Map generation method and device, unmanned equipment and storage medium

Abstract

The invention discloses a map generation method and device, unmanned equipment and a storage medium, and relates to the technical field of unmanned equipment. The method is applied to the unmanned equipment, the unmanned equipment comprises a central processing unit, a digital signal processor and a camera main control processor, the camera main control processor is connected with the central processing unit and the digital signal processor, and the method comprises the following steps: controlling a camera carried by the unmanned equipment to photograph a surveying and mapping area through the camera main control processor so as to generate a first image, transmitting the first image to a digital signal processor; preprocessing the first image through a digital signal processor to obtain image feature data of the first image, and transmitting the image feature data to a camera main control processor; the camera main control processor transmits the image feature data to the central processor, and the central processor generates a map of the surveying and mapping area based on the image feature data. Through the technical means, the problem that the unmanned equipment cannot further improve the map generation efficiency in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the technical field of unmanned equipment, and in particular to a map generation method, device, unmanned equipment and storage medium. Background Art

[0002] With the rapid development of unmanned equipment technology, it is widely used in various scenarios for high-altitude operations. Especially in surveying and mapping scenarios, unmanned equipment can take pictures of the surveying and mapping area through the camera on board, and generate high-precision maps of the surveying and mapping area based on the captured images.

[0003] In the prior art, unmanned equipment can process images in real time through a central processor to generate a high-precision map of the surveyed area. However, in order to control the cost of using unmanned equipment, the computing power resources of the central processor used are limited, and the unmanned equipment cannot further improve the efficiency of map generation. Summary of the invention

[0004] The present application provides a map generation method, device, unmanned equipment and storage medium, which pre-processes the image through a digital signal processor and then generates a high-precision map through a central processing unit, thereby improving the image preprocessing efficiency and map generation efficiency, and solving the problem in the prior art that unmanned equipment cannot further improve the map generation efficiency.

[0005] In a first aspect, the present application provides a map generation method, which is applied to an unmanned device, wherein the unmanned device includes a central processing unit, a digital signal processor, and a camera main control processor, wherein the camera main control processor is connected to the central processing unit and the digital signal processor, and the method includes:

[0006] Controlling the camera carried by the unmanned equipment to take a picture of the surveying area by the camera main control processor to generate a first image, and transmitting the first image to the digital signal processor;

[0007] Preprocessing the first image by the digital signal processor to obtain image feature data of the first image, and transmitting the image feature data to the camera main control processor;

[0008] The image feature data is transmitted to the central processor via the camera main control processor, and a map of the surveying area is generated based on the image feature data via the central processor.

[0009] In a second aspect, the present application provides a map generation device, which is applied to unmanned equipment, wherein the unmanned equipment includes a central processing unit, a digital signal processor, and a camera main control processor, wherein the camera main control processor is connected to the central processing unit and the digital signal processor, and the device includes:

[0010] An image acquisition module is configured to control the camera carried by the unmanned equipment to take a picture of the surveying area through the camera main control processor to generate a first image, and transmit the first image to the digital signal processor;

[0011] an image preprocessing module, configured to preprocess the first image through the digital signal processor to obtain image feature data of the first image, and transmit the image feature data to the camera main control processor;

[0012] The map generation module is configured to transmit the image feature data to the central processor via the camera main control processor, and generate a map of the surveying area based on the image feature data via the central processor.

[0013] In a third aspect, the present application provides an unmanned device, including:

[0014] One or more processors; a memory storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the map generation method as described in the first aspect.

[0015] In a fourth aspect, the present application provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the map generation method as described in the first aspect.

[0016] In the present application, the camera carried by the unmanned equipment is controlled by the camera main control processor to take a picture of the surveying area to generate a first image, and the first image is transmitted to the digital signal processor; the first image is preprocessed by the digital signal processor to obtain the image feature data of the first image, and the image feature data is transmitted to the camera main control processor; the image feature data is transmitted to the central processing unit by the camera main control processor, and the map of the surveying area is generated by the central processing unit based on the image feature data. Through the above technical means, after the image is preprocessed by the digital signal processor to obtain the image feature data, the central processing unit generates a high-precision map of the surveying area according to the image feature data. Since the digital signal processor is only used to preprocess the image, the image preprocessing process will not be affected by other tasks, which effectively improves the image preprocessing efficiency, thereby improving the generation efficiency of the high-precision map. After the digital signal processor is responsible for the image preprocessing task, the load pressure of the central processing unit is relieved, which is conducive to improving the computing efficiency of the central processing unit, thereby improving the generation efficiency of the high-precision map, and solving the problem that the unmanned equipment in the prior art cannot further improve the map generation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1is a structural block diagram of an unmanned device provided in an embodiment of the present application;

