CN115714894A

CN115714894A - Automatic image tracking all-in-one of discernment position

Info

Publication number: CN115714894A
Application number: CN202211424992.1A
Authority: CN
Inventors: 李广垒; 王飞; 陈祖涛
Original assignee: Anhui Baoxin Information Technology Co ltd
Current assignee: Anhui Baoxin Information Technology Co ltd
Priority date: 2022-11-15
Filing date: 2022-11-15
Publication date: 2023-02-24

Abstract

The invention discloses an image tracking all-in-one machine capable of automatically identifying positions, and belongs to the technical field of automatic image tracking. An image tracking all-in-one machine capable of automatically identifying positions comprises a bottom plate, a placing frame, a host, a display screen, an automatic focus following camera capable of automatically following focus to a shooting object, a shutter and an intelligent shooting module; the placing rack is arranged on the bottom plate, a placing groove is arranged on the front side of the placing rack, and a shooting hole for placing the automatic focus following camera is formed in the inner wall of the placing groove; the main machine is arranged in the placing groove, the automatic focus tracking camera is embedded in the upper part of the rear side of the main machine, the display screen is arranged on the front side of the main machine, and the shutter is arranged on the lower part of the front side of the display screen; the intelligent shooting system comprises a host, a processor, a memory, a display screen, a shutter, an automatic focus tracking camera, an intelligent shooting module and a shutter control module, wherein the processor and the memory are arranged in the host, the memory, the display screen and the shutter are respectively in control connection with the processor, the automatic focus tracking camera is in communication connection with the processor, the intelligent shooting module is in control connection with the shutter, and the intelligent shooting module is used for triggering the shutter to enable the automatic focus tracking camera on the host to shoot a shooting object.

Description

Automatic image tracking all-in-one of discernment position

Technical Field

The invention relates to the technical field of automatic image tracking, in particular to an image tracking all-in-one machine capable of automatically identifying positions.

Background

The existing image tracking technology has become widely used in daily life, such as satellites, cameras, mobile phones and the like. The mobile phone is the most used image tracking device in daily life, the provided shooting function is shooting by adopting an image tracking principle, and the shot image is processed by a processor and then stored in a built-in storage device for a user to watch.

In the conventional mobile phone, although the position of a photographed portrait can be tracked by performing auto-focusing, the photographing can be performed only by manually pressing a shutter key after the auto-focusing, and thus, the photographing can be performed only for others. Although a selfie stick has been developed to solve this problem, the selfie stick can only take a picture of itself at a short distance, and because the length of the selfie stick is limited, only a half-length picture of an individual can be taken, and the selfie stick is held for a long time to make the arm of a person feel sour, thereby being inconvenient to use.

Disclosure of Invention

1. Technical problem to be solved

The invention aims to provide an image tracking all-in-one machine capable of automatically identifying positions, which can trigger a shooting host to continuously shoot by reaching a certain state through local characteristics of a shot object, and the shooting host can automatically screen images with low quality, so that the existing shooting host can automatically shoot the shot object.

2. Technical scheme

In order to solve the above problems, the present invention adopts the following technical solutions.

An image tracking all-in-one machine capable of automatically identifying positions comprises a bottom plate, a placing frame, a host, a display screen, an automatic focus following camera capable of automatically following focus to a shooting object, a shutter and an intelligent shooting module;

the placing rack is arranged on the bottom plate, a placing groove is arranged on the front side of the placing rack, and a shooting hole for placing the automatic focus following camera is formed in the inner wall of the placing groove;

the host is arranged in the placing groove, the automatic focus following camera is embedded in the upper part of the rear side of the host, the display screen is arranged on the front side of the host, and the shutter is arranged on the lower part of the front side of the display screen;

the intelligent shooting system comprises a host, a processor, a memory, a display screen, a shutter, an automatic focus tracking camera, an intelligent shooting module and a shutter control module, wherein the processor and the memory are arranged in the host, the memory, the display screen and the shutter are respectively in control connection with the processor, the automatic focus tracking camera is in communication connection with the processor, the intelligent shooting module is in control connection with the shutter, and the intelligent shooting module is used for triggering the shutter to enable the automatic focus tracking camera on the host to shoot a shooting object.

Furthermore, the intelligent shooting module comprises a host-based software identification module, a shutter trigger module, a continuous shooting trigger module and a deletion module;

the software identification module comprises an object identification module, a first interest identification module and a second interest identification module;

after the shutter is triggered, the memory stores the image shot by the host;

the first identification module of interest is higher priority than the second identification module of interest;

the automatic focus tracking camera is used as a sensor of the software identification module;

after the automatic focus-following camera automatically focuses on the shot object, the object identification module identifies whether at least one essential object exists in the shot object after the automatic focus-following camera automatically focuses;

after the identification is successful, the intelligent shooting module starts timing from zero; the shooting object is composed of a plurality of features, and the requirement object is a local feature in the shooting object;

the method comprises the steps that a first interesting identification module is started, the first interesting identification module identifies whether a shooting object has a preset first requirement characteristic or not within a delay first preset time, if yes, a first interesting condition is generated, then an intelligent shooting module jointly generates a condition according to the first interesting condition and a shutter trigger module, a continuous shooting trigger module and a deleting module are started, and if not, a first interesting condition is not generated, and then a second interesting identification module is started;

in a second preset time delay, the second interest identification module identifies whether the shot object has a preset second requirement characteristic, if so, a second interest condition is generated, and then the intelligent shooting module starts the continuous shooting trigger module and the deleting module according to the condition generated by the second interest condition and the shutter trigger module together;

