Inland waterway ship point cloud data transmission method and system

Abstract

The present invention provides a method and system for transmitting point cloud data of inland waterway ships, the method comprising performing a unified translation and rotation transformation on the point cloud data according to the parameters of the installation point and the observation point, and fusing the point cloud data after the translation and rotation transformation to obtain complete point cloud data; performing noise reduction, background separation and encoding on the complete point cloud data in sequence to separate the foreground frame and the background frame; obtaining a sampling period based on the foreground frame sampling frequency and the background frame sampling frequency, and transmitting the data stream according to the sampling period; decoding the data stream according to the communication protocol to obtain the relevant point cloud data of the foreground frame and the relevant point cloud data of the background frame. The present invention can avoid the influence of point cloud data on the transmission efficiency during transmission, and shield the upper application system from coupling with the physical environment, effectively reducing the use difficulty and computing load of the upper application system, and improving the overall stability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and transmission, and in particular to a method and system for transmitting point cloud data of an inland waterway ship. Background Art

[0002] In applications such as ship target identification, navigation trajectory tracking, bridge collision warning and virtual simulation in inland waterways, the commonly used technologies and methods are to deploy one to multiple multi-line laser radars and other point cloud acquisition devices on the bridge deck or the shore to collect the channel shape in real time, and then transmit the point cloud data stream collected by the equipment to the back-end application server in real time through the 4G / 5G network; the application server then analyzes and processes the data through technical means such as point cloud fusion and target segmentation, and further combines it with the business needs of inland waterways to provide it for use in scenarios such as ship target tracking and virtual simulation.

[0003] Among the existing technologies, 1. The transmission of point cloud data is not processed, which may cause a large network load, affecting the network transmission efficiency under poor network conditions or when there are many acquisition devices installed;

[0004] 2. The point cloud data is not downsampled in accordance with the business scenario before transmission, and all processing and analysis are centrally processed by the upper-level application server, which is prone to performance bottlenecks and single point failures, and is not conducive to the stability of the system;

[0005] 3. Unprocessed point cloud data contains a large amount of redundant data (such as static objects or buildings such as bridges, embankments, and shores). These data are usually very stable within a certain time range and are not of concern to the business. Summary of the invention

[0006] Based on this, the purpose of the present invention is to provide a method and system for transmitting point cloud data of inland waterway ships to solve the deficiencies in the above-mentioned prior art.

[0007] In a first aspect, the present invention provides a method for transmitting point cloud data of an inland waterway ship, the method comprising:

[0008] Collect point cloud data of ships in inland waterways;

[0009] Performing a uniform translation and rotation transformation on the point cloud data according to the parameters of the installation point and the observation point, and fusing the point cloud data after the translation and rotation transformation to obtain complete point cloud data;

[0010] Performing noise reduction, background separation and encoding on the complete point cloud data in sequence, so as to separate the complete point cloud data into corresponding foreground frames and background frames;

[0011] Setting the sampling frequencies of the foreground frame and the background frame to obtain the foreground frame sampling frequency and the background frame sampling frequency respectively;

[0012] A sampling period is obtained based on the foreground frame sampling frequency and the background frame sampling frequency, and a sampling strategy of the background frame is set based on a change rate threshold, a random sampling consistency algorithm is used to calculate the change rate of point cloud data of every two consecutive frames, and the change rate threshold is compared with the change rate. If the change rate is greater than the change rate threshold, background interpolation is performed on the transmitted data stream, and the data stream is transmitted according to the sampling period;

[0013] The data stream is decoded according to a communication protocol to obtain relevant point cloud data of the foreground frame and relevant point cloud data of the background frame.

[0014] Compared with the prior art, the beneficial effects of the present invention are: by translating and rotating the point cloud data, the transmission efficiency is avoided from being affected during transmission; the complete point cloud data can be separated through noise reduction, background separation and encoding; and through fusion processing, the coupling of the upper-level application system to the physical environment can be effectively shielded, and the difficulty of use and computing load of the upper-level application system are effectively reduced; and by setting the sampling frequency, time-sharing transmission can be performed to improve the overall stability of the system.

