Video processing method and device, electronic equipment and storage medium

Abstract

The invention provides a video processing method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting ship monitoring video data into a preset video compression model, recognizing redundant data in a ship monitoring video, and carrying out the compression, and obtaining target ship monitoring video data; coding the target ship monitoring video data based on a forward error correction algorithm to obtain verification data; adding the verification data into the target ship monitoring video data to obtain target transmission data; and sending the target transmission data to a ship monitoring platform based on a user datagram protocol. According to the application, the ship monitoring video data is compressed through the preset video compression model to reduce the video data volume, the compressed video data is processed by using the forward error correction algorithm to obtain the target transmission data, and the target transmission data is sent to the ship monitoring platform based on the user datagram protocol. Accurate transmission of video data in a complex maritime communication environment is ensured.

Description

Technical Field

[0001] This application relates to the field of video processing technologies, and particularly to a video processing method, apparatus, electronic device, and storage medium. Background Art

[0002] With the increasing prosperity of global maritime trade and the continuous development of marine resources, the safety monitoring of maritime vessels has become increasingly important. However, due to the complex and changeable marine environment and the limitations of communication conditions, especially the transmission of video surveillance data in narrow bandwidth environments, many challenges are faced. Existing video compression technologies, such as H.264, H.265, etc., often have problems such as poor compression effect, poor transmission stability, and insufficient adaptability when processing maritime vessel surveillance videos, and it is difficult to meet the actual needs. Therefore, there is an urgent need for an efficient video compression and stable transmission method suitable for narrow bandwidth environments to improve the efficiency and reliability of maritime vessel surveillance. Summary of the Invention

[0003] Embodiments of this application provide a video processing method, apparatus, electronic device, and storage medium to solve the problem of how to improve the efficiency and reliability of maritime vessel surveillance.

[0004] In a first aspect, embodiments of this application provide a video processing method, and the method includes:

[0005] Input ship surveillance video data into a preset video compression model, identify redundant data in the ship surveillance video and compress it to obtain target ship surveillance video data; wherein, the preset video compression model is obtained through deep learning training based on a historical ship surveillance video data set;

[0006] Encode the target ship surveillance video data based on a forward error correction algorithm to obtain redundant check data;

[0007] Add the check data to the target ship surveillance video data to obtain target transmission data;

[0008] Send the target transmission data to a ship surveillance platform based on the User Datagram Protocol.

[0009] In a second aspect, embodiments of this application further provide a video processing apparatus, and the apparatus includes:

[0010] A compression module, configured to input ship surveillance video data into a preset video compression model, identify redundant data in the ship surveillance video and compress it to obtain target ship surveillance video data; wherein, the preset video compression model is obtained through deep learning training based on a historical ship surveillance video data set;

[0011] The first processing module is used to encode the target ship monitoring video data based on a forward error correction algorithm to obtain redundant check data;

[0012] The second processing module is used to add the check data to the target ship monitoring video data to obtain target transmission data;

[0013] The sending module is used to send the target transmission data to the ship monitoring platform based on the User Datagram Protocol.

[0014] In a third aspect, an embodiment of the present application further provides an electronic device, which includes a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the above video processing method is implemented.

[0015] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above video processing method is implemented.

[0016] The embodiments of the present application at least include the following technical effects:

[0017] The technical solution of the embodiment of the present application effectively compresses the redundant data in the ship monitoring video data through a preset video compression model obtained by deep learning training based on a historical ship monitoring video data set, thereby reducing the video data volume and alleviating the transmission pressure in a narrow bandwidth environment. Subsequently, a forward error correction algorithm is used to further process the compressed video data to generate target transmission data. Based on the User Datagram Protocol, the target transmission data is sent to the ship monitoring platform. The present application combines a forward error correction mechanism with the User Datagram Protocol to ensure the accurate transmission of video data in a complex maritime communication environment and improve the stability of video transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art.

[0019] Figure 1 is a flowchart of the video processing method provided by the embodiment of the present application;

[0020] Figure 2 is a structural diagram of the video processing device provided by the embodiment of the present application;

[0021] Figure 3 is a block diagram of the electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0023] It should be understood that the term "one embodiment" or "an embodiment" mentioned throughout the specification means that a particular feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the present application. Therefore, the appearances of the phrases "in one embodiment" or "in an embodiment" throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0024] In various embodiments of the present application, it should be understood that the sequence numbers of the following processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0025] As Figure 1 shown, the embodiments of the present application provide a video processing method, and the method includes:

[0026] Step 101, input the ship monitoring video data into a preset video compression model, identify redundant data in the ship monitoring video and compress it to obtain target ship monitoring video data; wherein, the preset video compression model is obtained by deep learning training based on a historical ship monitoring video data set.