the first requirement characteristic and the second requirement characteristic are different local characteristic states of the shooting object;

if the first interested identification module and the second interested module are not triggered to generate corresponding interested conditions, manual shooting or software preset timing shooting is carried out;

the continuous shooting trigger module can send out a signal for triggering the shutter for multiple times after being triggered, the processor receives the signal for triggering the shutter for multiple times and processes the signal to control the shutter trigger module, and the shutter trigger module executes continuous shooting shutter triggering operation;

the deleting module identifies images and calculates the image quality according to the images shot by the host after the continuous shooting triggering module is started, deletes the images lower than the preset weight according to the comparison between the calculated weight value and the preset weight, reserves the images higher than the preset weight, and automatically finishes shooting.

Further, the shooting object is selected from one or any combination of at least one person or at least one non-person object.

Further, the photographic subject is selected from at least one person, and the first requirement characteristic and the second requirement characteristic are independently selected from one of a smiling face characteristic, an eye opening characteristic, a gesture characteristic or a leg characteristic of the person.

Further, the deleting module deletes the low-quality image shot by the host;

the sharpness is calculated according to the sharpness formula:

e = Σ ab (df/dx) 2|f (b) -f (a) | where a, b are edge points of the photographic subject in the selected image, f (a) represents the gray scale at the edge point a, f (b) represents the gray scale at the edge point b, df/dx is the gray scale change rate of the edge normal, and f (b) -f (a) is the total gray scale change of the edge normal.

Furthermore, a plurality of persons exist in the shooting object, or at least one person is combined with at least one non-person body or consists of a plurality of non-person bodies, and the requirement object is a local feature of the person or the non-person body;

the object identification module identifies that at least one essential object exists in the shot objects which are automatically focused by the automatic focusing camera and counts the number K1 of the essential objects;

the software identification module also comprises two analysis and judgment modules;

the first interest identification module identifies whether the shot object has a preset first requirement characteristic or not and counts the number M1 of the first requirement characteristic, the preset first requirement characteristic exists, the analysis and judgment module compares and analyzes the number M1 of the first requirement characteristic identified by the first interest identification module and the number K1 of the requirement object, judges whether K1-M1 is smaller than or equal to a first preset value or not, if so, a first interest condition is generated, otherwise, the first interest condition is not generated;

the second interest identification module identifies whether a preset second requirement characteristic exists in the shot object or not and counts the number M2 of the second requirement characteristic, the second requirement characteristic exists, the other analysis and judgment module is used for judging whether the number M2 of the second requirement characteristic identified by the second interest identification module is compared with the number K1 of the requirement objects or not and judging whether the number K2-M1 is less than or equal to a second preset value or not, if so, a second interest condition is generated, otherwise, the second interest condition is not generated.

Furthermore, the shutter trigger module comprises a control box, a magnet, a pressing contact rod, a return spring and an electromagnet;

the control box is arranged on the bottom plate, and a cavity is arranged in the control box;

the magnet is arranged in the cavity in a sliding mode, the electromagnet is arranged in the cavity and located on one side, away from the shutter, of the magnet, the electromagnet is magnetically connected with the magnet, and the processor is in control connection with the electromagnet;

the reset spring is arranged in the cavity, and two ends of the reset spring are respectively connected with the magnet and the inner wall of the cavity close to one side of the shutter;

the press contact rod penetrates through the rear side of the control box and is arranged on the magnet, the press contact rod is in sliding connection with the control box, and the press contact rod and the shutter are located at the same height.

Furthermore, the intelligent shooting module also comprises a voice prompt module;

when the analysis and judgment module judges that K1-M1 is larger than a first preset value, a voice prompt module is started, the voice prompt module sends a preset voice prompt to the shot object, the shot object adjusts the posture after hearing the voice prompt, the automatic focus-following camera automatically focuses on the shot object again, and when the analysis and judgment module judges that the times of K1-M1 larger than the first preset value exceed a third preset value L1, the first interest recognition module does not generate a first interest condition within a first delay preset time;

when the analysis and judgment module judges that the K2-M1 is greater than the second preset value, the voice prompt module is started, the voice prompt module sends a preset voice prompt to the shot object, the shot object is adjusted, the automatic focus tracking camera automatically tracks the shot object again, and when the analysis and judgment module judges that the times of the K2-M1 being greater than the second preset value exceed a fourth preset value L2, the second interest recognition module does not generate a second interest condition within the second delay preset time.

Further, when the analysis and judgment module judges that K2-M1 is larger than a second preset value, a voice prompt module is started, and sends a preset voice prompt to the shooting object;

the object to be shot hears the voice prompt, the posture of the object to be shot is adjusted, then, after the automatic focus tracking camera automatically tracks the object to be shot again, the object recognition module recognizes that at least one essential object exists in the object to be shot after the automatic focus tracking camera automatically tracks the focus, the intelligent shooting module starts timing from zero, the second interest recognition module starts until the analyzing and judging module judges that the times that K2-M1 is larger than the second preset value exceeds a fourth preset value L2, the second interest recognition module does not generate a second interest condition, or the analyzing and judging module judges that K2-M1 is smaller than the second preset value, the second interest recognition module generates the second interest condition, and the analyzing and judging module does not judge whether K2-M1 is smaller than the second preset value.

