Integrated video management system and method for variable video quality

Abstract

The present invention relates to an integrated video management system and method for variable video quality, which normally monitor videos of a plurality of channels received from cameras through an integrated screen, and when an event is detected in a specific channel, automatically improve the video quality of the channel in which the event is detected, so that the cause of the event can be quickly identified through more precise monitoring.

Description

Integrated video control system and method for variable video quality

[0001] The present invention relates to an integrated video monitoring technology for variable video quality, and more specifically, to an integrated video control system and method for variable video quality that normally monitors multiple channel-specific videos received from cameras through an integrated screen, and when an event is detected in a specific channel, automatically improves the video quality of the channel where the event was detected to enable rapid identification of the cause of the event through more precise monitoring.

[0002] A multi-channel integrated monitoring system refers to a system capable of monitoring multiple video feeds received from multiple cameras or sensors in real time on a single integrated screen. For example, it is a system that allows for the simultaneous monitoring and management of video feeds from multiple cameras in applications such as security, traffic management, and industrial site surveillance.

[0003] Multi-channel integrated monitoring systems are primarily used in control systems because they allow video transmitted from multiple cameras to be viewed simultaneously on a single screen, eliminating the need to monitor individual cameras separately and significantly increasing operational efficiency.

[0004] For example, since video footage from various regions can be managed in an integrated manner from a single location, it is highly advantageous for efficiently managing multiple sites, such as traffic control, monitoring production lines in large factories, and urban safety management. Furthermore, monitoring with an integrated system instead of operating multiple individual monitoring systems can reduce hardware and personnel costs.

[0005] In addition, it allows you to grasp information collected from various locations or angles at a glance, which helps in comprehensively understanding and judging the overall situation.

[0006] As an example of a multi-channel integrated monitoring system, local governments and public institutions install numerous cameras to monitor video footage for safety, crime prevention, management, and traffic; in particular, road traffic-related agencies, such as those operating on expressways and national roads, widely utilize this for Intelligent Transport Systems (ITS).

[0007] Even if numerous cameras are installed everywhere and an integrated monitoring system is introduced, it is difficult to find meaningful scenes among the vast amount of footage.

[0008] For example, in an environment where multiple cameras are installed, the image quality may vary depending on the position or performance of each camera, and lighting conditions, weather, and camera aging also affect the image quality, and it is easy to miss small movements or important details in low-quality video.

[0009] Furthermore, low-resolution cameras struggle to accurately capture details when shooting wide areas, which can make it time-consuming to identify meaningful scenes. Particularly when displaying multiple channels simultaneously, the reduced number of pixels allocated to a single screen lowers image clarity, and the possibility of missing minor changes or events cannot be ruled out.

[0010] In addition, since video captured by numerous cameras must be processed simultaneously in real time, the system's processing power or network bandwidth may be overloaded, which can cause video delays or temporary quality degradation, making it difficult to detect important moments in real time.

[0011] Korean Patent Publication No. 2019-0061241 discloses an adaptive object recognition technology that processes data from multi-channel video streams in real time. The prior art resolves resource shortages by mapping between virtual resources when fewer resources are allocated than the requested resource quota; however, the method of supplementing resources using virtual resources can lower video quality and has limitations in that it may miss important details.

[0012] The problem that the present invention aims to solve is to provide an integrated video control system and method with variable video quality that normally monitors multiple channel-specific videos received from cameras through an integrated screen, and when an event is detected in a specific channel, automatically improves the video quality of the channel where the event was detected to enable rapid identification of the cause of the event through more precise monitoring.

[0013] The present invention proposes, as one of the means for solving the problem, an integrated video control system with variable video quality comprising: a plurality of cameras; an image processor that converts channel-specific images received from the cameras into images of a preset quality; an image organizer that configures the channel-specific images into a single integrated screen; a video monitor that monitors the occurrence of a preset event for each channel of the integrated screen; and a software service server that includes an image controller that instructs the image processor to further improve the video quality of the channel where an event is detected when an event is detected in any one channel.