[0018] Figure 2 is a flow chart of a map generation method provided in an embodiment of the present application;

[0019] Figure 3 is a flow chart of preprocessing a first image by a digital signal processor provided in an embodiment of the present application;

[0020] Figure 4 is a flow chart of performing dark light enhancement processing on a first image provided by an embodiment of the present application;

[0021] Figure 5 is a schematic diagram of a first image before dark light enhancement processing provided in an embodiment of the present application;

[0022] Figure 6 is a schematic diagram of a first image after dark light enhancement processing provided by an embodiment of the present application;

[0023] Figure 7 is a flowchart of performing defogging processing on a first image provided by an embodiment of the present application;

[0024] Figure 8 is a schematic diagram of a first image before defogging provided in an embodiment of the present application;

[0025] Fig. 9 is a schematic diagram of a first image after defogging provided in an embodiment of the present application;

[0026] Fig.10 is a structural schematic diagram of a map generating device provided in an embodiment of the present application;

[0027] Fig.11 It is a structural schematic diagram of an unmanned device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0029] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0030] The map generation method provided in this embodiment can be executed by an unmanned device, which can be implemented by software and / or hardware, and can be composed of two or more physical entities or one physical entity. The unmanned device refers to a flying device or ground platform that operates according to remote control instructions or preset instructions, such as a drone and an unmanned vehicle.

[0031] For ease of understanding, this embodiment is described by taking an unmanned device as an example of the main body executing the map generation method.

[0032] In one embodiment, the unmanned device includes a central processing unit (CPU), a camera main control processor and a camera. When the unmanned device performs a surveying and mapping task, the camera main control processor controls the camera to shoot the surveying and mapping area to obtain an image containing the surveying and mapping area, and transmits the image to the central processing unit. The central processing unit pre-processes the image to obtain image feature data, and generates a high-precision map of the surveying and mapping area based on the image feature data. Since the computing power resources of the central processing unit are limited and the generation process of the high-precision map is relatively complicated, it is difficult to improve the efficiency of the unmanned device in generating high-precision maps even if the algorithm is improved.

[0033] In order to solve the problem in the above-mentioned prior art that unmanned equipment cannot further improve the efficiency of map generation, this embodiment provides a map generation method.

[0034] In one embodiment, Figure 1 is a structural block diagram of the unmanned equipment provided in the embodiment of the present application. Figure 1 As shown, the unmanned equipment includes a central processing unit, a digital signal processor (DSP), a camera main control processor and a camera, and the camera main control processor is connected to the camera, the central processing unit and the digital signal processor. Among them, the camera main control processor is used to control the camera to collect images of the surveying and mapping area, the digital signal processor is used to pre-process the image to obtain image feature data, and the central processing unit is used to process the image feature data to generate a high-precision map of the surveying and mapping area. In this embodiment, the digital signal processor and the camera main control processor are communicated and connected via HDMI (High Definition Multimedia Interface) or MIPI CSI (Mobile Industry Processor Interface Camera Serial Interface), and the central processing unit and the camera main control processor are communicated and connected via USB (Universal Serial Bus). This embodiment realizes the map generation method through the mutual cooperation between the camera main control processor, the digital signal processor and the central processing unit.

[0035] Figure 2 A flowchart of a map generation method provided by an embodiment of the present application is given. Figure 2 , the map generation method specifically includes:

[0036] S110, controlling the camera carried by the unmanned equipment to take a picture of the surveying area through the camera main control processor to generate a first image, and transmitting the first image to the digital signal processor.

