Target shooting method and device, electronic equipment and storage medium
By adding a moving device to the target shooting device and using posture estimation and motion control modules to achieve flexible adjustment of shooting orientation, the problems of limited shooting methods and poor scene adaptability in the prior art are solved, and the scene applicability of the equipment is improved.
Patent Information
- Application Number
- CN202411062086.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-01
AI Technical Summary
The existing target shooting equipment has limited shooting methods and cannot flexibly adjust the lens orientation, resulting in poor scene adaptability and inability to meet the shooting needs of diverse scenes.
By adding a motion device to the target shooting device, using the posture estimation module and the motion control module, the motion device is controlled to move the motion device according to the posture estimation result and reference posture of the shooting target, thereby achieving flexible adjustment of the shooting orientation.
It improves the freedom of movement and scene applicability of the target shooting equipment, and can achieve accurate target shooting in a variety of scenes.
Smart Images

Figure CN118890551A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of machine vision technology, and in particular to a method, device, electronic equipment and storage medium for photographing a target. Background Art
[0002] Currently, the shooting of targets such as animals and vehicles is usually achieved based on a pan-tilt camera, which can track the target and shoot the target by rotating the lens.
[0003] However, in the prior art, the lens position of the pan-tilt camera cannot be adjusted. In some shooting scenarios, such as capturing facial images, it is necessary not only to control the rotation angle of the lens, but also to adjust the lens position so that the lens can capture images of specific positions of the target, such as frontal images of the face.
[0004] Therefore, a target shooting solution that can adjust the shooting direction of the lens is needed to achieve multi-dimensional visual perception and meet the target shooting needs of diverse scenes. Summary of the invention
[0005] The present invention provides a target shooting method, device, equipment and storage medium to solve the problems of limited target shooting modes and poor scene adaptability of existing target shooting equipment. By adding a motion device to the target shooting device, the target shooting device can achieve flexible adjustment of the shooting direction, increase the movement freedom of the target shooting device, and improve the scene applicability of the target shooting device.
[0006] According to one aspect of the present invention, a method for photographing a target is provided, the method being performed by a target photographing system, the target photographing system comprising a photographing device and a moving device; the moving device carries the photographing device to move in at least one spatial dimension; the method comprising:
[0007] Taking a first image of the target to be photographed by a photographing device, and determining a posture estimation result of the target to be photographed according to the first image;
[0008] Determine motion control information of the motion device according to the posture estimation result and the reference posture of the target to be photographed acquired in advance, so as to move the photographing device by the motion device according to the motion control information;
[0009] If it is detected that the shooting orientation condition of the target to be photographed is met, the target to be photographed is photographed by a photographing device to obtain a second image of the target to be photographed.
[0010] According to another aspect of the present invention, a device for photographing a target is provided, wherein the device is configured in a target photographing system, wherein the target photographing system comprises a photographing device and a moving device; wherein the moving device carries the photographing device to move in at least one spatial dimension; and wherein the device comprises:
[0011] A posture estimation module, used to capture a first image of the target to be captured by a shooting device, and determine a posture estimation result of the target to be captured based on the first image;
[0012] A motion control module, used to determine motion control information of the motion device according to the posture estimation result and the reference posture of the target to be photographed acquired in advance, so as to move the shooting device by the motion device according to the motion control information;
[0013] The image shooting module is used to shoot the target to be shot by a shooting device to obtain a second image of the target to be shot if it is detected that the shooting orientation condition of the target to be shot is met.
[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0015] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for photographing a target described in any embodiment of the present invention.
[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the shooting method of the target described in any embodiment of the present invention when executed.
[0017] The technical solution of the embodiment of the present invention is to capture a first image of a target to be captured by a capturing device, and determine a posture estimation result of the target to be captured based on the first image; determine motion control information of a motion device based on the posture estimation result and a pre-acquired reference posture of the target to be captured, so that the motion device carries the capturing device to move according to the motion control information; if it is detected that the shooting orientation condition of the target to be captured is met, the target to be captured is captured by the capturing device to obtain a second image of the target to be captured. This technical solution solves the problems of limited target shooting methods and poor scene adaptability of existing target shooting devices by adding a motion device to the target shooting device, and can enable the target shooting device to achieve flexible adjustment of the shooting orientation, increase the freedom of movement of the target shooting device, and improve the scene applicability of the target shooting device.