Furthermore, the intelligent shooting module also comprises two counting control modules;

the counting control module is used for judging the times N1 when the K1-M1 is smaller than a first preset value or not and judging whether the N1 is larger than a third preset value L1 or not by the analysis and judgment module after the voice prompt module sends a preset voice prompt to the shooting object, if the N1 is larger than the L1, the analysis and judgment module does not judge whether the K1-M1 is smaller than the first preset value or not, and if the first interest identification module identifies that the shooting object does not have a preset first requirement characteristic within a first delay preset time, the first interest identification module does not generate a first interest condition;

and the other counting control module is used for recording the times N2 that whether the K2-M1 is smaller than a second preset value or not and judging whether the N2 is larger than the L2 or not after the voice prompt module sends a preset voice prompt to the shooting object, if the N2 is larger than the L2, the analyzing and judging module does not judge whether the K2-M1 is larger than the second preset value or not, and if the second interest recognition module recognizes that the shooting object does not have a preset second essential feature within a second preset time delay, a second interest condition is not generated.

3. Advantageous effects

Compared with the prior art, the invention has the advantages that:

(1) According to the invention, by arranging the intelligent shooting module, the intelligent shooting module can realize that the shooting host can be triggered to continuously shoot when the local characteristics of the shot object reach a certain state, and the shooting host can automatically screen some images with low quality, so that the existing shooting host can automatically shoot the shot object.

(2) According to the invention, through the arrangement of the first interest identification module and the second interest identification module, the continuous shooting trigger module and the deleting module are started by generating the first interest condition or the second interest condition respectively and jointly generating the conditions with the shutter trigger module, so that the use requirement of a user is met, and a picture with higher quality is shot.

(3) The invention can shoot a satisfactory combined image when the shooting object is composed of a plurality of people or at least one person and at least one non-person body or a plurality of non-person bodies by arranging two analysis and judgment modules.

(4) According to the invention, through arranging the voice prompt module, the voice prompt module is matched with the analysis and judgment module, when the shooting object is composed of a plurality of characters or at least one character and at least one non-character body or a plurality of non-character bodies, if the triggering interesting condition is not met, the voice prompt module can send out corresponding prompt tone to remind the shooting object to adjust the posture, so that the shooting host can shoot a satisfactory shooting image.

(5) According to the invention, two counting control modules are arranged, and the counting control modules are matched with the analysis and judgment module and the voice prompt module, so that when a shooting object is composed of a plurality of persons or a combination of at least one person and at least one non-person body or a plurality of non-person bodies, if the triggering interest condition is not met, the voice prompt module reminds, the analysis and judgment module judges that the frequency exceeds a preset value, and the first interest identification module and the second interest identification module do not generate the triggering condition any more, so that the shooting host can shoot a satisfactory shooting image, and the analysis and judgment module can judge for unlimited times.

Drawings

FIG. 1 is a schematic structural diagram of an intelligent photographing module according to the present invention;

FIG. 2 is a schematic diagram of a software identification module according to the present invention;

FIG. 3 is a flowchart of example 1 of the present invention;

FIG. 4 is a flowchart of embodiment 2 of the present invention;

FIG. 5 is a flowchart of embodiment 3 of the present invention;

FIG. 6 is a partial flowchart of embodiment 3 of the present invention;

FIG. 7 is a flowchart of embodiment 4 of the present invention;

FIG. 8 is a schematic diagram illustrating a first perspective structure according to an embodiment of the present invention;

fig. 9 is a schematic perspective view of an image tracking all-in-one machine according to the present invention;

FIG. 10 is an enlarged view of a portion of FIG. 9 at A;

FIG. 11 is a schematic diagram illustrating a second perspective view according to an embodiment of the present invention;

FIG. 12 is a partial enlarged view of FIG. 11 at B;

fig. 13 is a schematic diagram of an internal structure of a control device according to an embodiment of the present invention.

The reference numbers in the figures illustrate:

1. a base plate; 2. placing a rack; 201. a placement groove; 202. shooting holes; 203. heat dissipation holes; 3. a host; 4. a display screen; 5. automatically focusing the camera; 6. a shutter; 7. a control box; 701. a cavity; 8. a magnet; 9. pressing a feeler lever; 10. a leather sheath; 11. a return spring; 12. an electromagnet; 13. a storage battery; 14. a signal lamp; 15. a turntable; 16. a side plate; 17. a threaded rod; 18. a nut; 19. connecting blocks; 20. a support plate; 21. supporting legs; 22. a screw rod; 23. a connecting rod; 24. and (4) ball poking.

Detailed Description

The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited thereto, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.

Example 1: the utility model provides an image tracking all-in-one of automatic identification position, includes bottom plate 1, rack 2, host computer 3, display screen 4, can follow the burnt camera 5, shutter 6 and the intelligent shooting module of following focus to the automation of shooting the object automatically.

The placing rack 2 is arranged on the bottom plate 1, a placing groove 201 is arranged on the front side of the placing rack 2, and a shooting hole 202 for placing the automatic focus following camera 5 is formed in the inner wall of the placing groove 201.

2 rear sides of rack evenly are provided with a plurality of louvres 203, and a plurality of louvres 203 all communicate with standing groove 201, and louvre 203 is located shoots the hole 202 below, through setting up louvre 203, can make things convenient for components such as treater in the host computer body 3 to dispel the heat to guarantee its stable work.

Host computer 3 installs in standing groove 201, and automatic camera 5 of following focus is embedded at host computer 3 rear side upper portion, and display screen 4 sets up in host computer 3 front side, and shutter 6 sets up in display screen 4 front side lower part.