[0027] The video processing method provided by this application is applied to a video processing system. A preset video compression model is installed on the video processing system. This preset video compression model learns the characteristics of ship monitoring scenarios from the historical ship monitoring video dataset based on deep learning. By leveraging the powerful feature extraction ability of deep learning, it can accurately identify spatial redundancy (such as large areas of similar sea surface backgrounds), temporal redundancy (relatively stationary parts of ships in consecutive frames), and visual redundancy (details insensitive to the human eye) in the video. And on the premise of retaining key information, it compresses redundant data, reduces the amount of video data, and adapts to the narrow bandwidth transmission requirements. Compared with traditional compression technologies, it can significantly improve the compression efficiency and quality, and can compress the bit rate of the monitoring video to one-tenth of the original while ensuring that the picture and format remain unchanged, thus effectively solving the problem of poor compression effect. Among them, when training the preset video compression model, a large amount of historical ship monitoring video data needs to be collected, covering video segments of different weather conditions (such as sunny days, foggy days, rainy days, nights, etc.), time periods (such as strong daylight during the day, low illuminance at dusk, light reflection at night, etc.), ship types (such as cargo ships, fishing boats, speedboats, etc.), and navigation states (such as stationary, sailing, turning, docking, etc.) to construct a historical ship monitoring video dataset. After obtaining the historical ship monitoring video dataset, use this dataset to train a preset deep learning model (such as convolutional neural network, recurrent neural network, or Transformer, etc.) to obtain a video compression model, and continuously optimize the model parameters to improve the compression efficiency and picture quality retention ability of the video compression model.

[0028] In addition, when performing video compression, the method of combining the preset video compression model with traditional coding standards (such as H.265 / HEVC) can also be used. Specifically, the preset video compression model can accurately identify the key information and redundant parts in the scene through training with a large amount of ship monitoring video data. Key frames usually contain important pictures such as sudden changes in the navigation state of ships and entering and leaving ports, while non-key frames are pictures in a relatively stable state. H.265 / HEVC is an advanced video coding standard with efficient compression algorithms and flexible coding tools. Combining the key frame and non-key frame recognition results output by the deep learning model with the coding characteristics of H.265 / HEVC can adopt the optimal compression method for different types of frames, and while ensuring the clarity of the key content of the video, minimize the amount of data to the greatest extent.

[0029] The video processing system is also connected to a camera. The camera collects ship monitoring video data and inputs the ship monitoring video data into the trained preset video compression model. The model analyzes the characteristics of the video frames, identifies redundant data, and compresses it. For example, for the stationary sea area in consecutive frames, reduce its sampling rate or simplify the encoding; for key information such as ship details, use lossless or low-loss compression methods, and finally obtain the target ship monitoring video data.

[0030] Step 102: Encode the target ship monitoring video data based on the forward error correction algorithm to obtain redundant check data.

[0031] Step 103: Add the check data to the target ship monitoring video data to obtain target transmission data.

[0032] After obtaining the target ship monitoring video data, analyze and calculate the target ship monitoring video data using the forward error correction algorithm, and generate check data according to the set redundancy.

[0033] Add the generated check data to the target ship monitoring video data to form target transmission data containing the original video data and redundant check data, providing guarantee for error recovery during data transmission.

[0034] This application adds redundant check data to the target ship monitoring video data through the forward error correction algorithm, enabling the receiving end to recover the original video data based on the remaining data and check data in case of packet loss, reducing transmission delay, and improving the reliability of data transmission in a complex maritime communication environment.

[0035] Step 104: Send the target transmission data to the ship monitoring platform based on the User Datagram Protocol.

[0036] The embodiment of this application uses the User Datagram Protocol (UDP) to transmit the target transmission data. UDP has the characteristics of fast transmission speed and low latency.

[0037] Specifically, when using UDP to transmit the target transmission data, it is necessary to encapsulate the target transmission data into a UDP datagram, add UDP header information (source port, destination port, length, checksum), and then send the encapsulated UDP datagram to the ship monitoring platform through a maritime communication network (such as a satellite link).

