CN112995503B - Gesture control panoramic image acquisition method and device, electronic equipment and storage medium - Google Patents
Gesture control panoramic image acquisition method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112995503B CN112995503B CN202110170062.7A CN202110170062A CN112995503B CN 112995503 B CN112995503 B CN 112995503B CN 202110170062 A CN202110170062 A CN 202110170062A CN 112995503 B CN112995503 B CN 112995503B
- Authority
- CN
- China
- Prior art keywords
- shooting
- image
- gesture
- panoramic
- target
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/62—Control of parameters via user interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/63—Control of cameras or camera modules by using electronic viewfinders
- H04N23/631—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters
- H04N23/632—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters for displaying or modifying preview images prior to image capturing, e.g. variety of image resolutions or capturing parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Studio Devices (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application provides a gesture control panoramic image acquisition method and device, electronic equipment and a storage medium, and relates to the field of image processing. The method comprises the following steps: recognizing a designated gesture of a photographic target in a photographic image; performing panoramic shooting based on the designated gesture; determining the splicing position of each image in panoramic splicing based on the corresponding holder angle and/or hand position when the image of the shooting target is obtained in panoramic shooting each time; and carrying out panoramic stitching on all images of the shooting target based on the stitching position of each image in the panoramic stitching. The panoramic stitching is carried out by determining the position of the stitching part based on the corresponding holder angle and/or the hand position when the image of the target is shot, so that the image stitching efficiency and accuracy are improved.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a gesture control panoramic image acquisition method and device, electronic equipment and a storage medium.
Background
The panoramic picture splicing is called panoramic splicing, and is to perform stitching processing on an image shot by a digital camera so as to obtain a panoramic picture, wherein the splicing refers to the process of using a common camera to shoot a plurality of overlapped source images continuously in the same scene, and the common camera fuses the source images to generate an image with a larger view field angle.
The existing panoramic image splicing mode is generally to realize the splicing of two adjacent images after feature point matching is carried out on the overlapped parts of different images, and the problem of low efficiency or low accuracy exists in the feature point matching calculation of the overlapped parts of different images when the image complexity is higher or the overlap degree is lower.
Disclosure of Invention
In view of the above, an object of the embodiments of the present application is to provide a method and an apparatus for acquiring a panoramic image through gesture control, an electronic device, and a storage medium, so as to solve the problem in the prior art that when the complexity of an image is high or the degree of overlap is low, the efficiency or accuracy of feature point matching calculation of overlapping portions of different images is low.
The embodiment of the application provides a gesture control panoramic image acquisition method, which comprises the following steps: recognizing a designated gesture of a photographic target in a photographic image; performing panoramic shooting based on the designated gesture; determining the splicing position of each image in panoramic splicing based on the corresponding holder angle and/or hand position when the image of the shooting target is obtained in panoramic shooting each time; and carrying out panoramic stitching on all images of the shooting target based on the stitching position of each image in the panoramic stitching.
In the implementation mode, the position of the splicing position is determined to perform panoramic splicing based on the holder angle and/or the hand position corresponding to the shooting target image, and the method has higher splicing efficiency and higher splicing accuracy compared with the method for determining the splicing position based on the feature matching of the overlapped parts of different images.
Optionally, the performing panorama shooting based on the designated gesture includes: and acquiring an image of the shooting target each time the designated shooting gesture is recognized.
In the implementation mode, the image acquisition is controlled by specifying the shooting gesture, so that the shooting control steps are simplified, and the image shooting efficiency is improved.
Optionally, the acquiring an image of the shooting target each time a designated shooting gesture is recognized includes: when the appointed shooting gesture is recognized each time, recognizing whether the shooting target keeps the appointed shooting gesture; and when the shooting target does not keep the specified shooting gesture, acquiring an image of the shooting target.