[0014] In one embodiment, the quality of the image may be at least one of frames per second (fps) and resolution.

[0015] In one embodiment, the image constructor may reconstruct the integrated screen so that the image size of the channel where the event was detected is enlarged.

[0016] In one embodiment, the image controller may instruct the image processor to increase the image quality of the channel where the event was detected when an event is detected in any one channel, and to decrease the image quality of other channels.

[0017] In one embodiment, the image controller may determine the up-adjustment value and down-adjustment value of the image quality by considering the available resources of the image processing processor (GPU).

[0018] In one embodiment, the event may be any one of a fire, a traffic accident, a traffic jam, a violation of safety rules, facial recognition of a wanted person, or recognition of a speeding vehicle.

[0019] In one embodiment, the video surveillance device may use at least one AI learning model, and may perform classification, regression analysis, clustering, association analysis, and anomaly detection through CNN, RNN, LSTM, or GAN.

[0020] As another means of solving the problem, the present invention proposes an integrated video control system with variable video quality comprising: a plurality of cameras that capture videos of different quality by remote setting; a video organizer that configures channel-specific videos received from the cameras into a single integrated screen; a video monitor that monitors the occurrence of a preset event for each channel of the integrated screen; and a software service server that includes a video controller that instructs the camera of the channel where the event was detected to transmit a higher quality video when an event is detected in at least one channel video.

[0021] In one embodiment, the quality of the image may be at least one of frames per second (fps) and resolution.

[0022] In one embodiment, the image constructor may reconstruct the integrated screen so that the image size of the channel where the event was detected is enlarged.

[0023] In one embodiment, when an event is detected in at least one channel video, the image controller may instruct the camera of the channel in which the event was detected to transmit a higher quality video and instruct the camera of the other channel to transmit a lower quality video.

[0024] In one embodiment, the image controller may determine the level of upward and downward adjustment of the image quality by considering the available resources of the image processing processor (GPU).

[0025] In one embodiment, the event may be any one of a fire, a traffic accident, a traffic jam, a violation of safety rules, facial recognition of a wanted person, or recognition of a speeding vehicle.

[0026] In one embodiment, the video surveillance device may use at least one AI learning model, and may perform classification, regression analysis, clustering, association analysis, and anomaly detection through CNN, RNN, LSTM, or GAN.

[0027] As another means of solving the problem, the present invention proposes an integrated video control method with variable video quality, comprising: a step in which an image processor of a software service server converts channel-specific images received from a plurality of cameras into images of a preset quality; a step in which an image organizer of the software service server configures the channel-specific images into a single integrated screen; a step in which an image monitor of the software service server monitors the occurrence of a preset event for each channel of the integrated screen; and a step in which, when an event is detected in any one channel, an image controller of the software service server instructs the image processor to further improve the video quality of the channel in which the event was detected.

[0028] In one embodiment, the quality of the image may be at least one of frames per second (fps) and resolution.

[0029] In one embodiment, the image organizer of the integrated screen configuration step may reconfigure the integrated screen so that the image size of the channel where the event was detected is enlarged.

[0030] In one embodiment, the image controller in the step of instructing to increase the image quality of the channel where the event is detected may, when an event is detected in any one channel, instruct the image processor to further increase the image quality of the channel where the event is detected and to further decrease the image quality of other channels.

[0031] In one embodiment, the image controller in the step of instructing to increase the image quality of the channel where the event is detected may determine the upward adjustment value and the downward adjustment value of the image quality by considering the available resources of the image processing processor (GPU).

[0032] In one embodiment, the event may be any one of a fire, a traffic accident, a traffic jam, a violation of safety rules, facial recognition of a wanted person, or recognition of a speeding vehicle.

[0033] In one embodiment, the video monitor of the event occurrence monitoring step may use at least one AI learning model, and may perform classification, regression analysis, clustering, association analysis, and anomaly detection through CNN, RNN, LSTM, or GAN.

