CN108848389B

CN108848389B - Panoramic video processing method and playing system

Info

Publication number: CN108848389B
Application number: CN201810844382.4A
Authority: CN
Inventors: 孟宪民; 李小波; 赵德贤
Original assignee: Hengxin Shambala Culture Co ltd
Current assignee: Hengxin Shambala Culture Co ltd
Priority date: 2018-07-27
Filing date: 2018-07-27
Publication date: 2021-03-30
Anticipated expiration: 2038-07-27
Also published as: CN108848389A

Abstract

The application discloses a panoramic video processing method and a panoramic video playing system. The method comprises the following steps: acquiring a video frame of a panoramic video; classifying and frame regression are carried out on the focus objects in each frame of image by using a neural network algorithm to obtain a focus area of each frame of image; and outputting the focus area image data in a high-definition mode, and simultaneously compressing and outputting each frame of background image data. This application will focus area image data with background image data exports for video playback device, plays the picture after fusing, can not only effectively reduce panorama video data transmission volume, still does not reduce user's immersion VR experience effect.

Description

Panoramic video processing method and playing system

Technical Field

The present application relates to the field of video processing technologies, and in particular, to a panoramic video processing method and a panoramic video playing system.

Background

In the field of VR image transmission, especially, because the VR requires binocular output, there is a demand for image output with double size in transmission, for example, a 4k image has a (3840 × 2160 × 4) byte size in transmission amount on a common network transmission, and a video image transmitting a 24 frame per second requires 32M × 24 — 759M data, while the binocular output of the VR requires 759M × 2 — 1518M data per second.

According to the feasible scheme at present, if the transmitting end uses X264 coding compression and then uses h264 decoding at the receiving end, compressed video stream data can be transmitted in real time, and the data volume of network transmission can be effectively reduced. However, in the field of network transmission, there are the situations that high-definition and ultra-high-definition video transmission causes delay aggravation and the possibility that real-time observation cannot be performed, and particularly, the transmission pressure of the 4K or 8K video is higher, and the higher the compression ratio of the corresponding video coding field is, the lower the definition is, the possibility that real-time transmission and high-definition video watching of a client cannot be performed can not be satisfied, and the requirement of VR binocular output panoramic high-definition images cannot be satisfied.

Disclosure of Invention

The embodiment of the application provides a panoramic video processing method and a panoramic video playing system, and aims to solve the problem of possibility of instant transmission and high-definition video watching of a client.

In order to solve the above technical problem, the embodiments of the present specification are implemented as follows:

according to a first aspect of embodiments of the present specification, a panoramic video processing method is provided. The method comprises the following steps:

acquiring a video frame of a panoramic video;

classifying and frame regression are carried out on the focus objects in each frame of image by using a neural network algorithm to obtain a focus area of each frame of image;

and outputting the image data of the focus area in a high-definition mode, and simultaneously compressing and outputting each frame of background image data to a video playing device.

Optionally, acquiring a video frame of a panoramic video includes: the video frame of the panoramic video is that a focus object is set for each lens by a director by using a panoramic camera and a photography and composition technical angle method.

Obtaining a video frame of a panoramic video, further comprising: setting the focus object is setting the training sample label.

Optionally, classifying and performing border regression on the focus object in each frame of image by using a neural network algorithm to obtain a focus area of each frame of image, including:

the neural network algorithm adopts a Faster R-CNN algorithm.

The training samples of the Faster R-CNN algorithm are obtained by the director determining the focus object class and by a separation algorithm.

The separation algorithm employs the FLANN approximate K nearest neighbor algorithm provided in OpenCV.

Optionally, the high-definition outputting the image data of the focus area, and compressing and outputting each frame of background image data to the video playing device, includes: the focus area includes information such as the type, position frame, and size of the focus object.

Outputting the focus area image data with high definition is to transmit the focus area image data with 4K resolution.

The compression output of the background image data of each frame means that the image of each frame is reduced to a 1k picture for ordinary transmission.