[0037] Exemplarily, when the unmanned device performs a surveying and mapping task, the unmanned device can be controlled to fly above the surveying and mapping area according to the flight route in the surveying and mapping task. When the unmanned device flies to the shooting point corresponding to the surveying and mapping area, the camera main control processor controls the camera carried by the unmanned device to take pictures of the surveying and mapping area. When the camera collects image data corresponding to the surveying and mapping area, the image data is transmitted to the camera main control processor, and the camera main control processor encodes the image data to obtain a first image. It should be noted that if the camera carried by the unmanned device has an encoding function, it can also encode the image data after collecting it to obtain a first image, and transmit the first image to the camera main control processor.

[0038] After acquiring the first image, the camera main control processor transmits the first image to the digital signal processor through the communication connection between the camera main control processor and the digital signal processor, so that the digital signal processor pre-processes the first image to obtain image feature data of the first image.

[0039] S120, pre-processing the first image by a digital signal processor to obtain image feature data of the first image, and transmitting the image feature data to a camera main control processor.

[0040] Among them, image feature data can be understood as data that characterizes image content information, including feature information of the image such as feature points and / or images of other resolutions obtained by upsampling or downsampling the image. Exemplarily, the feature points of the image are key data for generating a high-precision map. The digital signal processor can extract the feature points of the first image through a feature extraction algorithm, such as the SIFT (Scale Invariant Feature Transform) algorithm, and transmit the feature points of the first image to the camera main control processor, so that the camera main control processor transmits the feature points of the first image to the central processing unit, and the central processing unit generates a high-precision map of the surveying area based on the feature points of the first image.

[0041] It is easy to understand that the richer the image feature data of the first image acquired by the digital signal processor, the higher the accuracy of the map generated by the central processing unit based on the image feature data. Although the digital signal processor needs to spend more time to preprocess the first image, the operation of the digital signal processor and the central processing unit are independent of each other, and therefore the operation of the central processing unit will not affect the data processing efficiency of the digital signal processor. Overall, the preprocessing efficiency of the digital signal processor is still higher than the efficiency of preprocessing the first image by the central processing unit. In this regard, the present embodiment proposes that the first image can be downsampled while the feature information of the first image is extracted by the digital signal processor to obtain richer image feature data. In this embodiment, Figure 3 1 is a flow chart of preprocessing a first image by a digital signal processor provided in an embodiment of the present application. Figure 3 As shown, the step of preprocessing the first image by the digital signal processor specifically includes S1201-S1204:

[0042] S1201. Perform dedistortion processing on a first image to obtain a second image.

[0043] Exemplarily, after receiving the first image transmitted by the camera main control processor, the digital signal processor performs dedistortion processing on the first image according to the distortion coefficient of the camera to eliminate the distortion of the first image, so as to ensure the accuracy of the subsequently generated map.

[0044] It should be noted that the various image preprocessing algorithms run by the digital signal processor are generally only for images in color format (BGR format). Therefore, before the digital signal processor performs dedistortion processing on the first image, it can first determine whether the first image is in color format. If the first image is not in color format, the first image is converted from the current format to the color format. If the first image is in color format, the first image can be directly dedistorted. In this embodiment, since only images in bright chroma format (YUV format) can be transmitted to the central processor, the camera main control processor will generate a first image in bright chroma format during encoding. Based on this, after receiving the first image transmitted by the camera main control processor, the digital signal processor first converts the first image from bright chroma format to color format, and then performs dedistortion processing on the first image.

[0045] In one embodiment, if the ambient light intensity is weak when the camera captures the first image, the content of the first image will be dark and the image clarity will be low, affecting the clarity of the subsequently generated high-precision map. In this regard, the digital signal processor can determine the clarity of the first image based on the ambient light intensity when the first image was captured before performing dedistortion processing on the first image. If the clarity of the first image is low, the first image can be subjected to dark light enhancement processing to improve the clarity of the first image, thereby improving the clarity of the high-precision map. For example, Figure 4 This is a flowchart of performing dark light enhancement processing on a first image provided by an embodiment of the present application.

[0046] like Figure 4 As shown, the step of performing dark light enhancement processing on the first image specifically includes S1205-S1206:

[0047] S1205. Obtain the ambient light intensity collected by the camera through the camera main control processor, and transmit the ambient light intensity to the digital signal processor.

[0048] Exemplarily, when capturing the first image, the camera collects ambient light intensity, and transmits the ambient light intensity together with the first image to the camera main control processor, which transmits the ambient light intensity together with the first image to the digital signal processor via a communication connection with the digital signal processor.

