CN-121985098-A - Video low-delay transmission method, system, equipment and medium

CN121985098ACN 121985098 ACN121985098 ACN 121985098ACN-121985098-A

Abstract

The application provides a video low-delay transmission method, a system, equipment and a medium, which relate to the technical field of unmanned aerial vehicles, and the method comprises the steps of dividing a disaster area into a plurality of subareas, and acquiring the area type, the topographic data and the aftershock risk level of each subarea; the method comprises the steps of arranging a plurality of unmanned aerial vehicles in each subarea, receiving video data of the corresponding subarea shot by each unmanned aerial vehicle, carrying out feature recognition on each video data to generate transmission priority scores of each video data, generating emergency coefficients of each subarea by combining the type of the subarea, the topographic data and the aftershock risk level, generating comprehensive priority scores of each video data by combining the transmission priority scores and the emergency coefficients, sequencing each video data according to the sequence from large to small of the comprehensive priority scores to generate a transmission sequence, and sending each video data to a ground station according to the transmission sequence according to network bandwidth resources. The application has the technical effect of improving the accuracy of rescue command.

Inventors

LU GUANGQIANG
YANG YI
XING ZHIGANG
WANG XIAOLEI
LIU YANG
Quan Changke
WANG XUEWEI

Assignees

深圳市斯贝达电子有限公司

Dates

Publication Date: 20260505
Application Date: 20260318

Claims (10)

1. A method for low-latency video transmission, the method comprising: Dividing a disaster area into a plurality of subareas, and acquiring the area type, the terrain data and the aftershock risk level of each subarea, wherein each subarea is provided with a plurality of unmanned aerial vehicles; receiving video data corresponding to the subareas shot by each unmanned aerial vehicle, performing feature recognition on each video data, and generating a transmission priority score of each video data; Generating an emergency coefficient of each subarea by combining the area type, the topographic data and the aftershock risk level, wherein the emergency coefficient is used for representing the transmission emergency degree of video data shot by the unmanned aerial vehicle of each subarea; Generating a comprehensive priority score of each video data by combining the transmission priority score and the emergency coefficient, and sequencing each video data according to the sequence from the large to the small of the comprehensive priority score to generate a transmission sequence; and acquiring network bandwidth resources, and transmitting each video data to a ground station according to the transmission sequence according to the network bandwidth resources.
2. The method of claim 1, wherein said performing feature recognition on each of said video data to generate a transmission priority score for each of said video data comprises: Performing feature recognition on each video data, and recognizing a specific target in each video data, wherein the specific target is at least one of preset disaster factors, vital signs, infrastructure states, environmental changes and security risks; classifying the specific targets to generate a plurality of target groups, and acquiring weight coefficients corresponding to the target groups and the number of the specific targets in the target groups; calculating importance scores of the video data by combining weight coefficients corresponding to the target groups and the number of the specific targets in the target groups; Evaluating the timeliness of each video data, and generating a timeliness score, wherein the timeliness score is used for representing the influence degree of the shooting time of each video data on the transmission emergency degree from the time interval of the current time; And acquiring picture quality parameters of the video data, and generating a transmission priority grade of the video data by combining the importance grade, the picture quality parameters and the timeliness grade, wherein the picture quality parameters are used for representing the image integrity of the video data.
3. The method of low-latency video transmission according to claim 2, wherein the generating a transmission priority score for each of the video data in combination with the importance score, the picture quality parameter, and the timeliness score comprises: Substituting the importance score, the picture quality parameter and the timeliness score into a preset formula to generate a transmission priority score of each video data, wherein, The preset formula IS as follows: p=is×α+qp x β+ts x γ; wherein P IS a transmission priority score, IS IS an importance score, QP IS a picture quality parameter, TS IS an timeliness score, alpha IS an importance weight coefficient, beta IS a picture quality weight coefficient, and gamma IS an timeliness weight coefficient.
4. The method of claim 1, wherein the generating the emergency coefficient of each sub-area by combining the area type, the topographic data and the aftershock risk level comprises: determining basic emergency coefficients of all the subareas from a preset area type mapping table according to the area types; combining the topographic data and the aftershock risk level to generate an adjustment coefficient; arithmetically multiplying the adjustment coefficient by the basic emergency coefficient to generate an emergency coefficient of each sub-region.
5. The method of low-latency video transmission according to claim 4, wherein the combining the terrain data and the aftershock risk level to generate an adjustment coefficient comprises: Determining the terrain destruction level of each subarea according to the terrain data, and generating a terrain destruction coefficient used for representing the dangerous level of each subarea according to the terrain destruction level; acquiring a corresponding aftershock risk coefficient from a preset risk level mapping table according to the aftershock risk level; substituting the terrain destruction coefficient and the aftershock risk coefficient into an adjustment formula to generate an adjustment coefficient, wherein, The regulation formula is AC=TCI multiplied by delta+RAF multiplied by epsilon; wherein, AC is an adjusting coefficient, TCI is a terrain destruction coefficient, RAF is a aftershock risk coefficient, and delta and epsilon are weight coefficients.
6. The method of low-latency video transmission according to claim 1, wherein the combining the transmission priority score and the emergency factor generates a composite priority score for each of the video data, comprising: substituting the transmission priority score and the emergency coefficient into a comprehensive score formula to calculate the comprehensive priority score of each video data, The comprehensive scoring formula is CPS=P x lambda+EC x mu; wherein CPS is the composite priority score, P is the transmission priority score, EC is the emergency coefficient, lambda is the transmission priority weight coefficient, and mu is the emergency coefficient weight coefficient.
7. The method of low-latency video transmission according to claim 1, wherein said transmitting each of said video data to a ground station in accordance with said transmission sequence according to said network bandwidth resource comprises: Monitoring the available bandwidth of the current network bandwidth resource in real time; determining the amount of video data which can be transmitted in unit time according to the available bandwidth; sequentially selecting each video data for transmission according to the transmission sequence, and suspending selection and starting transmission when the accumulated selected video data amount reaches the video data amount which can be transmitted in the unit time; In the transmission process, monitoring the network transmission state in real time, and adjusting the transmission rate when detecting network congestion; And after the transmission is completed, re-evaluating the network bandwidth resources, and continuously transmitting the rest video data according to the transmission sequence until all video data are transmitted.
8. A video low-delay transmission system is characterized by comprising a first acquisition module, a receiving module, a first combination module, a second combination module and a second acquisition module, The first acquisition module is used for dividing the disaster area into a plurality of subareas and acquiring the area type, the terrain data and the aftershock risk level of each subarea, wherein each subarea is provided with a plurality of unmanned aerial vehicles; The receiving module is used for receiving video data corresponding to the subareas shot by each unmanned aerial vehicle, carrying out feature recognition on each video data and generating a transmission priority grade of each video data; The first combination module is used for combining the region type, the topographic data and the aftershock risk level to generate an emergency coefficient of each sub-region, wherein the emergency coefficient is used for representing the transmission emergency degree of video data shot by the unmanned aerial vehicle of each sub-region; The second combination module is configured to combine the transmission priority score and the emergency coefficient to generate a comprehensive priority score of each video data, and order each video data according to the order of the comprehensive priority score from big to small to generate a transmission sequence; the second acquisition module is configured to acquire a network bandwidth resource, and send each video data to a ground station according to the transmission sequence according to the network bandwidth resource.
9. An electronic device comprising a processor, a memory, a user interface, and a network interface, the memory for storing instructions, the user interface and the network interface for communicating to other devices, the processor for executing the instructions stored in the memory to cause the electronic device to perform the method of any of claims 1-7.
10. A computer readable storage medium, characterized in that a computer program is stored which can be loaded by a processor and which performs the method according to any of claims 1-7.