[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0020] Figure 1 is a flow chart of a method for photographing a target provided according to Embodiment 1 of the present invention;
[0021] Figure 2A is a flow chart of a method for photographing a target provided according to Embodiment 2 of the present invention;
[0022] Figure 2B is a schematic diagram of distance compensation provided according to the second embodiment of the present invention;
[0023] Figure 3 is a schematic structural diagram of a target photographing device provided according to Embodiment 3 of the present invention;
[0024] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the photographing method of the embodiment of the present invention. DETAILED DESCRIPTION
[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.
[0027] Embodiment 1
[0028] Figure 1 A flowchart of a method for photographing a target is provided for the first embodiment of the present invention. This embodiment can be applied to target monitoring scenarios in places such as schools and banks. The method can be executed by a target photographing device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:
[0029] S110 , capturing a first image of a target to be captured by a capturing device, and determining a posture estimation result of the target to be captured based on the first image.
[0030] This solution can be executed by a target shooting system, which may include a shooting device and a moving device; wherein the shooting device may be a camera device such as a PTZ camera or a panoramic camera, and the moving device may be a moving mechanism such as a lifting platform, a rocker arm, and a mechanical arm. The shooting device may be a device separated from the moving device, or coupled with the moving device, and the moving device may carry the shooting device to move in at least one spatial dimension. For example, the lifting platform carries the shooting device to move in the vertical direction, that is, to move in one-dimensional space, and the mechanical arm may carry the shooting device to move in three-dimensional space.
[0031] Before capturing a target image that meets the orientation requirements, the shooting device may capture a first image of the target to be captured. The target to be captured may be a moving object such as a person or an animal in its entirety, or may be a part of a moving object, such as a face, a gesture, or other human body parts. The first image may be an image containing the target to be captured, such as a panoramic image. The target to be captured may be located at any position in the first image, and the imaging area ratio of the target to be captured in the first image may be of any size. In a feasible solution, the imaging area ratio of the target to be captured in the first image may be determined based on the target recognition capability of the target shooting system and the physical size of the target to be captured.
[0032] After obtaining the first image, the target shooting system performs target recognition, target detection or target segmentation on the first image, and estimates the posture of the target to be shot according to the processing result to obtain a posture estimation result of the target to be shot. The posture estimation can be a two-dimensional posture estimation or a three-dimensional posture estimation.
[0033] In a feasible solution, the step of capturing a first image of the target to be captured by a capturing device includes:
[0034] Using a photographing device, photographing at least two first images of a target to be photographed at a preset frequency;
[0035] The step of determining a posture estimation result of the target to be photographed according to the first image includes:
[0036] According to the posture estimation results of each first image, based on a preset motion model, a posture estimation result of the target to be photographed is determined.
[0037] It is understandable that the number of first images may be one or more. The shooting device may periodically collect multiple first images of the target to be shot at a certain frequency. The target shooting system may perform target detection processing on each first image based on the same target detection model, and output the posture estimation results corresponding to each first image based on the target detection results of each first image and the same posture estimation model.
[0038] After obtaining the pose estimation results of each first image, the photographing device may perform motion preservation, filtering and other processing on the pose estimation results of the plurality of first images based on a preset motion model, and output a pose estimation result of the target to be photographed. Specifically, the motion model may be constructed based on a multi-order motion state equation, and may track and filter the plurality of pose estimation results to obtain a pose estimation result of the target to be photographed that is not affected by accidental factors.
[0039] This solution can obtain a posture estimation result of the target to be photographed with high accuracy and strong robustness by performing tracking and filtering processing on the posture estimation results of multiple frames of the first image, which is conducive to achieving accurate azimuth shooting of the target to be photographed.
[0040] S120 , determining motion control information of the motion device according to the posture estimation result and the pre-acquired reference posture of the target to be photographed, so as to move the photographing device by the motion device according to the motion control information.
[0041] The user can set the reference posture of the target to be photographed in the target shooting system in advance. The reference posture can be used to represent the view orientation of the target to be photographed that the user needs to obtain, such as a front view of a face, a top view of a gesture, etc. It is easy to understand that the posture estimation result can be used to represent the shooting orientation of the target image to be photographed currently obtained by the shooting device. The posture estimation result is compared with the reference posture, and the target shooting system can use the comparison result to determine the shooting orientation of the target image to be photographed.
[0042] The motion control information of the motion device is determined based on the motion mode of the motion device. The motion mode of the motion device can be determined based on the spatial dimension in which the motion device can move. The target shooting system can control the motion device to carry the shooting device for synchronous movement according to the motion control information.