Be provided with treater and memory in the host computer 3, memory, display screen 4 and shutter 6 are equallyd divide and are connected with treater control, and automatic camera 5 of following focus is connected with the treater communication, and intelligent shooting module and shutter 6 control connection, and intelligent shooting module is used for triggering shutter 6 and makes automatic camera 5 of following focus on the host computer 3 to shoot the object.

The storage battery 13 is arranged on the bottom plate 1, and the storage battery 13 is electrically connected with the display screen 4, the processor, the memory, the automatic focus following camera 5, the shutter 6 and the control device. The signal lamp 14 sets up on bottom plate 1, and treater and signal lamp 14 control connection, battery 13 and signal lamp 14 electric connection, through setting up signal lamp 14, can convenience of customers judge, whether accomplish the shooting.

The intelligent shooting module comprises a software identification module based on the host 3, a shutter trigger module, a continuous shooting trigger module and a deletion module; the software identification module comprises an object identification module, a first interest identification module and a second interest identification module; after the shutter is triggered, the memory stores the image shot by the host 3; the first identity of interest module has a higher priority than the second identity of interest module; the automatic focus tracking camera 5 is used as a sensor of the software identification module; after the automatic focus-following camera 5 automatically focuses on the shot object, the object identification module identifies whether at least one essential object exists in the shot object after the automatic focus-following camera 5 automatically focuses; after the identification is successful, the intelligent shooting module starts timing from zero; the subject is composed of a plurality of features, and the requirement object is a local feature in the subject.

The method comprises the steps that a first interesting identification module is started, the first interesting identification module identifies whether a shooting object has a preset first requirement characteristic or not within a first preset time delay, if yes, a first interesting condition is generated, then an intelligent shooting module jointly generates a condition according to the first interesting condition and a shutter trigger module, a continuous shooting trigger module and a deleting module are started, and if not, a second interesting identification module is started after the first interesting condition is not generated.

And in a second preset time delay, the second interest identification module identifies whether the shooting object has a preset second requirement characteristic, if so, a second interest condition is generated, and then the intelligent shooting module starts the continuous shooting triggering module and the deleting module according to the condition generated by the second interest condition and the shutter triggering module together.

The first requirement characteristic and the second requirement characteristic are different local characteristic states of the shooting object.

If the first interested identification module and the second interested module are not triggered to generate corresponding interested conditions, manual shooting or software preset timing shooting is carried out; the continuous shooting trigger module can send out a signal for triggering the shutter for multiple times after being triggered, and the processor receives the signal for triggering the shutter for multiple times, processes the signal and controls the shutter trigger module to execute continuous shooting shutter triggering operation.

The image quality screening conditions may include one or more of: an image sharpness screening condition, an image brightness screening condition, an image exposure screening condition, an image saturation screening condition, or an image contrast screening condition. For example, the image definition screening condition may be that the image definition is within a certain threshold range, where the threshold range may be preset in the host, or a policy for determining the threshold range may be preset in the host. In addition, in this embodiment of the application, the image quality screening condition may further include other screening conditions related to image quality, for example, whether an image has a color block or not, whether a color cast or not, and the like.

The deleting module identifies images and calculates the image quality according to the images shot by the host 3 after the continuous shooting triggering module is started, deletes the images lower than the preset weight according to the comparison between the calculated weight value and the preset weight, retains the images higher than the preset weight, and automatically finishes shooting.

The deleting module is used for deleting the low-quality images shot by the host 3;

the sharpness is calculated according to the sharpness formula:

e = Σ ab (df/dx) 2|f (b) -f (a) | where a and b are edge points of the photographic subject in the selected image, fa represents the gray level at the edge point a, fb represents the gray level at the edge point b, df/dx is the gray level change rate of the edge normal, and f (b) -f (a) is the total gray level change of the edge normal, the sharper the gray level change is, the sharper the edge is, and specifically, if the sharpness of the image cannot meet the requirement of the preset sharpness weight, the image is a blurred image and is deleted by the deletion module.

The definition of the image can also be calculated by using an edge detection operator (such as a sobel operator) to calculate the edge of the target area and sum the edge, and the column direction mean value is used as the definition value of the output, wherein the edge detection operator is generally a 3*3 matrix which is a transverse matrix and a longitudinal matrix respectively, the matrix and the image of the target area are subjected to plane convolution, and the results obtained after the convolution are summed and the mean value is calculated, namely the definition value of the image.

The shooting object comprises a plurality of persons, or at least one person and at least one non-person body or a plurality of non-person bodies, and the requirement object is a local feature of the person or the non-person body.

The non-human body can be animals such as pets, cats, dogs, monkeys and the like, and can also be automobiles, sea waves and the like.

When the photographic subject is selected from at least one person, the first requirement characteristic and the second requirement characteristic can be independently selected from one of facial characteristics such as a face characteristic turned from the side, a smiling face characteristic, an eye opening characteristic, a gesture characteristic or a leg characteristic, but the first requirement characteristic and the second requirement are not limited to local characteristic states of the requirement subjects, and can be other local characteristic states, such as a state that the person jumps off the ground; the character gesture features can be scissors gestures, ok gestures, heart-to-heart gestures and the like, so that the host can shoot the shot object and can shoot the shot object.