[0015] Furthermore, the step of uniformly translating and rotating the point cloud data according to the parameters of the installation point and the observation point includes:

[0016] Performing a translation transformation on the point cloud data based on a translation transformation formula to convert the coordinates of the point cloud data into system monitoring point coordinates;

[0017] The point cloud data is subjected to a rotation transformation based on a rotation transformation formula.

[0018] Furthermore, the translation transformation formula is expressed as:

[0019] ;

[0020] In the formula, , , They represent the horizontal coordinate after translation transformation, the vertical coordinate after translation transformation, and the vertical coordinate after translation transformation, respectively. , , They represent the horizontal coordinate, the vertical coordinate, and the ordinate of the original coordinate respectively. , , Respectively represent the horizontal coordinate of the monitoring point, the vertical coordinate of the monitoring point, and the vertical coordinate of the monitoring point;

[0021] The expression of the rotation transformation formula is:

[0022] ;

[0023] In the formula, , , They represent the horizontal coordinate after rotation transformation, the vertical coordinate after rotation transformation, and the ordinate after rotation transformation, respectively. , , They represent the horizontal coordinate, the vertical coordinate, and the ordinate of the original coordinate respectively. , , They respectively represent the rotation angle on the horizontal axis, the rotation angle on the vertical axis, and the rotation angle on the vertical axis.

[0024] Furthermore, the step of fusing the point cloud data after translation and rotation transformation to obtain complete point cloud data includes:

[0025] Registering the point cloud data after translation and rotation transformation according to an iterative closest point ICP algorithm;

[0026] The registered point cloud data is vertically spliced ​​to obtain complete point cloud data.

[0027] Furthermore, the step of sequentially performing noise reduction, background separation and encoding on the complete point cloud data to separate the complete point cloud data into corresponding foreground frames and background frames includes:

[0028] Performing statistical analysis on the neighborhood of each point in the complete point cloud data to exclude outliers in the complete point cloud data;

[0029] Separating the complete point cloud data into foreground point cloud data and background point cloud data according to the channel parameters;

[0030] Segmenting the foreground point cloud according to the morphological features of the ship to obtain ship point cloud data of each ship, and encoding the ship point cloud data to obtain a foreground frame;

[0031] Frame header information is added to the background point cloud data and encoded to obtain a background frame.

[0032] Furthermore, the step of obtaining a sampling period based on the foreground frame sampling frequency and the background frame sampling frequency includes:

[0033] Set the foreground frame sampling frequency to , and set the background frame sampling frequency to ,in ;

[0034] The sampling period is obtained according to the foreground frame sampling frequency and the background frame sampling frequency, and background frames sampled outside the sampling period are discarded.

[0035] Furthermore, before the step of transmitting the data stream according to the sampling period, the method further includes:

[0036] Setting a sampling strategy for the background frame based on a change rate threshold;

[0037] A random sampling consistency algorithm is used to calculate the change rate of point cloud data of every two consecutive frames, and the change rate threshold is compared with the change rate;

[0038] If the change rate is greater than the change rate threshold, background frame insertion is performed on the transmitted data stream.

[0039] In a second aspect, the present invention further provides a point cloud data transmission system for inland waterway ships, the system comprising:

[0040] Access module, used to collect point cloud data of ships in inland waterways;

[0041] A processing module, used for uniformly performing translation and rotation transformation on the point cloud data according to the parameters of the installation point and the observation point, and fusing the point cloud data after the translation and rotation transformation to obtain complete point cloud data;

[0042] A separation module, used to perform noise reduction, background separation and encoding on the complete point cloud data in sequence, so as to separate the complete point cloud data into corresponding foreground frames and background frames;

[0043] A setting module, used for setting the sampling frequencies of the foreground frame and the background frame, so as to obtain the foreground frame sampling frequency and the background frame sampling frequency respectively;

[0044] A transmission module, used to obtain a sampling period based on the foreground frame sampling frequency and the background frame sampling frequency, and set a sampling strategy for the background frame based on a change rate threshold, use a random sampling consistency algorithm to calculate the change rate of point cloud data of every two consecutive frames, and compare the change rate threshold with the change rate. If the change rate is greater than the change rate threshold, background interpolation is performed on the transmitted data stream, and the data stream is transmitted according to the sampling period;

[0045] The decoding module is used to decode the data stream according to the communication protocol to obtain the relevant point cloud data of the foreground frame and the relevant point cloud data of the background frame.