[0049] S1206: Compare the ambient light intensity with a preset intensity threshold through a digital signal processor, and when the ambient light intensity is less than the preset intensity threshold, process the first image through a dark light enhancement algorithm.

[0050] The preset intensity threshold is the minimum ambient light intensity when the camera set in this embodiment captures a clear image. Exemplarily, when the digital signal processor receives the first image and ambient light intensity sent by the camera main control processor, it compares the ambient light intensity with the preset intensity threshold. If the ambient light intensity is greater than or equal to the preset intensity threshold, it indicates that the clarity of the first image is not affected by the ambient light intensity, so the first image may not be subjected to dark light enhancement processing. If the ambient light intensity is less than the preset intensity threshold, it indicates that the clarity of the first image is affected by the ambient light intensity, and the content of the first image is dark. At this time, the first image may be processed by the preset dark light enhancement algorithm to improve the clarity of the first image. Figure 5 and Figure 6 Schematic diagrams of the first image before and after dark light enhancement processing are shown respectively. Figure 5 and Figure 6 It can be seen that in shooting scenarios with low ambient light intensity, unmanned equipment can also obtain high-definition images.

[0051] In addition to the fact that the ambient light intensity will affect the clarity of the first image, the presence of haze in the shooting scene will also affect the clarity of the first image. In this regard, before de-distorting the first image, or when it is determined that the ambient light intensity corresponding to the first image is greater than or equal to a preset intensity threshold, the digital signal processor can determine whether there is haze in the first image. If there is haze in the first image, the first image is de-fogged to improve the clarity of the first image, thereby improving the success rate of map solving and the clarity of the map. For example, Figure 7 : is a flow chart of performing defogging on a first image provided by an embodiment of the present application. Figure 7 As shown, the step of performing defogging processing on the first image specifically includes S1207-S1208:

[0052] S1207: Obtain a dark channel image of the first image, and determine a pixel median value of each pixel point according to the pixel value of each pixel point of the dark channel image.

[0053] Exemplarily, the digital signal processor generates a grayscale image of the same size as the first image based on the minimum value of each pixel in the three RGB color channels in the first image, takes a rectangular window of a certain size with each pixel as the center in the grayscale image, takes the minimum value of the pixels in the rectangular window instead of the pixel value of the center pixel, and obtains a dark channel image. The pixel values ​​of the dark channel image are sorted, and the pixel value in the middle is taken as the pixel median.

[0054] S1208. When the pixel median value is greater than a preset pixel threshold, the first image is processed using a defogging algorithm.

[0055] Among them, the preset pixel threshold is the maximum value of the pixel median of the corresponding dark channel image when haze exists in the image, which is set in this embodiment, and is generally 0.01. Exemplarily, if the pixel median of the dark channel image of the first image is less than or equal to the preset pixel threshold, it indicates that haze does not exist in the first image, so the first image may not be defogged. If the pixel median of the dark channel image of the first image is greater than the preset pixel threshold, it indicates that haze exists in the first image, and the first image may be processed by the defogging algorithm. Figure 8 and Fig. 9 Schematic diagrams of the first image before and after defogging are shown respectively. Figure 8 and Fig. 9 It can be seen that in shooting scenes with haze, unmanned equipment can also obtain high-definition images.

[0056] Furthermore, after the digital signal processor performs dehazing processing on the first image, or after determining that the first image does not need to be dehazed, the digital signal processor may process the first image through a tone mapping algorithm. The tone mapping algorithm may map the color of the first image from the original tone to the target tone, and the mapping result is displayed through a medium, so as to achieve the effect of restoring the original scene as much as possible under the visual characteristics of the human eye, so as to improve the contrast and clarity of the first image.

[0057] S1202: Downsample the second image to obtain a first resolution image, and extract feature points of the first resolution image.

[0058] Exemplarily, the resolution of the first image is 4000*3000, and accordingly, the resolution of the second image obtained after the first image is dedistorted is also 4000*3000. The second image is downsampled to obtain a first resolution image with a resolution of 2000*1500. Since the current first resolution image is a color image, and the SIFT algorithm generally performs feature extraction on grayscale images, before extracting the feature points of the first resolution image through the SIFT algorithm, the first resolution image is converted into a single-channel grayscale image, and the single-channel grayscale image is subjected to feature extraction through the SIFT algorithm to obtain the feature points of the first resolution image. It should be noted that, compared to directly performing SIFT algorithm processing on the first image, this embodiment performs SIFT algorithm processing on the first image after downsampling processing to avoid losing some stable feature points in the first image, which is beneficial to improving the success rate of subsequent map solving.