[0034] According to an embodiment of the present invention, in normal circumstances, multiple channel-specific videos received from cameras are monitored through an integrated screen, and when an event is detected in a specific channel, the video quality of the channel where the event was detected is automatically enhanced so that the cause of the event can be quickly identified through more precise monitoring.

[0035] FIG. 1 is a schematic diagram showing the overall concept of an integrated video control system with variable image quality according to Embodiment 1 of the present invention.

[0036] FIG. 2 is a block diagram showing the detailed configuration of the software service server exemplified in FIG. 1.

[0037] FIG. 3 is a block diagram showing the configuration of an integrated video control system with variable video quality according to Embodiment 2 of the present invention.

[0038] FIG. 4 is a flowchart illustrating an integrated video control method for variable video quality according to Example 3.

[0039] Several embodiments of the present invention will be described in detail below with reference to the drawings. However, this is not intended to limit the present invention to any specific embodiment, and it should be understood that all transformations, equivalents, and substitutions including the technical concept of the present invention are included within the scope of the present invention.

[0040] In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0041] Where in this specification it is stated that one component “have” or “comprise” a sub-component, it means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0042] In this specification, the terms "...Unit," "...Module," and "Component" refer to a unit that processes at least one function or operation, and may be implemented in hardware, software, or a combination of hardware and software.

[0043] In this specification, the term “connect” may mean that two components are directly connected, but is not necessarily limited thereto, and may also mean that they are connected via one or more other components positioned between the components.

[0044] <Example 1>

[0045] FIG. 1 is a schematic diagram showing the overall concept of an integrated video control system with variable image quality according to Embodiment 1 of the present invention.

[0046] As shown in FIG. 1, the system of the present embodiment includes a plurality of cameras (10) and a software service server (Software as a Service, SaaS).

[0047] The camera (10) is also referred to as a video surveillance device and may perform the function of capturing and recording video or transmitting it over a network. For example, the camera (10) used in this embodiment may be an IP camera (10) (Internet Protocol Camera). An IP camera (10) is a digital camera (10) that transmits data using the Internet Protocol and is a device capable of transmitting video over a network and monitoring it remotely.

[0048] The camera (10) is installed in various regions or various locations, and the images captured by the camera (10) are used in a software service server to efficiently manage various locations, such as traffic control, monitoring of production lines in large factories, urban safety management, and crime prevention.

[0049] The software service server normally provides multiple channel-specific videos received from cameras (10) as an integrated screen, thereby making it advantageous for the user to efficiently manage multiple locations by monitoring multiple channels of video. In particular, when an event is detected in a specific channel, the software service server automatically improves the video quality of the channel where the event was detected, enabling the user to quickly identify the cause of the event through more precise monitoring.

[0050] The software service server of this embodiment may be operated as Software as a Service (SaaS).

[0051] Software as a Service (SaaS) is a software service model provided over the Internet without the need for installation or maintenance; the software runs on cloud servers, and users can access it anytime, anywhere via an Internet connection.

[0052] The user terminal (20) is a terminal used by a person in charge of the control center, and can access Software as a Service (SaaS) to view the integrated monitoring screen provided by the software service server.

[0053] In this embodiment, the user terminal (20) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a navigation system, a laptop equipped with a web browser, a desktop, a laptop, etc. The user terminal is a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a navigation system, a PCS (Personal Communication System), a GSM (Global System for Mobile communications), a PDC (Personal Digital Cellular), a PHS (Personal Handyphone System), a PDA (Personal Digital Assistant), an IMT (International Mobile Telecommunication)-2000, a CDMA (Code Division Multiple Access)-2000, a W-CDMA (W-Code Division Multiple Access), a Wibro (Wireless Broadband Internet) terminal, a smartphone, a smartpad, a tablet PC, etc.

[0054] FIG. 2 is a block diagram showing the detailed configuration of the software service server (100) exemplified in FIG. 1.

