77 results about "Close-up" patented technology

The embodiment of the invention provides an operation scene monitoring method and system based on panoramic stitching and holder linkage, and belongs to the technical field of video monitoring. The method comprises the following steps: respectively acquiring real-time panoramic video data and historical video data of an operation scene and a partial discharge signal of high-voltage electrical equipment; simulating electrical disease characteristics of the high-voltage electrical equipment based on the partial discharge signals and the environmental parameters of the real-time panoramic video data; obtaining work prediction information of the real-time panoramic video based on the historical video data and the electrical disease features; calculating deviation information of a real-time panoramic video according to the operation prediction information and the real-time panoramic video data; positioning a risk target area of the operation scene based on the deviation information, and determining a risk early warning signal of the operation scene for the deviation information based on a preset risk rule base; and issuing the risk early warning signal to a pan-tilt camera of the operation scene, and monitoring a close-up monitoring picture of the risk target area in real time. According to the invention, the risk handling efficiency of operation scene monitoring can be improved.

A non-transitory, processor-readable medium stores instructions that, when executed by a processor, cause the processor to receive video-derived detection data associated with a plurality of persons. For a first person from the plurality of persons, a portion of the video-derived detection data associated with the first person is assigned to a first motion track based on a motion model, and a closeup image of the first person is generated based on the portion of video-derived detection data. A quality score is generated based on the closeup image, and the closeup image is assigned to the first motion track based on the quality score. The first motion track is selected from a plurality of motion tracks associated with the plurality of persons. Using a neural network, first identity data is generated based on the closeup image, and the first motion track is updated based on the first identity data.

The invention discloses a multi-camera target duplicate removal method and device, equipment, a storage medium and a program product, and relates to the technical field of computer vision, and the method comprises the steps: obtaining a panoramic image and at least one close-up image; determining an overlapping area of the panoramic image and the close-up image, detecting a first target person in the overlapping area in the panoramic image, and detecting a second target person in the close-up image; performing similarity matching on a first spatial distribution relationship of the first target person in the overlapping region and a second spatial distribution relationship of the second target person in the close-up image to obtain a similarity matching result; and according to a similarity matching result, determining repeated figures and removing the repeated figures from an output picture which is a panoramic image or a close-up image where the repeated figures are located. According to the method and the device, the real-time processing requirement of edge equipment is met while the de-duplication accuracy is guaranteed, and accurate identification and removal of repeated targets in multiple paths of video streams under the condition of limited computing power are realized.

The invention discloses a marketing video generation method and system, a storage medium and electronic equipment, and relates to the technical field of video processing. The method comprises the steps of obtaining a manufacturing instruction of a target marketing product, and determining key features of the product according to additional requirements and product materials; generating a product close-up sequence based on the product materials and the product key features, and generating a scene artistic conception sequence based on the use scene and the product key features in the second path; performing picture segmentation on the product close-up sequence and the scene artistic conception sequence to generate a visual element library; generating a narrative script and an audio script according to the group characteristics of the target audience group and the product key characteristics, arranging the visual element library according to the narrative script, and generating a picture display sequence; generating an audio sequence corresponding to the picture display sequence according to the audio script; and performing time sequence combination on the picture display sequence and the audio sequence to generate a marketing video of the target marketing product. By implementing the technical scheme provided by the invention, the display effect of the marketing video is improved.

The present invention belongs to the field of shooting, and provides a shooting method and camera based on multi-camera linkage. The first camera is a fixed wide-angle camera, and tracks and acquires the position of the shooting target in real time. The image processing technology is used to analyze the composition quality and determines an optimal second camera shooting position coordinate. The control module sends a rotation instruction to enable the second camera to track the shooting target in real time, so as to ensure that the shooting target keeps the center position in the close-up image. When it is analyzed that the shooting target occupies the proper proportion and angle in the picture, the second camera is started to track and shoot, and during shooting, the second camera is zoomed and rotated according to the position of the shooting target, so that better image shooting is achieved.

The invention relates to a logistics packaging video tracing system and method based on data fusion, and relates to the technical field of video monitoring and logistics management. The system comprises a camera module, a coding processing unit, an external data acquisition device and an infrared positioning unit. The coding processing unit receives logistics information of a code scanning gun or an electronic scale, displays the logistics information in a video picture through a character superimposition technology, and establishes a video database by taking a logistics order number as an index; the camera module adopts a binocular or multi-ocular lens and is provided with an infrared positioning unit, when a code scanning signal is received, an infrared light target is used for assisting in positioning, and digital optical hybrid zooming from a wide angle to close-up is triggered. According to the method, automatic zooming, automatic segmented video recording and infrared auxiliary positioning are triggered through code scanning, so that the problems of unclear express sheet information, difficulty in searching and tedious operation of the logistics video in the prior art are solved, and deep binding and quick retrieval of the video and the logistics data are realized.