Description

Video low-delay transmission method, system, equipment and medium Technical Field The application relates to the technical field of unmanned aerial vehicles, in particular to a video low-delay transmission method, a system, equipment and a medium. Background In the sudden event of natural disasters such as earthquake, flood, typhoon and the like, timely obtaining video information of disaster area sites is important to rescue command decision-making. The traditional unmanned aerial vehicle cruising or ground personnel investigation mode has the problems of high safety risk, limited coverage range, low response speed and the like, so that the disaster area video acquisition technology based on the unmanned aerial vehicle gradually becomes an important means for emergency rescue. However, disaster area environments are complex, and generally comprise different types of areas such as residential areas, commercial areas and industrial areas, the rescue emergency degrees of the areas are obviously different, meanwhile, disaster area network infrastructures are often seriously damaged, available bandwidth resources are extremely limited, and how to realize efficient transmission of multi-channel video data under limited network conditions becomes a technical problem to be solved urgently. In the prior art, video data transmission is mainly performed in a first-come first-serve or polling scheduling mode, namely, video data of an unmanned aerial vehicle are sequentially transmitted according to the time sequence of arrival or a preset polling period. Although the method can ensure the transmission of multiple paths of video data, under the condition of extremely limited bandwidth resources, the method has the technical defects of single transmission scheduling strategy and lack of pertinence, and can preferentially transmit video data with lower rescue value, and the video data containing key rescue information is arranged at the rear position of a transmission queue, so that the accuracy of rescue command is seriously affected. Disclosure of Invention The application provides a video low-delay transmission method, a system, equipment and a medium, which are used for improving the accuracy of rescue command. The application provides a video low-delay transmission method, which comprises the steps of dividing a disaster area into a plurality of subareas, obtaining the area type, the topographic data and the aftershock risk level of each subarea, wherein each subarea is provided with a plurality of unmanned aerial vehicles, receiving video data shot by each unmanned aerial vehicle and corresponding to the subarea, carrying out feature recognition on each video data to generate a transmission priority grade of each video data, combining the area type, the topographic data and the aftershock risk level, generating an emergency coefficient of each subarea, wherein the emergency coefficient is used for representing the transmission emergency degree of the video data shot by each unmanned aerial vehicle of each subarea, combining the transmission priority grade and the emergency coefficient, generating a comprehensive priority grade of each video data, sequencing each video data according to the sequence from large to small according to the comprehensive priority grade, generating a transmission sequence, obtaining network bandwidth resources, and sending each video data to a ground station according to the transmission sequence. By adopting the technical scheme, the disaster area is divided into a plurality of subareas, the area types, the topographic data and the aftershock risk grades of the subareas are obtained, the transmission priority scores are generated by combining the feature recognition of the video data shot by each unmanned aerial vehicle, the emergency coefficients of the subareas are generated by integrating the area features, the comprehensive priority scores of the video data are finally formed, the transmission sequence is generated according to the comprehensive priority scores, and the intelligent transmission scheduling based on the area features and the video content features is realized. According to the scheme, the video data of the high-emergency-coefficient subarea containing the key rescue information can be transmitted preferentially, meanwhile, the transmission strategy is dynamically adjusted according to the network bandwidth resources, the problem of important video data transmission delay possibly caused by a traditional first-come first-serve or polling scheduling mode is effectively avoided, the pertinence and timeliness of the video data transmission of the disaster area are obviously improved, and the accuracy of rescue command is improved. In a second aspect, the application provides a video low-delay transmission system, which comprises a first acquisition module, a receiving module, a first combination module, a second combination module and a second acquisition module, The syste