[0038] This application processes target transmission data processed by a forward error correction algorithm based on UDP transmission. In the narrow-bandwidth maritime environment, the fast transmission ability of UDP helps to send as much video data as possible within the limited bandwidth. After receiving the data packets, the receiving end (i.e., the ship monitoring platform) can decode according to the verification data and recover the lost data even if some data packets are lost, ensuring the stable transmission of video data under poor network conditions, reducing phenomena such as video stuttering and interruption, and guaranteeing the integrity and accuracy of video data. Thus, it can not only ensure the fast transmission of video data but also guarantee data accuracy with the help of the forward error correction mechanism, solving the problems of low transmission efficiency and high latency of the traditional TCP protocol in narrow bandwidth. In summary, through the complementary advantages of UDP and the forward error correction algorithm, this application can effectively cope with the complex maritime communication environment of narrow bandwidth and high latency.

[0039] In an embodiment of this application, the redundant data in the ship monitoring video data is effectively compressed by a preset video compression model obtained through deep learning training based on the historical ship monitoring video data set, thereby reducing the amount of video data and alleviating the transmission pressure in the narrow-bandwidth environment. Subsequently, the forward error correction algorithm is used to further process the compressed video data to generate target transmission data. Based on the User Datagram Protocol, the target transmission data is sent to the ship monitoring platform. Through the combination of the forward error correction mechanism and the User Datagram Protocol, this application ensures the accurate transmission of video data in the complex maritime communication environment and improves the stability of video transmission.

[0040] In an optional embodiment of this application, sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol includes:

[0041] Obtain the network bandwidth of the transmission network, where the transmission network is used to send the target transmission data to the ship monitoring platform;

[0042] Determine transmission parameters according to the network bandwidth, where the transmission parameters at least include: transmission unit size, retransmission parameters, and congestion window size;

[0043] Based on the User Datagram Protocol and the transmission parameters, send the target transmission data to the ship monitoring platform.

[0044] Considering that bad weather (such as typhoons and heavy rains) and complex sea conditions (multipath effects caused by sea waves and tides) will interfere with signal transmission and reduce the bandwidth, the network bandwidth of the maritime transmission network shows dynamic changes, and traditional fixed-parameter transmission is likely to lead to low bandwidth utilization or unstable transmission. UDP, as a connectionless protocol, has the characteristics of low latency and high transmission efficiency, but there is a risk of packet loss.

[0045] In order to reduce the packet loss rate, when the target transmission data is sent to the ship monitoring platform based on the User Datagram Protocol (UDP), the network bandwidth of the transmission network is monitored in real time. Exemplarily, indicators such as the throughput, latency, and packet loss rate of the transmission network can be obtained in real time through a network interface to calculate the current available bandwidth. And according to the network bandwidth, the transmission parameters are adjusted in real time. The transmission parameters here include but are not limited to: the size of the transmission unit, the retransmission parameters, and the size of the congestion window.

[0046] Specifically, the present application sets the size of the transmission unit according to the network bandwidth, that is, sets the Maximum Transmission Unit (MTU). Among them, when the bandwidth is sufficient, the MTU is increased, and when the bandwidth is insufficient, the MTU is reduced. For whether the bandwidth is sufficient, a judgment condition can be preset in advance. When the condition is met, it is determined that the bandwidth is sufficient, and when the condition is not met, it is determined that the bandwidth is insufficient. The present application can also set the retransmission parameters according to the network bandwidth. Exemplarily, when the network bandwidth indicates that the current network environment is a high packet loss rate scenario, the retransmission waiting time is shortened and the number of retransmissions is increased. When the network bandwidth indicates that the current network environment is a low packet loss rate scenario, the waiting time can be extended to reduce bandwidth occupancy. For example, when the packet loss rate exceeds 10%, the retransmission interval is shortened from 1 second to 0.5 seconds. The present application can also set the size of the congestion window according to the network bandwidth. When the bandwidth increases, the window is enlarged to accelerate the transmission rate; when the bandwidth decreases, the window is reduced to avoid network overload.

[0047] After determining the transmission parameters matching the current network environment according to the network bandwidth, these transmission parameters are configured into the UDP transmission protocol stack to ensure the stable transmission of the target transmission data.