[0043] S130: If it is detected that the shooting orientation condition of the target to be photographed is met, photograph the target to be photographed by a photographing device to obtain a second image of the target to be photographed.
[0044] Since the target to be photographed is a moving object, during the movement of the moving device carrying the photographing device, the target photographing system can detect whether the current photographing orientation of the target to be photographed meets the photographing orientation condition according to a preset detection cycle. The photographing orientation condition can be that the current photographing orientation of the target to be photographed is the view orientation of the target to be photographed that needs to be obtained. If it is detected that the current photographing orientation is the view orientation of the target to be photographed that needs to be obtained, the target photographing system can control the photographing device to photograph the target to be photographed, thereby obtaining a second image of the target to be photographed that meets the user's view orientation requirements.
[0045] The technical solution of the embodiment of the present invention is to capture a first image of a target to be captured by a capturing device, and determine a posture estimation result of the target to be captured based on the first image; determine motion control information of a motion device based on the posture estimation result and a pre-acquired reference posture of the target to be captured, so that the motion device carries the capturing device to move according to the motion control information; if it is detected that the shooting orientation condition of the target to be captured is met, the target to be captured is captured by the capturing device to obtain a second image of the target to be captured. This technical solution solves the problems of limited target shooting methods and poor scene adaptability of existing target shooting devices by adding a motion device to the target shooting device, and can enable the target shooting device to achieve flexible adjustment of the shooting orientation, increase the freedom of movement of the target shooting device, and improve the scene applicability of the target shooting device.
[0046] Embodiment 2
[0047] Figure 2A This is a flow chart of a method for photographing a target provided by Embodiment 2 of the present invention. This embodiment is based on the above embodiment and is refined. Figure 2A As shown, the method includes:
[0048] S210: Capture a first image of a target by using a photographing device.
[0049] S220: Perform object detection on the first image based on a pre-built object detection model to determine an object detection result of the first image.
[0050] In this solution, the target shooting system can input the first image into a pre-built target detection model to obtain a target detection result output by the target detection model. The target detection model can be a model built based on traditional graphics algorithms, deep learning algorithms, etc., and is used to detect the target to be photographed in the first image. For example, the target detection model can be a one-stage target detection model built based on deep learning algorithms such as YOLO and SSD, or a two-stage target detection model built based on deep learning algorithms such as Faster R-CNN.
[0051] S230: Determine a posture estimation result of the target to be photographed according to the target detection result and based on a pre-built posture estimation model.
[0052] The target detection result obtained in S220 is input into a pre-built pose estimation model, and the target shooting system can obtain the pose estimation result of the target to be shot. The pose estimation model can be an end-to-end model built based on a deep learning algorithm, such as OpenPose, MoveNet, and PoseNet. The pose estimation model can be a pose estimation model based on a monocular image or a pose estimation model based on a multi-objective image.
[0053] S240: Compare the posture estimation result with the reference posture of the target to be photographed to determine the posture difference in each spatial dimension.
[0054] It can be understood that the pose estimation result can be used to represent the shooting orientation of the target image to be photographed currently acquired by the shooting device, and the reference pose can be used to characterize the view orientation of the target to be photographed that the user needs to obtain. Both the pose estimation result and the reference pose can be represented by three-dimensional space coordinates, with each spatial dimension corresponding to a coordinate value. By comparing the pose estimation result with the reference pose of the target to be photographed, the target shooting system can determine the pose difference of each spatial dimension. For example, if the pose estimation result is (10, 20, 30), the reference pose is (10, 20, 40), and the pose difference is (0, 0, 40).
[0055] S250: Determine motion control information of the motion device in each spatial dimension according to the posture difference in each spatial dimension.
[0056] It can be understood that the target shooting system can determine the motion control information of the motion device in each spatial dimension according to the posture difference in each spatial dimension and the spatial dimension in which the motion device can move.
[0057] In this embodiment, the motion device moves in each spatial dimension through the axis structure matching each spatial dimension. The motion device may include one or more axis structures, and the axis structure matching each spatial dimension can move in the spatial dimension. In a specific example, if any point in the space is used as the origin, a spatial rectangular coordinate system is established, and the three mutually perpendicular coordinate axes are the X-axis, the Y-axis, and the Z-axis. The motion device may include three axis structures, the first axis structure can rotate around the Y-axis, the second axis structure can rotate around the X-axis, and the third axis structure can rotate around the Z-axis.
