A method and apparatus for constructing a map

Abstract

The specification discloses a method and device for constructing a map, determining a relative pose of a specified collection device relative to lane lines involved in collected image data, and a depth value of the lane lines involved in the image data, and determining positioning data of the collection device in an absolute coordinate system when collecting the image data. According to the obtained relative pose, the depth value of the lane lines, and the positioning data, parameters for representing a spatial relationship between an image position of the lane lines in the image data and an actual position of the lane lines in the absolute coordinate system are determined as transformation parameters. According to the determined transformation parameters, an image of a lane line tracked from the image data is mapped to a preset common space. Each lane line mapped to the common space is fitted to obtain a fitted lane line, and a map is constructed according to the fitted lane line.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of unmanned driving, and in particular to a method and device for constructing a map. BACKGROUND

[0002] In the field of unmanned driving, an unmanned device needs to construct a map in advance for the unmanned device to travel, wherein the map needs to contain environmental information, such as lane line information in the process of the unmanned device traveling.

[0003] At present, the main way to construct a travel map of an unmanned device is to use image acquisition devices (cameras, cameras, etc.) loaded around the unmanned driving device to splice the images around the unmanned driving device collected by the image acquisition devices at the same position, to form an Inverse Perspective Mapping (IPM) image. Then, the lane lines are extracted from the IPM image, and the lane lines are mapped to a three-dimensional space in combination with the pose of the image acquisition device when the IPM image is collected, to construct a map of the region. Through the above-mentioned way, a plurality of region maps are obtained, and the region maps are combined by using the common view relationship between the region maps, to obtain a travel map of the unmanned device. SUMMARY

[0004] The present specification provides a method and device for constructing a map to partially solve the above-mentioned problems existing in the prior art.

[0005] The present specification adopts the following technical solutions:

[0006] The present specification provides a method for constructing a map, comprising:

[0007] determining a relative pose of a specified acquisition device with respect to a lane line involved in the collected image data, and a depth value of the lane line involved in the image data, and determining positioning data of the acquisition device in an absolute coordinate system when collecting the image data;

[0008] determining a parameter for representing a spatial relationship between an image position of the lane line in the image data and an actual position of the lane line in the absolute coordinate system as a transformation parameter according to the relative pose, the depth value, and the positioning data;

[0009] mapping an image of the lane line tracked from the image data to a preset common space according to the transformation parameter;

[0010] fitting each lane line mapped to the common space to obtain a fitted lane line;

[0011] constructing a map according to the fitted lane line.

[0012] Optionally, the parameters for representing the spatial relationship between the image position of the lane line in the image data and the actual position of the lane line in the absolute coordinate system are determined according to the relative pose, the depth value and the positioning data, and specifically include:

[0013] The pose of the lane line in the coordinate system of the specified acquisition device is determined according to the relative pose and the depth value.

[0014] The transformation parameters are determined with the optimization condition that the deviation between the pose obtained by transforming the pose by the transformation parameters and the positioning data is minimized.

[0015] Optionally, the transformation parameters include rotation parameters, translation parameters and scale parameters, wherein the rotation parameters and the translation parameters are used to realize the mutual transformation of the relative pose and the positioning data in space, and the scale parameters are used to represent the relationship between the scale of the lane line involved in the image data in the image data and the actual scale of the lane line involved in the image data in the absolute coordinate system.

[0016] Optionally, the parameters for representing the spatial relationship between the image position of the lane line in the image data and the actual position of the lane line in the absolute coordinate system are determined according to the relative pose, the depth value and the positioning data, and specifically include:

[0017] The transformation parameters are determined according to the following formula:

[0018] Loss = ∑ (X g -s*(R*X v +t)) 2

[0019] Wherein, X g is the positioning data, s is the scale parameter, R is the rotation parameter, t is the translation parameter, and X v is the pose of the lane line in the coordinate system of the specified acquisition device determined according to the relative pose and the depth value.

[0020] Optionally, the lane lines mapped to the common space are fitted to obtain fitted lane lines, including:

[0021] For each road segment, the lane lines mapped to the road segment by each image data in the common space are determined as the lane lines corresponding to the road segment.