[0048] Specifically, during the process of sending the target transmission data, the embodiment of the present application will continuously monitor the network bandwidth, determine the matching transmission parameters in real time according to the network bandwidth, and send the target transmission data based on the transmission parameters determined in real time.

[0049] The above implementation scheme of the present application monitors the network bandwidth in real time, dynamically adjusts the transmission parameters, makes the transmission process match the network conditions, makes the transmission rate accurately match the network bandwidth, and avoids bandwidth waste or overload. It can also optimize the retransmission and congestion control strategies, effectively reduce the packet loss rate and latency. Quickly respond to network state changes, ensure the video transmission quality in different marine environments, and significantly improve the reliability of the ship monitoring system.

[0050] In an optional embodiment of the present application, before inputting the ship monitoring video data into a preset video compression model to identify redundant data in the ship monitoring video and perform compression to obtain the target ship monitoring video data, the method further includes:

[0051] Obtain the motion state data collected by the motion sensors installed on the ship;

[0052] Adjust the ship monitoring video data according to the motion state data.

[0053] Marine ships are in a continuous motion state affected by wind and waves, which may cause unstable phenomena such as jitter and offset in the monitoring video images. In the embodiments of the present application, a variety of motion sensors are installed on the ship. For example, an accelerometer is installed at the center of gravity of the ship to monitor the translational and swaying accelerations of the ship, and a gyroscope is installed at the key structures of the ship to monitor the change in the rotation angle. The motion state data of the ship is collected in real time by the motion sensors. Here, the motion state data includes, but is not limited to, data such as translation, rotation, and swaying amplitude.

[0054] When adjusting the ship monitoring video data according to the motion state data, the motion state data can be first converted into parameters required for video adjustment, such as the amount of video frame translation, rotation angle, etc. For example, through mathematical models and algorithms, sensor data such as acceleration and angular velocity are mapped into geometric transformation parameters of video frames. Then, according to the adjustment parameters, geometric transformation is performed on the ship monitoring video. The set changes here include operations such as translating, rotating, and scaling the video frames to compensate for the offset and jitter of the video images caused by the ship's motion and make the video images stable again. For example, when the ship sways to the right and causes the video image to shift to the left, the video image is restored to the original position through translation operation.

[0055] In the above implementation scheme of the present application, the ship monitoring video data is adjusted by the motion state data collected by the motion sensors, which can pre-compensate for the video image changes caused by the ship's motion, reduce the redundant information and unstable factors between video frames, make the video content more stable and continuous, and provide a better data basis for subsequent compression processing. Further, for the video data after motion state adjustment, the correlation and stability between frames are improved. When inputting into a preset video compression model, the model can more accurately identify and compress redundant data, avoid misjudgment or invalid compression caused by unstable video images, and thus further improve the compression efficiency and quality on the premise of ensuring the integrity of the key information of the video.

[0056] In an optional embodiment of the present application, before inputting the ship monitoring video data into a preset video compression model, identifying the redundant data in the ship monitoring video and compressing it to obtain the target ship monitoring video data, the method further includes:

[0057] Input the environmental information into a preset sea condition prediction model to obtain sea condition parameters indicating the sea motion trend;

[0058] Adjust the ship monitoring video data according to the sea condition parameters.

[0059] Considering that the marine environment (such as wind, waves, tides, etc.) will directly cause the ship to rock, resulting in periodic jitter in the surveillance video.

[0060] The video processing system provided by the embodiment of the present application is installed with a preset sea condition prediction model, which can be obtained through deep learning training based on historical data (including environmental parameters and corresponding ship motion videos). The preset sea condition prediction model can accurately calculate sea condition parameters indicating the sea surface movement trend according to the input environmental information. Specifically, the sea condition parameters can be quantitative indicators such as the fluctuation amplitude of the sea surface, water flow velocity, and direction change, etc., so as to comprehensively reflect the movement state of the sea surface.

[0061] Before inputting the ship surveillance video data into the preset video compression model, the embodiment of the present application collects environmental information, such as various data related to the marine environment, such as meteorological data, wave height, tide information, etc. And input the environmental information into the preset sea condition prediction model to obtain sea condition parameters indicating the sea surface movement trend. Then, adjust the ship surveillance video data according to the sea condition parameters to compensate for the picture displacement and rotation caused by the ship's movement, so that the picture remains relatively stable. In addition, the brightness, contrast, color, etc. of the video can also be optimized to improve the clarity and visibility of the video picture.