[0055] As shown in FIGS. 1 and 2, the software service server (100) includes an image processor (110), an image configurator (120), an image monitor (130), and an image controller (140).

[0056] The image processor (110) converts the channel-specific images received from the cameras (10) into images of a preset quality so that they can be displayed on an integrated screen. Additionally, the image processor (110) converts the images into images of a preset quality according to the instructions of the image controller (140) to be described later.

[0057] For example, the image quality converted in the image processor (110) may be at least one of the frames per second (fps) and the resolution of the captured image.

[0058] The image processor (110) may convert the image quality using a video compression codec or may convert the image quality using video editing software.

[0059] For example, the image processor (110) can convert the number of frames per second and the resolution during the process of compressing image data using a video codec (e.g., H.264, H.265, VP9, ​​etc.). Converting the number of frames per second is a method of sampling frames, for example, converting a 60 FPS video to 30 FPS by omitting some of the frames.

[0060] A streaming protocol may be used for real-time transmission of video between the image processor (110) and the camera (10). For example, RTSP (Real-Time Streaming Protocol) may be used, and RTSP is a real-time transmission control protocol that controls media streaming and provides functions such as play, pause, and stop.

[0061] The video organizer (120) organizes multiple channel-specific videos into a single integrated screen.

[0062] For example, the video organizer (120) may be configured to arrange multiple channel-specific videos into a uniformly divided screen layout so that multiple channel videos can be monitored simultaneously. For example, the video organizer (120) may arrange multiple channel-specific videos uniformly in a 2x2, 3x3, 4x4, etc. manner according to the screen division layout, and thereby allow the person in charge to view the videos of multiple cameras (10) in real time on one screen.

[0063] As another example, the video organizer (120) may organize multiple channel-specific videos into a single integrated screen, and may divide and arrange the channel at the point where an event occurs repeatedly, the channel at the point where an event occurred recently, or the channel where the distance between the camera (10) and the subject is large into a larger area than other channels.

[0064] Meanwhile, the video constructor (120) may reconstruct the integrated screen by enlarging the video size of the channel where the event was detected when an event is detected in any one channel.

[0065] The image organizer (120) may enlarge the size of the image of the channel where the event was detected and temporarily display only the image of the channel where the event was detected on the screen, or may place the image of the channel where the event was detected towards the center of the screen while in an enlarged state.

[0066] As such, if only the video of the channel where an event was detected is displayed on the integrated screen or enlarged and displayed at the center of the integrated screen, it can increase focus on important events and enhance security or surveillance capabilities.

[0067] The video monitor (130) monitors the occurrence of pre-set events for each channel of the integrated screen.

[0068] The events monitored by the video monitor (130) may be any one of the following: fire, traffic accident, traffic congestion, violation of safety rules, recognition of a wanted person's face, or recognition of a speeding vehicle, but are not limited to these.

[0069] For example, the video monitor (130) may use at least one AI learning model, and may perform classification, regression analysis, clustering, association analysis and anomaly detection through a CNN (convolutional neural network), RNN (recurrent neural network), LSTM (long term short memory) or GAN (generative adversarial network).

[0070] CNNs are neural networks used in image processing. They excel at learning spatial patterns in image data and extract image features using multiple convolution filters. As such, CNNs are widely used for object recognition, face recognition, and event detection within images or videos. CNNs recognize objects in each frame and analyze what actions those objects are performing. For example, when a person falls or performs abnormal actions in a camera (10) video, the CNN can detect this pattern and send a warning.

[0071] An RNN is a neural network designed to process sequential data and is used to analyze changes over time in images by remembering previous information (temporal dependencies) and calculating the output of the next step. For example, an RNN can analyze human movement or the trajectory of an object by identifying temporal changes between frames in an image.

[0072] LSTM is an extension of RNN and is a model designed to solve the long-term dependency problem. LSTM is used to track and analyze important events over time in images.