The shutter trigger module comprises a control box 7, a magnet 8, a pressing contact rod 9, a return spring 11 and an electromagnet 12; the control box 7 is arranged on the bottom plate 1, and a cavity 701 is arranged in the control box 7; the magnet 8 is arranged in the cavity 701 in a sliding mode, the electromagnet 12 is arranged in the cavity 701, the electromagnet 12 is located on one side, away from the shutter 6, of the magnet 8, the electromagnet 12 is in magnetic connection with the magnet 8, the processor is in control connection with the electromagnet 12, and the storage battery 13 is electrically connected with the electromagnet 12; the return spring 11 is arranged in the cavity 701, and two ends of the return spring 11 are respectively connected with the magnet 8 and the inner wall of the cavity 701 close to the shutter 6; the press contact rod 9 penetrates through the rear side of the control box 7 and is arranged on the magnet 8, the press contact rod 9 is connected with the control box 7 in a sliding mode, and the press contact rod 9 and the shutter 6 are located at the same height.

The leather sheath 10 is sleeved at one end, close to the shutter 6, of the touch rod 9, the leather sheath 10 is an elastic piece, a round angle is arranged at one end, close to the shutter 6, of the leather sheath 10, and the leather sheath 10 can protect the shutter 6 and further avoid scraping the shutter 6 by the touch rod 9.

When the embodiment is used, for example, the shooting object is a human object, and the essential object is a human face; firstly, setting a first requirement characteristic and a second requirement characteristic in advance, wherein the first requirement characteristic is a character smiling face characteristic, the second requirement characteristic is a character gesture characteristic, such as a scissor gesture characteristic, the first preset time is 5s, and the second preset time is 10s; performing face recognition, namely acquiring whether a face region exists in the shot object by utilizing adaboost + haar characteristic training, and recognizing whether the face region exists in the shot object by using a mature opencv open source method; the face features are obtained, a Support Vector Machine (SVM for short) and a Gabor technology can be used for obtaining the face expression, and the face expression can be smiling face, crying, depression and the like; the adaboost + haar technology can be utilized to carry out eye closing detection on the human face region so as to obtain eye closing, eye opening and other eye states; the SVM and gabor technology can be utilized to obtain the human face postures of the front face, the measurement and the like. .

The user first starts the device and then energizes the processor, memory, display 4, auto-focus camera 5, shutter 6 and shutter trigger module. At this time, the user can stand in front of the automatic focus following camera 5 and put the photographing posture to perform photographing operation. When photographing, the automatic focus-following camera 5 identifies the human shape, performs automatic focusing, identifies the position of the human shape, and the object identification module of the intelligent photographing module identifies the human face; after the identification is successful, the intelligent shooting module starts timing from zero.

The first interesting identification module is started, within 5s of delay, the first interesting identification module identifies whether the smiling face characteristic of the person exists in the shot object, if yes, a first interesting condition is generated, then the intelligent shooting module starts the continuous shooting trigger module and the deleting module according to the condition generated by the first interesting condition and the shutter trigger module together, and if not, the second interesting identification module is started after the first interesting condition is not generated.

And in a second preset time delay, the second interest identification module identifies whether the shooting object has the gesture characteristics of scissors or not, if so, a second interest condition is generated, and then the intelligent shooting module starts the continuous shooting trigger module and the deleting module according to the condition generated by the second interest condition and the shutter trigger module together.

And if the first interested identification module and the second interested module are not triggered to generate corresponding interested conditions, manual shooting or software preset timing shooting is carried out.

The continuous shooting trigger module can send out a signal for triggering the shutter for multiple times after being triggered, and the processor receives the signal for triggering the shutter for multiple times, processes the signal and controls the shutter trigger module to execute continuous shooting shutter triggering operation.

When a first interesting condition or a second interesting condition is generated, the first interesting identification module or the second interesting identification module transmits a signal to the processor, at the moment, the processor energizes the electromagnet 12 of the shutter trigger module, the energized electromagnet 12 is magnetic and repels the magnet 8, the magnet 8 is far away from the electromagnet 12, and meanwhile, the pressing touch rod 9 is driven to touch the shutter 6, so that the automatic photographing of the device is realized.

During the touch of the shutter 6 by the touch lever 9, the return spring 11 continues to be compressed. And when the shutter 6 is touched, the shutter 6 sends out a control signal to control the processor to acquire images. The processor transmits the collected image to the memory for storage, and controls the display screen 4 to display the collected image.

The first interested identification module and the shutter trigger module jointly generate conditions or the second interested identification module and the shutter trigger module jointly generate conditions, and the continuous shooting trigger module and the deleting module in the intelligent shooting module are started; and the processor receives the signal for triggering the shutter for multiple times and controls the shutter triggering module to execute the operation of triggering the shutter for continuous shooting after processing the signal.

The deleting module identifies images and calculates the image quality according to the images shot by the host 3, compares the calculated weight value with the preset weight value, deletes the images lower than the preset weight value, keeps the images higher than the preset weight value, screens out the images with the preset number and higher than the preset weight value, sends the signals to the processor, and after the processor processes the signals, the processor cuts off the power of the electromagnet 12 of the shutter triggering module, the electromagnet 12 does not have magnetism after being cut off, does not generate repulsive magnetic force on the magnet 8, resets the magnet 8 under the action of the reset spring 11, the leather sheath 10 leaves the shutter 6, and meanwhile, the processor controls the signal lamp 14 to send out a shooting end signal, and the signal lamp 14 is on to represent that the shooting is ended.

