CN111818299A - Target identification method and device - Google Patents
Target identification method and device Download PDFInfo
- Publication number
- CN111818299A CN111818299A CN202010544400.4A CN202010544400A CN111818299A CN 111818299 A CN111818299 A CN 111818299A CN 202010544400 A CN202010544400 A CN 202010544400A CN 111818299 A CN111818299 A CN 111818299A
- Authority
- CN
- China
- Prior art keywords
- lens
- type
- target position
- class
- photographing
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- 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
Abstract
The invention discloses a target identification method and a device, which adopt a photographing device for identification, wherein the photographing device comprises: the first-class lenses and the second-class lenses are used for determining the first-class lenses identifying the object to be identified from the first-class lenses according to the identification result of the object to be identified of each first-class lens, and defining the first-class lenses as reference lenses; judging whether the reference lens identifies the target position of the object to be identified; if yes, controlling the second type of lens to snapshot the target position according to the identification result of the reference lens; if not, controlling the second type lens to snapshot the target position according to the identification result of each first type lens. Therefore, on the basis of one photographing device, the target position of the object to be recognized can be captured through the cooperation of the multiple lenses; in addition, only one photographing device is adopted, so that the number of photographing devices is reduced, and the cost required by identification is favorably reduced.
Description
Technical Field
The invention relates to the technical field of video monitoring, in particular to a target identification method and a target identification device.
Background
In order to realize face snapshot, a panoramic camera and a plurality of snapshot cameras are generally required to be adopted, so that the plurality of cameras are required to be matched for use, and the required cost is high; in addition, as a plurality of cameras are required to be matched for use and the cameras are independent from each other, a complex process is required during snapshot, so that the snapshot efficiency is reduced, and the problem of inaccurate snapshot result may also occur.
Therefore, how to reduce the cost required by face snapshot, improve the snapshot efficiency and simplify the snapshot process is a technical problem to be solved urgently by technical personnel in the field.
Disclosure of Invention
The embodiment of the invention provides a target identification method, which is used for reducing the cost required by face snapshot, improving the snapshot efficiency and simplifying the snapshot process.
In a first aspect, an embodiment of the present invention provides a target identification method, where a photographing device is used for identification, and the photographing device includes: a plurality of first type lenses and a second type lens; the method comprises the following steps:
determining a first-class shot for identifying the object to be identified from the first-class shots according to the identification result of the object to be identified by each first-class shot, and defining the first-class shot as a reference shot;
judging whether the reference lens identifies the target position of the object to be identified;
if yes, controlling the second type lens to snapshot the target position according to the identification result of the reference lens;
if not, controlling the second type lens to snapshot the target position according to the identification result of each first type lens.
In a possible implementation manner, in the method provided in an embodiment of the present invention, controlling the second type lens to capture the target position according to the recognition result of the reference lens specifically includes:
sending a first control signal to the second type of lens according to the identification result of the reference lens;
wherein the first control signal is to: and controlling the second type lens to adjust the photographing angle according to the recognition result of the reference lens and photographing.
In a possible implementation manner, in the method provided in an embodiment of the present invention, controlling the second type of lens to capture the target position according to the recognition result of each first type of lens specifically includes:
respectively sending a second control signal to the second type lens according to the identification result of each first type lens;
wherein each of the second control signals corresponds to an identification result of each of the first type of lenses, and the second control signals are used for: and controlling the second type of lens to adjust the photographing angle according to the recognition result of the first type of lens and photographing.
In a possible implementation manner, in the foregoing method provided in an embodiment of the present invention, after controlling the second type of lens to capture the target position according to the recognition result of each first type of lens, the method further includes:
receiving N photos sent by the second type of lens; n is the number of the first-class lenses, and the N pictures are obtained according to the identification result of each first-class lens;
according to a preset target recognition algorithm and an influence factor influencing the target position recognition result, respectively evaluating the target positions in the N pictures to determine an evaluation value corresponding to each picture;
and when the maximum value is selected from the determined evaluation values, determining and storing the picture corresponding to the maximum value.