[0073] GANs are generative models in which two neural networks (generators and discriminators) learn from data while competing against each other. The generator attempts to produce data similar to reality, while the discriminator is trained to distinguish between real data and generated data. In GANs, the discriminator distinguishes between normal and abnormal images and can send alerts when unusual events are detected.

[0074] When an event is detected in any one channel, the image controller (140) instructs the image processor (110) to increase the image quality of the channel in which the event was detected.

[0075] The integrated video control system of the present embodiment receives video from multiple channels of cameras (10) in real time. Since high-resolution video or video with a high frame rate uses a lot of bandwidth, it may be inefficient to always maintain the video quality of all channels at the highest level.

[0076] Therefore, when no event occurs, the videos for each channel displayed on the integrated screen can be maintained at a low resolution or low frame rate to reduce overall bandwidth usage and manage resources efficiently.

[0077] At this time, since it is necessary to observe important situations more clearly in the channel where the event is detected, the video controller (140) can temporarily increase the quality of the video where the event is detected only at this time and use bandwidth intensively, thereby allowing for more precise verification of important video without overloading the network.

[0078] For example, the video controller (140) may instruct the output of video where no event is detected at 30 frames, and then instruct the output of video where an event is detected at 60 frames.

[0079] Additionally, for more efficient resource management, the image controller (140) may instruct the image processor (110) to increase the image quality of the channel where the event was detected when an event is detected in one channel, and to lower the image quality of other channels.

[0080] For example, the video controller (140) may instruct the output of the video in which no event is detected to be 30 frames, and when an event is detected in any one of the videos, the output of the video in which the event is detected is increased to 60 frames, while the output of the video in which no event is detected is decreased to 15 frames.

[0081] In one embodiment, the image controller (140) may determine the up-adjustment value and down-adjustment value of the image quality by considering the available resources of the image processing processor (GPU). For reference, if the software service server (100) is implemented in a SaaS form, the software service server (100) may receive available resource information from the user terminal (20).

[0082] High-resolution video or high frame rates require more processing power from the video processor (110), and there is a problem that high-spec hardware is required to process all channels in high quality on the integrated screen, or that the CPU or GPU may be overloaded.

[0083] Therefore, to conserve resources when no event occurs, the video for each channel displayed on the integrated screen is maintained at a low resolution or low frame rate; when an event is detected, the quality of the video is temporarily increased according to available resources to enable faster and more accurate extraction of important information; and the remaining channels are processed at basic video quality or their quality is downgraded according to available resources to efficiently allocate hardware resources.

[0084] In one embodiment, the image controller (140) instructs the channel where no event is detected to perform low-resolution or low-frame-rate image processing to minimize GPU usage, while concentrating the GPU's computational resources on the channel where an event is detected to improve the image quality of the channel and enable real-time high-resolution processing.

[0085] In one embodiment, the image controller (140) may adjust the priority to prioritize the processing of image quality for the channel where the event was detected by reflecting the event in GPU scheduling when an event is detected in any one channel.

[0086] Accordingly, the image controller (140) can achieve the goals of resource saving, processing performance optimization, and rapid response to events by maximizing resource efficiency of the entire system through the redistribution and scheduling of GPU resources, and optimizing high-quality image processing by intensively using GPU resources only in the channel where an event is detected.

[0087] <Example 2>

[0088] Example 2 relates to a technology in which a plurality of cameras (10) capture images of different quality by remote setting, and the captured images of multiple channels are monitored through an integrated screen, and the camera of the channel where an event is detected captures and transmits an image of higher quality.

[0089] FIG. 3 is a block diagram showing the configuration of an integrated video control system with variable video quality according to Embodiment 2 of the present invention.

[0090] As shown in FIG. 3, the system of the present embodiment includes a plurality of cameras (10) and a software service server (200).

[0091] Multiple cameras (10) can perform the function of capturing images and transmitting them to a network.

[0092] The camera (10) used in this embodiment may be an IP camera (10) (Internet Protocol Camera).

[0093] Multiple cameras (10) can capture images of different quality by remote settings transmitted from the software service server (200).