In the implementation mode, whether the designated shooting gesture is kept by the shooting target is recognized when the designated shooting gesture is recognized, and image acquisition is carried out after the designated shooting gesture is not kept by the shooting target, so that the situation that the shooting image is obtained when the shooting target is in the designated shooting gesture which is not a gesture required to be shot by the shooting target generally is avoided, and the accuracy of image acquisition is improved.
Optionally, the acquiring an image of the shooting target each time a designated shooting gesture is recognized includes: carrying out target following on the shooting target; and when the appointed shooting gesture is recognized each time, adjusting the position of the holder to enable the shooting target to be positioned at the center of the image, and acquiring the image of the shooting target.
In the implementation mode, the position of the holder is adjusted by the target following so that the shot target is positioned at the center of the image and then the image is obtained, and the accuracy of obtaining the image of the shot target is improved.
Optionally, the performing panorama shooting based on the designated gesture includes: when the appointed starting gesture is recognized, starting panoramic shooting; determining the body position information of the shooting target in an image; determining a rotational angle of the holder based on the position information; shooting an image after the lens rotates the rotational angle of the holder; and when the designated stop gesture is recognized, stopping panoramic shooting.
In the implementation mode, the cradle head is rotated through the body position information of the shooting target in the image so that the shooting target is in a position which is favorable for shooting and imaging in the image, and the problem that the shooting angle cannot follow the shooting target or the proper image of the shooting target cannot be obtained due to too large or too small rotation angle is avoided.
Optionally, the determining the position information of the shooting target in the image includes: and determining the pixel number occupied by the shooting target in the image based on a pedestrian detection and segmentation algorithm, and taking the pixel number as the position information representing the position size.
In the implementation mode, the number of pixels occupied by the shooting target in the image is determined as the position information based on the pedestrian detection and segmentation algorithm, so that the relation between the current shooting target in the image and the current view field angle of the camera can be accurately judged, and the position of the shooting target in the current image can be accurately acquired.
Optionally, the determining a rotational angle of the pan/tilt head based on the body position information includes: dividing the position information by the transverse resolution of the image, and taking the result multiplied by the transverse field angle as a position angle; and setting and controlling the rotation angle of the holder to be the body position angle of the preset number based on angle adjustment.
In the implementation mode, the shooting angle is rotated by the preset individual body position angle after the image is shot every time, so that the matching of the image of the next shooting angle and the distance of the current shooting target can be ensured, and the shooting target can be accurately framed in the image of the next shooting angle.
The embodiment of the present application further provides a gesture control panoramic image acquisition device, the device includes: the gesture recognition module is used for recognizing the designated gesture of the shooting target in the shot image; the shooting module is used for carrying out panoramic shooting based on the specified gesture; the splicing identification module is used for determining the splicing position of each image in panoramic splicing based on the holder angle and/or the hand position corresponding to the shooting target image acquired each time in the panoramic shooting; and the splicing module is used for carrying out panoramic splicing on all images of the shooting target based on the splicing position of each image in the panoramic splicing.
In the implementation mode, the position of the splicing position is determined to carry out panoramic splicing based on the holder angle and/or the hand position corresponding to the shooting of the image of the target, and compared with the method for determining the splicing position based on the characteristic matching of the overlapped parts of different images, the method has the advantages of higher splicing efficiency and higher splicing accuracy.
Optionally, the shooting module is specifically configured to: and acquiring an image of the shooting target each time the designated shooting gesture is recognized.
In the implementation mode, the image acquisition is controlled by specifying the shooting gesture, so that the shooting control steps are simplified, and the image shooting efficiency is improved.
Optionally, the shooting module is specifically configured to: identifying whether the shooting target keeps the specified shooting gesture each time the specified shooting gesture is identified; and when the shooting target does not keep the specified shooting gesture, acquiring an image of the shooting target.
In the implementation mode, whether the designated shooting gesture is kept by the shooting target is recognized when the designated shooting gesture is recognized, and image acquisition is carried out after the designated shooting gesture is not kept by the shooting target, so that the situation that the shooting image is obtained when the shooting target is in the designated shooting gesture which is not a gesture required to be shot by the shooting target generally is avoided, and the accuracy of image acquisition is improved.