In a possible implementation manner, in the foregoing method provided in an embodiment of the present invention, if the target position is a human face, the influence factor includes at least one of the following:
face state angle, face definition, face pixel size, photographing light intensity and face shielding state.
In a possible implementation manner, in the foregoing method provided in an embodiment of the present invention, after controlling the second type lens to capture the target position according to the recognition result of the reference lens, the method further includes:
and receiving and storing the photos sent by the second type of lens.
In a second aspect, an embodiment of the present invention further provides a target identification apparatus, which performs identification by using a photographing device, where the photographing device includes: a plurality of first type lenses and a second type lens; the device includes:
the first unit is used for determining a first-class shot for identifying the object to be identified from the first-class shots according to the identification result of the object to be identified by each first-class shot and defining the first-class shot as a reference shot;
the second unit is used for judging whether the reference lens identifies the target position of the object to be identified; if yes, controlling the second type lens to snapshot the target position according to the identification result of the reference lens; if not, controlling the second type lens to snapshot the target position according to the identification result of each first type lens.
In a possible implementation manner, in the above apparatus provided in an embodiment of the present invention, the second unit is specifically configured to:
sending a first control signal to the second type of lens according to the identification result of the reference lens;
wherein the first control signal is to: controlling the second type lens to adjust a photographing angle according to the recognition result of the reference lens and photographing;
or respectively sending a second control signal to the second type of lens according to the identification result of each first type of lens;
wherein each of the second control signals corresponds to an identification result of each of the first type of lenses, and the second control signals are used for: and controlling the second type of lens to adjust the photographing angle according to the recognition result of the first type of lens and photographing.
In a possible implementation manner, in the apparatus provided in an embodiment of the present invention, after controlling the second type lenses to capture the target position according to the recognition result of each first type lens, the second unit is further configured to:
receiving N photos sent by the second type of lens; n is the number of the first-class lenses, and the N pictures are obtained according to the identification result of each first-class lens;
according to a preset target recognition algorithm and an influence factor influencing the target position recognition result, respectively evaluating the target positions in the N pictures to determine an evaluation value corresponding to each picture;
and when the maximum value is selected from the determined evaluation values, determining and storing the picture corresponding to the maximum value.
In a third aspect, an embodiment of the present invention further provides a photographing apparatus, including: a plurality of first-type lenses, a second-type lens, and the object recognition apparatus provided in the embodiment of the present invention;
the first type of lens is used for: and identifying the object to be identified, and sending the obtained identification result to the target identification device so that the target identification device controls the second-class lens to capture the target position of the object to be identified according to the identification result.
The invention has the following beneficial effects:
the embodiment of the invention provides a target identification method and a target identification device, which adopt a photographing device for identification, wherein the photographing device comprises: the first-class lenses and the second-class lenses are used for determining the first-class lenses identifying the object to be identified from the first-class lenses according to the identification result of the object to be identified of each first-class lens, and defining the first-class lenses as reference lenses; judging whether the reference lens identifies the target position of the object to be identified; if yes, controlling the second type of lens to snapshot the target position according to the identification result of the reference lens; if not, controlling the second type lens to snapshot the target position according to the identification result of each first type lens. Therefore, on the basis of adopting one photographing device, the target position of the object to be recognized can be captured through the synergistic effect among a plurality of lenses included in the photographing device; moreover, the target position of the object to be recognized can be captured through one photographing device, so that only one network cable and one power line are needed, and the implementation mode is simple and efficient; in addition, only one photographing device is adopted, so that the number of the photographing devices is reduced, the cost required by recognition is favorably reduced, the accuracy and the efficiency of target recognition can be improved, the process of target recognition is simplified, and the recognition method has high practicability.
Drawings
Fig. 1 is a schematic structural diagram of a photographing apparatus provided in an embodiment of the present invention;
fig. 2 is a flowchart of a target identification method provided in an embodiment of the present invention;
fig. 3 is a schematic diagram of a first type of shot for identifying a front face of a person according to an embodiment of the present invention;
fig. 4 is a schematic diagram of another first-type shot for identifying a front face of a person according to an embodiment of the present invention;
FIG. 5 is a flow chart of a method according to a first embodiment of the present invention;
fig. 6 is a schematic structural diagram of a target identification apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of another photographing apparatus provided in the embodiment of the present invention.