[0094] For example, a plurality of cameras (10) can take photos by adjusting at least one of the frames per second (fps) and resolution by remote settings.

[0095] Multiple cameras (10) may adjust the frame rate per second and resolution by changing the settings of the cameras (10) to take pictures, and the quality of the captured video may be adjusted by installing a video compression codec or video editing software on the cameras (10).

[0096] The software service server (200) normally monitors multiple channel-specific videos received from cameras (10) through an integrated screen, thereby making it advantageous to manage multiple locations efficiently, but when an event is detected in a specific channel, it receives a high-quality video from the camera (10) where the event was detected, enabling it to quickly identify the cause of the event through more precise monitoring.

[0097] The software service server (200) includes a video configurator (210), a video monitor (220), and a video controller (230).

[0098] The video organizer (210) organizes multiple channel-specific videos received from multiple cameras (10) into a single integrated screen.

[0099] For example, the video organizer (210) may be configured to arrange multiple channel-specific videos into a uniformly divided screen layout so as to allow monitoring of multiple channel videos simultaneously.

[0100] Meanwhile, the video constructor (210) may reconstruct the integrated screen by enlarging the video size of the channel where the event was detected when an event is detected in any one channel.

[0101] The image organizer (210) may enlarge the size of the image of the channel where the event was detected and temporarily display only the image of the channel where the event was detected on the screen, or enlarge the size of the image of the channel where the event was detected and position it toward the center of the screen.

[0102] The video monitor (220) monitors the occurrence of pre-set events for each channel of the integrated screen.

[0103] The events monitored by the video monitor (220) may be any one of the following: fire, traffic accident, traffic congestion, violation of safety rules, recognition of a wanted person's face, or recognition of a speeding vehicle, but are not limited to these.

[0104] For example, the video monitor (220) may use at least one AI learning model, and may perform classification, regression analysis, clustering, association analysis and anomaly detection through a CNN (convolutional neural network), RNN (recurrent neural network), LSTM (long term short memory) or GAN (generative adversarial network).

[0105] The AI ​​learning model is the same as that described in Example 1, so a redundant explanation is omitted.

[0106] When an event is detected in at least one channel video, the video controller (230) instructs the camera (10) of the channel where the event was detected to transmit a higher quality video.

[0107] For example, the image controller (230) may instruct the transmission of the image of the camera (10) where no event is detected at 30 frames, and the transmission of the image of the camera (10) where an event is detected at 60 frames.

[0108] Additionally, the video controller (230) may instruct that the video in which no event is detected be transmitted at 30 frames, and when an event is detected in the video of any one camera (10), the video of the camera in which the event is detected be increased to 60 frames, while the video of the camera (10) in which no event is detected is decreased to 15 frames and transmitted.

[0109] In one embodiment, the image controller (230) may determine and instruct the camera (10) to increase and decrease the image quality by taking into account the available resources of the image processing processor (GPU).

[0110] <Example 3>

[0111] FIG. 4 is a flowchart illustrating an integrated video control method for variable video quality according to Example 3.

[0112] As shown in FIG. 4, the integrated video control method for variable video quality of the present embodiment includes a plurality of camera video reception steps (S11), a conversion step to a video of preset quality (S12), an integrated screen configuration step (S13), an event occurrence monitoring step (S14), and a video quality adjustment instruction step (S15).

[0113] In the method of the present embodiment, when images are received from a plurality of cameras (S11), the image processor converts the channel-specific images received from the cameras into images of a preset quality (S12).

[0114] At this time, the image processor may also convert to the default frame and resolution settings.

[0115] The video organizer compiles multiple channel-specific videos into a single integrated screen (S13).

[0116] For example, the video organizer can be configured to allow simultaneous monitoring of multiple channels' videos by arranging them into a uniformly divided screen layout. For instance, the video organizer can arrange multiple channels' videos uniformly in a 2x2, 3x3, 4x4, or similar manner according to the screen division layout, thereby allowing the operator to view videos from multiple cameras in real time on a single screen.

