CN113870271A

CN113870271A - 3D point cloud compression method, device, equipment and storage medium

Info

Publication number: CN113870271A
Application number: CN202111151186.7A
Authority: CN
Inventors: 程京; 焦少慧; 杜绪晗
Original assignee: Beijing Youzhuju Network Technology Co Ltd
Current assignee: Beijing Youzhuju Network Technology Co Ltd
Priority date: 2021-09-29
Filing date: 2021-09-29
Publication date: 2021-12-31

Abstract

The embodiment of the disclosure discloses a method, a device, equipment and a storage medium for compressing 3D point cloud. Performing semantic segmentation on the collected RGBD data to obtain a plurality of 3D semantic regions; acquiring compression ratios respectively corresponding to the 3D semantic regions; and respectively compressing the point clouds in the 3D semantic regions based on a compression ratio to obtain the compressed RGBD data. According to the 3D point cloud compression method provided by the embodiment of the disclosure, the point clouds in different 3D semantic regions are compressed by adopting different compression ratios, so that the 3D point cloud can be compressed in a self-adaptive manner, the number of the point clouds can be effectively reduced, and the point cloud reconstruction effect can be ensured to a certain extent.

Description

3D point cloud compression method, device, equipment and storage medium

Technical Field

The embodiment of the disclosure relates to the technical field of image processing, in particular to a method, a device, equipment and a storage medium for compressing 3D point cloud.

Background

A point cloud is a collection of points in a three-dimensional (3-dimensional, 3D) space, capable of retaining the original geometric information in the 3D space without any discretization. It is therefore a preferred representation of many context-understanding-related applications, such as autopilot and robotics. Meanwhile, with the continuous development of hardware equipment, the point cloud technology has continuously entered our lives, and the point cloud technology is applied to some virtual reality 3D modeling products.

Because the point cloud is a collection of a large number of points, storing the point cloud data not only consumes a large amount of memory, but also is not beneficial to transmission, and at present, no bandwidth with such a large amount can support the direct transmission of the point cloud on a network layer without compression, so that the compression of the point cloud is necessary.

Disclosure of Invention

The embodiment of the disclosure provides a compression method, a compression device and a storage medium for 3D point cloud, which can realize self-adaptive compression of the 3D point cloud, not only can effectively reduce the number of the point cloud, but also can ensure the effect of point cloud reconstruction to a certain extent.

In a first aspect, an embodiment of the present disclosure provides a method for compressing a 3D point cloud, including:

performing semantic segmentation on the collected RGBD data to obtain a plurality of 3D semantic regions;

obtaining compression ratios respectively corresponding to the 3D semantic regions;

and respectively compressing the point clouds in the 3D semantic regions based on the compression ratio to obtain compressed RGBD data.

In a second aspect, an embodiment of the present disclosure further provides a device for compressing a 3D point cloud, including:

the 3D semantic region acquisition module is used for performing semantic segmentation on the acquired RGBD data to acquire a plurality of 3D semantic regions;

the compression ratio acquisition module is used for acquiring the compression ratio corresponding to each 3D semantic area;

and the 3D point cloud compression module is used for respectively compressing the point clouds in the 3D semantic regions based on the compression ratio to obtain the compressed RGBD data.

In a third aspect, an embodiment of the present disclosure further provides an electronic device, where the electronic device includes:

one or more processing devices;

storage means for storing one or more programs;

when executed by the one or more processing devices, cause the one or more processing devices to implement a method of compressing a 3D point cloud as described in embodiments of the disclosure.

In a fourth aspect, the present disclosure also provides a computer-readable medium, on which a computer program is stored, where the computer program, when executed by a processing device, implements the method for compressing a 3D point cloud according to the present disclosure.