Detailed Description
The following describes in detail a specific implementation of a target identification method and apparatus provided in an embodiment of the present invention with reference to the accompanying drawings. It should be noted that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Before describing a target identification method provided by an embodiment of the present invention, the following description is first made on the structure of a photographing apparatus.
For the photographing device adopted by the embodiment of the invention, the target can be identified, and the photographing device comprises: a plurality of first type lenses and a second type lens;
the photographing device can be called a multi-view camera or an integrated camera, a plurality of first-type lenses and a second-type lens are installed in a cavity of the multi-view camera, the setting positions of the first-type lenses and the second-type lenses in the photographing device are not specifically limited, and the first-type lenses and the second-type lenses can be set according to actual needs.
For example, two first-type lenses, i.e., a lens a and a lens B, and a second-type lens are installed in the photographing apparatus, see the structure of the multi-view camera shown in fig. 1.
It should be noted that the number of the first type lenses included in the cavity of the multi-view camera is not limited to two lenses shown in fig. 1, and may also be three, four or more, and the first type lenses may be set according to actual requirements to meet the requirements of different application scenarios, so as to improve the flexibility of design.
An embodiment of the present invention provides a target identification method, as shown in fig. 2, the method may include:
s201, according to the identification result of each first-class lens on the object to be identified, determining the first-class lens identifying the object to be identified from each first-class lens, and defining the first-class lens as a reference lens;
the first type of lens may be a wide-angle lens, a standard lens, a zoom lens, and the like, and is not limited herein.
S202, judging whether the reference lens identifies the target position of the object to be identified; if yes, go to step S203; if not, executing step S204;
s203, controlling a second type lens to snapshot a target position according to the identification result of the reference lens;
as shown in fig. 3 and 4, the object to be recognized is a person, and the target position of the object to be recognized is the front face of the person, so that for recognizing the target position of the object to be recognized by referring to the shot, it can be understood that: the reference shots have identified the front face of the person. In conjunction with the structure of the photographing apparatus shown in fig. 1, the area between the solid lines 1 and 3 may be the field of view of the reference lens (e.g., lens a in fig. 1), the area between the solid lines 2 and 4 may be the field of view of any other first-type lens (e.g., lens B in fig. 1), and the area between the dotted lines is the field of view of the second-type lens.
And S204, controlling the second type of lens to snapshot the target position according to the identification result of each first type of lens.
The second type of lens can enlarge and reduce the monitoring picture by changing the focal length, so that a user can conveniently monitor details in the monitoring picture and monitor the panorama of the monitoring picture. In addition, the second type of lens can be through rotating the angle of shooing to monitor and gather each position of waiting to discern the object in the control picture.
The second type of lens may be, but is not limited to, a lens whose photographing angle can be adjusted and which can implement functions such as zooming.
Therefore, on the basis of adopting one photographing device, the target position of the object to be recognized can be captured through the synergistic effect among a plurality of lenses included in the photographing device; moreover, the target position of the object to be recognized can be captured through one photographing device, so that only one network cable and one power line are needed, and the implementation mode is simple and efficient; in addition, only one photographing device is adopted, so that the number of the photographing devices is reduced, the cost required by recognition is favorably reduced, the accuracy and the efficiency of target recognition can be improved, the process of target recognition is simplified, and the recognition method has high practicability.
In specific implementation, in the embodiment of the present invention, the controlling the second type of lens to capture the target position according to the recognition result of the reference lens specifically includes:
sending a first control signal to a second type of lens according to the identification result of the reference lens;
wherein the first control signal is to: and controlling the second type lens to adjust the photographing angle according to the recognition result of the reference lens and photographing.
Therefore, when the reference lens identifies the target position of the object to be identified, the controller in the photographing device can control the second-class lens according to the identification result of the reference lens so as to adjust the photographing angle of the second-class lens and photograph the target position of the object to be identified, and the controller does not need to control the second-class lens to photograph according to the identification result of other first-class lenses, so that the second-class lens can photograph for one time, the processing amount of the photographing device is reduced, and the processing speed of the photographing device is improved.