[0022] According to the distance between the lane lines corresponding to the road segment in the common space, the lane lines corresponding to the road segment are fitted to obtain the fitted lane lines of the road segment.

[0023] Optionally, constructing a map according to the fitted lane line comprises:

[0024] In the common space, connecting the fitted lane line of each image data corresponding road segment based on tracking of the same lane line contained in the image data to obtain a connected lane line, and constructing a map according to the connected lane line.

[0025] Optionally, constructing a map according to the fitted lane line comprises:

[0026] Determining a lane line missing road segment in the common space according to the fitted lane line;

[0027] Selecting a road segment for determining the lane line in the lane line missing road segment from each road segment adjacent to the lane line missing road segment as a target road segment;

[0028] Extending the fitted lane line contained in the target road segment to obtain the lane line in the lane line missing road segment as the fitted lane line in the lane line missing road segment;

[0029] Constructing a map according to the fitted lane line contained in each road segment.

[0030] Optionally, selecting a road segment for determining the lane line in the lane line missing road segment from each road segment adjacent to the lane line missing road segment as a target road segment comprises:

[0031] Selecting a road segment containing a fitted lane line and having an included angle with the lane line missing road segment in a road direction meeting a preset angle condition as a target road segment from each road segment adjacent to the lane line missing road segment.

[0032] The present specification provides a device for constructing a map, comprising:

[0033] A determination module is configured to determine a relative pose of a specified acquisition device relative to a lane line involved in acquired image data, a depth value of the lane line involved in the image data, and positioning data of the acquisition device in an absolute coordinate system when acquiring the image data;

[0034] A parameter determination module is configured to determine a parameter for representing a spatial relationship between an image position of the lane line in the image data and an actual position of the lane line in the absolute coordinate system as a transformation parameter according to the relative pose, the depth value, and the positioning data;

[0035] A mapping module is configured to map an image of a lane line tracked from the image data to a preset common space according to the transformation parameter.

[0036] a fitting module configured to fit each lane line mapped to the common space to obtain a fitted lane line;

[0037] a constructing module configured to construct a map according to the fitted lane line.

[0038] The present specification provides a computer readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the method for constructing a map.

[0039] The present specification provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor, when executing the program, implements the method for constructing a map.

[0040] The above at least one technical solution adopted by the present specification can achieve the following beneficial effects:

[0041] In the method for constructing a map provided by the present specification, the relative pose of a specified collection device relative to a lane line involved in collected image data is determined, as well as the depth value of the lane line involved in the image data, and the positioning data of the collection device in an absolute coordinate system when collecting the image data is determined. According to the obtained relative pose, the depth value of the lane line, and the positioning data, parameters for representing the spatial relationship between the image position of the lane line in the image data and the actual position of the lane line in the absolute coordinate system are determined as transformation parameters. According to the determined transformation parameters, the image of the lane line tracked from the image data is mapped to a preset common space. Each lane line mapped to the common space is fitted to obtain a fitted lane line, and a map is constructed according to the fitted lane line.

[0042] As can be seen from the above method, by the method for constructing a map, the lane lines tracked from each image data can be mapped to a preset common space according to the relationship between the determined relative pose and the positioning data, so as to fit the lane lines in the common space. In this way, without a complex optimization process, the images of the lane lines tracked from the image data can be mapped to the common space according to the position and scale of the lane lines in the absolute coordinate system, so as to fit each complete lane line in the common space, and a map is constructed according to the fitted lane lines, thereby ensuring that the map is accurately constructed, and the efficiency of constructing the map is effectively improved. BRIEF DESCRIPTION OF DRAWINGS

[0043] The drawings described herein are used to provide further understanding of the present specification, and form a part of the present specification. The illustrative embodiments of the present specification and their descriptions serve to explain the present specification, and do not constitute an improper limitation on the present specification. In the drawings:

[0044] Figure 1 a flowchart of a method for constructing a map provided in the specification;