The invention discloses a target tracking method, electronic equipment and a storage medium. A panoramic image of a current application scene is collected by a first camera, a plurality of candidate targets in the scene are obtained through target detection, and a to-be-tracked target is automatically determined in combination with a recognition result of interaction actions of the candidate targets; and mapping the position of the to-be-tracked target in the panoramic image to a shooting coordinate system of the close-up camera based on double-shooting calibration information between the first camera and the second camera, driving the close-up camera to actively adjust the shooting direction, enabling the to-be-tracked target to quickly enter a shooting view field of the to-be-tracked target, and executing target tracking on the basis. According to the invention, the interaction target can be accurately selected from the panoramic view angle and can be stably and quickly switched to the close-up camera for continuous tracking, automatic switching of the target to be tracked from panoramic perception to close-up tracking is realized, the stability and continuity of the close-up tracking process are improved, and the tracking efficiency is improved. And the application requirements of intelligent shooting and automatic tracking in different scenes are met.

The invention provides an electrical equipment test data acquisition method based on image recognition, and relates to the technical field of intelligent operation and maintenance and digital twinning of electrical equipment, and the method comprises the steps: synchronously acquiring a panoramic video stream of a test site and a close-up video stream driven by a controllable holder; based on real-time analysis of the panoramic video stream, through a dynamic attention control mechanism, a holder is driven to adjust an acquisition target of the close-up video stream, so that the acquisition target is focused on a key instrument or equipment connection point in a current test stage; analyzing the panoramic video stream, identifying a continuous operation behavior of a tester, and comparing the continuous operation behavior with a preset standard test process to generate a process compliance judgment result; and performing association fusion on the reading obtained by analysis and a process compliance judgment result to generate a structured test data record with process context information. According to the invention, the whole test process can be intelligently sensed, the concerned target can be automatically tracked, and the data quality and the operation compliance can be intelligently judged.

The application discloses a method and system for detecting students playing mobile phones. The system comprises a pan-tilt camera arranged at the left and right ends of the back side of a classroom, a shooting control module and an analysis module. The analysis method used by the analysis module comprises the following steps: obtaining close-up pictures of positions of students; performing mobile phone detection and screen-on detection on the close-up pictures; if the mobile phone detection result is that a mobile phone exists and the screen-on detection result is that the mobile phone is in a screen-on state, marking that a student at the position corresponding to the close-up picture is playing a mobile phone. The two pan-tilt cameras are arranged at the left and right ends of the back side of the classroom, so that positions that are difficult to shoot can be ensured to be shot, and the mobile phone detection and the screen-on detection are used for filtering before posture detection, so that the cost can be reduced.

The embodiment of the application discloses an image acquisition device, a terminal, a method and a storage medium for a video conference, and relates to the technical field of camera terminals. The device comprises: a wide-angle lens for acquiring a first field of view area; a plurality of telephoto lenses symmetrically arranged with respect to the center of the wide-angle lens, the optical axes of the plurality of telephoto lenses intersecting with the optical axis of the wide-angle lens at the same virtual optical center, and the absolute value of the difference between the second field of view area obtained by merging the field of view areas of the plurality of telephoto lenses and the first field of view area being less than a field of view area threshold. The image acquisition device of the embodiment of the application combines the wide-angle lens and the telephoto lens, can improve the field of view coverage rate, can also fuse the telephoto lens and the wide-angle lens to perform lossless magnification on the picture, avoids image distortion caused by different focusing information of different lenses based on the setting of the virtual optical center and the field of view area, and can fuse the telephoto lens to perform magnification close-up in most of the field of view area of the wide-angle lens.

This application discloses a marine detection device and control method. The marine detection device can be installed on the bottom of unmanned surface vessels (USVs) and other underwater vehicles. During the detection of a real target, the central optical axis of the laser illumination device is kept aligned with the central optical axis of the camera on the seabed, and the laser illumination device is controlled to illuminate the target with a large light output size. After identifying the target element in the detection image, a tracking mode is activated. On the one hand, the central optical axes of both the laser illumination device and the camera are kept aligned with the real target; on the other hand, the laser illumination device is controlled to illuminate the real target with a smaller light output size, and the camera is controlled to adjust its focus to capture a close-up shot of the real target. This application allows for accurate illumination of a large area during detection, facilitating the discovery of the real target through the detection image; during tracking, it facilitates clearer observation of the real target.