According to a second aspect of the embodiments of the present specification, there is provided a panoramic video processing method. The method comprises the following steps:

receiving focus area image data and background image data output by a panoramic video processing device;

fusing focus area image data and background image data;

and playing the fused image data picture.

Optionally, fusing the image data of the focus area and the background image data and playing the picture, including:

fusion refers to a method of automatically generating lines and shapes in the filter band between the edge contour 1 of the image data of the focal region and the edge contour 2 of the background image data.

According to a third aspect of the embodiments of the present specification, there is provided a panoramic video processing apparatus. The method comprises the following steps: the device comprises an input module, a classification and frame regression module and an output module;

acquiring a video frame of a panoramic video through an input module; the classification and frame regression module uses a neural network algorithm to classify and frame-regress the focus objects in each frame of image to obtain the focus area of each frame of image; the output module outputs the image data of the focus area in a high-definition mode, and simultaneously compresses and outputs each frame of background image data to the video playing device.

Optionally, the input module obtains a video frame of the panoramic video, and sets a focus object for each lens by using the panoramic camera and a shooting and composition technology angle method used by a director.

The input module further comprises:

setting the focus object is setting the training sample label.

Optionally, the classification and bounding box regression module includes:

the neural network algorithm adopts a Faster R-CNN algorithm.

The classification and border regression module further comprises:

The classification and frame regression module further comprises:

the focus area includes information such as the type, position frame, and size of the focus object.

Optionally, the output module outputs the image data of the focus area in a high-definition manner, and simultaneously compresses and outputs each frame of background image data to the video playing device, including:

the focus area image data is transmitted at 4K resolution.

The output module further comprises:

According to a fourth aspect of the embodiments of the present specification, there is provided a video playback apparatus including:

the system comprises a receiving module, a fusion module and a playing module;

the receiving module receives focus area image data and background image data output by the panoramic video processing device;

the fusion module fuses the focus area image data and the background image data;

and the playing module plays the fused image data.

Optionally, the fusing module fuses the focus area image data and the background image data, including:

According to a fifth aspect of embodiments herein, there is provided a video processing apparatus comprising:

at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to:

acquiring a video frame of a panoramic video;

According to a sixth aspect of embodiments of the present specification, there is provided a video playback apparatus including:

receiving the focus area image data and the background image data output by a panoramic video processing device;

fusing focus area image data and background image data;

and playing the fused image data picture.

According to a seventh aspect of embodiments herein, there is provided a panoramic video playback system including: a video processing device and a video playing device;

the video processing apparatus adopts the video processing apparatus according to the third aspect; the video playing device adopts the video playing device described in the fourth aspect.

According to an eighth aspect of embodiments herein, there is provided a non-transitory computer readable storage medium having instructions stored thereon which, when executed by a processor of an apparatus, enable the apparatus to perform a panoramic video processing method, the method comprising:

acquiring a video frame of a panoramic video;

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the specification.

The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:

the method comprises the steps of classifying focus objects in each frame of image and performing frame regression by using a neural network algorithm to obtain a focus area of each frame of image, outputting the focus area image data and the background image data to a video playing device, playing a picture after fusion, effectively reducing the transmission quantity of panoramic video data, and not reducing the immersive VR experience effect of a user.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

In the drawings:

FIG. 1 is a flow diagram illustrating a panoramic video processing method in accordance with an exemplary embodiment;

FIG. 2 illustrates a flow diagram of a panoramic video processing method in accordance with an exemplary embodiment;

FIG. 3 is a block diagram illustrating a panoramic video playback system in accordance with an exemplary embodiment;

FIG. 4 is a block diagram illustrating a video processing device according to an exemplary embodiment;

FIG. 5 is a block diagram of a video playback device in accordance with an exemplary embodiment;

fig. 6 is a block diagram illustrating an apparatus according to an example embodiment.

Detailed Description

The embodiment of the specification provides a panoramic video processing method, a panoramic video processing device and a panoramic video processing system.

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.

After the user experiences the VR helmet, what the user can observe is often the limited area he can see at present, the video is a complete and unlimited serial transmission of images, and the co-transmission of other invisible areas brings huge network bandwidth transmission requirements and machine codec performance requirements.