In specific implementation, in the embodiment of the present invention, the controlling the second type of lens to capture the target position according to the recognition result of each first type of lens specifically includes:
respectively sending a second control signal to the second type of lens according to the identification result of each first type of lens;
each second control signal corresponds to the recognition result of each first-class lens, and the second control signals are used for: and controlling the second type lens to adjust the photographing angle according to the recognition result of the first type lens and photographing.
Specifically, when the reference lens does not recognize the target position of the object to be recognized, the controller in the photographing apparatus not only needs to control the second type lens according to the recognition result of the reference lens to adjust the angle of the second type lens to photograph the object to be recognized, but also needs to adjust the angle of the second type lens according to the recognition result of the other first type lens to continue to photograph the object to be recognized, that is, the controller needs to control the second type lens to photograph the object to be recognized according to each first type lens, so that the second type lens needs to photograph for multiple times.
Therefore, the controller respectively controls the second type of lenses to photograph the object to be recognized according to the recognition result of each first type of lens, so that the problem that the target position of the photographed object to be recognized is inaccurate due to the fact that the second type of lenses photograph the object to be recognized only once is avoided, and the target position is captured.
In specific implementation, in the embodiment of the present invention, after controlling the second type of lens to capture the target position according to the recognition result of each first type of lens, the method further includes:
receiving N photos sent by the second type of lens; n is the number of the first-class lenses, and N pictures are obtained according to the identification result of each first-class lens;
according to a preset target recognition algorithm and an influence factor influencing the target position recognition result, respectively evaluating the target positions in the N pictures to determine an evaluation value corresponding to each picture;
and when the maximum value is selected from the determined evaluation values, determining and storing the picture corresponding to the maximum value.
The content of "respectively evaluating the target positions in the N photographs according to a preset target recognition algorithm and an influence factor influencing the target position recognition result, and determining an evaluation value corresponding to each photograph" may be understood as:
the controller in the photographing apparatus receives the N photographs transmitted by the second type lens, and evaluates the target positions of the objects to be recognized in the received N photographs and determines an evaluation value corresponding to each photograph according to the above-mentioned influence factor, that is, the controller evaluates the target positions in the N photographs (for example, the evaluation values are expressed by numerical values of 1 to 100), wherein the higher the evaluation value is, the more accurate the recognition result of the target positions of the objects to be recognized in the photographs is; the lower the evaluation value is, the less accurate the recognition result indicating the target position of the object to be recognized in the photograph is, and the larger the deviation of the recognition result is.
Therefore, according to the above scoring result, it is advantageous to select one of the processed N photographs with the largest evaluation value as the final recognition result to complete the recognition process of the target position.
Specifically, for "N is the number of the first-type shots, and N photos are obtained according to the recognition result of each first-type shot", see the following detailed explanation:
for example, the number of the first shots is 3, that is, N is 3, and the 3 first shots are respectively marked as a shot a, a shot B, and a shot C.
When the lens a does not recognize the target position of the object to be recognized, the controller in the photographing apparatus may respectively control the second type of lens according to the recognition results of the lens a, the lens B, and the lens C to sequentially adjust the angles of the second type of lens to photograph the object to be recognized, so that the second type of lens needs to photograph the object to be recognized three times, and the photographs photographed three times may be respectively marked as photograph a, photograph B, and photograph C.
The picture A can be shot by a second type lens under the control of the controller according to the recognition result of the lens A;
the picture B can be shot by a second type lens under the control of the controller according to the recognition result of the lens B;
the photograph C may be taken by the second type lens under the control of the controller according to the recognition result of the lens C.
Therefore, the N pictures are evaluated according to the preset target recognition algorithm to obtain the processed N pictures, the controller can select the picture with the largest evaluation value, and the target position is recognized.
Specifically, in the embodiment of the present invention, if the target position is a human face, the influence factor includes at least one of the following factors:
face state angle, face definition, face pixel size, photographing light intensity and face shielding state.
