illustrates referring to the part of embodiment of the method.
It is worth noting that, in said apparatus embodiment, included modules are simply drawn according to function logic
Point, but above-mentioned division is not limited to, as long as corresponding function can be realized；In addition, each functional module is specific
Title is also only to facilitate mutually distinguish, the protection domain being not intended to limit the invention.
Can it will appreciated by the skilled person that realizing that all or part of step in the various embodiments described above method is
To instruct the hardware of correlation to complete by program, corresponding program can be stored in a computer read/write memory medium
In, described storage medium, such as ROM/RAM, disk or CD.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (10)
1. a kind of target detection and the method for identification, it is characterised in that methods described is applied to unmanned aerial vehicle platform, methods described bag
Include：
Receive the picture signal that the image capture device carried by unmanned plane is shot；
Described image signal is detected in real time, judges whether need to be distinguished in described image signal according to default examination criteria
Know target；
When detecting the target to be identified in described image signal, according to the criteria for classification of setting to the mesh to be identified
Mark carries out classification discrimination and exports identification result.
2. target detection according to claim 1 and the method for identification, it is characterised in that the criteria for classification includes line
One or more combination in reason, shape and color.
3. target detection according to claim 1 or 2 and the method for identification, it is characterised in that described in the unmanned plane
On described image signal is detected in real time, judge whether to have in described image signal according to default examination criteria to be identified
After target, methods described also includes：
When being not detected by the target to be identified in described image signal, output detection failure.
4. target detection according to claim 1 or 2 and the method for identification, it is characterised in that described when in described image
When the target to be identified is detected in signal, according to the criteria for classification of setting on the unmanned plane to the target to be identified
After carrying out classification discrimination and exporting identification result, methods described also includes：
UAV Intelligent shooting is carried out to the target to be detected according to the identification result.
5. target detection according to claim 4 and the method for identification, it is characterised in that the UAV Intelligent shooting bag
Include UAV Intelligent tracking and UAV Intelligent monitoring.
6. a kind of target detection and the device of identification, it is characterised in that described device is applied to unmanned aerial vehicle platform, described device bag
Include：
Image receiver module, the picture signal shot for receiving the image capture device carried by unmanned plane；
Module of target detection, for being detected in real time to described image signal, the figure is judged according to default examination criteria
As whether there is target to be identified in signal；
Classification identification module, for when detecting the target to be identified in described image signal, according to the classification of setting
Standard carries out classification discrimination to the target to be identified and exports identification result.
7. target detection according to claim 6 and the device of identification, it is characterised in that the criteria for classification includes line
The combination of one or more of reason, shape and color.
8. the device of the target detection and identification according to claim 6 or 7, it is characterised in that described device also includes：
Detection failure module, for when being not detected by the target to be identified in described image signal, output detection to fail.
9. the device of the target detection and identification according to claim 6 or 7, it is characterised in that described device also includes：
Intelligent-tracking module, for carrying out UAV Intelligent shooting to the target to be detected according to the identification result.
10. target detection according to claim 9 and the device of identification, it is characterised in that the UAV Intelligent shooting
Including UAV Intelligent tracking and UAV Intelligent monitoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610554579.5A CN107622273B (en) | 2016-07-13 | 2016-07-13 | Target detection and identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610554579.5A CN107622273B (en) | 2016-07-13 | 2016-07-13 | Target detection and identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107622273A true CN107622273A (en) | 2018-01-23 |
| CN107622273B CN107622273B (en) | 2021-03-19 |
Family
ID=61087457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610554579.5A Active CN107622273B (en) | 2016-07-13 | 2016-07-13 | Target detection and identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107622273B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019206078A1 (en) * | 2018-04-27 | 2019-10-31 | 深圳市大疆创新科技有限公司 | Control device and photographing method |
| US10853658B2 (en) | 2018-10-30 | 2020-12-01 | Sony Corporation | Image-based detection of offside in gameplay |