This application provides a method, system, equipment, and medium for automatic compliance verification in warehousing scenarios, belonging to the field of intelligent warehouse management technology. The method includes: collecting environmental photos and close-up photos of invoices related to the warehousing operation; performing image recognition on the environmental photos to determine whether they simultaneously contain three key elements: the operator's face, the shape of the goods, and the scale reading; extracting facial features and matching them with a pre-built authorization database; performing OCR recognition on the invoice photos to extract category and weight information, and comparing it with the weighing reading and the entered category; and determining non-compliance and blocking the warehousing process in real time when any key element is missing, the identity is unauthorized, the weight deviation exceeds a threshold, or the category is inconsistent. This invention transforms compliance judgment from post-event manual sampling to real-time control during the process, ensuring the integrity and validity of the stored photos, achieving automatic cross-verification of invoice information and weighing data, effectively preventing misrecording, omissions, and forgery, and reducing regulatory costs.

The invention discloses a portrait tracking picture display method, system and device and a storage medium, and the method comprises the steps: receiving and outputting a close-up picture of a first speaker on a video conference device when the first speaker is detected to speak; detecting a new speaking event in a preset time window; if at least one new speaker is detected to speak, synchronously obtaining close-up pictures of the new speakers; and according to the speaking time sequence of the new speakers, sub-display areas are divided for each new speaker in sequence, and the close-up pictures of the speakers are displayed on a display interface of the video conference equipment according to a preset layout rule. According to the invention, the picture display can be dynamically adjusted according to the speaking conditions of the participants, and the picture display effect and user experience of the video conference are improved.

A non-transitory, processor-readable medium stores instructions that, when executed by a processor, cause the processor to receive video-derived detection data associated with a plurality of persons. For a first person from the plurality of persons, a portion of the video-derived detection data associated with the first person is assigned to a first motion track based on a motion model, and a closeup image of the first person is generated based on the portion of video-derived detection data. A quality score is generated based on the closeup image, and the closeup image is assigned to the first motion track based on the quality score. The first motion track is selected from a plurality of motion tracks associated with the plurality of persons. Using a neural network, first identity data is generated based on the closeup image, and the first motion track is updated based on the first identity data.

This application provides a photographing method and a related device. The photographing method may be applied to an electronic device provided with a camera and a display. According to the photographing method, in a photographing scene in which a plurality of photographed objects are photographed together, the electronic device may perform focus tracking on one of the photographed objects, and creates two encoders to respectively encode an original image displayed in a large preview window and a close-up image displayed in a small preview window, to obtain an original video and a close-up video. In some embodiments of this application, the electronic device may obtain one original video and a plurality of close-up videos through photographing.

The application discloses a reservoir short-pile water gauge water level detection method based on improved YOLOv11 and DeepLabV3+, which comprises the following steps: acquiring a panoramic image of a reservoir area and a close-up image of a water gauge character; constructing an improved YOLOv11 model, introducing an RCM module and a CA module in a backbone network and a neck network part, and realizing accurate detection of the number of water gauges and the character area; optimizing a DeepLabV3+ model, replacing the main network thereof with MobileNetV3, and fusing a DenseASPP and a spatial pyramid SP module, so as to realize high-precision segmentation of a water area and a water level line; and establishing a dynamic conversion model of a pixel distance and an actual water level according to a character detection result, so as to effectively eliminate measurement errors caused by a shooting angle and lens distortion. The application significantly improves the automation degree and precision of water level recognition, and is suitable for real-time monitoring of reservoir water levels in a wide range and a multi-angle environment.

To provide an excellent work system.SOLUTION: A work system 10 where a work mobile body 12 to be operated by a user U performs a work includes: an image acquisition section for acquiring a close-up image in the periphery of the work mobile body 12; and a head-mounted display 14 mounted on the user U so as to provide a provision image corresponding to the close-up image acquired by the image acquisition section to the user U.SELECTED DRAWING: Figure 1

The invention relates to the technical field of visual control, and discloses a visual control method and system for a tractor hook picking and hooking process. The method comprises the steps that carriage distance data are obtained through weighted fusion of ultrasonic and infrared distance measurement values, and electric push rod stroke and tractor position data are collected; constructing a three-dimensional virtual scene according to the data, and dynamically mapping the position of the carriage and the rotation angle of the bolt; dividing a scene into a panoramic view layer and a close-up view layer, and superposing a data instrument panel on the panoramic view layer; according to the carriage distance change rate and the electric push rod stroke, the operation stage is judged, and view display modes are automatically switched; and drawing a thrust change curve on the close-up view layer, generating abnormal diagnosis information through thrust threshold comparison, and popping up a diagnosis panel. The problems that in the prior art, the tractor hook picking and hooking operation process is lack of visual monitoring, and abnormal conditions are difficult to find and process in time are solved, and the operation intuition and the troubleshooting efficiency are improved.