If the face state angle, the face definition, the face pixel size, the photographing light intensity and the face shielding state are considered as the influence factors during face recognition, each photo can be evaluated according to at least one of the influence factors, and the evaluation value corresponding to each photo is determined.
In this way, one of the N processed photos is selected with the highest score, that is, the target photo is optimized, the best photo is selected, and the other photos are discarded, so that the repetition rate is reduced.
In specific implementation, in the embodiment of the present invention, after controlling the second type of lens to capture the target position according to the recognition result of the reference lens, the method further includes:
and receiving and storing the photos sent by the second type of lens.
Therefore, the photos sent by the second type of lens are stored, and the subsequent output and display of the photos are facilitated.
The following describes a target identification method provided by an embodiment of the present invention with a specific embodiment.
The first embodiment is as follows: taking the number of the first-type shots included in the photographing device as 2, and taking the two first-type shots as the number of the shots a and the shots B as an example, the method is described with reference to the flowchart of the method shown in fig. 5.
S501, respectively identifying the object to be identified by the lens A and the lens B;
s502, according to the recognition results of the lens A and the lens B, the controller determines that the lens A recognizes the object to be recognized;
s503, judging whether the lens A identifies the target position of the object to be identified by the controller; if yes, go to step S504; if not, go to step S506;
s504, the controller sends a first control signal to the second lens according to the identification result of the lens A;
s505, the second-class lens takes a picture of the target position of the target to be recognized according to the received first control signal and stores the picture; step S510 is performed.
S506, the controller respectively sends second control signals to the second type of lens according to the recognition results of the lens A and the lens B;
s507, the second type of lens adjusts the photographing angle to photograph according to the received second control signal in sequence to obtain 2 photos;
s508, respectively evaluating the target positions in the obtained 2 pictures according to a preset target recognition algorithm and influence factors influencing the target position recognition result, and determining an evaluation value corresponding to each picture;
s509, a maximum value is selected from the obtained 2 evaluation values, and a picture corresponding to the maximum value is determined and stored.
And S510, outputting the picture.
Based on the same inventive concept, embodiments of the present invention provide a target identification apparatus, and since the apparatus has a similar working principle to the aforementioned target identification method, specific embodiments of the apparatus may refer to the above embodiment of the determination method, and repeated details are omitted.
Specifically, the object recognition apparatus provided in the embodiment of the present invention employs a photographing device for recognition, where the photographing device includes: a plurality of first type lenses and a second type lens; as shown in fig. 6, the apparatus includes:
a first unit 601, configured to determine, according to the recognition result of each first-type shot on the object to be recognized, a first-type shot in which the object to be recognized is recognized from each first-type shot, and define the first-type shot as a reference shot;
a second unit 602, configured to determine whether the reference lens identifies a target position of the object to be identified; if yes, controlling the second type of lens to snapshot the target position according to the identification result of the reference lens; if not, controlling the second type lens to snapshot the target position according to the identification result of each first type lens.
In practical implementation, in the foregoing apparatus provided in the embodiment of the present invention, the second unit 602 is specifically configured to:
sending a first control signal to a second type of lens according to the identification result of the reference lens;
wherein the first control signal is to: and controlling the second type lens to adjust the photographing angle according to the recognition result of the reference lens and photographing.
In practical implementation, in the foregoing apparatus provided in the embodiment of the present invention, the second unit 602 is specifically configured to:
respectively sending a second control signal to the second type of lens according to the identification result of each first type of lens;
each second control signal corresponds to the recognition result of each first-class lens, and the second control signals are used for: and controlling the second type lens to adjust the photographing angle according to the recognition result of the first type lens and photographing.
In specific implementation, in the apparatus provided in the embodiment of the present invention, after controlling the second type of lens to capture the target position according to the recognition result of each first type of lens, the second unit 602 is further configured to:
receiving N photos sent by the second type of lens; n is the number of the first-class lenses, and N pictures are obtained according to the identification result of each first-class lens;
according to a preset target recognition algorithm and an influence factor influencing the target position recognition result, respectively evaluating the target positions in the N pictures to determine an evaluation value corresponding to each picture;
and when the maximum value is selected from the determined evaluation values, determining and storing the picture corresponding to the maximum value.