For the reasons, we find out the idea of local focus sharpening through blurring of non-visible areas, sharpening the parts of a video which need to be emphasized clearly to reach the sharpness of 4K or even 8K, such as people and animals, and the sharpness of secondary image areas such as scenes, buildings, flowers and plants is reduced to the level of 2K or even 1K, and the focus content in each image is outlined through artificial intelligence, for example, when one person is taken as the focus, the shape of the person is mostly sharpened, and then the surrounding radiation gradually becomes non-sharpened and spreads.

Fig. 1 is a flowchart illustrating a panoramic video processing method according to an exemplary embodiment, where the panoramic video processing method is used in a video processing apparatus, such as smart glasses, a playing device, a mobile phone, a computer, a tablet device, a personal digital assistant, and the like, as shown in fig. 1. The panoramic video processing method includes the following steps.

In step 101, a video frame of a panoramic video is acquired.

In the embodiment of the present specification, when video shooting is performed using a panoramic camera, a director sets a focus object for each shot by using a photography composition technique angle method, that is, sets a training sample label in advance.

Specifically, the panoramic video is a video shot in all directions by 360 degrees by using a 3D camera, and a user can adjust the video to watch the panoramic video up and down and left and right at will when watching the panoramic video. The panoramic video is a video image which is obtained by converting a static panoramic picture into a dynamic video, so that a user can watch the dynamic video at any angle from left to right and up to down, and a feeling of being personally on the scene in a real sense is generated. The panoramic video has depth of field, dynamic images, sound and the like, and simultaneously has sound and picture alignment and sound and picture synchronization. For example, the aerial panoramic video looks like the viewing angle of the air eagle overlooking the earth, and the air space portion of the picture has a great sense of depth of field and spaciousness, which can make us have nothing to do; and the panoramic video shot by the ground at head level can clearly express a plurality of details of the environment, so that people can know the specific position, the specific shape, the details and the like of the environment.

Specifically, the shooting composition technical angle is to select shooting points around a subject on the same horizontal plane with the subject as a center. Under the condition that the shooting distance and the shooting height are not changed, different side images of the shot object can be shown in different shooting directions, and different combination relations between the main body and the accompanying body and between the main body and the environment are changed. The shooting direction is generally divided into: a front angle, an oblique side angle, a reverse side angle, and a back angle. Such as: in a two-person fighting scene, the process of playing one person's front first and then playing two-person fighting from the side is possible, and two shots are generated. The front side of the shooting is a lens, and the side surface of the shooting is also a lens; statistics are made of the objects present in the different angles of photography and a person will be treated as a focus if it appears in all cameras at the same time.

In step 102, a neural network algorithm is used to classify and frame-regress the focus object in each frame of image, and a focus area of each frame of image is obtained.

In the embodiment of the present specification, the neural network algorithm uses the FasterR-CNN algorithm.

Specifically, the Faster R-CNN model is mainly composed of two modules: the RPN candidate frame extraction module and the Fast R-CNN detection module can be further divided into 4 parts: convolutional Layer (Conv Layer), frame candidate extraction Layer (RPN), Pooling Layer (RoI Pooling), Classification and bounding Regression Layer (Classification and Regression).

Specifically, the convolutional layer includes a series of convolution (Conv + Relu) and Pooling (Pooling) operations for extracting features (feature maps) of the image, and generally, the existing classical network model ZF or VGG16 is directly used, and weight parameters of the convolutional layer are shared by RPN and Fast RCNN, which is also the key point for accelerating the training process and improving the real-time performance of the model.

Specifically, the RPN network is used for generating a regional candidate frame propofol, based on a multi-scale Anchor introduced by a network model, classifying whether anchors belong to a target (for future) or a background (background) through Softmax, and performing Regression prediction on the anchors by using Bounding Box Regression to obtain an accurate position of the propofol, and the accuracy position is used for subsequent target identification and detection.

Specifically, the Pooling layer (RoI posing) integrates information of convolutional layer feature maps and candidate frame feature maps, maps coordinates of the feature in the input image to the last layer of feature map (conv5-3), performs Pooling operation on the corresponding region in the feature map to obtain a Pooling result output by a fixed size (7 × 7), and connects with the following full connection layer.