[0046] In a third aspect, the present invention further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned inland waterway ship point cloud data transmission method.

[0047] In a fourth aspect, the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned inland waterway ship point cloud data transmission method when executing the computer program. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of the method for transmitting point cloud data of an inland waterway ship in the first embodiment of the present invention;

[0049] Figure 2 It is a schematic diagram of data stream transmission according to a sampling period in the first embodiment of the present invention;

[0050] Figure 3 It is a schematic diagram of data stream transmission when the sampling strategy of setting the background frame uses the change rate threshold strategy in the first embodiment of the present invention;

[0051] Figure 4 It is a structural block diagram of the inland waterway ship point cloud data transmission system in the second embodiment of the present invention;

[0052] Figure 5 It is a structural block diagram of a computer device in the third embodiment of the present invention.

[0053] Description of main component symbols:

[0054] 11. Access module; 12. Processing module; 13. Separation module; 14. Setting module; 15. Transmission module; 16. Decoding module;

[0055] 10. Memory; 20. Processor; 30. Computer program.

[0056] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0057] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0058] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0060] Embodiment 1

[0061] See also Figure 1 , which shows a method for transmitting point cloud data of an inland waterway ship in a first embodiment of the present invention, and the method comprises steps S1 to S6:

[0062] S1, collects point cloud data of ships in inland waterways;

[0063] It should be noted that in order to preset the relevant parameters for system access, processing and output, it is first necessary to install the IP address of the point cloud acquisition device, and then set the coordinates of the waterway monitoring points, the point cloud acquisition frequency and the background transmission strategy.

[0064] S2, performing a uniform translation and rotation transformation on the point cloud data according to the parameters of the installation point and the observation point, and fusing the point cloud data after the translation and rotation transformation to obtain complete point cloud data;

[0065] Specifically, the step S2 includes steps S21 to S24:

[0066] S21, performing translation transformation on the point cloud data based on a translation transformation formula to convert the coordinates of the point cloud data into system monitoring point coordinates;

[0067] It can be understood that the point cloud data collected by each point cloud data channel is based on the installation coordinates of the device as the origin coordinates, and needs to be converted into the system monitoring point coordinates as the original coordinates through translation transformation before use. In this embodiment, the translation transformation formula is expressed as:

[0068] ;

[0069] In the formula, , , They represent the horizontal coordinate after translation transformation, the vertical coordinate after translation transformation, and the vertical coordinate after translation transformation, respectively. , , They represent the horizontal coordinate, the vertical coordinate, and the ordinate of the original coordinate respectively. , , Respectively represent the horizontal coordinate of the monitoring point, the vertical coordinate of the monitoring point, and the vertical coordinate of the monitoring point;

[0070] S22, performing a rotation transformation on the point cloud data based on a rotation transformation formula;

[0071] It is understandable that since the installation of the point cloud acquisition device will produce an angle with the observation coordinates of the waterway monitoring point, the point cloud data needs to be rotated. In this embodiment, the expression of the rotation transformation formula is:

[0072] ;

[0073] In the formula, , , They represent the horizontal coordinate after rotation transformation, the vertical coordinate after rotation transformation, and the ordinate after rotation transformation, respectively. , , They represent the horizontal coordinate, the vertical coordinate, and the ordinate of the original coordinate respectively. , , Respectively represent the rotation angle on the horizontal axis, the rotation angle on the vertical axis, and the rotation angle on the vertical axis;

[0074] S23, registering the point cloud data after translation and rotation transformation according to an iterative closest point ICP algorithm;

[0075] S24, performing moment vertical stitching on the registered point cloud data to obtain complete point cloud data;

[0076] It can be understood that after the multi-channel point cloud data are transformed into data of a unified coordinate system through translation and rotation, the multi-channel point cloud data are aligned according to the iterative closest point ICP algorithm, and finally the point cloud data of a complete waterway monitoring point are formed by vertical splicing.