Drawings

FIG. 1 is a flow chart of a method of compressing a 3D point cloud in an embodiment of the disclosure;

FIG. 2 is a schematic diagram of a method of compression of a 3D point cloud in an embodiment of the present disclosure;

FIG. 3 is a schematic structural diagram of a 3D point cloud compressing apparatus according to an embodiment of the disclosure;

fig. 4 is a schematic structural diagram of an electronic device in an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

Fig. 1 is a flowchart of a 3D point cloud compression method provided in an embodiment of the present disclosure, where the present embodiment is applicable to a case of compressing a 3D point cloud, and the method may be executed by a 3D point cloud compression apparatus, where the apparatus may be composed of hardware and/or software, and may be generally integrated in a device having a 3D point cloud compression function, and the device may be an electronic device such as a server, a mobile terminal, or a server cluster. As shown in fig. 1, the method specifically includes the following steps:

and 110, performing semantic segmentation on the acquired RGBD data to obtain a plurality of 3D semantic regions.

The RGBD data comprises an RGB (Red Green Blue, RGB) image and a Depth image, and can be acquired by a Depth camera, and the point cloud in the RGBD data comprises color (Red Green Blue, RGB) information and Depth (Depth, D) information.

The semantic segmentation can be understood as recognizing semantic information or semantic labels of each 3D point in the RGBD data. Semantic information is used to characterize the object class to which the 3D point belongs, for example: buildings, vehicles, target objects, ground, sky or water surfaces, etc.; wherein the target object may be a human figure or an animal.

In this embodiment, semantic segmentation of RGBD data may be implemented by using a Region-Convolutional Neural Networks (R-CNN), a Full Convolutional Network (FCN), or a weak supervised semantic segmentation (SED, expanded and constraint, SED) method, so as to obtain a plurality of 3D semantic regions. Wherein, the semantic information of the 3D points included in each 3D semantic region is the same, for example: one of the 3D semantic regions represents a 'wall surface', the other 3D semantic region represents a 'table', and the like.

Optionally, the process of performing semantic segmentation on the acquired RGBD data to obtain a plurality of 3D semantic regions may be: performing semantic segmentation on the RGB image; and aligning the RGB image after semantic segmentation with the depth image to obtain a plurality of 3D semantic regions.

The RGB map and the depth map are both two-dimensional (2D) maps, each pixel point in the RGB map carries RGB information and first coordinate information, and each pixel point in the depth map carries depth information and second coordinate information. And obtaining a conversion matrix between the RGB image and the depth image according to the internal and external reference calibration of the depth camera.

In this embodiment, the RGB map is first input into an R-CNN network or an FCN network or semantic segmentation is achieved by using an SED method, and then second coordinate information of each pixel point in the depth map is converted according to a conversion matrix, so that the depth map is aligned with the RGB map, thereby achieving semantic segmentation of the RGBD data and obtaining a plurality of 3D semantic regions.

In the embodiment of the disclosure, for RGBD data not including a target object, semantic segmentation may be directly performed, and for RGBD data including a target object, in order to improve the accuracy of target object segmentation, target object segmentation needs to be performed first, and then semantic segmentation is performed on a target object image and a background image, respectively.

Optionally, the process of performing semantic segmentation on the acquired RGBD data to obtain a plurality of 3D semantic regions may be: if the RGBD data contains the target object, performing target object segmentation on the RGBD data to obtain a target object image and a background image; performing target object part segmentation on the target object image to obtain a plurality of 3D target object parts; and performing semantic segmentation on the background image to obtain a plurality of 3D background semantic regions.

The target object segmentation can be understood as segmenting the target object from the background, and the process can be understood as: the contour of the target object in the image is identified and then separated from the background. The method can be implemented by adopting any existing target object segmentation technology, and details are not repeated here. The target object may be a human body or an animal, etc.

In this embodiment, after the target object image and the background image are obtained, the target object portion is segmented by an Artificial Intelligence (AI) technique to obtain a plurality of 3D target object portions. For example: if the target object is a human body, the human body is divided into a head, hands, a trunk, four limbs, and the like. And performing semantic segmentation on the background image through an AI technology to obtain a plurality of 3D background semantic areas. For example: table tops, windows, floors, walls, etc.