[0045] Figure 2 a schematic diagram of lane line tracking provided in the specification;

[0046] Figures 3A-3B a schematic diagram of a fitting mode of lane line missing provided in the specification;

[0047] Figure 4 a schematic diagram of a device for constructing a map provided in the specification;

[0048] Figure 5 a schematic diagram of an electronic device corresponding to Figure 1 provided in the specification. DETAILED DESCRIPTION

[0049] In order to make the purposes, technical solutions and advantages of the specification clearer, the technical solutions of the specification will be described clearly and completely below in combination with specific embodiments of the specification and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the specification, not all the embodiments. Based on the embodiments in the specification, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the specification.

[0050] The main way of constructing a map at present needs to splice the collected IPM images first, then extract lane lines from the IPM images, and map the extracted lane lines to a three-dimensional space according to the pose of the collection device when collecting the IPM images.

[0051] This way needs to splice the collected IPM images, and also needs to combine the maps of multiple areas, resulting in that the use of this way of constructing a map needs a large amount of optimization, increasing the cost required for constructing a map.

[0052] In order to simplify the optimization process when constructing a map while ensuring the accuracy of the constructed map, the specification provides a method for constructing a map, which will be described in detail below in combination with the drawings.

[0053] Figure 1 A flowchart of a method for constructing a map provided in the specification includes the following steps:

[0054] S101: determining the relative pose of a specified collection device relative to the lane lines involved in the collected image data, and the depth values of the lane lines involved in the image data, and determining the positioning data of the collection device in the absolute coordinate system when collecting the image data.

[0055] In the present specification, the execution subject of the method for constructing a map can be a terminal device such as a desktop computer, a notebook computer, etc., a server or the like, or an unmanned device such as an unmanned vehicle, an unmanned aerial vehicle, an autonomous robot, etc. The map constructed by the method for constructing a map provided in the present specification can be used for unmanned devices to perform delivery tasks in the delivery field, such as express delivery, logistics, take-out delivery, etc. In the following, for the convenience of description, the method for constructing a map provided in the present specification will be described in detail with the terminal device as the execution subject.

[0056] At present, the main way to construct a driving map for an unmanned device is to use a collection device loaded on an image collector (such as a camera, a camera, etc.) to collect images of multiple regions, extract feature points in the images of each region from the collected images, project the extracted feature points into a preset space, and fit each lane line in each region according to the feature points in the preset space, and then connect each lane line in each region according to the connection relationship of each region.

[0057] The lane lines fitted according to this method often do not match the lane lines in reality, such as curved or overlapping lane lines, resulting in low accuracy of the finally constructed map, and this method needs to continuously collect images of each region to connect the lane lines in each region, resulting in high cost of constructing a map each time.

[0058] To solve the above technical problems, the present specification provides a method for constructing a map. First, the terminal device obtains image data collected by a collection device. The collection device can be a device equipped with an image collector such as a camera, a camera, etc., such as an unmanned device, a manned device, etc.

[0059] It should be noted that the image data involved in the present specification is two-dimensional image data, not three-dimensional point cloud image collected by a sensor, and the image data mentioned in the present specification can be collected by a monocular camera.

[0060] After the terminal device acquires each image data, for each image data, the relative pose of the collection device relative to the lane line involved in the image data is determined according to the image data, and the depth value of the lane line involved in the image data. Wherein, the lane line is a line used to regulate the trajectory of the vehicle, and the terminal device recognizes the lane line involved in the image data. The way can be to input the image data into a preset image recognition model, and the image recognition model recognizes the lane line contained in the image data by extracting the feature points in the image data. Of course, the lane line can also be recognized from the image data in other ways, such as, on the basis of having recognized the lane line image contained in an image data, the lane line image contained in other image data can be tracked according to the positional relationship of the image data in the collection position. For example, the position of the lane line is detected from each image data by LaneNet algorithm. Other ways will not be illustrated in detail here.

[0061] It should be noted that the relative pose of the lane line involved in the image data is used to represent the relative position and relative angle between the collection device and the lane line when the collection device observes the lane line when collecting the image data, that is, the pose of the collection device in the right-handed coordinate system with the optical center of the image data as the origin and the optical axis as the vertical axis.