Specifically, the classification and border regression layer is a full connection layer followed by two sub-connection layers, namely a classification layer (cls) and a regression layer (reg), wherein the classification layer is used for judging the type of the Proposal, and the regression layer predicts the accurate position of the Proposal through bounding box regression.

In the embodiment of the present specification, for an image of an arbitrary size P × Q, scaling is first performed to a fixed size M × N (it is required that the long side does not exceed 600 and the short side does not exceed 600), and then the scaled image is input to a Conv Layer using a VGG16 model, where the last feature map is Conv5-3 and the feature number (channels) is 512. The RPN network executes 3 multiplied by 3 convolution operation on the characteristic diagram conv5-3, then is connected with a 512-dimensional full connection layer, and is connected with two sub connection layers after the full connection layer, wherein the two sub connection layers are respectively used for classification and frame regression of anchors, and then proposals is obtained through calculation and screening. The Rois Pooling layer extracts the Proprosal feature from the feature maps by utilizing the Proposal to perform Pooling operation, and sends the pool to a subsequent FastR-CNN network for classification and frame regression. Classification and frame regression are carried out in the RPN and the FastR-CNN, but the classification and the frame regression are different, the classification in the RPN is to judge the probability (score) that corresponding anchors in conv5-3 belong to a target and a background, offset and scaling of the anchors are obtained through regression, and the Proposal used for subsequent detection and identification is screened according to the target score value; FastR-CNN is used for classifying and identifying the Proposal extracted from the RPN network, and the accurate position of the target (Object) is obtained through regression parameter adjustment.

In the embodiment of the present specification, the training samples of the FasterR-CNN algorithm are obtained through a separation algorithm, and a relationship list between different shots and objects is manually collected, for example, 100 shots are found to respectively specify which are focus objects, and then the objects are put into the separation algorithm to obtain samples, and the more training sample data, the more accurate the obtained focus object is. The separation algorithm uses a FLANN approximate K nearest neighbor algorithm provided in OpenCV, continuous frames use a characteristic point comparison mode, and the more similar the characteristic points of the images of the front and rear frames, the higher the probability of representing the same shot; separating all time periods of the same shot by using a FLANN approximate K nearest neighbor algorithm, thereby obtaining a labeled training set of a Faster R-CNN algorithm; executing a fast R-CNN algorithm on the training set to obtain a trained classification and frame regression model; when the trained classification and frame regression model is input into the video frame, the focus area of each frame of image can be obtained, and the focus area comprises information such as the category, position frame and size of the focus object.

In step 103, the focus area image data is output in high definition, and each frame of background image data is simultaneously compressed and output to the video playing device.

In the embodiment of the present specification, the high definition output focus area image data is transmission of the focus area image data at 4K resolution; the compression output of the background image data of each frame means that the image of each frame is reduced to a 1k picture for ordinary transmission.

Fig. 2 is a flowchart illustrating a panoramic video processing method according to an exemplary embodiment, where the panoramic video processing method is used in a video playing apparatus, such as smart glasses, a playing device, a mobile phone, a computer, a tablet device, a personal digital assistant, and the like, as shown in fig. 2. The panoramic video processing method includes the following steps.

In step 201, focus area image data and background image data output by the panoramic video processing apparatus are received.

In step 202, focus area image data and the background image data are fused.

In step 203, the fused image data frame is played.

In the embodiment of the specification, the fusion is a method for automatically generating lines and shapes in a filter band between a focus area image data edge outline 1 and a background image data edge outline 2 by blurring a focus area edge and setting the focus area edge as a transparent channel, gradually transparency and displaying the focus area as a background image. When the video playing device plays, a non-high-definition image (background image) is rendered, then a layer of focus image is rendered in the corresponding area on the non-high-definition image, and the focus image is directly pasted to generate a fault phenomenon, namely, the fusion edge abnormality caused by the sudden display change from the high-definition image to the non-high-definition image is generated; the process of using lines from (edge contour 1) intense (focus high definition image) to gradually changing to edge contour 2 (background image) makes it possible to feel a more comfortable area (blend area) like excessive depth of field over the entire display.

