KR-102963987-B1 - Video node distribution and multiple artificial intelligence-based web browser control system for unmanned aerial vehicles

Abstract

The present invention relates to a web browser control system based on video node distribution and multiple artificial intelligence for unmanned aerial vehicles, wherein RTSP (Real Time Streaming Protocol) video received from multiple unmanned aerial vehicles is distributed and processed by multiple defined artificial intelligence (AI) models, and the results of analysis by multiple AI models are transmitted to a web browser client through a central server to enable optimal control of the unmanned aerial vehicles. The system comprises: a mediating server that receives RTSP-transmitted video from multiple unmanned aerial vehicles and distributes the received video to supply it to an AI server; an AI server that analyzes the supplied video using multiple AI models defined in advance according to analysis items and outputs the analysis results; a central server that aggregates the analysis results output from the AI server and transmits them via the web; and a web browser control unit that classifies the video analysis results into original video and analyzed video, and selects and streams the classified original video or analyzed video in real-time for the control of the unmanned aerial vehicles.

Inventors

• 이재혁
• 홍성호

Assignees

• 주식회사 호그린에어

Dates

Publication Date

20260513

Application Date

20231120

Claims (5)

1. Multiple unmanned aerial vehicles that acquire video through shooting and transmit the acquired video to a pre-configured video node using the Real-time Streaming Protocol (RTSP); An intermediary server that receives images transmitted from the aforementioned plurality of unmanned aerial vehicles, distributes the received images, and supplies them to an artificial intelligence server; An AI server unit that analyzes a video supplied from the above-mentioned intermediary server using a plurality of predefined AI models according to analysis items and outputs the analysis results; A central server that collects analysis results output from the artificial intelligence server unit and transmits them via the web; and It includes a web browser control unit that classifies video analysis results transmitted from the above central server into original video and analyzed video, and selects and streams in real-time the classified original video or analyzed video for the control of the unmanned aerial vehicle. The above-mentioned intermediary server is, The system includes: a video receiving unit that receives video transmitted via RTSP from the aforementioned multiple unmanned aerial vehicles through multiple video nodes; a video distribution unit that distributes the multiple RTSP videos received from the video receiving unit according to an artificial intelligence model; and a video supply unit that distributes and supplies the videos distributed from the video distribution unit to an artificial intelligence server unit. The above-mentioned video distribution unit distributes the received RTSP video to multiple AI models designated in advance by video analysis items by a web browser user who wishes to control an unmanned aerial vehicle, and simultaneously supplies the video to the corresponding AI models. The user of the aforementioned web browser specifies the required AI analysis model via the web and receives and utilizes the analysis results obtained through the specified AI analysis model, thereby efficiently performing control of unmanned aerial vehicles by utilizing the analysis results of all necessary AI models without building multiple AI analysis models. A web browser control system based on image node distribution and multiple artificial intelligence for unmanned aerial vehicles, characterized in that the above AI analysis model includes a terrain feature recognition model for recognizing terrain features from an image, an artificial object recognition model for recognizing artificial objects from an image, and an object recognition model for recognizing objects from an image.
2. delete
3. delete
4. In claim 1, the central server is, A video analysis result receiving unit that receives multiple video analysis results individually analyzed from a plurality of artificial intelligence servers of the above artificial intelligence server unit; Analysis result combining unit that combines individual video analysis results received from the above video analysis result receiving unit for each client; A web browser control system for an unmanned aerial vehicle based on image node distribution and multiple artificial intelligence, characterized by including a video transmission unit that transmits an analysis video combined in a combination unit to a web browser control unit via the web based on the above analysis results.
5. In claim 1, the web browser control unit, A video receiving unit that receives an analysis video transmitted from the above central server; A video classification unit that classifies the video received from the above video receiving unit into an original video and an AI-analyzed video; A video selection unit that selects one of the original video and the AI-analyzed video classified by the above video classification unit; A web browser control system for an unmanned aerial vehicle based on image node distribution and multiple artificial intelligence, characterized by including an image display unit that displays an image selected by the image selection unit above in a web browser.