When the device is used, the camera 5 can be automatically focused through setting, and the shooting object at the rear side of the host body 3 can be automatically focused, so that the user can be automatically shot, the convenience of the user can shoot the user, and the convenience of the user can shoot collective photos such as family happiness. The device is provided with a signal lamp 14 which can remind a user of finishing photographing during photographing; and capturing a certain state of the shooting object through a preset first requirement characteristic and a preset second requirement characteristic.

Embodiment 2 is based on embodiment 1, wherein a plurality of persons are present in the photographic subject, or at least one person is combined with at least one non-person body or consists of a plurality of non-person bodies, and the requirement object is a local feature of the person or the non-person body.

The object identification module identifies that at least one essential object exists in the shot objects automatically focused by the automatic focusing camera 5 and counts the number K1 of the essential objects.

the first interest identification module identifies whether a preset first requirement characteristic exists in the shot object or not, counts the number M1 of the first requirement characteristic, and performs comparison analysis on the number M1 of the first requirement characteristic identified by the first interest identification module and the number K1 of the requirement objects, judges whether K1-M1 is smaller than or equal to a first preset value or not, generates a first interest condition if the number is smaller than or equal to the first preset value, and does not generate the first interest condition if the number is not smaller than or equal to the first preset value;

the second interest identification module identifies whether the shot object has a preset second requirement characteristic or not and counts the number M2 of the second requirement characteristic, the second requirement characteristic exists, the other analysis and judgment module is used for judging whether the number M2 of the second requirement characteristic identified by the second interest identification module is compared with the number K1 of the requirement objects, whether the K2-M1 is less than or equal to a second preset value or not is judged, if the number is less than or equal to the second preset value, a second interest condition is generated, and otherwise, the second interest condition is not generated.

The first preset value and the second preset value can be set in advance, and the higher the requirement on the quality of the picture is, the smaller the value set by the first preset value and the second preset value is.

The first requirement characteristic and the second requirement characteristic are preset in advance, and are set according to the local characteristic state of the photographic subject, such as one of a person eye opening state, a person eye closing state, a person smiling face characteristic, a person eye opening characteristic, a person gesture characteristic or a person leg characteristic; a photographer can set a first requirement characteristic and a second requirement characteristic according to the requirement of the photographer on a shot image, if two local characteristics of the shot object are compared, the most important local characteristic of the shot object is set as the first requirement characteristic, and only when K1-M1 is less than or equal to a first preset value, a first interesting condition is generated, and the shooting host 3 can shoot; another local feature of the subject is set as a second requirement feature, and only when K2-M1 is less than or equal to a second preset value, a second interesting condition is generated, and the photographing host 3 performs photographing. The picture shot by the shooting host 3 can meet the requirement of a user on the shot picture to the maximum extent.

The first preset value and the second preset value are both greater than or equal to 0.

The embodiment 2 is suitable for taking a photo album, for example, when an existing shooting host shoots a photo album of people, the shooting host often has several closed eyes, the states of the people in the shooting object are inconsistent, and finally the shot picture has several closed eyes, which causes poor quality.

The purpose of this embodiment 2 is to make the shooting host computer can take the picture that the quality is high, and the setting of analysis and judgment module is used for right when the object is shot, can take a candid photograph to satisfied group, only satisfies specific condition, just can produce the condition of interest, just can take.

Example 3: embodiment 3 is based on embodiment 2, and the intelligent shooting module further includes a voice prompt module;

when the analysis and judgment module judges that K1-M1 is larger than a first preset value, a voice prompt module is started, the voice prompt module sends a preset voice prompt to the shot object, the shot object adjusts the posture after hearing the voice prompt, the automatic focus following camera 5 automatically focuses the shot object again, and when the analysis and judgment module judges that the times of K1-M1 being larger than the first preset value exceed a third preset value L1, the first interest identification module does not generate a first interest condition within a first delay preset time;

and when the analysis and judgment module judges that the K2-M1 is greater than the second preset value, starting the voice prompt module, sending a preset voice prompt to the shot object by the voice prompt module, adjusting the shot object, automatically and repeatedly focusing the shot object by the automatic focusing camera 5, and judging that the second interest recognition module does not generate a second interest condition within a second delay preset time when the analysis and judgment module judges that the times of the K2-M1 which is greater than the second preset value exceed a fourth preset value L2.

The third preset value L1 and the fourth preset value L2 need to be set in advance, when the analysis and judgment module does not generate the first interesting condition or the second interesting condition, after the voice prompt module sends a preset voice prompt to the shooting object, the automatic focus-following camera 5 automatically focuses on the shooting object again, until the analysis and judgment module judges whether the first interesting condition or the second interesting condition is generated again, the length of the required time sets the third preset value L1 and the fourth preset value L2, if the required time is long, the values of the third preset value L1 and the fourth preset value L2 are set to be a little, and the values of the third preset value L1 and the fourth preset value L2 are both greater than or equal to 1.

The voice prompt module is used for prompting the shooting object, enabling the shooting object to know that the posture of the shooting object is not correct, and adjusting, and when the analysis and judgment module judges that K1-M1 is larger than a first preset value or when the analysis and judgment module judges that K2-M1 is larger than a second preset value, the voice prompt module can send a preset voice prompt to the shooting object.