[0117] Meanwhile, if an event is detected in any one channel during step S15, the video constructor may reconstruct the integrated screen by enlarging the video size of the channel where the event was detected.

[0118] At this time, the video organizer may enlarge the size of the video of the channel where the event was detected to temporarily display only the video of the channel where the event was detected on the screen, or it may enlarge the size of the video of the channel where the event was detected while positioning it toward the center of the screen.

[0119] The video monitor monitors the occurrence of preset events for each channel of the integrated screen (S14).

[0120] The events monitored by the video surveillance system may be any one of the following: fire, traffic accident, traffic congestion, violation of safety regulations, facial recognition of wanted persons, and recognition of speeding vehicles, but are not limited to these.

[0121] For example, video surveillance may use at least one AI learning model, and may perform classification, regression analysis, clustering, association analysis, and anomaly detection through CNN (convolutional neural network), RNN (recurrent neural network), LSTM (long term short memory), or GAN (generative adversarial network).

[0122] When an event is detected in any one channel, the image controller instructs the image processor to increase the image quality of the channel where the event was detected (S15).

[0123] For example, the video controller may instruct the output to be 30 frames for video where no event is detected, and then increase the output to 60 frames for video where an event is detected.

[0124] In addition, for more efficient resource management, the image controller may instruct the image processor to increase the image quality of the channel where an event is detected and to lower the image quality of other channels when an event is detected in any one channel.

[0125] For example, the video controller may instruct the output to be 30 frames for video where no event is detected, and when an event is detected in any video, it may instruct the output to be increased to 60 frames for the video where the event is detected, while decreasing the output to 15 frames for video where no event is detected.

[0126] The image controller instructs the image processor to maintain image quality if no event is detected on any channel.

[0127] Although the present invention has been described above with reference to several embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as described in the following claims.

[0128] In addition, among the embodiments described above, the invention relating to the method may be implemented as a program or as a computer-readable recording medium on which the program is stored.

[0129] That is, the present invention can be implemented in the form of an application, and can be implemented as a software program that runs on a mobile terminal such as a smartphone or tablet PC running on Google’s Android or Apple’s iOS, or as a software program that runs on a wearable device such as Google Glass, Apple Watch, Samsung Galaxy Watch, or smartwatch, or as a software program that runs on a laptop PC or desktop PC running on Microsoft’s Windows or Google’s Chrome OS.

[0130] In addition, partial functions of the device or system described above may be provided by being included in a computer-readable recording medium by tangibly implementing a program of instructions for implementing them. A computer-readable recording medium may include program instructions, data files, data structures, etc., either individually or in combination. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and USB memory.

Claims

1. Multiple cameras; and A software service server comprising: an image processor that converts channel-specific images received from the cameras into images of a preset quality; an image organizer that composes the channel-specific images into a single integrated screen; an image monitor that monitors the occurrence of a preset event for each channel of the integrated screen; and an image controller that, when an event is detected in any one channel, instructs the image processor to increase the image quality of the channel where the event was detected. An integrated video control system with variable video quality including 2. In Paragraph 1, An integrated video control system for variable video quality, characterized in that the quality of the above video is at least one of frames per second (fps) and resolution.

3. In Paragraph 2, The above video constructor is, An integrated video control system with variable video quality characterized by reconstructing the integrated screen so that the video size of the channel where an event is detected is enlarged.

4. In Paragraph 2, The above image controller is, An integrated video control system for variable video quality, characterized by instructing the video processor to increase the video quality of the channel where the event was detected and to decrease the video quality of other channels when an event is detected in one channel.

5. In Paragraph 4, The above image controller is, An integrated video control system for variable video quality characterized by determining the up-adjustment and down-adjustment values ​​of the video quality by considering the available resources of the video processing processor (GPU).