[0058] After obtaining the attitude difference of each spatial dimension, the target shooting system can plan the movement route of the motion device in space according to the attitude difference of each spatial dimension, and then determine the motion control information of the motion device in each spatial dimension according to the movement route. The motion control information may include information such as movement distance, movement speed and movement time.
[0059] S260, using the motion device, according to the motion control information of each spatial dimension, control the axis structure matching each spatial dimension to carry the shooting device to move.
[0060] After obtaining the motion control information, the motion device can control the axis structure supporting the shooting device that matches each spatial dimension to move synchronously according to the motion control information of each spatial dimension. Specifically, after obtaining the posture difference of the target to be photographed in each spatial dimension, the target shooting system can plan the motion route of the motion device in space according to the posture difference of each spatial dimension, and then determine the control information of the motion device in each spatial dimension according to the motion route. The motion device can control the axis structure supporting the shooting device that matches each spatial dimension to move synchronously according to the motion control information of each spatial dimension.
[0061] For example, a motion device includes three axis structures, namely, a PAN axis, a PITCH axis, and a ROLL axis. The PAN axis angular velocity of the motion device can be controlled by the PAN axis angle, the PITCH axis angular velocity of the motion device can be controlled by the PITCH axis angle, and the ROLL axis angular velocity of the motion device can be controlled by the ROLL axis angle. The three axis structures can be independent of each other.
[0062] For a motion device with three-axis structure, such as a robotic arm, the target shooting system can further map {distance (the distance between the target to be shot and the shooting device), PAN axis angular velocity, PITCH axis angular velocity} into a curve in space, and then hand over the curve to the motion mechanism of the robotic arm for execution. Compared with motion devices with only rotation functions, such as a gimbal, a robotic arm can directly translate the spatial position, and control the movement of the robotic arm by converting information such as distance, angle, and speed into position vectors in three-dimensional space, that is, converting distance and rotation information into position coordinates in three-dimensional space to control the movement of the robotic arm.
[0063] In addition, the motion device can also have a two-axis structure, such as a rocker arm. For a motion device with a two-axis structure, the target shooting system can directly use the motion control information of each spatial dimension to control the rotation of the rocker arm. The motion control information of each spatial dimension can represent the attitude difference of each spatial dimension. After the attitude difference is amplified by the hysteresis controller, it can be converted into the control amount of speed or angle, and then control the axis structure matching each spatial dimension.
[0064] S270: Determine the distance between the target to be photographed and the photographing device through the photographing device, and determine the focus adjustment result of the photographing device according to the distance between the target to be photographed and the photographing device.
[0065] During the movement of the moving device carrying the shooting device, the shooting device can obtain the distance between the target to be photographed and the shooting device according to the preset acquisition cycle, and zoom the shooting device according to the distance between the target to be photographed and the shooting device to obtain a clear target image. Specifically, the shooting device can directly collect the distance between the target to be photographed and the shooting device through a distance sensing device configured in the shooting device, such as a distance sensor such as dTOF (direct time of flight) or iTOF (indirect time of flight); it can also indirectly measure the distance between the target to be photographed and the shooting device through focus information; it can also estimate the distance between the target to be photographed and the shooting device based on a visual algorithm, such as binocular vision estimation, monocular vision estimation and other visual algorithms; furthermore, it can estimate the distance between the target to be photographed and the shooting device through feature information of the target, such as feature point positioning, bounding box and other auxiliary information.
[0066] In a preferred solution, after determining the focus adjustment result of the shooting device, before shooting the target by the shooting device according to the focus adjustment result, the method further includes:
[0067] Determine the velocity component of the tangential velocity of the axis structure matched in each spatial dimension in the target shooting direction;
[0068] The focus adjustment result is distance compensated according to the velocity component of the tangential velocity of the axis structure matched in each spatial dimension in the target shooting direction.
[0069] After obtaining the focal length adjustment result of the shooting device, the target shooting system can obtain the tangential velocity of the axis structure matching each spatial dimension through the motion device, and perform orthogonal decomposition on the tangential velocity to obtain the velocity component of the tangential velocity in the target shooting direction. The target shooting system can perform distance compensation on the focal length adjustment result obtained in S280 according to the velocity component of the tangential velocity of the axis structure corresponding to each spatial dimension in the target shooting direction, so as to eliminate the influence of the motion device on the distance between the shooting device and the target to be shot during the rotation or translation process.