In a specific implementation, in the apparatus provided in the embodiment of the present invention, if the target position is a human face, the influence factor includes at least one of the following factors:
face state angle, face definition, face pixel size, photographing light intensity and face shielding state.
In specific implementation, in the apparatus provided in the embodiment of the present invention, after controlling the second type lens to capture the target position according to the recognition result of the reference lens, the second unit 602 is further configured to:
and receiving and storing the photos sent by the second type of lens.
Alternatively, the object identifying means may be the controller mentioned in the foregoing.
Based on the same inventive concept, an embodiment of the present invention provides a photographing apparatus, as shown in fig. 7, including: a plurality of first-type lenses 701, a second-type lens 702, and the object recognition device 703 according to the embodiment of the present invention;
the first type of lens is used for 701: and identifying the object to be identified, and sending the obtained identification result to the target identification device 703, so that the target identification device 703 controls the second-class lens 702 to capture the target position of the object to be identified according to the identification result.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
The embodiment of the invention provides a target identification method and a target identification device, which adopt a photographing device for identification, wherein the photographing device comprises: the first-class lenses and the second-class lenses are used for determining the first-class lenses identifying the object to be identified from the first-class lenses according to the identification result of the object to be identified of each first-class lens, and defining the first-class lenses as reference lenses; judging whether the reference lens identifies the target position of the object to be identified; if yes, controlling the second type of lens to snapshot the target position according to the identification result of the reference lens; if not, controlling the second type lens to identify the target according to the identification result of each first type lens. Therefore, on the basis of adopting one photographing device, the target position of the object to be recognized can be captured through the synergistic effect among a plurality of lenses included in the photographing device; moreover, the target position of the object to be recognized can be captured through one photographing device, so that only one network cable and one power line are needed, and the implementation mode is simple and efficient; in addition, only one photographing device is adopted, so that the number of the photographing devices is reduced, the cost required by recognition is favorably reduced, the accuracy and the efficiency of target recognition can be improved, the process of target recognition is simplified, and the recognition method has high practicability.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A target identification method is characterized in that a photographing device is adopted for identification, and the photographing device comprises: a plurality of first type lenses and a second type lens; the method comprises the following steps:
determining a first-class shot for identifying the object to be identified from the first-class shots according to the identification result of the object to be identified by each first-class shot, and defining the first-class shot as a reference shot;
judging whether the reference lens identifies the target position of the object to be identified;
if yes, controlling the second type lens to snapshot the target position according to the identification result of the reference lens;
if not, controlling the second type lens to snapshot the target position according to the identification result of each first type lens.
2. The method according to claim 1, wherein controlling the second type of lens to capture the target position according to the recognition result of the reference lens specifically comprises:
sending a first control signal to the second type of lens according to the identification result of the reference lens;
wherein the first control signal is to: and controlling the second type lens to adjust the photographing angle according to the recognition result of the reference lens and photographing.
3. The method according to claim 1, wherein controlling the second type of lens to capture the target position according to the recognition result of each first type of lens specifically comprises:
respectively sending a second control signal to the second type lens according to the identification result of each first type lens;
wherein each of the second control signals corresponds to an identification result of each of the first type of lenses, and the second control signals are used for: and controlling the second type of lens to adjust the photographing angle according to the recognition result of the first type of lens and photographing.
4. The method according to any one of claims 1 to 3, wherein after controlling the second type of lens to capture the target position according to the recognition result of each first type of lens, the method further comprises:
receiving N photos sent by the second type of lens; n is the number of the first-class lenses, and the N pictures are obtained according to the identification result of each first-class lens;
according to a preset target recognition algorithm and an influence factor influencing the target position recognition result, respectively evaluating the target positions in the N pictures to determine an evaluation value corresponding to each picture;
and when the maximum value is selected from the determined evaluation values, determining and storing the picture corresponding to the maximum value.