Specifically, when the RGBD data includes a target object, firstly, the RGB image is subjected to target object segmentation to obtain a 2D target object image and a 2D background image; performing target object part segmentation on the 2D target object image, and aligning the segmented 2D target object image with the depth map to obtain a plurality of 3D target object parts; and performing semantic segmentation on the 2D background image, and aligning the segmented 2D background image with the depth map to obtain a plurality of 3D background semantic regions.

And step 120, acquiring compression ratios respectively corresponding to the 3D semantic regions.

In this embodiment, the compression rates corresponding to different semantic regions are different. The semantic region with more details (such as the face, the hand, the desktop, the window and the like) can be compressed by a lower compression rate, and the semantic region with more details (such as the trunk, the limbs, the wall and the ground) can be compressed by a higher compression rate.

In this embodiment, the manner of obtaining the compression ratio corresponding to each 3D semantic region may be: establishing a corresponding relation between semantic information and a compression ratio; and determining the compression rate respectively corresponding to each 3D semantic area according to the corresponding relation.

Wherein the correspondence between the semantic information and the compression ratio can be set by a user.

Optionally, the manner of obtaining the compression ratio corresponding to each 3D semantic region may also be: inputting the RGB map into a set neural network model to obtain compression ratios corresponding to semantic information in the RGB map; and determining the compression ratio corresponding to each 3D semantic region based on the compression ratio corresponding to each semantic information.

The set neural network model can be a compression rate identification model used for determining compression rates of various semantic information in the image. The principle of setting the neural network model may be to first identify semantic information included in the RGB image, then determine the weight of each semantic information in the RGB image, and determine the compression rate of each semantic information based on the weight. Specifically, after the compression rate of each semantic information is determined, the compression rate is determined as the compression rate of the 3D semantic area corresponding to the semantic information.

Optionally, if the RGBD data includes the target object, the process of obtaining the compression ratio corresponding to each 3D semantic region may be: and acquiring a first compression ratio corresponding to each 3D target object part and a second compression ratio corresponding to each 3D background semantic area.

The first compression rate can be determined according to the corresponding relation between the semantic information of the target object part and the compression rate, or the target object image is input into a set neural network model to obtain the target object image. The second compression rate can be determined according to the corresponding relation between the semantic information and the compression rate, or the background image is input into a set neural network model to obtain the background image.

And step 130, respectively compressing the point clouds in the 3D semantic regions based on a compression rate to obtain compressed RGBD data.

Optionally, if the RGBD data includes the target object, the 3D target object portions are respectively compressed based on a first compression ratio, and the 3D background semantic regions are respectively compressed based on a second compression ratio, so as to obtain the compressed RGBD data.

In this embodiment, a voxelized grid method may be used to implement downsampling, thereby implementing compression of the 3D point cloud. Wherein the scale of the filter (voxelGrid filter) determines the compression rate. I.e. the larger the filter size, the larger the compression ratio; the smaller the filter scale and the smaller the compression ratio.

Specifically, each 3D semantic area is compressed based on a compression rate, and the process of obtaining the compressed RGBD data may be: for each 3D semantic region, carrying out voxel grid division on the 3D semantic region according to the compression rate to obtain a plurality of voxel grids; and respectively carrying out downsampling processing on the plurality of voxel grids to obtain compressed semantic regions.

Where the compression rate is proportional to the size of the voxel grid. I.e. the larger the compression rate, the larger the size of the voxel grid; the smaller the compression ratio, the smaller the size of the voxel grid. Namely, the larger the size of the voxel grid is, the fewer the point number of the filtered point cloud is, the speed is high, but the original point cloud is excessively blurred; the smaller the size of the voxel grid, the more the number of the filtered point clouds is, the slower the speed is, but most of the information of the original point cloud is retained.