[0070] Figure 2B is a schematic diagram of distance compensation provided according to the second embodiment of the present invention, such as Figure 2BAs shown in the figure, the tangential velocity of an axis structure with matching spatial dimensions is ω2, and the tangential velocity ω2 is orthogonally decomposed to obtain ω1 and υ, where υ is the velocity component of ω2 in the target shooting direction. Based on the focal length adjustment result, the target shooting system can introduce υ into the distance compensation loop in a feedforward manner to eliminate the distance error during the movement and ensure the shooting stability of the moving device during the movement. In practical applications, an input Δd is added to the distance compensation loop to compensate for the velocity component υ, for example: Δd = ∫vdt, and Δd is used to eliminate the distance error during the movement to ensure the shooting stability of the moving device during the movement.
[0071] S290: If it is detected that the shooting orientation condition of the target to be photographed is met, the target to be photographed is photographed by a shooting device according to the focus adjustment result to obtain a second image of the target to be photographed.
[0072] When it is detected that the shooting orientation condition of the target to be photographed is met, the target shooting system can shoot the target to be photographed according to the focal length adjustment result through the shooting device to obtain a second image that meets the user's viewing orientation requirement.
[0073] The technical solution of the embodiment of the present invention is to capture a first image of a target to be captured by a capturing device, and determine a posture estimation result of the target to be captured based on the first image; determine motion control information of a motion device based on the posture estimation result and a pre-acquired reference posture of the target to be captured, so that the motion device carries the capturing device to move according to the motion control information; if it is detected that the shooting orientation condition of the target to be captured is met, the target to be captured is captured by the capturing device to obtain a second image of the target to be captured. This technical solution solves the problems of limited target shooting methods and poor scene adaptability of existing target shooting devices by adding a motion device to the target shooting device, and can enable the target shooting device to achieve flexible adjustment of the shooting orientation, increase the freedom of movement of the target shooting device, and improve the scene applicability of the target shooting device.
[0074] Embodiment 3
[0075] Figure 3 The schematic diagram of the structure of a target shooting device provided in the third embodiment of the present invention. The device is configured in a target shooting system, and the target shooting system includes a shooting device and a moving device; the moving device carries the shooting device to move in at least one spatial dimension. Figure 3 As shown, the device comprises:
[0076] The posture estimation module 310 is used to capture a first image of the target to be captured by a shooting device, and determine a posture estimation result of the target to be captured based on the first image;
[0077] The motion control module 320 is used to determine the motion control information of the motion device according to the posture estimation result and the reference posture of the target to be photographed acquired in advance, so as to move the shooting device by the motion device according to the motion control information;
[0078] The image shooting module 330 is used to shoot the target to be shot by using a shooting device to obtain a second image of the target to be shot if it is detected that the shooting orientation condition of the target to be shot is met.
[0079] In this solution, optionally, the posture estimation module 310 is specifically used for:
[0080] Based on a pre-built object detection model, perform object detection on the first image to determine an object detection result of the first image;
[0081] According to the target detection result, based on the pre-built pose estimation model, the pose estimation result of the target to be photographed is determined.
[0082] In a feasible solution, the motion control module 320 is specifically used to:
[0083] Compare the pose estimation result with the reference pose of the target to be photographed to determine the pose difference in each spatial dimension;
[0084] According to the posture difference in each spatial dimension, the motion control information of the motion device in each spatial dimension is determined.
[0085] Based on the above solution, optionally, the motion device moves in each spatial dimension through an axis structure matching each spatial dimension;
[0086] The motion control module 320 is specifically used for:
[0087] Through the motion device, according to the motion control information of each spatial dimension, the axis structure supporting the shooting device matching each spatial dimension is controlled to move.
[0088] In this embodiment, the image capturing module 330 is specifically used for:
[0089] Determine the distance between the target to be photographed and the photographing device through the photographing device, and determine the focus adjustment result of the photographing device according to the distance between the target to be photographed and the photographing device;
[0090] The target to be photographed is photographed by a photographing device according to the focus adjustment result to obtain a second image of the target to be photographed.
[0091] Based on the above solution, optionally, the device further includes:
[0092] The distance compensation module is used to determine the speed component of the tangential velocity of the axis structure matching each spatial dimension in the target shooting direction after determining the focus adjustment result of the shooting device and before shooting the target to be shot by the shooting device according to the focus adjustment result; and perform distance compensation on the focus adjustment result according to the speed component of the tangential velocity of the axis structure matching each spatial dimension in the target shooting direction.