5. The method of claim 4, wherein if the target location is a human face, the impact factor comprises at least one of:
face state angle, face definition, face pixel size, photographing light intensity and face shielding state.
6. The method according to any one of claims 1 to 3, wherein after controlling the second type lens to capture the target position according to the recognition result of the reference lens, the method further comprises:
and receiving and storing the photos sent by the second type of lens.
7. The target recognition device is characterized in that a photographing device is adopted for recognition, and the photographing device comprises: a plurality of first type lenses and a second type lens; the device includes:
the first unit is used for determining a first-class shot for identifying the object to be identified from the first-class shots according to the identification result of the object to be identified by each first-class shot and defining the first-class shot as a reference shot;
the second unit is used for judging whether the reference lens identifies the target position of the object to be identified; if yes, controlling the second type lens to snapshot the target position according to the identification result of the reference lens; if not, controlling the second type lens to snapshot the target position according to the identification result of each first type lens.
8. The apparatus of claim 7, wherein the second unit is specifically configured to:
sending a first control signal to the second type of lens according to the identification result of the reference lens;
wherein the first control signal is to: controlling the second type lens to adjust a photographing angle according to the recognition result of the reference lens and photographing;
or respectively sending a second control signal to the second type of lens according to the identification result of each first type of lens;
wherein each of the second control signals corresponds to an identification result of each of the first type of lenses, and the second control signals are used for: and controlling the second type of lens to adjust the photographing angle according to the recognition result of the first type of lens and photographing.
9. The apparatus according to claim 7 or 8, wherein after controlling the second type of lens to capture the target position according to the recognition result of each first type of lens, the second unit is further configured to:
receiving N photos sent by the second type of lens; n is the number of the first-class lenses, and the N pictures are obtained according to the identification result of each first-class lens;
according to a preset target recognition algorithm and an influence factor influencing the target position recognition result, respectively evaluating the target positions in the N pictures to determine an evaluation value corresponding to each picture;
and when the maximum value is selected from the determined evaluation values, determining and storing the picture corresponding to the maximum value.
10. A photographing apparatus, comprising: a plurality of first type shots, a second type shot, and the object recognition device of any of claims 7-9;
the first type of lens is used for: and identifying the object to be identified, and sending the obtained identification result to the target identification device so that the target identification device controls the second-class lens to capture the target position of the object to be identified according to the identification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010544400.4A CN111818299B (en) | 2020-06-15 | 2020-06-15 | Target identification method and device and photographing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010544400.4A CN111818299B (en) | 2020-06-15 | 2020-06-15 | Target identification method and device and photographing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111818299A true CN111818299A (en) | 2020-10-23 |
| CN111818299B CN111818299B (en) | 2022-02-15 |
Family
ID=72845021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010544400.4A Active CN111818299B (en) | 2020-06-15 | 2020-06-15 | Target identification method and device and photographing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111818299B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080291278A1 (en) * | 2005-04-05 | 2008-11-27 | Objectvideo, Inc. | Wide-area site-based video surveillance system |
| CN101895727A (en) * | 2009-05-21 | 2010-11-24 | 索尼公司 | Monitoring system, image capturing apparatus, analysis apparatus, and monitoring method |
| US8115814B2 (en) * | 2004-09-14 | 2012-02-14 | Canon Kabushiki Kaisha | Mobile tracking system, camera and photographing method |