[0077] S3, performing noise reduction, background separation and encoding on the complete point cloud data in sequence, so as to separate the complete point cloud data into corresponding foreground frames and background frames;

[0078] Specifically, the step S3 includes steps S31 to S34:

[0079] S31, performing statistical analysis on the neighborhood of each point in the complete point cloud data to exclude outliers in the complete point cloud data;

[0080] It is understandable that due to the influence of the surrounding environment of the channel collection point (weather, floating objects, flying birds, etc.), the point cloud data collected by the equipment may contain some noise data, which are usually outliers. These outliers can be excluded by performing statistical analysis on the neighborhood of each point in the point cloud data;

[0081] S32, separating the complete point cloud data into foreground point cloud data and background point cloud data according to the channel parameters;

[0082] It can be understood that each frame of point cloud data after noise reduction is separated into foreground point cloud data and background point cloud data according to the channel parameter settings of the system, wherein the foreground point cloud mainly includes the point cloud data of ships traveling on the channel, and the background point cloud mainly includes the point cloud data of buildings and embankments around the channel collected;

[0083] S33, segmenting the foreground point cloud according to the morphological features of the ship to obtain ship point cloud data of each ship, and encoding the ship point cloud data to obtain a foreground frame;

[0084] S34, adding frame header information to the background point cloud data and encoding it to obtain a background frame;

[0085] It can be understood that, based on the separated foreground point cloud, the ship point cloud data of each ship is segmented according to the morphological characteristics of the ship, and the required frame header information is attached. In this embodiment, the frame header information includes frame category, acquisition time and point cloud size, and then further encoded to obtain the foreground frame, and the necessary frame header information is attached and further encoded according to the separated background point cloud data to obtain the background frame.

[0086] S4, setting the sampling frequencies of the foreground frame and the background frame to obtain the foreground frame sampling frequency and the background frame sampling frequency respectively;

[0087] It is understandable that after data separation, each frame of the original point cloud data is separated into corresponding foreground frames and background frames, and these data need to be transmitted. Data transmission uses TCP or IP protocol for network transmission, and foreground frames and background frames use the same network channel for time-sharing transmission. Different time-sharing methods are used according to different parameter settings. First, you need to set the sampling frequency of the foreground frame and the sampling frequency of the background frame.

[0088] S5, obtaining a sampling period based on the foreground frame sampling frequency and the background frame sampling frequency, and setting a sampling strategy for the background frame based on a change rate threshold, using a random sampling consistency algorithm to calculate the change rate of point cloud data of every two consecutive frames, and comparing the change rate threshold with the change rate, if the change rate is greater than the change rate threshold, performing background interpolation on the transmitted data stream, and transmitting the data stream according to the sampling period;

[0089] Specifically, the step S5 includes step S51 to step S52:

[0090] S51, setting the foreground frame sampling frequency to , and set the background frame sampling frequency to ,in ;

[0091] S52, obtaining the sampling period according to the foreground frame sampling frequency and the background frame sampling frequency, and discarding the background frames sampled outside the sampling period;

[0092] It should be noted that , then the sampling period , , They represent the time intervals between the transmission of the first background frame to the second background frame and the transmission of the second background frame to the third background frame. All background frames sampled during the rest of the time are discarded. The specific data streams are as follows: Figure 2 shown.

[0093] It can be understood that if the sampling strategy of the background frame is set to use the change rate threshold strategy, and the change rate threshold is set to R, the random sampling consistency algorithm is used to calculate the change rate r of the point cloud data of every two consecutive frames. If r is greater than R, the background frame is inserted into the transmitted data stream, and the background frames sampled during the rest of the time are also discarded. The transmitted data stream is as follows Figure 3 It is worth noting that Figure 2 and Figure 3 FF in the figure represents the foreground frame, and BF represents the background frame.

[0094] S6, decoding the data stream according to the communication protocol to obtain relevant point cloud data of the foreground frame and relevant point cloud data of the background frame;

[0095] It can be understood that the upper-level system decodes according to the communication protocol. In this embodiment, the communication protocol is TCP or IP protocol for decoding, which can obtain the information of the foreground frame and background frame and related point cloud data, and use the data in scenarios such as target detection and virtual simulation.