[0059] S1203: Downsample the first resolution image to obtain a second resolution image.

[0060] Exemplarily, a first resolution image with a resolution of 2000*1500 is downsampled to obtain a second resolution image with a resolution of 500*375, and the second resolution image can be used by a central processing unit to calculate the depth of the first image and construct a dense point cloud.

[0061] S1204: Transmit the second image, feature points, and the second resolution image to the camera main control processor.

[0062] Exemplarily, the second image, feature points of the first resolution image, and the second resolution image are all image feature data obtained after the digital signal processor pre-processes the first image. The digital signal processor can transmit the second image, feature points of the first resolution image, and the second resolution image to the camera main control processor through a communication connection with the camera main control processor, and the camera main control processor transmits them to the central processing unit for processing.

[0063] In this embodiment, the second image and the second resolution image are both in color format, and only images in bright chroma format can be transmitted to the central processor. Therefore, the digital signal processor converts the second image and the second resolution image from color format to bright chroma format before transmitting the second image, feature points and second resolution image to the camera main processor, so that after the camera main processor receives the second image, feature points of the first resolution image and second resolution image transmitted by the digital signal processor, it can transmit them to the central processor without processing them.

[0064] S130, transmitting the image feature data to the central processing unit via the camera main control processor, and generating a map of the surveying and mapping area based on the image feature data via the central processing unit.

[0065] Exemplarily, the camera main control processor transmits the second image, the feature points of the first resolution image, and the second resolution image to the central processor via a communication connection with the central processor. The central processor generates a high-precision map of the surveying area based on the second image, the feature points of the first resolution image, and the second resolution image.

[0066] In summary, the map generation method provided in the embodiment of the present application controls the camera carried by the unmanned equipment to take pictures of the surveying area through the camera main control processor to generate a first image, and transmits the first image to the digital signal processor; pre-processes the first image through the digital signal processor to obtain the image feature data of the first image, and transmits the image feature data to the camera main control processor; transmits the image feature data to the central processor through the camera main control processor, and generates a map of the surveying area based on the image feature data through the central processor. Through the above technical means, after the image is pre-processed by the digital signal processor to obtain the image feature data, the central processor generates a high-precision map of the surveying area according to the image feature data. Since the digital signal processor is only used to pre-process the image, the image pre-processing process will not be affected by other tasks, which effectively improves the image pre-processing efficiency, thereby improving the generation efficiency of the high-precision map. After the digital signal processor is responsible for the image pre-processing task, the load pressure of the central processor is relieved, which is conducive to improving the computing efficiency of the central processor, thereby improving the generation efficiency of the high-precision map, and solving the problem that the unmanned equipment in the prior art cannot further improve the map generation efficiency.

[0067] Based on the above embodiments, Fig.10 A schematic diagram of the structure of a map generation device provided in an embodiment of the present application. Fig.10 The map generation device provided in this embodiment specifically includes: an image acquisition module 21, an image preprocessing module 22 and a map generation module 23.

[0068] The image acquisition module 21 is configured to control the camera carried by the unmanned equipment to take a picture of the surveying area through the camera main control processor to generate a first image, and transmit the first image to the digital signal processor;

[0069] The image preprocessing module 22 is configured to preprocess the first image through a digital signal processor to obtain image feature data of the first image, and transmit the image feature data to a camera main control processor;

[0070] The map generation module 23 is configured to transmit the image feature data to the central processing unit via the camera main control processor, and generate a map of the surveying area based on the image feature data via the central processing unit.

[0071] Based on the above embodiment, the image preprocessing module 22 includes: a dedistortion unit, configured to perform dedistortion processing on the first image to obtain a second image; a feature extraction unit, configured to downsample the second image to obtain a first resolution image, and extract feature points of the first resolution image; a downsampling unit, configured to downsample the first resolution image to obtain a second resolution image; and a first transmission unit, configured to transmit the second image, feature points and the second resolution image to the camera main control processor.