[0093] In a preferred solution, the posture estimation module 310 is also used to:
[0094] Using a photographing device, photographing at least two first images of a target to be photographed at a preset frequency;
[0095] According to the posture estimation results of each first image, based on a preset motion model, a posture estimation result of the target to be photographed is determined.
[0096] The target photographing device provided in the embodiment of the present invention can execute the target photographing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0097] Embodiment 4
[0098] Figure 4 A schematic diagram of an electronic device 410 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0099] like Figure 4As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.
[0100] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0101] The processor 411 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as a method for shooting a target.
[0102] In some embodiments, the method for photographing a target may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the method for photographing a target described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to execute the method for photographing a target in any other appropriate manner (e.g., by means of firmware).
[0103] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0104] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable target camera, so that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.
[0105] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0106] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0107] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0108] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0109] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0110] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for photographing a target, characterized in that: The method is performed by a target shooting system, the target shooting system includes a shooting device and a moving device; the moving device carries the shooting device to move in at least one spatial dimension; the method includes: Taking a first image of the target to be photographed by a photographing device, and determining a posture estimation result of the target to be photographed according to the first image; Determine motion control information of the motion device according to the posture estimation result and the pre-acquired reference posture of the target to be photographed, so as to move the photographing device by the motion device according to the motion control information; If it is detected that the shooting orientation condition of the target to be photographed is met, the target to be photographed is photographed by a photographing device to obtain a second image of the target to be photographed.
2. The method according to claim 1, characterized in that: The step of determining a posture estimation result of the target to be photographed according to the first image includes: Based on a pre-built object detection model, perform object detection on the first image to determine an object detection result of the first image; According to the target detection result, based on the pre-built pose estimation model, the pose estimation result of the target to be photographed is determined.
3. The method according to claim 1, characterized in that The step of determining the motion control information of the motion device according to the posture estimation result and the pre-acquired reference posture of the target to be photographed includes: Compare the pose estimation result with the reference pose of the target to be photographed to determine the pose difference in each spatial dimension; According to the posture difference in each spatial dimension, the motion control information of the motion device in each spatial dimension is determined.
4. The method according to claim 3, characterized in that The method of moving the shooting device by the motion device according to the motion control information includes: Through the motion device, according to the motion control information of each spatial dimension, the axis structure supporting the shooting device matching each spatial dimension is controlled to move.
5. The method according to claim 4, characterized in that The method of photographing the target to be photographed by a photographing device to obtain a second image of the target to be photographed includes: Determine the distance between the target to be photographed and the photographing device through the photographing device, and determine the focus adjustment result of the photographing device according to the distance between the target to be photographed and the photographing device; The target to be photographed is photographed by a photographing device according to the focus adjustment result to obtain a second image of the target to be photographed.
6. The method according to claim 5, characterized in that After determining the focus adjustment result of the shooting device, before shooting the target by the shooting device according to the focus adjustment result, the method further includes: Determine the velocity component of the tangential velocity of the axis structure matched in each spatial dimension in the target shooting direction; The focus adjustment result is distance compensated according to the velocity component of the tangential velocity of the axis structure matched in each spatial dimension in the target shooting direction.
7. The method according to claim 1, characterized in that The method of capturing a first image of a target to be captured by a capturing device comprises: Using a photographing device, photographing at least two first images of a target to be photographed at a preset frequency; The step of determining a posture estimation result of the target to be photographed according to the first image includes: According to the posture estimation results of each first image, based on a preset motion model, a posture estimation result of the target to be photographed is determined.
8. A target shooting device, characterized in that: The device is configured in a target shooting system, and the target shooting system includes a shooting device and a moving device; the moving device carries the shooting device to move in at least one spatial dimension; and includes: A posture estimation module, used to capture a first image of the target to be captured by a shooting device, and determine a posture estimation result of the target to be captured based on the first image; A motion control module, used to determine motion control information of the motion device according to the posture estimation result and the reference posture of the target to be photographed acquired in advance, so as to move the shooting device by the motion device according to the motion control information; The image shooting module is used to shoot the target to be shot by a shooting device to obtain a second image of the target to be shot if it is detected that the shooting orientation condition of the target to be shot is met.
9. An electronic device, characterized in that: The electronic device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for photographing a target as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the shooting method of any one of claims 1 to 7 when executed.
Citation Information
Cited By
Construction site environment control method and automation equipment
CN119870093A