The invention relates to the technical field of intelligent positioning, in particular to a conference spokesman automatic positioning method, system and device and a medium. The method comprises the following steps: driving a microphone array to collect training sound data, and controlling a pan-tilt camera to spirally scan a conference room speaking area to collect training image data; when training human voice and lip micro-motion data are synchronously detected, extracting three-dimensional coordinates of a sound source and recording current shooting parameters (at least one of a horizontal rotation angle, a pitch angle and a focal length) of a camera to form a group of training samples; not less than 30 groups of samples are collected and input into a neural network for training, a coordinate transformation matrix of the camera relative to the microphone array is obtained, the microphone array obtains real-time sound source coordinates, visual search center coordinates are generated through the transformation matrix, and accordingly the camera is driven to complete spokesman close-up shooting. The method can be completed without manual intervention.

The application provides a photographing method and related equipment. According to the photographing method, the electronic device can change the aspect ratio of the window for shooting a close-up video without changing the shooting direction of the electronic device, thereby obtaining close-up videos with different proportions. In this process, the electronic device can change the cropping direction of the close-up image and perform rotation processing on the cropped close-up image, so that the size of the close-up image transmitted to the Buffer meets the aspect ratio of the Buffer. The camera application in the electronic device can also perform rotation processing on the close-up image transmitted by the Buffer again, and send the processed image to the rotated window for display. The above-mentioned method not only meets the demand of users for obtaining close-up images with multiple proportions, but also avoids the interruption of the camera path caused by the fact that the image transmitted to the Buffer does not meet the aspect ratio of the Buffer, that is, the phenomenon of freezing or blurring can be avoided.

Disclosed in the present description are an image processing method and apparatus, a storage medium and an electronic device. The method comprises: determining a first portrait area image in an input image, and acquiring portrait coordinates of the first portrait area image; determining a target size of the first portrait area image, and, on the basis of an adapted resolution of the target size, adjusting the first portrait area image, so as to obtain a first adapted image; on the basis of a super-resolution scaling factor, performing super-resolution processing on the first adapted image, so as to obtain a first super-resolution image; performing fusion on the first portrait area image, the first super-resolution image and a mask corresponding to the portrait coordinates, so as to obtain a second portrait area image; and, on the basis of the portrait coordinates, fusing the second portrait area image into the input image, so as to obtain a portrait close-up image. By means of the present description, a clear portrait image obtained by performing super-resolution processing on a portrait is fused into an input image, so as to obtain an image that presents a clear portrait and provides comfortable viewing experience, thereby improving the quality of generated close-up images and the performance ratio of image generation.

The invention discloses an image generation method based on an expired film in a specific year, and relates to the technical field of photographic image processing, comprising the following steps: selecting a colored or black and white expired film in a corresponding production year in advance according to the birth year of a photographed object, and determining the expired film according to the aging degree and the service life of the film by controlling the aging degree and the service life of the film; it is ensured that the negative film naturally presents atomization, mottle and particle aging characteristics in imaging; a mechanical film camera is used for shooting a target person, the shooting posture is front face, side face or half body close-up, and natural light or a stable artificial light source is mainly used as light. According to the invention, physical characteristics of expired films in a specific year are deeply combined with a digital collage technology, an image creation system crossing tradition and modern is constructed, dependence of traditional photography on instantaneity is broken through, an image not only records the appearance of a person, but also bears material memory in the specific year, and the image creation efficiency is improved. And a brand new aesthetic expression dimension is developed for the photography art.

The present application relates to display device technical field, specifically to a kind of close-up picture image smoothing method, device, equipment and storage medium, the present application includes: obtaining the display picture of conference panel acquisition and the first pixel position of existing close-up picture, existing close-up picture is used to track target person, existing close-up picture corresponds to intercept frame, according to display picture, determine the target person area corresponding to target person and the second pixel position of target person area in display picture, according to the first pixel position and the second pixel position, calculate the third pixel position that satisfies pixel alignment restriction condition, according to third pixel position, move intercept frame, obtain the intercept frame after moving, according to the target close-up picture of target person area in display picture being intercepted according to the intercept frame after moving, control conference panel display target close-up picture.Through the present application, it can be guaranteed that the situation that intercept frame does not appear picture jitter after moving following target person image, so that picture moves more smoothly.