Through the above embodiments, the panoramic video processing method of the present specification is applicable to a panoramic video playing system composed of a video processing device and a video playing device, where the video processing device and the video playing device may be two components of the same playing device, for example, a video processing module and a video playing module are integrated in smart glasses at the same time, or may be two independent devices, for example, a computer and smart glasses, where the computer performs video processing and the smart glasses perform video playing. Fig. 3 is a block diagram illustrating a panoramic video playback system in accordance with an exemplary embodiment. Referring to fig. 3, the panoramic video playback system 10 includes a video processing apparatus 11 and a video playback apparatus 12. The video processing device 11 is configured to acquire a video frame of a panoramic video; classifying and frame regression are carried out on the focus objects in each frame of image by using a neural network algorithm to obtain a focus area of each frame of image; and outputting the image data of the focus area in a high-definition mode, and simultaneously compressing and outputting each frame of background image data to a video playing device. The video playing device 12 is configured to receive the focus area image data and the background image data output by the panoramic video processing device; fusing the focus area image data and the background image data; and playing the fused image data picture.

Fig. 4 is a block diagram illustrating a video processing device according to an example embodiment. Referring to fig. 4, the video processing apparatus 20 includes a video input module 21, a classification and bounding box regression module 22, and an output module 23.

The input module 21 acquires a video frame of the panoramic video; the classification and frame regression module 22 uses a neural network algorithm to classify and frame-regress the focus objects in each frame of image, and obtains the focus area of each frame of image; the output module 23 outputs the image data of the focus area in high definition, and simultaneously compresses and outputs each frame of background image data to the video playing device.

Optionally, the input module 21 obtains a video frame of the panoramic video, and sets a focus object for each lens by using a panoramic camera and a shooting composition angle method used by a director.

The input module 21 further includes:

and the object with the focus is the label with the training sample.

Optionally, the classification and bounding box regression module 22 includes:

the neural network algorithm adopts a Faster R-CNN algorithm.

The classification and bounding box regression module 22 further includes:

the training sample of the Faster R-CNN algorithm is obtained by a director determining the focus object class and through a separation algorithm.

The classification and bounding box regression module 22 further includes:

the separation algorithm employs a FLANN approximate K nearest neighbor algorithm provided in OpenCV.

The classification and bounding box regression module 22 further includes:

Optionally, the output module 23 outputs the image data of the focus area in high definition, and simultaneously compresses and outputs each frame of background image data to the video playing device, and the method includes:

transmitting the focus area image data at a resolution of 4K.

The output module 23 further includes:

the compression output of each frame of background image data means that each frame of image is reduced to a 1k image for ordinary transmission.

Fig. 5 is a block diagram illustrating a video playback device according to an example embodiment. Referring to fig. 5, the video playback device 30 includes a receiving module 31, a fusing module 32, and a playback module 33.

The receiving module 31 receives the focus area image data and the background image data output by the panoramic video processing apparatus;

a fusion module 32 fuses the focus area image data and the background image data;

the playing module 33 plays the fused image data.

Optionally, the fusing module 32 fuses the focus area image data and the background image data, including:

the fusion is a method for automatically generating lines and shapes in a filter band between the edge profile 1 of the image data of the focus area and the edge profile 2 of the background image data.

FIG. 6 is a block diagram illustrating an apparatus in accordance with an example embodiment. For example, the apparatus 600 may be a mobile phone, a computer, a tablet device, a personal digital assistant, and the like. The apparatus 600 of the present embodiment can be used as a video processing apparatus in the above-described embodiment, and can also be used as a video playing apparatus in the above-described embodiment.

Referring to fig. 6, apparatus 600 may include one or more of the following components: a processing component 602, a memory 604, a power component 606, a multimedia component 608, an audio component 610, an interface to input/output (I/O) 612, a sensor component 614, and a communication component 616.