| CN107800964A (en) * | 2017-10-26 | 2018-03-13 | 武汉大学 | It is a kind of that method of the face automatic detection with capturing is realized based on dual camera |
| CN108965805A (en) * | 2018-07-10 | 2018-12-07 | 深圳市巨龙创视科技有限公司 | A kind of splicing linked system based on embedded deep learning algorithm |
| CN109815861A (en) * | 2019-01-11 | 2019-05-28 | 佰路得信息技术(上海)有限公司 | A kind of user behavior information statistical method based on recognition of face |
| CN109889718A (en) * | 2019-04-04 | 2019-06-14 | 郑州和光电子科技有限公司 | Panoramic camera for safety monitoring |
| CN110533700A (en) * | 2019-08-30 | 2019-12-03 | 腾讯科技（深圳）有限公司 | Method for tracing object and device, storage medium and electronic device |
| CN111246172A (en) * | 2020-01-20 | 2020-06-05 | 深圳英飞拓科技股份有限公司 | Linkage image acquisition device and image acquisition method |
-
2020
- 2020-06-15 CN CN202010544400.4A patent/CN111818299B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8115814B2 (en) * | 2004-09-14 | 2012-02-14 | Canon Kabushiki Kaisha | Mobile tracking system, camera and photographing method |
| US20080291278A1 (en) * | 2005-04-05 | 2008-11-27 | Objectvideo, Inc. | Wide-area site-based video surveillance system |
| CN101895727A (en) * | 2009-05-21 | 2010-11-24 | 索尼公司 | Monitoring system, image capturing apparatus, analysis apparatus, and monitoring method |
| CN107800964A (en) * | 2017-10-26 | 2018-03-13 | 武汉大学 | It is a kind of that method of the face automatic detection with capturing is realized based on dual camera |
| CN108965805A (en) * | 2018-07-10 | 2018-12-07 | 深圳市巨龙创视科技有限公司 | A kind of splicing linked system based on embedded deep learning algorithm |
| CN109815861A (en) * | 2019-01-11 | 2019-05-28 | 佰路得信息技术(上海)有限公司 | A kind of user behavior information statistical method based on recognition of face |
| CN109889718A (en) * | 2019-04-04 | 2019-06-14 | 郑州和光电子科技有限公司 | Panoramic camera for safety monitoring |
| CN110533700A (en) * | 2019-08-30 | 2019-12-03 | 腾讯科技（深圳）有限公司 | Method for tracing object and device, storage medium and electronic device |
| CN111246172A (en) * | 2020-01-20 | 2020-06-05 | 深圳英飞拓科技股份有限公司 | Linkage image acquisition device and image acquisition method |
Non-Patent Citations (1)
| Title |
|---|
| 刘文?: "基于模块化研发的智能环境监测平台", 《物联网技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111818299B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8885091B2 (en) | Imaging device and distance information detecting method | |
| WO2018201809A1 (en) | Double cameras-based image processing device and method | |
| US20120320239A1 (en) | Image processing device and image processing method | |
| US8830381B2 (en) | Imaging device and method to provide bokeh effect in captured image by determining distance and focus of captured objects in secondary image sequence | |
| CN107396068A (en) | The synchronous tiled system of panoramic video, method and panoramic video display device | |
| US8411159B2 (en) | Method of detecting specific object region and digital camera | |
| US8810665B2 (en) | Imaging device and method to detect distance information for blocks in secondary images by changing block size | |
| EP4156081A1 (en) | Image processing method and apparatus | |
| CN101369089B (en) | Continuous image shooting system and method | |
| TW201541141A (en) | Auto-focus system for multiple lens and method thereof | |
| JP2012195668A (en) | Image processing device, image processing method, and program | |
| CN110731076A (en) | Shooting processing method and device and storage medium | |
| US20130201355A1 (en) | Imaging apparatus, imaging method, and recording medium | |
| CN109981967B (en) | Shooting method and device for intelligent robot, terminal equipment and medium | |
| CN111798374A (en) | Image splicing method, device, equipment and medium | |
| EP2804379A1 (en) | System and method for providing 3-dimensional images | |
| CN112822371B (en) | Image processing chip, application processing chip, data statistical system and method | |
| TW201541143A (en) | Auto-focus system for multiple lens and method thereof | |
| US9094581B2 (en) | Imaging device and distance information detecting method | |
| CN111818299B (en) | Target identification method and device and photographing equipment | |
| EP3304551B1 (en) | Adjusting length of living images | |
| CN110399823B (en) | Subject tracking method and apparatus, electronic device, and computer-readable storage medium | |
| JP6483661B2 (en) | Imaging control apparatus, imaging control method, and program | |
| US20120293705A1 (en) | Image processing method | |
| CN105467741A (en) | Panoramic shooting method and terminal |
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 |