Optionally, the shooting module is specifically configured to: carrying out target following on the shooting target; and when the appointed shooting gesture is recognized each time, adjusting the position of the holder to enable the shooting target to be positioned at the center of the image, and acquiring the image of the shooting target.
In the implementation mode, the position of the holder is adjusted by the target following so that the shot target is positioned at the center of the image and then the image is obtained, and the accuracy of obtaining the image of the shot target is improved.
Optionally, the shooting module is specifically configured to: when the appointed starting gesture is recognized, starting panoramic shooting; determining the body position information of the shooting target in an image; determining a rotational angle of the holder based on the position information; shooting an image after the lens rotates the rotational angle of the holder; and when the designated stop gesture is recognized, stopping panoramic shooting.
In the implementation mode, the cradle head is rotated through the body position information of the shooting target in the image so that the shooting target is in a position which is favorable for shooting and imaging in the image, and the problem that the shooting angle cannot follow the shooting target or the proper image of the shooting target cannot be obtained due to too large or too small rotation angle is avoided.
Optionally, the shooting module is specifically configured to: and determining the pixel number occupied by the shooting target in the image based on a pedestrian detection and segmentation algorithm, and taking the pixel number as the position information representing the position size.
In the implementation mode, the number of pixels occupied by the shooting target in the image is determined as the position information based on the pedestrian detection and segmentation algorithm, so that the relation between the current shooting target in the image and the current view field angle of the camera can be accurately judged, and the position size of the shooting target in the current image can be accurately acquired.
Optionally, the shooting module is specifically configured to: dividing the position information by the transverse resolution of the image, and taking the result multiplied by the transverse field angle as a position angle; and setting and controlling the rotation angle of the holder to be the body position angle of the preset number based on angle adjustment.
In the implementation mode, the shooting angle is rotated by the preset individual body position angle after the image is shot every time, so that the matching of the image of the next shooting angle and the distance of the current shooting target can be ensured, and the shooting target can be accurately framed in the image of the next shooting angle.
An embodiment of the present application further provides an electronic device, where the electronic device includes a memory and a processor, where the memory stores program instructions, and the processor executes the steps in any one of the foregoing implementation manners when reading and executing the program instructions.
The embodiment of the present application further provides a readable storage medium, in which computer program instructions are stored, and the computer program instructions are read by a processor and executed to perform the steps in any of the above implementation manners.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of a method for acquiring a panoramic image through gesture control according to an embodiment of the present disclosure.
Fig. 2 is a schematic flowchart of a panoramic shooting step performed based on a designated gesture according to an embodiment of the present disclosure.
Fig. 3 is a schematic block diagram of a gesture-controlled panoramic image capturing apparatus according to an embodiment of the present disclosure.
Icon: 20-controlling the panoramic image acquisition device by gestures; 21-a gesture recognition module; 22-a shooting module; 23-a splice identification module; 24-splicing modules.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
An embodiment of the present application provides a method for acquiring a panoramic image through gesture control, please refer to fig. 1, where fig. 1 is a schematic flowchart of the method for acquiring a panoramic image through gesture control provided in the embodiment of the present application, and the method for acquiring a panoramic image through gesture control may include the following specific steps:
step S12: a designated gesture of a photographic subject in a photographic image is recognized.
Optionally, the embodiment may perform gesture recognition on a network based on a Neural network, and generally, the steps may be divided into gesture segmentation and gesture recognition, where the gesture segmentation may extract a palm contour by using image binarization and a gaussian skin color model algorithm based on a local adaptive threshold, and the gesture recognition may perform CNN (Convolutional Neural network) training on a gesture image segmented by using the gesture to obtain a relatively stable network, and then input a new image for classification and output. The CNN may be a convolutional neural network based on Keras, which is a very simple and highly modular neural network library, and contributes to rapid development of CNNs.