[0062] The above implementation scheme of the present application can effectively solve the problem of the decline in the quality of the video picture caused by the sea surface movement and environmental changes by adjusting the video data according to the sea condition parameters, which is beneficial for the preset video compression model to better identify the redundant data therein.

[0063] In an optional embodiment of the present application, before sending the target transmission data to the ship surveillance platform based on the User Datagram Protocol, the method further includes:

[0064] Obtain the network bandwidth of the transmission network, where the transmission network is used to send the target transmission data to the ship surveillance platform;

[0065] Judge whether the network bandwidth is greater than a preset bandwidth threshold;

[0066] When the network bandwidth is greater than or equal to the preset bandwidth threshold, execute the step of sending the target transmission data to the ship surveillance platform based on the User Datagram Protocol;

[0067] When the network bandwidth is less than the preset bandwidth threshold, judge whether the target transmission data is real-time video data;

[0068] When the target transmission data is real-time video data, execute the step of sending the target transmission data to the ship surveillance platform based on the User Datagram Protocol;

[0069] When the target transmission data is not real-time video data, store the target transmission data in a pre-established cache space.

[0070] Before sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol in an embodiment of this application, obtain the network bandwidth of the transmission network, and compare the network bandwidth with a preset bandwidth threshold, which can be a standard value set in advance according to factors such as the requirements of the ship monitoring platform for data transmission and business needs.

[0071] Based on the comparison result, it can be divided into the following two scenarios.

[0072] The first scenario is that the network bandwidth is greater than or equal to the preset bandwidth threshold. At this time, the current network has sufficient bandwidth to transmit the target transmission data, and the step of directly sending the target transmission data to the ship monitoring platform based on UDP can be executed.

[0073] The second scenario is that the network bandwidth is less than the preset bandwidth threshold. At this time, it is necessary to further determine the type of the target transmission data. If the target transmission data is real-time video data, considering that real-time video data has extremely high requirements for real-time performance, even if the network bandwidth is insufficient, the step of still sending it to the ship monitoring platform based on UDP needs to be executed. If the target transmission data is not real-time video data, store these data in a pre-established cache space. The cache space can be a local storage device or a specific storage space on the server, used to temporarily store these data and wait for the network bandwidth condition to improve before transmission.

[0074] The above implementation scheme of this application can flexibly adjust the data transmission method according to the actual situation of the network by first obtaining the network bandwidth and making a judgment. Different processing strategies are adopted for different types of data, ensuring the real-time performance requirements of real-time video data, avoiding the ineffective transmission of non-real-time data when the network bandwidth is insufficient, and improving the overall efficiency of data transmission.

[0075] In an optional embodiment of this application, when the network bandwidth is greater than or equal to the preset bandwidth threshold, sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol includes:

[0076] Determine a first bandwidth according to the target transmission data, and determine the remaining bandwidth in the network bandwidth except the first bandwidth as a second bandwidth;

[0077] Create a first transmission channel and a second transmission channel in the transmission network; wherein, the first transmission channel corresponds to the first bandwidth, and the second transmission channel corresponds to the second bandwidth;

[0078] Send the target transmission data to the ship monitoring platform based on the User Datagram Protocol through the first transmission channel;

[0079] Send the data stored in the cache space to the ship monitoring platform through the second transmission channel.

[0080] For the first scenario in the previous embodiment, that is, the network bandwidth is greater than or equal to the preset bandwidth threshold, when sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol, the embodiment of the present application first determines the required bandwidth according to factors such as the characteristics and size of the target transmission data, denoted as the first bandwidth. Then calculate the remaining part of the network bandwidth after removing the first bandwidth, and determine it as the second bandwidth. Such an allocation method can ensure that the target transmission data has sufficient bandwidth resources to guarantee the transmission quality and efficiency, while reasonably utilizing the remaining network bandwidth.

[0081] After determining the first bandwidth and the second bandwidth, create two transmission channels in the transmission network, namely the first transmission channel and the second transmission channel. The first transmission channel corresponds to the first bandwidth and is used to transmit the target transmission data to ensure its stable and fast transmission. The second transmission channel corresponds to the second bandwidth and is used to transmit the data stored in the cache space. The embodiment of the present application can achieve classified transmission of different data by creating different transmission channels, improving the orderliness and controllability of transmission.