[0096] In summary, the inland waterway ship point cloud data transmission method in the above-mentioned embodiments of the present invention, through point cloud fusion, point cloud filtering and other technologies, effectively reduces the amount of information required for the same information expression of point cloud data, improves data storage and transmission efficiency, and reduces network load; the foreground and background separation technology is used to transmit the collected point cloud data in time-sharing, and the upper-level application system can adopt different usage strategies for foreground and background data according to different usage scenarios, thereby further improving the overall performance of the system; it can support the access of multiple point cloud devices, and can transform and fuse the collected multi-channel point cloud data according to the inland waterway parameters and the installation parameters of each device, effectively shielding the coupling of the upper-level application system to the physical environment, and reducing the difficulty of use and computing load of the upper-level application system.

[0097] Embodiment 2

[0098] See also Figure 4 , which shows a point cloud data transmission system for inland waterway vessels in a second embodiment of the present invention, the system comprises:

[0099] Access module 11, used to collect ship point cloud data of inland waterways;

[0100] The processing module 12 is used to perform a uniform translation and rotation transformation on the point cloud data according to the parameters of the installation point and the observation point, and fuse the point cloud data after the translation and rotation transformation to obtain complete point cloud data;

[0101] A separation module 13, used to perform noise reduction, background separation and encoding on the complete point cloud data in sequence, so as to separate the complete point cloud data into corresponding foreground frames and background frames;

[0102] The setting module 14 is used to set the sampling frequencies of the foreground frame and the background frame to obtain the foreground frame sampling frequency and the background frame sampling frequency respectively;

[0103] The transmission module 15 is used to obtain a sampling period based on the foreground frame sampling frequency and the background frame sampling frequency, and set the sampling strategy of the background frame based on the change rate threshold, use a random sampling consistency algorithm to calculate the change rate of point cloud data of every two consecutive frames, and compare the change rate threshold with the change rate. If the change rate is greater than the change rate threshold, background interpolation is performed on the transmitted data stream, and the data stream is transmitted according to the sampling period;

[0104] The decoding module 16 is used to decode the data stream according to the communication protocol to obtain the relevant point cloud data of the foreground frame and the relevant point cloud data of the background frame.

[0105] In some optional embodiments, the processing module 12 includes:

[0106] A translation transformation unit, used for performing translation transformation on the point cloud data based on a translation transformation formula, so as to convert the coordinates of the point cloud data into the coordinates of the system monitoring points;

[0107] The expression of the translation transformation formula is:

[0108] ;

[0109] In the formula, , , They represent the horizontal coordinate after translation transformation, the vertical coordinate after translation transformation, and the vertical coordinate after translation transformation, respectively. , , They represent the horizontal coordinate, the vertical coordinate, and the ordinate of the original coordinate respectively. , , Respectively represent the horizontal coordinate of the monitoring point, the vertical coordinate of the monitoring point, and the vertical coordinate of the monitoring point;

[0110] A rotation transformation unit, used for performing a rotation transformation on the point cloud data based on a rotation transformation formula;

[0111] The expression of the rotation transformation formula is:

[0112] ;

[0113] In the formula, , , They represent the horizontal coordinate after rotation transformation, the vertical coordinate after rotation transformation, and the ordinate after rotation transformation, respectively. , , They represent the horizontal coordinate, the vertical coordinate, and the ordinate of the original coordinate respectively. , , Respectively represent the rotation angle on the horizontal axis, the rotation angle on the vertical axis, and the rotation angle on the vertical axis;

[0114] A registration unit, used for registering the point cloud data after translation and rotation transformation according to an iterative closest point ICP algorithm;

[0115] The stitching unit is used to perform moment vertical stitching on the registered point cloud data to obtain complete point cloud data.

[0116] In some optional embodiments, the separation module 13 includes:

[0117] A statistical analysis unit, configured to perform statistical analysis on a neighborhood of each point in the complete point cloud data to exclude outliers in the complete point cloud data;

[0118] A separation unit, used for separating the complete point cloud data into foreground point cloud data and background point cloud data according to the channel parameters;

[0119] A segmentation unit, configured to segment the foreground point cloud according to the morphological features of the ship to obtain ship point cloud data of each ship, and encode the ship point cloud data to obtain a foreground frame;

[0120] The encoding unit is used to add frame header information to the background point cloud data and encode it to obtain a background frame.