Alternatively, the designated gesture in this embodiment may be a designated shooting gesture indicating to shoot at the current time, a designated starting gesture indicating to start panoramic shooting, a designated stopping gesture indicating to stop panoramic shooting, a designated rotating gesture indicating to rotate a shooting angle, and the like, and different designated gestures may be set according to specific requirements, for example, the designated shooting gesture may be a two-hand fist making or a two-hand five-finger spread facing the lens, and the like.
Step S14: and carrying out panoramic shooting based on the designated gesture.
Alternatively, the present embodiment may control the start and stop of the panoramic shooting only by gestures, for example, start the image shooting when a specified start gesture is recognized, and rotate to the next shooting angle according to a preset angle and a preset interval time after each shooting until the maximum shooting angle is reached or the panoramic shooting is stopped when a specified stop gesture is recognized.
It should be understood that the panorama photographing process may also be a continuous photographing based on a photographing trajectory directly preset by the user.
Optionally, the embodiment may also control the whole process of the panoramic control through a gesture, for example, in the automatic rotation process of the pan/tilt head, shooting is started after a specified gesture indicating that shooting is started is recognized, and shooting is stopped after a specified gesture indicating that shooting is stopped is recognized.
As an optional implementation manner, in this embodiment, the manner of performing panoramic shooting based on gesture control may also be that an image of the shooting target is acquired each time a specified shooting gesture is recognized.
It should be understood that the different manners for stitching panoramic image capturing based on gesture control provided by the present embodiment may be combined arbitrarily, for example, a maximum capturing angle is allowed to be set during gesture capturing, capturing is stopped when the maximum capturing angle is reached, and trajectory capturing and fixed angle capturing are combined with each other.
Specifically, the specific steps of shooting based on the designated shooting gesture may be as follows:
step S141: and identifying whether the shooting target keeps the specified shooting gesture or not every time the specified shooting gesture is identified.
It should be understood that, since it is necessary to trigger the shooting action on the shooting target when the designated shooting gesture is recognized, the shooting target needs to be in the shooting picture at any time, so the present embodiment keeps the shooting target in the shooting picture by means of target following, specifically: carrying out target following on the shooting target; and when the appointed shooting gesture is recognized each time, adjusting the position of the holder to enable the shooting target to be positioned at the center of the image, and acquiring the image of the shooting target.
Step S142: when the shooting target does not keep the designated shooting gesture, acquiring an image of the shooting target.
Since the designated shooting gesture is not usually the gesture in which the shooting target needs to be shot, the shooting is performed again in step S142 when the shooting target does not maintain the designated shooting gesture, so that the shooting target can be ensured to adjust the gesture within the delay time, and an image with the required shooting gesture is obtained.
For example, steps S141 and S142 are described below, where the above steps require a user to start triggering through an application program or a hardware button before object following, then perform gesture recognition, start shooting a panoramic image when a specific gesture indicating that panoramic shooting is to be started is recognized, note that the gesture of the shooting object needs to be continuously recognized at this time, enter a shooting preparation state after a hand of the shooting object is put down, and prompt the user that the shooting object is currently in the shooting preparation state through voice and/or an indicator light after the hand of the shooting object is put down is recognized, and shoot a first image. And then, carrying out target following on the shot target, adjusting the position of the holder by the holder according to the target following result, carrying out secondary shooting when the shot target is positioned at the center of the shot picture, and then exiting from the target following mode.
And after exiting the target following mode, if an appointed gesture representing continuous shooting is identified, continuing the target following and shooting of the flow for the person who makes the appointed gesture, and if the person exits the panoramic shooting, waiting for the follow-up steps to splice the panoramic images.