[0072] On the basis of the above embodiment, the image preprocessing module 22 also includes: a second transmission unit, configured to obtain the ambient light intensity captured by the camera through the camera main control processor before dedistorting the first image to obtain the second image, and transmit the ambient light intensity to the digital signal processor; a dark light enhancement module, configured to compare the ambient light intensity with a preset intensity threshold through the digital signal processor, and process the first image through a dark light enhancement algorithm when the ambient light intensity is less than the preset intensity threshold.

[0073] On the basis of the above embodiment, the image preprocessing module 22 also includes: a pixel median determination unit, which is configured to obtain a dark channel image of the first image before dedistorting the first image to obtain the second image, and determine the pixel median of each pixel point according to the pixel value of each pixel point of the dark channel image; a defogging module, which is configured to process the first image through a defogging algorithm when the pixel median is greater than a preset pixel threshold.

[0074] On the basis of the above embodiment, the image preprocessing module 22 further includes: a tone mapping unit configured to process the first image by a tone mapping algorithm before performing a dedistortion process on the first image to obtain a second image.

[0075] Based on the above embodiment, the feature extraction unit includes: a grayscale image acquisition subunit, configured to convert the first resolution image into a single-channel grayscale image; a feature extraction subunit, configured to perform feature extraction on the single-channel grayscale image through a scale-invariant feature conversion algorithm to obtain feature points of the first resolution image.

[0076] Based on the above embodiment, the image preprocessing module 22 also includes: a first format conversion unit, configured to convert the first image from a brightness chroma format to a color format before dedistorting the first image to obtain the second image; a second format conversion unit, configured to convert the second image, the feature points and the second resolution image from a color format to a brightness chroma format before transmitting the second image, the feature points and the second resolution image to the camera main control processor.

[0077] As mentioned above, the map generation device provided in the embodiment of the present application controls the camera carried by the unmanned equipment to take a picture of the surveying area through the camera main control processor to generate a first image, and transmits the first image to the digital signal processor; pre-processes the first image through the digital signal processor to obtain the image feature data of the first image, and transmits the image feature data to the camera main control processor; transmits the image feature data to the central processor through the camera main control processor, and generates a map of the surveying area based on the image feature data through the central processor. Through the above technical means, after the image is pre-processed by the digital signal processor to obtain the image feature data, the central processor generates a high-precision map of the surveying area according to the image feature data. Since the digital signal processor is only used to pre-process the image, the image pre-processing process will not be affected by other tasks, which effectively improves the image pre-processing efficiency, thereby improving the generation efficiency of the high-precision map. After the digital signal processor is responsible for the image pre-processing task, the load pressure of the central processor is relieved, which is conducive to improving the computing efficiency of the central processor, thereby improving the generation efficiency of the high-precision map, and solving the problem that the unmanned equipment in the prior art cannot further improve the map generation efficiency.

[0078] The map generation device provided in the embodiment of the present application can be used to execute the map generation method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0079] Fig.11 This is a schematic diagram of the structure of an unmanned device provided in an embodiment of the present application, with reference to Fig.11 The unmanned device includes: a processor 31, a memory 32, a communication device 33, an input device 34 and an output device 35. The number of processors 31 in the unmanned device can be one or more, and the number of memories 32 in the unmanned device can be one or more. The processor 31, memory 32, communication device 33, input device 34 and output device 35 of the unmanned device can be connected through a bus or other methods.

[0080] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the map generation method of any embodiment of the present application (for example, the image acquisition module 21, the image preprocessing module 22 and the map generation module 23 in the map generation device). The memory 32 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the device, etc. In addition, the memory 32 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0081] The communication device 33 is used for data transmission.

[0082] The processor 31 executes the software programs, instructions and modules stored in the memory 32 to execute various functional applications and data processing of the device, that is, to implement the above-mentioned map generation method.

[0083] The input device 34 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 35 may include a display device such as a display screen.

[0084] The unmanned equipment provided above can be used to execute the map generation method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0085] An embodiment of the present application also provides a storage medium containing computer executable instructions, which are used to execute a map generation method when executed by a computer processor. The map generation method includes: controlling a camera carried by an unmanned device to take a picture of a surveying and mapping area through a camera main control processor to generate a first image, and transmitting the first image to a digital signal processor; pre-processing the first image through the digital signal processor to obtain image feature data of the first image, and transmitting the image feature data to the camera main control processor; transmitting the image feature data to a central processing unit through the camera main control processor, and generating a map of the surveying and mapping area based on the image feature data through the central processor.