6. In Paragraph 2, The above event is, An integrated video control system with variable video quality characterized by any one of the following: fire occurrence, traffic accident occurrence, traffic congestion occurrence, safety rule violation occurrence, wanted person facial recognition, or speeding vehicle recognition.

7. In Paragraph 6, The above video surveillance device is, An integrated video control system for variable video quality characterized by using at least one AI learning model, and performing classification, regression analysis, clustering, association analysis, and anomaly detection through CNN, RNN, LSTM, or GAN.

8. Multiple cameras capturing images of different qualities via remote settings; and A software service server comprising: a video organizer that organizes channel-specific videos received from the cameras into a single integrated screen; a video monitor that monitors the occurrence of a preset event for each channel of the integrated screen; and a video controller that, when an event is detected in at least one channel video, instructs the camera of the channel where the event was detected to transmit a higher quality video. An integrated video control system with variable video quality including 9. In Paragraph 8, An integrated video control system for variable video quality, characterized in that the quality of the above video is at least one of frames per second (fps) and resolution.

10. In Paragraph 9, The above video constructor is, An integrated video control system with variable video quality characterized by reconstructing the integrated screen so that the video size of the channel where an event is detected is enlarged.

11. In Paragraph 9, The above image controller is, An integrated video control system with variable video quality, characterized by instructing the camera in the channel where the event was detected to transmit a higher quality video when an event is detected in at least one channel video, and instructing the camera in other channels to transmit a lower quality video.

12. In Paragraph 11, The above image controller is, An integrated video control system for variable video quality characterized by determining the level of upward and downward adjustment of the video quality by considering the available resources of the video processing processor (GPU).

13. In Paragraph 9, The above event is, An integrated video control system with variable video quality characterized by any one of the following: fire occurrence, traffic accident occurrence, traffic congestion occurrence, safety rule violation occurrence, wanted person facial recognition, or speeding vehicle recognition.

14. In Paragraph 13, The above video surveillance device is, An integrated video control system for variable video quality characterized by using at least one AI learning model, and performing classification, regression analysis, clustering, association analysis, and anomaly detection through CNN, RNN, LSTM, or GAN.

15. A step in which an image processor of a software service server converts channel-specific images received from multiple cameras into images of preset quality; A step in which the video configurator of the software service server configures the channel-specific videos into a single integrated screen; A step in which a video monitor of the software service server monitors the occurrence of a preset event for each channel of the integrated screen; and A step in which, when an event is detected in one channel, the image controller of the software service server instructs the image processor to further improve the image quality of the channel in which the event was detected. An integrated video control method for variable video quality including 16. In Paragraph 15, An integrated video control method for variable video quality, characterized in that the quality of the above video is at least one of frames per second (fps) and resolution.

17. In Paragraph 16, The image organizer of the above integrated screen configuration step is, An integrated video control method for variable video quality characterized by reconstructing the integrated screen so that the video size of the channel where an event is detected is enlarged.

18. In Paragraph 16, The image controller in the step of instructing to improve the image quality of the channel where the above event was detected, An integrated video control method for variable video quality, characterized by instructing the video processor to increase the video quality of the channel where the event was detected and to decrease the video quality of other channels when an event is detected in one channel.

19. In Paragraph 18, The image controller in the step of instructing to improve the image quality of the channel where the above event was detected, An integrated video control method for variable video quality characterized by determining the up-adjustment value and down-adjustment value of the video quality by considering the available resources of the video processing processor (GPU).

20. In Paragraph 16, The above event is, An integrated video surveillance method for variable video quality characterized by any one of the following: occurrence of a fire, occurrence of a traffic accident, occurrence of traffic congestion, occurrence of a violation of safety rules, facial recognition of a wanted person, or recognition of a speeding vehicle.

21. In Paragraph 16, The video monitor in the event occurrence monitoring step above is, An integrated video control method for variable video quality, characterized by using at least one AI learning model and performing classification, regression analysis, clustering, association analysis, and anomaly detection through CNN, RNN, LSTM, or GAN.

Images