[0062] In this specification, the way to determine the depth value of the lane line involved in the image data can be various, such as, the image data can be input into a pre-trained depth prediction model to determine the depth value of the lane line involved in the image data through the depth prediction model. Wherein, the depth prediction model can be constructed by using (video to depth, deepV2D) algorithm. Other ways to determine the depth value of the lane line involved in the image data will not be described in detail here. And using these ways does not need to calibrate the external parameters of the collection device, and the depth value of the lane line can be obtained.

[0063] In the process of determining the relative pose of the lane line involved in the image data and the depth value of the lane line involved in the image data by the terminal device, the positioning data of the collection device in the absolute coordinate system when collecting the image data can be determined. The absolute coordinate system mentioned herein refers to the coordinate system in the real world. The positioning data mentioned herein can refer to the position and deflection direction of the collection device in the absolute coordinate system when collecting the image data. The positioning data can be determined by other sensors provided on the collection device. For example, the collection device can continuously collect image data through the image collector provided thereon during driving. During the collection of image data, the global navigation satellite system (GNSS) provided on the collection device can obtain the positioning data of the collection device in the absolute coordinate system when collecting each image data, and record the obtained positioning data in one-to-one correspondence with each collected image data.

[0064] For another example, the collection device can also be provided with a laser radar. When the collection device collects image data through the image collector, it also synchronously collects point cloud data through the laser radar, and determines the positioning data of the collection device in the real world when collecting each image data through the point cloud data, and records the determined positioning data in one-to-one correspondence with each collected image data. Other modes will not be described in detail here.

[0065] S102: According to the relative pose, the depth value and the positioning data, a parameter for representing the spatial relationship between the image position of the lane line in the image data and the actual position of the lane line in the absolute coordinate system is determined as a transformation parameter.

[0066] After the terminal device obtains the relative pose of the lane line involved in each image data, the depth value and the positioning data of the collection device in the absolute coordinate system when collecting each image data, it can further determine a parameter for representing the spatial relationship between the image position of the lane line involved in the image data and the actual position of the lane line involved in the image data in the absolute coordinate system according to the relative pose, the depth value and the positioning data, as a transformation parameter.

[0067] In this specification, the transformation parameter can include a rotation parameter, a translation parameter and a scale parameter. The rotation parameter and the translation parameter mentioned above are used to realize the mutual conversion of the relative pose and the positioning data in space, and the scale parameter is used to represent the relationship between the scale of the lane line involved in the image data in the image data and the actual scale of the lane line involved in the image data in the absolute coordinate system. The scale parameter can be determined by the transformed relative pose and the depth value.

[0068] Specifically, in the present specification, the terminal device can inversely solve the transformation parameter according to the above relative pose, the depth value and the positioning data, taking the deviation between the pose obtained by transforming the relative pose by the transformation parameter and the positioning data as the optimization condition.

[0069] The specific way of determining the transformation parameter can refer to the following formula:

[0070] Loss=∑(X g -s*(R*X v +t)) 2

[0071] Wherein, X g is the positioning data, s is the scale parameter, R is the rotation parameter, t is the translation parameter, X v is the pose of the lane line in the coordinate system of the specified collection device determined according to the relative pose and the depth value.

[0072] According to the above formula, the pose of the lane line in the coordinate system of the specified collection device is transformed by the transformation parameter, and the transformed pose is as close as possible to the positioning data, so as to solve the transformation parameter.

[0073] S103: According to the transformation parameter, the image of the lane line tracked from the image data is mapped to the preset common space.

[0074] The terminal device can determine the relative pose after spatial transformation according to the obtained transformation parameter, and restore the scale of each lane line involved in each image data to the actual scale of each lane line in the absolute coordinate system according to the scale parameter. Each lane line after spatial transformation and scale restoration is mapped to the preset common space. The preset common space can be a three-dimensional space.