When the analyzing and judging module judges that the times that K1-M1 is greater than the first preset value exceeds a third preset value L1, the first interesting identification module does not generate a first interesting condition within a first delay preset time; or when the analyzing and judging module judges that the times that the K2-M1 is greater than the second preset value exceeds a fourth preset value L2, the second interesting identification module does not generate a second interesting condition within the second preset time delay; through the analysis and judgment module and the voice prompt module, the shooting host 3 can shoot satisfactory photos, and on the other hand, the analysis and judgment module is prevented from falling into the state of judgment for infinite times.

Example 4: embodiment 4 is based on embodiment 3, and the intelligent shooting module further includes two counting control modules;

In this embodiment 4, through the mutual cooperation of the counting control module, the analysis and judgment module and the voice prompt module, when the object to be shot is composed of a plurality of persons or at least one person and at least one non-person body or is composed of a plurality of non-person bodies, if the triggering interest condition is not satisfied, after the voice prompt module reminds, the analysis and judgment module judges that the number of times exceeds the preset value, the first interest identification module and the second interest identification module do not generate the triggering condition any more, and the manual shooting or the software preset timing shooting is directly performed.

Example 5: embodiment 5 is based on

embodiment

1 or 2 or 3 or 4, and further includes a rotary table 15, a side plate 16, a threaded rod 17, a nut 18, a connecting block 19, a support plate 20, a support leg 21, a connecting rod 23 and a ball 24. The number of the side plates 16 is two, and the two side plates 16 are symmetrically arranged on the rotating disc 15. The threaded rod 17 penetrates the two side plates 16 and is rotatably connected with the side plates 16. A nut 18 is provided on the threaded rod 17. Connecting block 19 sets up in 1 bottom of bottom plate, and connecting

block

19 and 1 integrated into one piece of bottom plate, and connecting block 19 cover is established on threaded rod 17, and connecting block 19 rotates with threaded rod 17 to be connected, and connecting block 19 is located between two curb plates 16, and connecting block 19 passes through threaded rod 17 and nut 18 and curb plate 16 fixed connection.

As shown in fig. 8 and 10, the support legs 21 are provided in three, the three support legs 21 are all provided at the bottom of the support plate 20, and the three support legs 21 are evenly distributed around the central axis of the support plate 20. The turntable 15 is disposed on the support plate 20. The bottom of the rotary table 15 is provided with a screw rod 22, the screw rod 22 longitudinally penetrates through the support plate 20, and the screw rod 22 is in threaded connection with the support plate 20. The link 23 is provided at the side of the turntable 15. The ball 24 sets up the one end of keeping away from carousel 15 at connecting rod 23, and through setting up connecting rod 23 and ball 24, convenience of customers rotates carousel 15 to convenience of customers adjusts the height of carousel 15, and then convenience of customers adjusts the height of this device.

When this device used, if the user need follow focus the camera 5's altitude mixture control to the automation, only need rotate group ball 24, group ball 24 drives connecting rod 23 and rotates to drive carousel 15 and rotate, and then drive lead screw 22 and rotate in backup pad 20, and then can adjust the height of carousel 15, and then the height of adjustment automatic camera 5 that follows focus, so that the user shoots the use.

If the shooting angle of the automatic focus tracking camera 5 needs to be adjusted, the knob at one end of the threaded rod 17 only needs to be rotated, the threaded rod 17 is driven to rotate by the knob, the threaded rod 17 is unscrewed, the user can hold the bottom plate 1 to adjust the angle of the bottom plate 1, the connecting block 19 is driven to rotate on the threaded rod 17, and the automatic focus tracking camera 5 is driven to change the angle. The automatic focus tracking camera 5 is adjusted in angle and then the threaded rod 17 is screwed.

Claims

1. The utility model provides an image tracking all-in-one of automatic discernment position which characterized in that: the automatic focusing system comprises a bottom plate (1), a placing frame (2), a host (3), a display screen (4), an automatic focusing camera (5) capable of automatically focusing to a shooting object, a shutter (6) and an intelligent shooting module;

the placing rack (2) is arranged on the bottom plate (1), a placing groove (201) is arranged on the front side of the placing rack (2), and a shooting hole (202) for placing the automatic focus following camera (5) is formed in the inner wall of the placing groove (201);

the main machine (3) is installed in the placing groove (201), the automatic focus following camera (5) is embedded in the upper portion of the rear side of the main machine (3), the display screen (4) is arranged on the front side of the main machine (3), and the shutter (6) is arranged on the lower portion of the front side of the display screen (4);

be provided with treater and memory in host computer (3), memory, display screen (4) and shutter (6) are equallyd divide and do not control with the treater and are connected, and camera (5) of following focus is connected with the treater communication automatically, and the intelligence is shot module and shutter (6) control connection, and the intelligence is shot the module and is used for triggering shutter (6) and makes camera (5) of following focus automatically on host computer (3) right shoot the object.