The invention provides a method and a system for tracking a target object in a monitoring video. The method comprises the following steps: firstly, detecting and locking a target object from a monitoring video stream to obtain a first motion track, determining a motion trend of the target object, then judging whether the target object enters a preset target area, and when judging that the target object enters the preset target area, obtaining a local close-up video stream of the target object, before the target object enters the preset target area, extracting a feature template of the target object from the local close-up video stream, and when the target object is located in the preset target area, performing matching pursuit in the local close-up video stream according to the feature template to generate a second motion track of the target object, and finally, fusing the first movement track and the second movement track, and outputting a complete movement track. The technical scheme provided by the invention not only improves the robustness and continuity of tracking the target object in a complex scene, but also improves the quality and availability of the trajectory data.

This application provides a shooting method and a related device. The shooting method may be applied to an electronic device disposed with a camera. According to the shooting method, in a shooting scene in which a plurality of shooting objects are in a same frame, the electronic device can perform focus tracking on one of the shooting objects, and perform targeted close-up recording on the shooting object, so as to separately generate an original video and a focus-tracking video. Specifically, the electronic device may allocate a flow identifier to each of data flows of a large preview window and a small preview window, associate different video files and encoders according to different flow identifiers, and match different image effects, thereby implementing recording of an original video corresponding to the large preview window and a close-up video corresponding to the small preview window.

The invention discloses a student behavior identification method and device based on dynamic close-up shot switching. Wherein. The method comprises the following steps: receiving a panoramic video picture shot by a panoramic camera; detecting a person standing in a student area in the panoramic video picture; when two standing figures are detected, controlling a close-up camera to shoot close-up of the two standing figures so as to ensure that the two standing figures are both in a shooting range of the close-up camera; obtaining a close-up picture shot by a close-up camera; identifying a student identity in the close-up picture; and based on the identified student identity, recording behavior data of the student whose identity is identified in the classroom. According to the invention, not only can the whole classroom be grasped, but also a single student can be sufficiently understood.

The application discloses a multi-camera target deduplication method and device, equipment, a storage medium and a program product, and relates to the technical field of computer vision. The method comprises the following steps: acquiring a panoramic image and at least one close-up image; determining an overlapping area of the panoramic image and the close-up image; detecting a first target person in the overlapping area in the panoramic image, and detecting a second target person in the close-up image; performing similarity matching on a first spatial distribution relationship of the first target person in the overlapping area and a second spatial distribution relationship of the second target person in the close-up image to obtain a similarity matching result; and determining a repeated person and removing the repeated person from an output picture according to the similarity matching result, wherein the output picture is the panoramic image or the close-up image in which the repeated person is located. The application meets the real-time processing requirement of an edge device while ensuring the deduplication accuracy, and realizes accurate identification and removal of repeated targets in multiple video streams under the condition of limited computing power.

The invention relates to the technical field of tracking, and discloses a target tracking method, a close-up camera, a system and a storage medium, and the method comprises the steps: detecting a first bounding box of an overall region of a target object at a lower frame rate through a panorama camera, and then detecting a second bounding box of a local region of the target object at a higher frame rate based on the close-up camera. And fusing the first bounding box and the second bounding box to obtain a target tracking frame, tracking the target object based on the target tracking frame, performing linkage through the panorama camera and the close-up camera, performing coarse detection on the whole area by using the panorama camera, and performing fine detection on the local area by using the close-up camera, thereby improving the tracking precision.