[0086] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or may be located in a different second computer system, which is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0087] Of course, the storage medium containing computer executable instructions provided in the embodiment of the present application is not limited to the above map generation method, and the computer executable instructions can also execute related operations in the map generation method provided in any embodiment of the present application.

[0088] The map generation device, storage medium and unmanned equipment provided in the above embodiments can execute the map generation method provided in any embodiment of the present application. For technical details not described in detail in the above embodiments, please refer to the map generation method provided in any embodiment of the present application.

[0089] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the protection scope of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A map generation method, characterized in that: Applied to unmanned equipment, the unmanned equipment includes a central processing unit, a digital signal processor and a camera main control processor, the camera main control processor is connected to the central processing unit and the digital signal processor, and the method includes: Controlling the camera carried by the unmanned equipment to take a picture of the surveying area by the camera main control processor to generate a first image, and transmitting the first image to the digital signal processor; Preprocessing the first image by the digital signal processor to obtain image feature data of the first image, and transmitting the image feature data to the camera main control processor; The image feature data is transmitted to the central processor via the camera main control processor, and a map of the surveying area is generated based on the image feature data via the central processor.

2. The map generation method according to claim 1, characterized in that: The preprocessing of the first image by the digital signal processor to obtain image feature data of the first image, and transmitting the image feature data to the camera main control processor includes: Performing a dedistortion process on the first image to obtain a second image; Downsampling the second image to obtain a first resolution image, and extracting feature points of the first resolution image; Downsampling the first resolution image to obtain a second resolution image; The second image, the feature points and the second resolution image are transmitted to the camera main control processor.

3. The map generation method according to claim 2, characterized in that: Before performing dedistortion processing on the first image to obtain the second image, the method further includes: Acquire the ambient light intensity collected by the camera through the camera main control processor, and transmit the ambient light intensity to the digital signal processor; The digital signal processor compares the ambient light intensity with a preset intensity threshold, and when the ambient light intensity is less than the preset intensity threshold, the first image is processed by a dark light enhancement algorithm.

4. The map generation method according to claim 2, characterized in that: Before performing dedistortion processing on the first image to obtain the second image, the method further includes: Acquire a dark channel image of the first image, and determine a pixel median value of each pixel point according to a pixel value of each pixel point of the dark channel image; When the pixel median value is greater than a preset pixel threshold, the first image is processed by a defogging algorithm.

5. The map generation method according to claim 2 or 4, characterized in that: Before performing dedistortion processing on the first image to obtain the second image, the method further includes: The first image is processed by a tone mapping algorithm.

6. The map generation method according to claim 2, characterized in that: The extracting feature points of the first resolution image includes: Converting the first resolution image into a single-channel grayscale image; Feature extraction is performed on the single-channel grayscale image using a scale-invariant feature conversion algorithm to obtain feature points of the first resolution image.

7. The map generation method according to claim 2, characterized in that: Before performing dedistortion processing on the first image to obtain the second image, the method further includes: converting the first image from a luminance chrominance format to a color format; Accordingly, before transmitting the second image, the feature points and the second resolution image to the camera main control processor, the method further includes: The second image and the second resolution image are converted from a color format to a luminance chrominance format.

8. A map generating device, characterized in that: Applied to unmanned equipment, the unmanned equipment includes a central processing unit, a digital signal processor and a camera main control processor, the camera main control processor is connected to the central processing unit and the digital signal processor, and the device includes: An image acquisition module is configured to control the camera carried by the unmanned equipment to take a picture of the surveying area through the camera main control processor to generate a first image, and transmit the first image to the digital signal processor; an image preprocessing module, configured to preprocess the first image through the digital signal processor to obtain image feature data of the first image, and transmit the image feature data to the camera main control processor; The map generation module is configured to transmit the image feature data to the central processor via the camera main control processor, and generate a map of the surveying area based on the image feature data via the central processor.

9. An unmanned device, characterized in that: include: one or more processors; The memory stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the map generation method as described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the map generation method as described in any one of claims 1-7 when executed by a computer processor.

Images