[0082] Send the target transmission data to the ship monitoring platform based on the User Datagram Protocol through the first transmission channel. At the same time, send the data stored in the cache space to the ship monitoring platform through the second transmission channel. This can gradually transmit the data in the cache using the remaining bandwidth on the premise of ensuring the priority transmission of the target transmission data, avoiding the backlog of cache data and improving the overall efficiency of data transmission.

[0083] The above implementation scheme of the present application, through reasonable allocation and utilization of the network bandwidth, ensures the priority transmission of the target transmission data, can also make full use of the remaining bandwidth to transmit cache data, avoids waste of bandwidth, improves the utilization rate of network resources, and maximizes the effective use of the network bandwidth.

[0084] In an optional embodiment of the present application, when the network bandwidth is less than the preset bandwidth threshold and the target transmission data is real-time video data, sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol includes:

[0085] Extract the audio data and key data in the target transmission data to obtain the first target transmission data, and determine the data other than the first target transmission data in the target transmission data as the second target transmission data;

[0086] Send the first target transmission data to the ship monitoring platform based on the User Datagram Protocol;

[0087] Store the second target transmission data in the cache space.

[0088] For the second scenario in the previous embodiment, that is, the network bandwidth is less than the preset bandwidth threshold. When the target transmission data is real-time video data, when sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol, first process the target transmission data, extract the audio data and key data from the target transmission data to obtain the first target transmission data. The audio data carries important information such as the sounds of the ship's surrounding environment and crew communication; the key data covers the core information closely related to the ship's safety and operation, such as the ship's navigation status and equipment operation parameters. At the same time, determine the other data in the target transmission data except the first target transmission data, such as non-critical background images and minor details in the video, as the second target transmission data.

[0089] After completing the data extraction and division, use the User Datagram Protocol to send the first target transmission data to the ship monitoring platform, so that the audio data and key data can be sent out quickly, ensuring that the ship monitoring platform can obtain the core information related to the ship's operation and safety in a timely manner. At the same time, store the second target transmission data in the pre-established cache space. Since the current network bandwidth is insufficient, if all data is transmitted, it may cause delays or losses in the transmission of key data, affecting the ship monitoring effect. In this application, by temporarily storing the second target transmission data and retrieving it from the cache space for transmission after the network bandwidth condition improves, it avoids the invalid transmission of data and the waste of bandwidth resources.

[0090] In the above implementation scheme of this application, by extracting and transmitting the first target transmission data including audio data and key data, it ensures that the ship monitoring platform can obtain the most core and important information in a timely manner under the condition of limited network bandwidth. By storing the non-critical second target transmission data in the cache space, it avoids transmitting unnecessary data when the bandwidth is insufficient and prevents further network congestion. By reasonably allocating network resources, the limited bandwidth gives priority to the transmission of key data, and at the same time reserves data for subsequent transmission and processes it when the network conditions permit, improving the overall utilization efficiency of bandwidth resources.

[0091] The above introduced the video processing method provided by the embodiments of this application. Next, the video processing device provided by the embodiments of this application will be introduced in conjunction with the accompanying drawings.

[0092] As Figure 2 shown, the embodiments of the present invention also provide a video processing device, and the device includes:

[0093] A compression module 201, configured to input the ship monitoring video data into a preset video compression model, identify redundant data in the ship monitoring video and compress it to obtain target ship monitoring video data; wherein, the preset video compression model is obtained through deep learning training based on a historical ship monitoring video dataset;

[0094] A first processing module 202, configured to encode the target ship monitoring video data based on a forward error correction algorithm to obtain redundant check data;

[0095] A second processing module 203, configured to add the check data to the target ship monitoring video data to obtain target transmission data;

[0096] A sending module 204, configured to send the target transmission data to a ship monitoring platform based on the User Datagram Protocol.

[0097] Optionally, the sending module includes:

[0098] A first obtaining sub-module, configured to obtain the network bandwidth of a transmission network, where the transmission network is used to send the target transmission data to the ship monitoring platform;

[0099] A first determining sub-module, configured to determine transmission parameters according to the network bandwidth, where the transmission parameters at least include: transmission unit size, retransmission parameters, and congestion window size;

[0100] A first sending sub-module, configured to send the target transmission data to the ship monitoring platform based on the User Datagram Protocol and the transmission parameters.