[0121] In some optional embodiments, the transmission module 15 includes:

[0122] A setting unit is used to set the foreground frame sampling frequency to , and set the background frame sampling frequency to ,in ;

[0123] The sampling unit is used to obtain the sampling period according to the foreground frame sampling frequency and the background frame sampling frequency, and discard the background frames sampled outside the sampling period.

[0124] The functions or operation steps implemented when the above modules and units are executed are generally the same as those in the above method embodiments, and will not be repeated here.

[0125] The inland waterway ship point cloud data transmission system provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0126] Embodiment 3

[0127] The present invention also provides a computer device, see Figure 5 , shown is a computer device in the third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned inland waterway ship point cloud data transmission method is implemented.

[0128] The memory 10 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 10 may be an internal storage unit of a computer device, such as a hard disk of the computer device. In other embodiments, the memory 10 may also be an external storage device, such as a plug-in hard disk, a smart memory card (Smart MediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Further, the memory 10 may also include both an internal storage unit of a computer device and an external storage device. The memory 10 may be used not only to store application software and various types of data installed in the computer device, but also to temporarily store data that has been output or is to be output.

[0129] Among them, in some embodiments, the processor 20 can be an electronic control unit (Electronic Control Unit, abbreviated as ECU, also known as a vehicle computer), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run the program code stored in the memory 10 or process data, such as executing access restriction programs, etc.

[0130] It should be pointed out that Figure 5 The structure shown does not constitute a limitation on the computer device. In other embodiments, the computer device may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0131] An embodiment of the present invention further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned inland waterway ship point cloud data transmission method.

[0132] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0133] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0134] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0135] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0136] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for transmitting point cloud data of inland waterway ships, characterized in that: The method comprises: Collect point cloud data of ships in inland waterways; Performing a uniform translation and rotation transformation on the point cloud data according to the parameters of the installation point and the observation point, and fusing the point cloud data after the translation and rotation transformation to obtain complete point cloud data; Performing noise reduction, background separation and encoding on the complete point cloud data in sequence, so as to separate the complete point cloud data into corresponding foreground frames and background frames; Setting the sampling frequencies of the foreground frame and the background frame to obtain the foreground frame sampling frequency and the background frame sampling frequency respectively; A sampling period is obtained based on the foreground frame sampling frequency and the background frame sampling frequency, and a sampling strategy of the background frame is set based on a change rate threshold, a random sampling consistency algorithm is used to calculate the change rate of point cloud data of every two consecutive frames, and the change rate threshold is compared with the change rate. If the change rate is greater than the change rate threshold, background interpolation is performed on the transmitted data stream, and the data stream is transmitted according to the sampling period; The obtaining of the sampling period based on the foreground frame sampling frequency and the background frame sampling frequency specifically includes: Set the foreground frame sampling frequency to , and set the background frame sampling frequency to ,in ; The sampling period is obtained according to the foreground frame sampling frequency and the background frame sampling frequency, and background frames sampled outside the sampling period are discarded; Sampling period , , They represent the time intervals between the transmission of the first background frame to the second background frame and the transmission of the second background frame to the third background frame, and all background frames sampled during the rest of the time are discarded; If the change rate is greater than the change rate threshold, background frame insertion is performed on the transmitted data stream, specifically including: The sampling strategy of the background frame is set to use the change rate threshold strategy. The change rate threshold is set to R. The random sampling consistency algorithm is used to calculate the change rate r of the point cloud data of every two consecutive frames. If r is greater than R, the background frame is inserted into the transmitted data stream, and the background frames sampled in the rest of the time are also discarded. The data stream is decoded according to a communication protocol to obtain relevant point cloud data of the foreground frame and relevant point cloud data of the background frame.

2. The method for transmitting point cloud data of inland waterway ships according to claim 1, characterized in that: The step of uniformly performing translation and rotation transformation on the point cloud data according to the parameters of the installation point and the observation point comprises: Performing a translation transformation on the point cloud data based on a translation transformation formula to convert the coordinates of the point cloud data into system monitoring point coordinates; The point cloud data is subjected to a rotation transformation based on a rotation transformation formula.