As an alternative embodiment, in the manner of controlling the start and the end of the panoramic shooting through gestures, it is considered that the problem that a complete shooting target cannot be shot or the imaging of the shooting target is too small in the case that the shooting target is too far away or too close to the camera due to the limitation of the view field angle or due to the limitation of the field range, or the problem that the shooting target image cannot be accurately acquired due to the too large or too small rotation angle after each shooting of the panoramic shooting is performed is often solved. Therefore, the embodiment may also set the rotation angle after each shooting based on the body position information of the shooting target in the image, so as to ensure that the shooting target is located at a suitable position in the image, and the specific steps may be as shown in fig. 2, where fig. 2 is a schematic flow diagram of the panoramic shooting step based on the designated gesture provided by the embodiment of the present application, and the specific steps may be as follows:
step S143: and when the appointed starting gesture is recognized, starting panoramic shooting.
Step S144: and determining the position information of the shooting target in the image.
Specifically, width information (the number of pixels that the photographic target actually occupies in the image) of the photographic target (the pedestrian making the specified gesture) is determined based on a pedestrian detection and segmentation algorithm, while the field angle and the image resolution of the camera are known, and then the image percentage or angle information that the current photographic target occupies is calculated, taking the number of pixels as the body position information representing the body position size.
Optionally, the Pedestrian Detection (Pedestrian Detection) in this embodiment uses a computer vision technology to determine whether there is a Pedestrian in an image or a video sequence and to give accurate positioning, which may be a Pedestrian Detection mode based on global features, a Pedestrian Detection mode based on human body parts, a Pedestrian Detection mode based on stereoscopic vision, or the like.
After the shot target is determined through pedestrian detection, the shot target is accurately segmented by adopting a segmentation algorithm, so that the number of pixels occupied by the shot target in an image can be calculated. Alternatively, the segmentation algorithm in this implementation may be a region growing-based segmentation algorithm, a mean iterative segmentation algorithm, a maximum inter-class variance segmentation algorithm, or a maximum entropy segmentation algorithm, etc.
Step S145: and determining the rotation angle of the holder based on the body position information.
Specifically, the step of determining the rotational angle of the holder may be: dividing the position information by the transverse resolution of the image, and taking the result multiplied by the transverse field angle as a position angle; and setting the rotating angles of the control holder to be the preset number of body position angles based on angle adjustment. For example, if the preset number of body position angles of the cradle head set by the user for carrying out cradle head rotation angle adjustment each time is 5, the information is converted into specific angle information so as to control the cradle head to adjust to a fixed angle.
Optionally, one-body-angle = one-body-occupied pixel information/image resolution (image width) × camera-lateral field angle.
Step S146: and shooting an image after the lens rotates by the rotation angle of the holder.
After the lens rotates each rotational angle of the holder, the rotational angle of the holder is determined based on the body position information of the shot target in the image, and the distance between the shot target and the lens can be adapted, so that the shot target can be more accurately positioned in the middle of the image after the lens rotates each rotational angle of the holder, and the shooting imaging effect is improved.
Step S147: and when the designated stop gesture is recognized, stopping panoramic shooting.
When the rotational angle of the holder is adjusted based on the body position information of the shot target, the holder can be rotated in the vertical direction based on the size of the shot target occupying the image in the vertical direction in addition to the adjustment in the horizontal direction. For example, the result of dividing the position information by the longitudinal resolution of the image and multiplying the result by the longitudinal field angle is used as a longitudinal position angle; and setting the longitudinal body position angles of the control holder to be a preset number based on the angle adjustment.
It should be understood that steps S141-S142 and steps S143-S147 are not sequential in execution, but are parallel in optionally different execution manners.
Step S16: and determining the splicing position of each image in panoramic splicing based on the corresponding holder angle and/or hand position when the image of the shooting target is acquired in the panoramic shooting each time.
In the shooting process of the embodiment, the angle information of the holder and the position information of the hand recognized each time are recorded, the position relation between the two images is determined according to the hand position recognized by the gesture, the splicing position between the two images is determined, the searching time of the panoramic splicing position is shortened, meanwhile, the probability of mismatching is reduced, the problem of misdetection splicing of repetitive texture positions is reduced, and therefore the speed and the precision of panoramic splicing are improved.