[0075] In the present specification, the collection device can collect continuous image data during driving, and for continuous image data, the images of the lane lines contained in the image data are actually from the same lane line, so in order to further improve the efficiency of constructing the map, the terminal device can track the images of the lane lines contained in the image data to identify the lane lines commonly contained in different image data of continuous multiple frames. In this way, the process of splicing multiple images mentioned in the prior art can be avoided, and only the lane line tracking technology can be used to connect the lane lines in different image data.

[0076] Specifically, after the terminal device obtains the continuous multiple frames of image data collected by the collection device, the terminal device can take the image data as an image sequence, and then, for any adjacent multiple frames of image data in the image sequence, the terminal device can associate the lane lines in the adjacent multiple frames of image data by using a preset tracking algorithm, so as to track the lane lines in the image data. Meanwhile, in the tracking process of the lane lines, the tracked lane lines can be identified, so that the same lane line corresponds to the same identification. The tracking algorithm mentioned herein can include a Kalman filter tracking algorithm.

[0077] S104: fitting each lane line mapped to the common space to obtain a fitted lane line.

[0078] After mapping each lane line to the common space, for each road segment, the terminal device can determine, in the common space, the lane lines mapped to the road segment by the image data as the lane lines corresponding to the road segment. The terminal device fits the lane lines corresponding to the road segment according to the distances between the lane lines in the common space, to obtain a fitted lane line of the road segment.

[0079] The fitting of each lane line can be as follows: the terminal device can determine each lane line corresponding to the same lane line in the real space as a lane line group. The terminal device can determine the center position of each lane line group according to the positions of the lane lines at both ends of the lane line group, and determine the lane line closest to the center position of the lane line group as the final fitted lane line.

[0080] S105: constructing a map according to the fitted lane line.

[0081] After the terminal device obtains the fitted lane line, the terminal device can connect the fitted lane line of each image data corresponding to the road segment in the common space based on the tracking of the same lane line in the image data, to obtain a connected lane line, and construct a map according to the connected lane line, as shown in Figure 2 .

[0082] Figure 2 A schematic diagram of lane line tracking provided in the specification.

[0083] In Figure 2In the embodiment, the lane line A and the lane line B are two lane lines projected into the common space by a lane line image included in one image data. The tracked lane line C and the tracked lane line D are two lane lines fitted based on another image data and existing in the preset common space. The terminal device can connect the lane line A and the tracked lane line C based on the tracking of the lane line A to obtain a connected lane line, and the terminal device can connect the lane line B and the tracked lane line D based on the tracking of the lane line B to obtain a connected lane line.

[0084] Since the image data that can be used may have a case that some road sections are not collected, or the clarity of the image data of some road sections is not enough, the lane lines of these road sections cannot be extracted and fitted. These road sections can be referred to as lane line missing road sections.

[0085] In order to enable the constructed map to record complete lane line data, in the present specification, the terminal device can select a road section for determining the lane line in the lane line missing road section as a target road section from each road section adjacent to the lane line missing road section. The terminal device can extend the fitted lane line included in the target road section to obtain the lane line in the lane line missing road section as the fitted lane line in the lane line missing road section, and construct the map according to the fitted lane line included in each road section. As shown in Figure 3A .

[0086] Figure 3A A schematic diagram of a fitting method of a lane line missing provided in the present specification.

[0087] In Figure 3A , the lane line A, the lane line B, the lane line C and the lane line D are four lane lines included in the target road section. The terminal device can obtain the lane line at the missing road section a by extending the lane line A and / or the lane line C. Similarly, the terminal device can obtain the lane line at the missing road section b by extending the lane line B and / or the lane line D, thereby obtaining a complete lane line.

[0088] In the present specification, the target road section can refer to a road section satisfying a preset angle condition of an included angle between the target road section and the lane line missing road section in the road direction, wherein the preset angle condition mentioned herein can refer to that the included angle between the target road section and the lane line missing road section is not more than a set angle, and the set angle can be set according to actual needs, as shown in Figure 3B .

[0089] Figure 3B A schematic diagram of a fitting method of a lane line missing provided in the present specification.