Description

Video node distribution and multiple artificial intelligence-based web browser control system for unmanned aerial vehicles The present invention relates to a web browser control system based on image node distribution and multiple artificial intelligence for unmanned aerial vehicles, and more specifically, to a web browser control system based on image node distribution and multiple artificial intelligence for unmanned aerial vehicles that distributes and processes RTSP (Real Time Streaming Protocol) images received from multiple unmanned aerial vehicles across multiple defined artificial intelligence (AI) models, and transmits the results analyzed by the multiple AI models to web browser clients via a central server to enable optimal control of the unmanned aerial vehicles. Until now, unmanned aerial vehicles (UAVs) have primarily been developed for military purposes, but their use in the civilian sector is expected in the future. Applications in the civilian sector include rescue operations, wildfire monitoring, and aerial photography, and explosive demand is anticipated, particularly in the imaging field. Korea is surrounded by the sea on three sides, and maritime accidents occur frequently. Particularly in the West Sea, illegal fishing by Chinese vessels is increasing daily, leading domestic fishermen to discuss the resulting sharp decline in catch volumes. This issue remains a challenge that must be resolved at the national level and can also become a serious matter that could lead to diplomatic disputes between nations. Currently, the available bandwidth through unmanned aerial vehicle (UAV) communication equipment is limited by the size provided by mobile carriers. During flight, control tailored to flight conditions using multiple artificial intelligence (AI) models is required; however, equipping the UAV with all these models and enabling the vehicle itself to analyze situations and respond appropriately presents various difficulties, such as weight, real-time response, and cost. Therefore, technology is required to analyze video captured by unmanned aerial vehicles in real time and remotely control the aircraft accordingly to respond optimally. Meanwhile, a conventional technology for processing images of unmanned aerial vehicles is disclosed in the following <Patent Document 1>. The prior art disclosed in <Patent Document 1> relates to an image processing device that identifies objects by processing images acquired from an unmanned aerial vehicle. These conventional technologies also identify objects by processing images generated from a single unmanned aerial vehicle, and there are limitations to simultaneously processing real-time streaming images generated from multiple unmanned aerial vehicles. FIG. 1 is a schematic diagram of a web browser control system based on image node distribution and multiple artificial intelligence for an unmanned aerial vehicle according to the present invention, and FIG. 2 is a block diagram of an exemplary embodiment of the intermediary server of FIG. 1, and FIG. 3 is a block diagram of an exemplary embodiment of the central server of FIG. 1, and Figure 4 is a block diagram of an exemplary embodiment of the web browser control unit of Figure 1. A web browser control system based on image node distribution and multiple artificial intelligence for an unmanned aerial vehicle according to a preferred embodiment of the present invention will be described in detail below with reference to the attached drawings. The terms or words used in the present invention described below should not be interpreted as being limited to their ordinary or dictionary meanings, but should be interpreted in a meaning and concept consistent with the technical spirit of the present invention, based on the principle that the inventor can appropriately define the concept of the terms to best describe his invention. Therefore, the embodiments described in this specification and the configurations illustrated in the drawings are merely preferred embodiments of the present invention and do not represent all technical concepts of the present invention; thus, it should be understood that various equivalents and modifications that can replace them may exist at the time of filing this application. FIG. 1 is a schematic diagram of a web browser control system based on image node distribution and multiple artificial intelligence for unmanned aerial vehicles according to a preferred embodiment of the present invention, and may include a plurality of unmanned aerial vehicles (101 - 101+N), an intermediary server (210), an artificial intelligence server unit (220), a central server (230), and a web browser control unit (300). Multiple unmanned aerial vehicles (101 - 101+N) take pictures using a vision system such as a camera to acquire images, and transmit the acquired images to a mediating server (210) through a pre-configured image node using a real-time streaming protocol (RTSP). Since the configuration