Optionally, in the panoramic shooting process, the holder is ensured to be always in a horizontal state, and the distortion problem existing between images under different rotation angles is prevented.
Step S18: and carrying out panoramic stitching on all images of the shooting target based on the stitching position of each image in the panoramic stitching.
The panoramic stitching mode of the embodiment can adopt a common stitching algorithm to carry out image matching, image stitching and image fusion on images shot at different angles.
The image matching may be a Feature-independent matching method, such as correlation matching, or may be performed according to features, for example, feature points in adjacent pictures are matched according to local Feature points in material pictures such as SIFT (Scale-invariant Feature transform) and SURF (Speed Up Robust Feature), and an inter-image projection transformation matrix is estimated to perform image matching.
And image splicing is to splice the shot images shot at different angles together according to the mutual relation obtained by image matching.
In order to cooperate with the above-mentioned gesture-controlled panoramic image acquisition method provided in this embodiment, an embodiment of the present application further provides a gesture-controlled panoramic image acquisition apparatus 20.
Referring to fig. 3, fig. 3 is a schematic block diagram of a gesture-controlled panoramic image capturing apparatus according to an embodiment of the present disclosure.
The gesture control panoramic image capturing apparatus 20 includes:
a gesture recognition module 21 for recognizing a designated gesture of a photographic subject in a photographic image;
a shooting module 22, configured to perform panoramic shooting based on the designated gesture;
the splicing identification module 23 is configured to determine a splicing position of each image in panoramic splicing based on a cradle head angle and/or a hand position corresponding to each time when an image of a shooting target is acquired in panoramic shooting;
and the splicing module 24 is configured to perform panoramic splicing on all images of the shooting target based on the position of the spliced position of each image in the panoramic splicing.
Optionally, the shooting module 22 is specifically configured to: each time a designated photographing gesture is recognized, an image of a photographing target is acquired.
Optionally, the shooting module 22 is specifically configured to: when the appointed shooting gesture is recognized each time, whether the shooting target keeps the appointed shooting gesture is recognized; and when the shooting target does not keep the designated shooting gesture, acquiring an image of the shooting target.
Optionally, the shooting module 22 is specifically configured to: carrying out target following on the shooting target; and when the appointed shooting gesture is recognized each time, adjusting the position of the holder to enable the shooting target to be positioned at the center of the image, and acquiring the image of the shooting target.
Optionally, the shooting module 22 is specifically configured to: when the appointed starting gesture is recognized, starting panoramic shooting; determining the body position information of a shooting target in an image; determining the rotation angle of the holder based on the body position information; after the lens rotates by the rotation angle of the holder, shooting an image; and when the designated stop gesture is recognized, stopping panoramic shooting.
Optionally, the shooting module 22 is specifically configured to: and determining the pixel number occupied by the shooting target in the image based on a pedestrian detection and segmentation algorithm, and taking the pixel number as the body position information representing the body position size.
Optionally, the shooting module 22 is specifically configured to: dividing the position information by the transverse resolution of the image, and taking the result multiplied by the transverse field angle as a position angle; and setting the rotating angles of the control holder to be the preset number of body position angles based on angle adjustment.
The embodiment of the application further provides electronic equipment, which comprises a memory and a processor, wherein program instructions are stored in the memory, and when the processor reads and runs the program instructions, the steps in any one of the methods for acquiring the panoramic image through gesture control provided by the embodiment are executed.
It should be understood that the electronic device may be a Personal Computer (PC), a tablet PC, a smart phone, a Personal Digital Assistant (PDA), or other electronic devices having a logic calculation function.
The embodiment of the application also provides a readable storage medium, wherein computer program instructions are stored in the readable storage medium, and when the computer program instructions are read and run by a processor, the steps in the method for controlling the acquisition of the panoramic image through the gestures are executed.