[0090] In Figure 3BIn the example shown in FIG. 6, the lane line A, the lane line B, the lane line C and the lane line D are four lane lines included in the target section. Since the angle between the lane line C and the missing section a is 90°, which exceeds the set angle, the terminal device cannot obtain the lane line at the missing section a by extending the lane line C, but can only obtain the lane line at the missing section a by extending the lane line A. Similarly, since the angle between the lane line D and the missing section b is too large, the terminal device cannot obtain the lane line at the missing section b by extending the lane line D, but can only obtain the lane line at the missing section b by extending the lane line B.

[0091] As can be seen from the method of constructing a map provided in the present specification, the terminal device can map the lane lines tracked from the image data into the preset common space according to the relationship between the determined relative pose and the positioning data. In this way, without a complex optimization process, the images of the lane lines tracked from the image data can be mapped into the common space according to the positions and scales of the lane lines in the absolute coordinate system, so as to fit each complete lane line in the common space, and thereby construct a map, thereby ensuring accurate construction of the map while effectively improving the efficiency of constructing the map.

[0092] Figure 4 A schematic diagram of an apparatus for constructing a map provided in the present specification includes:

[0093] The determining module 401 is configured to determine a relative pose of a specified acquisition device relative to a lane line involved in acquired image data, and a depth value of the lane line involved in the image data, and determine positioning data of the acquisition device in an absolute coordinate system when acquiring the image data.

[0094] The parameter determining module 402 is configured to determine, as a transformation parameter, a parameter for representing a spatial relationship between an image position of the lane line in the image data and an actual position of the lane line in the absolute coordinate system according to the relative pose, the depth value and the positioning data.

[0095] The mapping module 403 is configured to map an image of a lane line tracked from the image data into a preset common space according to the transformation parameter.

[0096] The fitting module 404 is configured to fit each lane line mapped into the common space to obtain a fitted lane line.

[0097] The constructing module 405 is configured to construct a map according to the fitted lane line.

[0098] Optionally, the parameter determination module 402 is specifically configured to determine a pose of the lane line in a coordinate system of a specified acquisition device according to the relative pose and the depth value; and determine the transformation parameter by taking a minimum deviation between a pose obtained by transforming the pose and the positioning data as an optimization condition.

[0099] Optionally, the transformation parameter includes a rotation parameter, a translation parameter and a scale parameter, wherein the rotation parameter and the translation parameter are used to realize mutual transformation of the relative pose and the positioning data in space, and the scale parameter is used to represent a relationship between a scale of the lane line involved in the image data in the image data and an actual scale of the lane line involved in the image data in the absolute coordinate system.

[0100] Optionally, the parameter determination module 402 is specifically configured to determine the transformation parameter according to the following formula:

[0101] Loss=∑(X g -s*(R*X v +t)) 2

[0102] wherein X g is the positioning data, s is the scale parameter, R is the rotation parameter, t is the translation parameter, and X v is the pose of the lane line in the coordinate system of the specified acquisition device determined according to the relative pose and the depth value.

[0103] Optionally, the fitting module 404 is specifically configured to, for each road segment, determine lane lines of the road segment mapped to the road segment by each image data in the common space as lane lines corresponding to the road segment; and fit the lane lines corresponding to the road segment according to distances between the lane lines corresponding to the road segment in the common space to obtain a fitted lane line of the road segment.

[0104] Optionally, the construction module 405 is specifically configured to, in the common space, connect the fitted lane line of each image data corresponding to a road segment based on tracking of a same lane line contained in the image data to obtain a connected lane line, and construct a map according to the connected lane line.

[0105] Optionally, the construction module 405 is specifically used to: determine lane line missing sections in the public space based on the fitted lane lines; select from each section adjacent to the lane line missing sections to determine the lane lines in the lane line missing sections as target sections; extend the fitted lane lines contained in the target sections to obtain the lane lines in the lane line missing sections as fitted lane lines in the lane line missing sections; and construct a map based on the fitted lane lines contained in each section.