1. The name of the design product: custom video source interactive graphical user interface for electronic device. 2. The use of the design product: for electronic device. 3. The design points of the design product: the interface interaction and content of the graphical user interface in the screen. 4. The picture or photo that best indicates the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: for building on electronic devices with screens, showing information and human-computer interaction interfaces. The main view of Design 1 is an initial graphical user interface of a custom video source, the central part of the interface displays a video window, and the periphery of the interface displays various function modules capable of adjusting the picture of the video source, and the user can click different function modules to perform editing operations on the selected video source for corresponding purposes; clicking Add Source in the main view of Design 1 or the first icon from top to bottom on the left side of the interface, entering the graphical user interface shown in Design 1 interface change state diagram 1, the interface displays a plurality of video sources, the user can select the required video source from the plurality of video sources, clicking Video 1 in Design 1 interface change state diagram 1 and clicking Done in the upper right corner of the interface, entering the graphical user interface shown in Design 1 interface change state diagram 2, at this time the video window displays the preview picture of the video source Video 1, the user can perform personalized editing on the selected video source Video 1 on this page, clicking the first icon from top to bottom on the left side of the interface in Design 1 interface change state diagram 2 and clicking Video 2, entering Design 1 interface change state diagram 3, clicking Done in the upper right corner of Design 1 interface change state diagram 3, entering the graphical user interface shown in Design 1 interface change state diagram 4, clicking the zoom icon in the lower right corner of Video 2 in Design 1 interface change state diagram 4, and dragging the zoom icon to adjust Video 2 to the required size, and then clicking Save in the upper right corner of the interface, entering Design 1 interface change state diagram 5, at this time the video window simultaneously displays the preview pictures of the dual video sources Video 1 and Video 2; the main view of Design 2 is an initial graphical user interface of a custom video source, the central part of the interface displays a video window, and the periphery of the interface displays various function modules capable of adjusting the picture of the video source, and the user can click different function modules to perform editing operations on the selected video source for corresponding purposes; clicking Add Source in the main view of Design 2 or the first icon from top to bottom on the left side of the interface, entering the graphical user interface shown in Design 2 interface change state diagram 1, the interface displays a plurality of video sources, the user can select the required video source from the plurality of video sources, clicking Video 1 in Design 2 interface change state diagram 1 and clicking Done in the upper right corner of the interface, entering the graphical user interface shown in Design 2 interface change state diagram 2, at this time the video window displays the preview picture of the video source Video 1, the user can perform personalized editing on the selected video source Video 1 on this page, clicking Crop at the bottom of the interface, entering the graphical user interface shown in Design 2 interface change state diagram 3, the user can select an appropriate size picture as a close-up shot on this page according to the ratio or freely moving the crop box, after the selection is completed, clicking Save in the upper right corner of the interface, entering the graphical user interface shown in Design 2 interface change state diagram 4, the user can preview the effects of the close-up picture of the video source Video 1;The design 3 main view is an initial graphical user interface of the custom video source, the central part of the interface displays a video window, and the periphery of the interface displays various function modules capable of adjusting the picture of the video source, and the user can click different function modules to perform editing operations on the selected video source for corresponding purposes; clicking "Add Source" in the design 3 main view or the first icon from top to bottom on the left side of the interface, entering the graphical user interface as shown in design 3 interface change state diagram 1, the interface displays a plurality of video sources, the user can select the required video source from the plurality of video sources, clicking "Video 1" in the interface and clicking "Done" in the upper right corner of the interface, entering the graphical user interface as shown in design 3 interface change state diagram 2, at this time the video window displays the preview picture of the video source "Video 1", the user can perform personalized editing on the selected video source "Video 1" on this page, clicking the first icon from top to bottom on the right side of design 3 interface change state diagram 2, entering the graphical user interface as shown in design 3 interface change state diagram 3, the user can obtain a plurality of background materials of picture type or video type from different sources on this interface, clicking "background 1.jpg" in the interface and clicking "Done" in the upper right corner of the interface, entering the graphical user interface as shown in design 3 interface change state diagram 4, the user can preview the picture effect of the custom video source after adding the background material; the design 4 main view is an initial graphical user interface of the custom video source, the central part of the interface displays a video window, and the periphery of the interface displays various function modules capable of adjusting the picture of the video source, and the user can click different function modules to perform editing operations on the selected video source for corresponding purposes; clicking the first icon from top to bottom on the right side of the design 4 main view, entering the graphical user interface as shown in design 4 interface change state diagram 1, the user can obtain a plurality of background materials of picture type or video type from different sources on this interface, clicking "background 1.jpg" in the interface and clicking "Done" in the upper right corner of the interface, entering the graphical user interface as shown in design 4 interface change state diagram 2, clicking "Add Source" in design 4 interface change state diagram 2 or the first icon from top to bottom on the left side of the interface, entering the graphical user interface as shown in design 4 interface change state diagram 3, the interface displays a plurality of video sources, the user can select the required video source from the plurality of video sources, clicking "Video 1" in the interface and clicking "Done" in the upper right corner of the interface, entering the graphical user interface as shown in design 4 interface change state diagram 4, the user can preview the picture effect of the custom video source after adding the background material.