The processing component 602 generally controls overall operation of the device 600, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 602 can include one or more modules that facilitate interaction between the processing component 602 and other components. For example, the processing component 602 can include a multimedia module to facilitate interaction between the multimedia component 608 and the processing component 602.

The memory 604 is configured to store various types of data to support operations at the apparatus 600. Examples of such data include instructions for any application or method operating on device 600, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 604 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

Power components 1006 provide power to the various components of device 600. Power components 1006 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for device 600.

The multimedia component 608 includes a screen that provides an output interface between the device 600 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 600 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 610 is configured to output and/or input audio signals. For example, audio component 610 includes a Microphone (MIC) configured to receive external audio signals when apparatus 600 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory 604 or transmitted via the communication component 616. In some embodiments, audio component 610 further includes a speaker for outputting audio signals.

The I/O interface 612 provides an interface between the processing component 602 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor component 614 includes one or more sensors for providing status assessment of various aspects of the apparatus 600. For example, the sensor component 614 may detect an open/closed state of the device 600, the relative positioning of components, such as a display and keypad of the device 600, the sensor component 614 may also detect a change in position of the device 600 or a component of the device 600, the presence or absence of user contact with the device 600, orientation or acceleration/deceleration of the device 600, and a change in temperature of the device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 614 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 616 is configured to facilitate communications between the apparatus 600 and other devices in a wired or wireless manner. The apparatus 600 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 600 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer readable storage medium comprising instructions, such as the memory 604 comprising instructions, executable by the processor 620 of the apparatus 600 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the electronic device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and the relevant points can be referred to the partial description of the embodiments of the method.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose logic functions are determined by programming the device by a user. A digital system is "integrated" on a PLD by the designer's own programming without the need for the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Language, HDL, las, software, Hardware Description Language (software Description Language), and so on. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: the ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, the present specification embodiments may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data.

Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM),

Digital Versatile Disks (DVDs) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium may be used to store information that may be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that 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. The use of the phrase "including a" does not exclude the presence of other, identical elements in the process, method, article, or apparatus that comprises the same element, whether or not the same element is present in all of the same element.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

While preferred embodiments of the present specification have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present specification without departing from the spirit and scope of the specification. Thus, if such modifications and variations of the present specification fall within the scope of the claims of the present specification and their equivalents, the specification is intended to include such modifications and variations.

Claims

1. A panoramic video processing method, comprising:

acquiring a video frame of a panoramic video;

outputting the image data of the focus area in a high-definition mode, and simultaneously compressing and outputting each frame of background image data to a video playing device;

the acquiring the video frame of the panoramic video comprises: the video frame of the panoramic video is that a panoramic camera is used, and a director sets a focus object for each lens by using a photographic composition technical angle method; the set focus object is a set training sample label;

the shooting direction of the shooting composition technical angle is divided into: a front angle, a diagonal angle, a side angle, a reverse angle, and a back angle;

counting objects existing in the shooting at different angles, and if a certain object appears in all the cameras at different angles at the same time, treating the object as a focus object;

wherein the neural network algorithm adopts a Faster R-CNN algorithm.

2. The method of claim 1, further comprising:

the training samples of the Faster R-CNN algorithm are obtained by a separation algorithm.

3. The method of claim 2, further comprising:

4. The method of claim 1, further comprising:

the focus area includes a category, a position frame, and size information of a focus object.

5. A panoramic video processing method, comprising:

receiving the focus area image data and the background image data obtained by the panoramic video processing method according to any one of claims 1 to 4;

fusing the focus area image data and the background image data;

playing the fused image data picture;

wherein the fusion is blurred through the edge of the focus area and set as a transparent channel, and the focus area is gradually transparent and displayed as a background image.

6. The method of claim 5, wherein fusing the focus area image data and the background image data to play a picture comprises:

the fusion is a method for automatically generating lines and shapes in a filter band between the edge profile of the image data of the focus area and the edge profile of the background image data.

7. A panoramic video playback system, comprising: a video processing device and a video playing device;

the video processing device is used for executing the panoramic video processing method of any one of claims 1-4; the video playing device is used for executing the panoramic video processing method of any one of claims 5-6.