In this example, the downsampling processing mode for the voxel grid may be: and averaging or weighted averaging the RGBD information of the points in the voxel grid to obtain one point.

In this embodiment, a voxelized mesh method is used to realize down-sampling, which can reduce the number of 3D points, thereby reducing the point cloud data and maintaining the shape characteristics of the point cloud.

For example, fig. 2 is a schematic diagram of a compression method of a 3D point cloud in the present embodiment. As shown in fig. 2, the target object is a human body, and for RGBD data, firstly, human image segmentation is performed to obtain a human body image and a background image; then, segmenting the human body part of the human body image to obtain a plurality of human body parts; performing semantic segmentation on the background image to obtain a plurality of semantic regions; then, compressing the coarse-grained human body part and the coarse-grained semantic region by adopting a high compression rate, and compressing the fine-grained human body part and the fine-grained semantic region by adopting a low compression rate; and finally, obtaining the compressed RGBD data.

According to the technical scheme of the embodiment, semantic segmentation is carried out on the collected RGBD data to obtain a plurality of 3D semantic areas; acquiring compression ratios respectively corresponding to the 3D semantic regions; and respectively compressing the point clouds in the 3D semantic regions based on a compression ratio to obtain the compressed RGBD data. According to the 3D point cloud compression method provided by the embodiment of the disclosure, the point clouds in different 3D semantic regions are compressed by adopting different compression ratios, so that the 3D point cloud can be compressed in a self-adaptive manner, the number of the point clouds can be effectively reduced, and the point cloud reconstruction effect can be ensured to a certain extent.

Fig. 3 is a schematic structural diagram of a 3D point cloud compression apparatus according to an embodiment of the present disclosure. As shown in fig. 3, the apparatus includes:

the 3D semantic region obtaining module 210 is configured to perform semantic segmentation on the acquired RGBD data to obtain a plurality of 3D semantic regions;

a compression ratio obtaining module 220, configured to obtain compression ratios corresponding to the 3D semantic regions, respectively;

and a 3D point cloud compression module 230, configured to compress the point clouds in the 3D semantic regions respectively based on the compression ratio, so as to obtain compressed RGBD data.

Optionally, the RGBD data includes an RGB map and a depth map; the 3D semantic area obtaining module 210 is further configured to:

performing semantic segmentation on the RGB image;

and aligning the RGB image after semantic segmentation with the depth image to obtain a plurality of 3D semantic regions.

Optionally, the 3D semantic area obtaining module 210 is further configured to:

if the RGBD data contains a target object, performing target object segmentation on the RGBD data to obtain a target object image and a background image;

performing target object part segmentation on the target object image to obtain a plurality of 3D target object parts;

and performing semantic segmentation on the background image to obtain a plurality of 3D background semantic regions.

Optionally, the compression rate obtaining module 220 is further configured to:

acquiring a first compression ratio corresponding to each 3D target object part and a second compression ratio corresponding to each 3D background semantic area;

optionally, the 3D point cloud compression module 230 is further configured to:

and respectively compressing the 3D target object parts based on the first compression ratio, and respectively compressing the 3D background semantic areas based on the second compression ratio to obtain the compressed RGBD data.

Optionally, the compression rate obtaining module 220 is further configured to:

inputting the RGB map into a set neural network model to obtain compression ratios corresponding to semantic information in the RGB map;

and determining the compression ratio corresponding to each 3D semantic region based on the compression ratio corresponding to each semantic information.

Optionally, the compression rate obtaining module 220 is further configured to:

establishing a corresponding relation between semantic information and a compression ratio;

and determining the compression rate respectively corresponding to each 3D semantic area according to the corresponding relation.

Optionally, the 3D point cloud compression module 230 is further configured to:

for each 3D semantic region, carrying out voxel grid division on the 3D semantic region according to the compression rate to obtain a plurality of voxel grids;

and respectively carrying out downsampling processing on the plurality of voxel grids to obtain a compressed semantic area.