[0101] Optionally, before inputting the ship monitoring video data into a preset video compression model, identifying redundant data in the ship monitoring video and compressing it to obtain target ship monitoring video data, the apparatus further includes:

[0102] A first obtaining module, configured to obtain motion state data collected by motion sensors installed on the ship;

[0103] A third processing module, configured to adjust the ship monitoring video data according to the motion state data.

[0104] Optionally, before inputting the ship monitoring video data into a preset video compression model, identifying redundant data in the ship monitoring video and compressing it to obtain target ship monitoring video data, the apparatus further includes:

[0105] A second obtaining module, configured to input environmental information into a preset sea condition prediction model to obtain sea condition parameters indicating the sea surface motion trend;

[0106] A fourth processing module, configured to adjust the ship monitoring video data according to the sea condition parameters.

[0107] Optionally, before sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol, the apparatus further includes:

[0108] A third acquisition module, configured to acquire the network bandwidth of the transmission network, where the transmission network is used to send the target transmission data to the ship monitoring platform;

[0109] A first judgment module, configured to judge whether the network bandwidth is greater than a preset bandwidth threshold;

[0110] The sending module is further configured to, when the network bandwidth is greater than or equal to the preset bandwidth threshold, perform the step of sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol;

[0111] A second judgment module, configured to judge whether the target transmission data is real-time video data when the network bandwidth is less than the preset bandwidth threshold;

[0112] The sending module is further configured to, when the target transmission data is real-time video data, perform the step of sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol;

[0113] A storage module, configured to store the target transmission data in a pre-established cache space when the target transmission data is not real-time video data.

[0114] Optionally, when the network bandwidth is greater than or equal to the preset bandwidth threshold, the sending module includes:

[0115] A second determination sub-module, configured to determine a first bandwidth according to the target transmission data, and determine the remaining bandwidth in the network bandwidth except the first bandwidth as a second bandwidth;

[0116] A channel creation sub-module, configured to create a first transmission channel and a second transmission channel in the transmission network; where the first transmission channel corresponds to the first bandwidth, and the second transmission channel corresponds to the second bandwidth;

[0117] A second sending sub-module, configured to send the target transmission data to the ship monitoring platform through the first transmission channel based on the User Datagram Protocol;

[0118] A third sending sub-module, configured to send the data stored in the cache space to the ship monitoring platform through the second transmission channel.

[0119] Optionally, when the network bandwidth is less than the preset bandwidth threshold and the target transmission data is real-time video data, the sending module includes:

[0120] A third determination sub-module, configured to extract audio data and key data from the target transmission data to obtain first target transmission data, and determine the data other than the first target transmission data in the target transmission data as second target transmission data;

[0121] A fourth sending sub-module, configured to send the first target transmission data to the ship monitoring platform based on the User Datagram Protocol;

[0122] A storage sub-module, configured to store the second target transmission data in the cache space.

[0123] The video processing device provided in this application effectively compresses redundant data in ship monitoring video data through a preset video compression model obtained by deep learning training based on a historical ship monitoring video data set, thereby reducing the amount of video data and alleviating the transmission pressure in a narrow bandwidth environment. Subsequently, the forward error correction algorithm is used to further process the compressed video data to generate target transmission data. Based on the User Datagram Protocol, the target transmission data is sent to the ship monitoring platform. By combining the forward error correction mechanism and the User Datagram Protocol, this application ensures the accurate transmission of video data in a complex maritime communication environment and improves the stability of video transmission.

[0124] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For related parts, refer to the partial description of the method embodiment.

[0125] This application embodiment also provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements each process of the above video processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0126] For example, Figure 3 shows a schematic physical structure diagram of an electronic device. As Figure 3As shown in the figure, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330. The processor 310 is used to perform the following steps: input the ship monitoring video data into a preset video compression model, identify the redundant data in the ship monitoring video and compress it to obtain the target ship monitoring video data; wherein, the preset video compression model is obtained by deep learning training based on a historical ship monitoring video data set; encode the target ship monitoring video data based on the forward error correction algorithm to obtain redundant check data; add the check data to the target ship monitoring video data to obtain the target transmission data; send the target transmission data to the ship monitoring platform based on the User Datagram Protocol. The processor 310 can also execute other solutions in the embodiments of the present application, which will not be further elaborated here.

[0127] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software function units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0128] The embodiments of the present application also provide a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it realizes each process of the above video processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disc, etc.

[0129] It should be noted that in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including such element.

[0130] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to enable a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0131] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them belong to the protection scope of the present application.