3. The method for transmitting point cloud data of inland waterway ships according to claim 2, characterized in that: The expression of the translation transformation formula is: ； In the formula, , , They represent the horizontal coordinate after translation transformation, the vertical coordinate after translation transformation, and the vertical coordinate after translation transformation, respectively. , , They represent the horizontal coordinate, the vertical coordinate, and the ordinate of the original coordinate respectively. , , Respectively represent the horizontal coordinate of the monitoring point, the vertical coordinate of the monitoring point, and the vertical coordinate of the monitoring point; The expression of the rotation transformation formula is: ； In the formula, , , They represent the horizontal coordinate after rotation transformation, the vertical coordinate after rotation transformation, and the ordinate after rotation transformation, respectively. , , They represent the horizontal coordinate, the vertical coordinate, and the ordinate of the original coordinate respectively. , , They respectively represent the rotation angle on the horizontal axis, the rotation angle on the vertical axis, and the rotation angle on the vertical axis.

4. The method for transmitting point cloud data of inland waterway ships according to claim 1, characterized in that: The step of fusing the point cloud data after translation and rotation transformation to obtain complete point cloud data includes: Registering the point cloud data after translation and rotation transformation according to an iterative closest point ICP algorithm; The registered point cloud data is vertically spliced ​​to obtain complete point cloud data.

5. The method for transmitting point cloud data of inland waterway ships according to claim 1, characterized in that: The step of sequentially performing noise reduction, background separation and encoding on the complete point cloud data to separate the complete point cloud data into corresponding foreground frames and background frames comprises: Performing statistical analysis on the neighborhood of each point in the complete point cloud data to exclude outliers in the complete point cloud data; Separating the complete point cloud data into foreground point cloud data and background point cloud data according to the channel parameters; Segmenting the foreground point cloud according to the morphological features of the ship to obtain ship point cloud data of each ship, and encoding the ship point cloud data to obtain a foreground frame; Frame header information is added to the background point cloud data and encoded to obtain a background frame.

6. An inland waterway ship point cloud data transmission system, characterized in that: The system comprises: Access module, used to collect point cloud data of ships in inland waterways; A processing module, used for uniformly performing translation and rotation transformation on the point cloud data according to the parameters of the installation point and the observation point, and fusing the point cloud data after the translation and rotation transformation to obtain complete point cloud data; A separation module, used to perform noise reduction, background separation and encoding on the complete point cloud data in sequence, so as to separate the complete point cloud data into corresponding foreground frames and background frames; A setting module, used for setting the sampling frequencies of the foreground frame and the background frame, so as to obtain the foreground frame sampling frequency and the background frame sampling frequency respectively; A transmission module, used to obtain a sampling period based on the foreground frame sampling frequency and the background frame sampling frequency, and set a sampling strategy for the background frame based on a change rate threshold, use a random sampling consistency algorithm to calculate the change rate of point cloud data of every two consecutive frames, and compare the change rate threshold with the change rate. If the change rate is greater than the change rate threshold, background interpolation is performed on the transmitted data stream, and the data stream is transmitted according to the sampling period; The obtaining of the sampling period based on the foreground frame sampling frequency and the background frame sampling frequency specifically includes: Set the foreground frame sampling frequency to , and set the background frame sampling frequency to ,in ; The sampling period is obtained according to the foreground frame sampling frequency and the background frame sampling frequency, and background frames sampled outside the sampling period are discarded; Sampling period , , They represent the time intervals between the transmission of the first background frame to the second background frame and the transmission of the second background frame to the third background frame, and all background frames sampled during the rest of the time are discarded; If the change rate is greater than the change rate threshold, background frame insertion is performed on the transmitted data stream, specifically including: The sampling strategy of the background frame is set to use the change rate threshold strategy. The change rate threshold is set to R. The random sampling consistency algorithm is used to calculate the change rate r of the point cloud data of every two consecutive frames. If r is greater than R, the background frame is inserted into the transmitted data stream, and the background frames sampled in the rest of the time are also discarded. The decoding module is used to decode the data stream according to the communication protocol to obtain the relevant point cloud data of the foreground frame and the relevant point cloud data of the background frame.

7. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for transmitting point cloud data of an inland waterway ship as described in any one of claims 1 to 5 is implemented.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the inland waterway ship point cloud data transmission method as described in any one of claims 1 to 5.

Images