[0106] Optionally, the construction module 405 is specifically used to select, from the road segments adjacent to the road segment with missing lane lines, a road segment containing fitted lane lines and whose angle with the road segment with missing lane lines in the road direction meets a preset angle condition, as the target road segment.

[0107] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 This provides a method for building maps.

[0108] This instruction manual also provides Figure 5 One of the corresponding Figure 1 A schematic diagram of the structure of an electronic device. (e.g.) Figure 5 At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for the business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above-mentioned functions. Figure 1 The method for constructing the map is described above. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0109] In the 1990s, it was quite obvious to distinguish whether an improvement in a technology was in hardware (e.g., improvement in circuit structures of diodes, transistors, switches, etc.) or in software (improvement in method flow). However, as technology has evolved, many improvements in method flow today can be considered as direct improvements in hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structures by programming the improved method flow into hardware circuits. Therefore, it cannot be said that an improvement in a method flow cannot be implemented by hardware entity modules. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is an integrated circuit whose logic function is determined by user programming of the device. A digital system is "integrated" on a PLD by the designer programming it, rather than by asking a chip manufacturer to design and fabricate a custom integrated circuit chip. Moreover, instead of manually fabricating integrated circuit chips, this programming is now mostly implemented by "logic compiler" software, which is similar to software compilers used in program development, and the original code to be compiled is written in a specific programming language, which is called a hardware description language (HDL), and there are many such languages, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., and the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should be aware that, as long as the method flow is logically programmed in the above-mentioned hardware description languages and programmed into an integrated circuit, a hardware circuit implementing the logical method flow can be easily obtained.

[0110] The controller can be implemented in any suitable way, for example, the controller can take the form of a microprocessor or processor and a computer readable medium storing computer readable program code, such as software or firmware, executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that, in addition to being implemented in pure computer readable program code, the controller can equally well be implemented to perform the same functions using logic gates, switches, an application specific integrated circuit, a programmable logic controller and an embedded microcontroller, etc. by means of a logical programming of the method steps. The controller can thus be considered as a hardware component, and the means comprised therein for performing the various functions can be considered as structures within the hardware component. Alternatively, the means for performing the various functions can even be considered as both a software module implementing the method and a structure within the hardware component.

[0111] The systems, apparatuses, modules or units illustrated by the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0112] For the sake of description, the above apparatuses are described in functional division and are described respectively. Of course, the functions of the units can be implemented in the same or multiple software and / or hardware when implementing the present specification.

[0113] Those skilled in the art will understand that the embodiments of the present specification can be provided as a method, a system, or a computer program product. Therefore, the present specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] The specification is presented with reference to flow diagrams and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing element or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Flow diagrams and / or block diagrams can also present a method, apparatus or computer program product to achieve functions specified in flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Flow diagrams and / or block diagrams can also present a method, apparatus or computer program product to achieve functions specified in flow diagrams and / or block diagrams block or blocks.

[0115] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Flow diagrams and / or block diagrams can also present a method, apparatus or computer program product to achieve functions specified in flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Flow diagrams and / or block diagrams can also present a method, apparatus or computer program product to achieve functions specified in flow diagrams and / or block diagrams block or blocks.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Flow diagrams and / or block diagrams can also present a method, apparatus or computer program product to achieve functions specified in flow diagrams and / or block diagrams block or blocks. ​ The flow diagrams and / or block diagrams in the specification can present a method, apparatus or computer program product according to embodiments of the specification. Flow diagrams and / or block diagrams can also present a method, apparatus or computer program product to achieve functions specified in flow diagrams and / or block diagrams block or blocks.

[0117] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0118] The memory can include non-persistent memory and / or storage mechanisms such as, for example, random access memory (RAM), non-volatile memory (NVM), and / or a persistent memory such as, for example, read-only memory (ROM) or flash memory. The memory is an example of computer-readable media.

[0119] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0120] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0121] Those skilled in the art will appreciate that embodiments of the present specification can be provided as methods, systems or computer program products. Therefore, the present specification can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0122] The present specification can be described in the general context of computer-executable instructions, such as program modules, executed by computers. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The present specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including storage devices.