[0132] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the embodiments of the present application can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0133] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0134] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0137] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0138] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application.

Claims

1. A video processing method, characterized in that, The method includes: Inputting the ship monitoring video data into a preset video compression model, identifying redundant data in the ship monitoring video and compressing it to obtain target ship monitoring video data; wherein, the preset video compression model is obtained through deep learning training based on a historical ship monitoring video data set; Encoding the target ship monitoring video data based on a forward error correction algorithm to obtain redundant check data; Adding the check data to the target ship monitoring video data to obtain target transmission data; Sending the target transmission data to a ship monitoring platform based on the User Datagram Protocol.

2. The video processing method according to claim 1, wherein Sending the target transmission data to a ship monitoring platform based on the User Datagram Protocol includes: Obtaining the network bandwidth of a transmission network, where the transmission network is used to send the target transmission data to the ship monitoring platform; Determining transmission parameters according to the network bandwidth, where the transmission parameters at least include: transmission unit size, retransmission parameters, and congestion window size; Sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol and the transmission parameters.

3. The video processing method according to claim 1, wherein Before inputting the ship monitoring video data into a preset video compression model, identifying redundant data in the ship monitoring video and compressing it to obtain target ship monitoring video data, the method further includes: Obtaining motion state data collected by motion sensors installed on the ship; Adjusting the ship monitoring video data according to the motion state data.

4. The video processing method according to claim 1, wherein Before inputting the ship monitoring video data into a preset video compression model, identifying redundant data in the ship monitoring video and compressing it to obtain target ship monitoring video data, the method further includes: Inputting environmental information into a preset sea condition prediction model to obtain sea condition parameters indicating the sea surface motion trend; Adjusting the ship monitoring video data according to the sea condition parameters.

5. The video processing method according to claim 1, characterized in that, Before sending the target transmission data to a ship monitoring platform based on the User Datagram Protocol, the method further includes: Obtaining the network bandwidth of a transmission network, where the transmission network is used to send the target transmission data to the ship monitoring platform; Judging whether the network bandwidth is greater than a preset bandwidth threshold; When the network bandwidth is greater than or equal to the preset bandwidth threshold, performing the step of sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol; When the network bandwidth is less than the preset bandwidth threshold, judging whether the target transmission data is real-time video data; When the target transmission data is real-time video data, performing the step of sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol; When the target transmission data is not real-time video data, storing the target transmission data in a pre-established cache space.

6. The video processing method according to claim 5, wherein When the network bandwidth is greater than or equal to the preset bandwidth threshold, sending the target transmission data to a ship monitoring platform based on the User Datagram Protocol includes: Determining a first bandwidth according to the target transmission data, and determining the remaining bandwidth in the network bandwidth except the first bandwidth as a second bandwidth; Create a first transmission channel and a second transmission channel in the transmission network; wherein, the first transmission channel corresponds to the first bandwidth, and the second transmission channel corresponds to the second bandwidth; Send the target transmission data to the ship monitoring platform based on the User Datagram Protocol through the first transmission channel; Send the data stored in the cache space to the ship monitoring platform through the second transmission channel.

7. The video processing method according to claim 5, wherein When the network bandwidth is less than the preset bandwidth threshold and the target transmission data is real-time video data, sending the target transmission data to the ship monitoring platform based on the User Datagram Protocol includes: Extract the audio data and key data from the target transmission data to obtain first target transmission data, and determine the data other than the first target transmission data in the target transmission data as second target transmission data; Send the first target transmission data to the ship monitoring platform based on the User Datagram Protocol; Store the second target transmission data in the cache space.

8. A video processing device, characterized in that, Includes: A compression module, configured to input ship monitoring video data into a preset video compression model, identify redundant data in the ship monitoring video and perform compression to obtain target ship monitoring video data; wherein, the preset video compression model is obtained by deep learning training based on a historical ship monitoring video data set; A first processing module, configured to encode the target ship monitoring video data based on a forward error correction algorithm to obtain redundant check data; A second processing module, configured to add the check data to the target ship monitoring video data to obtain target transmission data; A sending module, configured to send the target transmission data to the ship monitoring platform based on the User Datagram Protocol.

9. An electronic device, characterized in that, Includes a processor, a memory, and a computer program stored on the memory and executable on the processor, and when the computer program is executed by the processor, it implements the video processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the video processing method according to any one of claims 1 to 7.

Images