| WO2021026855A1 (en) * | 2019-08-15 | 2021-02-18 | 深圳市大疆创新科技有限公司 | Machine vision-based image processing method and device |
| CN113476815A (en) * | 2021-05-17 | 2021-10-08 | 张昌昊 | Intelligent sports auxiliary training method and system based on E-ink |
| CN113780181A (en) * | 2021-09-13 | 2021-12-10 | 浙江大学 | Football match offside judgment method and device based on unmanned aerial vehicle and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130188827A1 (en) * | 2012-01-19 | 2013-07-25 | Electronics And Telecommunications Research Institute | Human tracking method and apparatus using color histogram |
| CN104820998A (en) * | 2015-05-27 | 2015-08-05 | 成都通甲优博科技有限责任公司 | Human body detection and tracking method and device based on unmanned aerial vehicle mobile platform |
| CN104881650A (en) * | 2015-05-29 | 2015-09-02 | 成都通甲优博科技有限责任公司 | Vehicle tracking method based on unmanned aerial vehicle (UAV) dynamic platform |
| CN105578034A (en) * | 2015-12-10 | 2016-05-11 | 深圳市道通智能航空技术有限公司 | Control method, control device and system for carrying out tracking shooting for object |
-
2016
- 2016-07-13 CN CN201610554579.5A patent/CN107622273B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130188827A1 (en) * | 2012-01-19 | 2013-07-25 | Electronics And Telecommunications Research Institute | Human tracking method and apparatus using color histogram |
| CN104820998A (en) * | 2015-05-27 | 2015-08-05 | 成都通甲优博科技有限责任公司 | Human body detection and tracking method and device based on unmanned aerial vehicle mobile platform |
| CN104881650A (en) * | 2015-05-29 | 2015-09-02 | 成都通甲优博科技有限责任公司 | Vehicle tracking method based on unmanned aerial vehicle (UAV) dynamic platform |
| CN105578034A (en) * | 2015-12-10 | 2016-05-11 | 深圳市道通智能航空技术有限公司 | Control method, control device and system for carrying out tracking shooting for object |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019206078A1 (en) * | 2018-04-27 | 2019-10-31 | 深圳市大疆创新科技有限公司 | Control device and photographing method |
| CN111328399A (en) * | 2018-04-27 | 2020-06-23 | 深圳市大疆创新科技有限公司 | Control device and photographing method |
| US10853658B2 (en) | 2018-10-30 | 2020-12-01 | Sony Corporation | Image-based detection of offside in gameplay |
| WO2021026855A1 (en) * | 2019-08-15 | 2021-02-18 | 深圳市大疆创新科技有限公司 | Machine vision-based image processing method and device |
| CN113476815A (en) * | 2021-05-17 | 2021-10-08 | 张昌昊 | Intelligent sports auxiliary training method and system based on E-ink |
| CN113780181A (en) * | 2021-09-13 | 2021-12-10 | 浙江大学 | Football match offside judgment method and device based on unmanned aerial vehicle and electronic equipment |
| CN113780181B (en) * | 2021-09-13 | 2023-11-14 | 浙江大学 | Football match offside judging method and device based on unmanned aerial vehicle and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107622273B (en) | 2021-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062349B (en) | Video monitoring method and system based on video structured data and deep learning | |
| CN107622273A (en) | A kind of target detection and the method and apparatus of identification | |
| CN106802113B (en) | Intelligent hit telling system and method based on many shell hole algorithm for pattern recognitions | |
| CN104036236B (en) | A kind of face gender identification method based on multiparameter exponential weighting | |
| CN108805900B (en) | Method and device for determining tracking target | |
| CN101477626B (en) | Method for detecting human head and shoulder in video of complicated scene | |
| Liu et al. | Argus: Efficient activity detection system for extended video analysis | |
| TWI687159B (en) | Fry counting system and fry counting method | |
| KR101697161B1 (en) | Device and method for tracking pedestrian in thermal image using an online random fern learning | |
| CN104573617B (en) | A kind of camera shooting control method | |
| CN114842397B (en) | Real-time old man falling detection method based on anomaly detection | |
| Huang et al. | Players and ball detection in soccer videos based on color segmentation and shape analysis | |
| CN106339657B (en) | Crop straw burning monitoring method based on monitor video, device | |
| CN105872363A (en) | Adjustingmethod and adjusting device of human face focusing definition | |
| CN110443137A (en) | The recognition methods of various dimensions identity information, device, computer equipment and storage medium | |
| Park et al. | Detection of construction workers in video frames for automatic initialization of vision trackers | |
| CN112070043A (en) | Safety helmet wearing convolutional network based on feature fusion, training and detecting method | |
| CN106445146B (en) | Gesture interaction method and device for Helmet Mounted Display | |
| CN107862333A (en) | A kind of method of the judgment object combustion zone under complex environment | |
| CN114140745A (en) | Method, system, device and medium for detecting personnel attributes of construction site | |
| CN110348366B (en) | Automatic optimal face searching method and device | |
| Hayashi et al. | Head and upper body pose estimation in team sport videos | |
| CN109858308B (en) | Video retrieval device, video retrieval method, and storage medium | |
| CN111160299A (en) | Living body identification method and device | |
| Gilmore et al. | An IR-based pedestrian detection system implemented with matlab-equipped laptop and low-cost microcontroller |
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 |