To sum up, the embodiment of the present application provides a method and an apparatus for acquiring a panoramic image through gesture control, an electronic device, and a storage medium, where the method includes: recognizing a designated gesture of a photographic target in a photographic image; performing panoramic shooting based on the designated gesture; determining the splicing position of each image in panoramic splicing based on the corresponding holder angle and/or hand position when the image of the shooting target is obtained in panoramic shooting each time; and carrying out panoramic stitching on all images of the shooting target based on the stitching position of each image in the panoramic stitching.
In the implementation mode, the position of the splicing position is determined to perform panoramic splicing based on the holder angle and/or the hand position corresponding to the shooting target image, and the method has higher splicing efficiency and higher splicing accuracy compared with the method for determining the splicing position based on the feature matching of the overlapped parts of different images.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. The apparatus embodiments described above are merely illustrative, and for example, the block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of devices according to various embodiments of the present application. In this regard, each block in the block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams, and combinations of blocks in the block diagrams, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. The present embodiment further provides a readable storage medium, which stores computer program instructions, and when the computer program instructions are read and executed by a processor, the computer program instructions perform the steps of any one of the block data storage methods. Based on such understanding, the technical solutions of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a portable hard disk, a Read-Only Memory (ROM), a RanDom Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
Claims (9)
1. A gesture-controlled panoramic image acquisition method, the method comprising:
recognizing a designated gesture of a photographic target in a photographic image;
panoramic shooting is carried out based on the designated gesture, and the panoramic shooting comprises the following steps: when the appointed starting gesture is recognized, starting panoramic shooting; determining the position information of the shooting target in the image; determining a rotational angle of the holder based on the position information; shooting an image after the lens rotates the rotational angle of the holder; stopping panoramic shooting when a specified stopping gesture is recognized;
determining the splicing position of each image in panoramic splicing based on the corresponding holder angle and/or hand position when the image of the shooting target is obtained in panoramic shooting each time;
and carrying out panoramic stitching on all images of the shooting target based on the stitching position of each image in the panoramic stitching.
2. The method of claim 1, wherein panning based on the specified gesture comprises:
and acquiring an image of the shooting target each time the designated shooting gesture is recognized.
3. The method according to claim 2, wherein the acquiring the image of the photographic target each time the designated photographic gesture is recognized comprises:
identifying whether the shooting target keeps the specified shooting gesture each time the specified shooting gesture is identified;
and when the shooting target does not keep the specified shooting gesture, acquiring an image of the shooting target.
4. The method of claim 2, wherein the acquiring the image of the photographic target each time the designated photographic gesture is recognized comprises:
carrying out target following on the shooting target;
and when the appointed shooting gesture is recognized each time, adjusting the position of the holder to enable the shooting target to be positioned at the center of the image, and acquiring the image of the shooting target.
5. The method according to claim 1, wherein the determining the position information of the photographic target in the image comprises:
and determining the pixel number occupied by the shooting target in the image based on a pedestrian detection and segmentation algorithm, and taking the pixel number as the position information representing the position size.
6. The method according to claim 1 or 5, wherein said determining a pan-tilt angle based on said position information comprises:
dividing the position information by the transverse resolution of the image, and taking the result multiplied by the transverse field angle as a position angle;
and setting and controlling the rotation angle of the holder to be the body position angle of the preset number based on angle adjustment.
7. A gesture-controlled panoramic image capture apparatus, the apparatus comprising:
the gesture recognition module is used for recognizing the designated gesture of the shooting target in the shot image;
the shooting module is used for carrying out panoramic shooting based on the specified gesture;
the shooting module is further configured to: when the appointed starting gesture is recognized, starting panoramic shooting; determining the position information of the shooting target in the image; determining a rotational angle of the holder based on the position information; shooting an image after the lens rotates the rotational angle of the holder; stopping panoramic shooting when a specified stopping gesture is recognized;
the splicing identification module is used for determining the splicing position of each image in panoramic splicing based on the holder angle and/or the hand position corresponding to the shooting target image acquired each time in the panoramic shooting;
and the splicing module is used for carrying out panoramic splicing on all images of the shooting target based on the splicing position of each image in the panoramic splicing.