The device can execute the methods provided by all the embodiments of the disclosure, and has corresponding functional modules and beneficial effects for executing the methods. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in all the foregoing embodiments of the disclosure.

Referring now to FIG. 4, a block diagram of an electronic device 300 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like, or various forms of servers such as a stand-alone server or a server cluster. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 4, electronic device 300 may include a processing means (e.g., central processing unit, graphics processor, etc.) 301 that may perform various appropriate actions and processes in accordance with a program stored in a read-only memory device (ROM)302 or a program loaded from a storage device 305 into a random access memory device (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and a communication device 309. The communication means 309 may allow the electronic device 300 to communicate wirelessly or by wire with other devices to exchange data. While fig. 4 illustrates an electronic device 300 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program containing program code for performing a method for recommending words. In such an embodiment, the computer program may be downloaded and installed from a network through the communication means 309, or installed from the storage means 305, or installed from the ROM 302. The computer program, when executed by the processing device 301, performs the above-described functions defined in the methods of the embodiments of the present disclosure.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: performing semantic segmentation on the collected RGBD data to obtain a plurality of 3D semantic regions; obtaining compression ratios respectively corresponding to the 3D semantic regions; and respectively compressing the point clouds in the 3D semantic regions based on the compression ratio to obtain compressed RGBD data.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, a method for compressing a 3D point cloud is disclosed, including:

Further, the RGBD data comprises an RGB map and a depth map; performing semantic segmentation on the acquired RGBD data to obtain a plurality of 3D semantic regions, including:

performing semantic segmentation on the RGB image;

Furthermore, performing semantic segmentation on the acquired RGBD data to obtain a plurality of 3D semantic regions, including:

Further, obtaining compression ratios respectively corresponding to the 3D semantic regions includes:

compressing the 3D semantic regions respectively based on the compression ratio to obtain compressed RGBD data, including:

Further, the compressing the 3D semantic regions based on the compression ratio to obtain the compressed RGBD data includes:

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present disclosure and the technical principles employed. Those skilled in the art will appreciate that the present disclosure is not limited to the particular embodiments described herein, and that various obvious changes, adaptations, and substitutions are possible, without departing from the scope of the present disclosure. Therefore, although the present disclosure has been described in greater detail with reference to the above embodiments, the present disclosure is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present disclosure, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for compressing a 3D point cloud, comprising:

performing semantic segmentation on the collected color depth RGBD data to obtain a plurality of 3D semantic regions;

2. The method of claim 1, wherein the RGBD data comprises an RGB map and a depth map; performing semantic segmentation on the acquired RGBD data to obtain a plurality of 3D semantic regions, including:

performing semantic segmentation on the RGB image;

3. The method of claim 1 or 2, wherein performing semantic segmentation on the acquired RGBD data to obtain a plurality of 3D semantic regions comprises:

if the RGBD data contains a target object, segmenting the RGBD data by the target object to obtain a target object image and a background image;

4. The method according to claim 3, wherein obtaining compression ratios corresponding to the respective 3D semantic regions comprises:

5. The method according to claim 2, wherein obtaining compression ratios corresponding to the respective 3D semantic regions comprises:

6. The method according to claim 1, wherein obtaining compression ratios corresponding to the respective 3D semantic regions comprises:

7. The method according to claim 1, wherein the compressing the 3D semantic regions based on the compression ratio to obtain compressed RGBD data comprises:

8. An apparatus for compressing a 3D point cloud, comprising:

9. An electronic device, characterized in that the electronic device comprises:

one or more processing devices;

storage means for storing one or more programs;

when executed by the one or more processing devices, cause the one or more processing devices to implement the method of compressing a 3D point cloud of any of claims 1-7.

10. A computer-readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processing device, implements the method of compressing a 3D point cloud according to any one of claims 1-7.