2. The machine of claim 1, wherein the machine comprises: the intelligent shooting module comprises a software identification module based on a host (3), a shutter trigger module, a continuous shooting trigger module and a deletion module;

after the shutter is triggered, the memory stores the image shot by the host (3);

the first identity of interest module has a higher priority than the second identity of interest module;

the automatic focus tracking camera (5) is used as a sensor of the software identification module;

after the automatic focus tracking camera (5) automatically tracks the shot object, the object identification module identifies whether at least one essential object exists in the shot object after the automatic focus tracking camera (5) automatically tracks the shot object;

the method comprises the steps that a first interesting identification module is started, the first interesting identification module identifies whether a shooting object has a preset first requirement characteristic or not within a first preset time delay, if yes, a first interesting condition is generated, then an intelligent shooting module jointly generates a condition according to the first interesting condition and a shutter trigger module, a continuous shooting trigger module and a deleting module are started, and if not, a second interesting identification module is started after the first interesting condition is not generated;

in a second preset time delay, a second interest identification module identifies whether the shot object has a preset second requirement characteristic, if so, a second interest condition is generated, and then the intelligent shooting module starts a continuous shooting triggering module and a deleting module according to the condition generated by the second interest condition and the shutter triggering module together;

the continuous shooting trigger module can send out a signal for triggering the shutter for multiple times after being triggered, the processor receives the signal for triggering the shutter for multiple times and controls the shutter trigger module after processing the signal, and the shutter trigger module executes continuous shooting trigger shutter operation;

the deleting module identifies images and calculates the image quality according to the images shot by the host (3) after the continuous shooting trigger module is started, compares the calculated weight value with a preset weight, deletes the images lower than the preset weight, retains the images higher than the preset weight, and automatically finishes shooting.

3. The machine of claim 2, wherein the machine comprises: the shooting object is selected from one or any combination of at least one person or at least one non-human object.

4. An image tracking kiosk with automatic position recognition as recited in claim 3, wherein: the photographic subject is selected from at least one person, and the first requirement characteristic and the second requirement characteristic are independently selected from one of a smiling face characteristic of the person, an eye opening characteristic of the person, a gesture characteristic of the person or a leg characteristic of the person.

5. The machine of claim 2, wherein the machine comprises: the deleting module is used for deleting the low-quality images shot by the host (3);

the sharpness is calculated according to the sharpness formula:

6. The machine of claim 2, wherein the machine comprises: the shooting object comprises a plurality of persons, or at least one person and at least one non-person body which are combined or composed of a plurality of non-person bodies, and the requirement object is a local feature of the persons or the non-person bodies;

the object identification module identifies that at least one essential object exists in the shot objects automatically focused by the automatic focusing camera (5) and counts the number K1 of the essential objects;

the second interest identification module identifies whether the shot object has a preset second requirement characteristic or not and counts the number M2 of the second requirement characteristic, the second requirement characteristic exists, the other analysis and judgment module is used for judging whether the number M2 of the second requirement characteristic identified by the second interest identification module is compared with the number K1 of the requirement objects, whether the number K2-M1 is smaller than or equal to a second preset value or not is judged, if so, a second interest condition is generated, and otherwise, the second interest condition is not generated.

7. The machine of claim 2, wherein the machine comprises: the shutter trigger module comprises a control box (7), a magnet (8), a pressing contact rod (9), a return spring (11) and an electromagnet (12);

the control box (7) is arranged on the bottom plate (1), and a cavity (701) is arranged in the control box (7);

the magnet (8) is arranged in the cavity (701) in a sliding mode, the electromagnet (12) is arranged in the cavity (701), the electromagnet (12) is located on one side, away from the shutter (6), of the magnet (8), the electromagnet (12) is in magnetic connection with the magnet (8), and the processor is in control connection with the electromagnet (12);

the reset spring (11) is arranged in the cavity (701), and two ends of the reset spring (11) are respectively connected with the magnet (8) and the inner wall of one side of the cavity (701) close to the shutter (6);

the press contact rod (9) penetrates through the rear side of the control box (7) and is arranged on the magnet (8), the press contact rod (9) is in sliding connection with the control box (7), and the press contact rod (9) and the shutter (6) are located at the same height.

8. The machine of claim 6, wherein the machine further comprises: the intelligent shooting module also comprises a voice prompt module;

when the analysis and judgment module judges that K1-M1 is larger than a first preset value, a voice prompt module is started, the voice prompt module sends a preset voice prompt to the shot object, the shot object adjusts the posture after hearing the voice prompt, the automatic focus following camera (5) automatically focuses the shot object again, and when the analysis and judgment module judges that the times of K1-M1 being larger than the first preset value exceed a third preset value L1, the first interest recognition module does not generate a first interest condition within a first delay preset time;

and when the analysis and judgment module judges that the K2-M1 is greater than the second preset value, the voice prompt module is started, the voice prompt module sends a preset voice prompt to the shot object, the shot object is adjusted, the automatic focus tracking camera (5) automatically tracks the shot object again, and when the analysis and judgment module judges that the times of the K2-M1 being greater than the second preset value exceed a fourth preset value L2, the second interest recognition module does not generate a second interest condition within the second preset delay time.

9. An image tracking kiosk for automatically identifying location as recited in claim 8, wherein: when the analysis and judgment module judges that K2-M1 is larger than a second preset value, a voice prompt module is started, and the voice prompt module sends a preset voice prompt to the shooting object;

after the shooting object hears the voice prompt and adjusts the posture of the shooting object, then the automatic focus-following camera (5) automatically focuses on the shooting object again, the object identification module identifies that at least one essential object exists in the shooting object automatically focused by the automatic focus-following camera (5), the intelligent shooting module starts timing from zero, the second interest identification module starts until the times that the analysis and judgment module judges that the K2-M1 is larger than the second preset value exceed a fourth preset value L2, the second interest identification module does not generate a second interest condition, or the analysis and judgment module judges that the K2-M1 is smaller than the second preset value, the second interest identification module generates the second interest condition, and the analysis and judgment module does not judge whether the K2-M1 is smaller than the second preset value.

10. An image tracking kiosk for automatically identifying location as recited in claim 9, wherein: the intelligent shooting module also comprises two counting control modules;