8. An electronic device comprising a memory having stored therein program instructions and a processor that, when executed, performs the steps of the method of any of claims 1-6.
9. A readable storage medium having stored thereon computer program instructions which, when executed by a processor, perform the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110170062.7A CN112995503B (en) | 2021-02-07 | 2021-02-07 | Gesture control panoramic image acquisition method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110170062.7A CN112995503B (en) | 2021-02-07 | 2021-02-07 | Gesture control panoramic image acquisition method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112995503A CN112995503A (en) | 2021-06-18 |
| CN112995503B true CN112995503B (en) | 2023-04-07 |
Family
ID=76349100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110170062.7A Active CN112995503B (en) | 2021-02-07 | 2021-02-07 | Gesture control panoramic image acquisition method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112995503B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113938605A (en) * | 2021-09-23 | 2022-01-14 | 维沃移动通信有限公司 | Photographing method, device, equipment and medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BR122016017488A2 (en) * | 2013-12-13 | 2019-08-27 | Huawei Device Shenzhen Co Ltd | method and terminal for panoramic image acquisition |
| CN105627991B (en) * | 2015-12-21 | 2017-12-12 | 武汉大学 | A kind of unmanned plane image real time panoramic joining method and system |
| WO2019023914A1 (en) * | 2017-07-31 | 2019-02-07 | 深圳市大疆创新科技有限公司 | Image processing method, unmanned aerial vehicle, ground console, and image processing system thereof |
| CN109076161B (en) * | 2017-12-29 | 2021-11-02 | 深圳市大疆创新科技有限公司 | Image processing method, mobile platform, control equipment and system |
| CN111031202A (en) * | 2019-11-25 | 2020-04-17 | 长春理工大学 | Intelligent photographing unmanned aerial vehicle based on four rotors, intelligent photographing system and method |
-
2021
- 2021-02-07 CN CN202110170062.7A patent/CN112995503B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112995503A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107087107B (en) | Image processing apparatus and method based on dual camera | |
| EP3236391B1 (en) | Object detection and recognition under out of focus conditions | |
| US7034848B2 (en) | System and method for automatically cropping graphical images | |
| US9813607B2 (en) | Method and apparatus for image capture targeting | |
| CN107770452B (en) | Photographing method, terminal and related medium product | |
| JP4757173B2 (en) | Imaging apparatus, control method thereof, and program | |
| CN107395957B (en) | Photographing method and device, storage medium and electronic equipment | |
| US8577098B2 (en) | Apparatus, method and program for designating an object image to be registered | |
| CN109451240B (en) | Focusing method, focusing device, computer equipment and readable storage medium | |
| CN112887609B (en) | Shooting method and device, electronic equipment and storage medium | |
| US10666858B2 (en) | Deep-learning-based system to assist camera autofocus | |
| CN108600610A (en) | Shoot householder method and device | |
| CN110213492B (en) | Device imaging method and device, storage medium and electronic device | |
| CN113873166A (en) | Video shooting method and device, electronic equipment and readable storage medium | |
| CN114390201A (en) | Focusing method and device thereof | |
| WO2019084756A1 (en) | Image processing method and device, and aerial vehicle | |
| CN112995503B (en) | Gesture control panoramic image acquisition method and device, electronic equipment and storage medium | |
| JP5159390B2 (en) | Object detection method and apparatus | |
| TW201421101A (en) | Method for automatically focusing on specific movable object, photographic apparatus including automatic focus function, and computer readable storage media for storing automatic focus function program | |
| CN115022549B (en) | Shooting composition method, shooting composition device, computer equipment and storage medium | |
| CN112219218A (en) | Method and electronic device for recommending image capture mode | |
| CN115623313A (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
| JP2019185541A (en) | Image processing apparatus, image processing method, and program | |
| JP2019071047A (en) | Method, system and device for selecting frame of video sequence | |
| CN113691731B (en) | Processing method and device and electronic equipment |
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 |