[0123] The various embodiments described in this specification are described using a numbering of embodiments approach: these are each individually integrated contributions pertaining to different but related aspects of the description. Each of the various embodiments can stand on its own, and each can be combined with the subject matter of other embodiments to produce further embodiments. Where appropriate, therefore, the contents of the specification can be regarded as being incorporated by reference, including the description, drawings, claims, abstract and the like.

[0124] The above description is embodied in the form of examples only, and is not intended to limit the specification. The specification can be variously changed and modified by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the specification should be included in the scope of the claims of the specification.

Claims

1. A method for constructing a map, characterized in that, include: Determine the relative pose of the specified acquisition device with respect to the lane lines involved in the acquired image data, as well as the depth value of the lane lines involved in the image data, and determine the positioning data of the acquisition device in the absolute coordinate system when acquiring the image data; Based on the relative pose, the depth value, and the positioning data, parameters are determined to characterize the spatial relationship between the image position of the lane line in the image data and the actual position of the lane line in the absolute coordinate system, and these parameters are used as transformation parameters. Based on the transformation parameters, the lane lines tracked from the image data are mapped into a preset public space; The lane lines mapped to the public space are fitted to obtain the fitted lane lines; Based on the fitted lane lines, construct a map; The transformation parameters include: rotation parameters, translation parameters, and scale parameters. The rotation parameters and translation parameters are used to realize the mutual conversion between the relative pose and the positioning data in space. The scale parameters are used to characterize the relationship between the scale of the lane lines involved in the image data in the image data and the actual scale of the lane lines involved in the image data in the absolute coordinate system. Based on the relative pose, the depth value, and the positioning data, parameters are determined to characterize the spatial relationship between the image position of the lane line in the image data and the actual position of the lane line in the absolute coordinate system, specifically including: The transformation parameters are determined according to the following formula: in, The location data, The scale parameter is... The rotation parameters are... The translation parameters are... The position of the lane line in the coordinate system of the specified acquisition device is determined based on the relative pose and the depth value.

2. The method as described in claim 1, characterized in that, Based on the relative pose, the depth value, and the positioning data, parameters are determined to characterize the spatial relationship between the image position of the lane line in the image data and the actual position of the lane line in the absolute coordinate system, including: Based on the relative pose and the depth value, the pose of the lane line in the coordinate system of the specified acquisition device is determined; The transformation parameters are determined with the minimum deviation between the pose obtained after transformation by the transformation parameters and the positioning data as the optimization condition.

3. The method as described in claim 1, characterized in that, The lane lines mapped to the public space are fitted to obtain the fitted lane lines, including: For each road segment, lane lines mapped to that road segment by each image data are determined in the public space and used as the corresponding lane lines for that road segment; Based on the distances between the lane lines corresponding to the road segment in the public space, the lane lines corresponding to the road segment are fitted to obtain the fitted lane lines of the road segment.

4. The method as described in claim 1 or 3, characterized in that, Based on the fitted lane lines, a map is constructed, including: In the public space, based on the tracking of the same lane lines contained in the image data, the fitted lane lines of each image data corresponding to the road segment are connected to obtain the connected lane lines, and a map is constructed based on the connected lane lines.

5. The method as described in claim 1 or 3, characterized in that, Based on the fitted lane lines, a map is constructed, including: Based on the fitted lane lines, determine the road segments with missing lane lines in the public space; From the road segments adjacent to the road segment with missing lane lines, select the road segment used to determine the lane lines in the road segment with missing lane lines as the target road segment; The fitted lane lines contained in the target road segment are extended to obtain the lane lines in the lane line missing road segment, which are used as the fitted lane lines in the lane line missing road segment. A map is constructed based on the fitted lane lines contained in each road segment.

6. The method as described in claim 5, characterized in that, From the road segments adjacent to the road segment with missing lane lines, select the road segment used to determine the lane lines in the road segment with missing lane lines as the target road segment, including: From the road segments adjacent to the road segment with missing lane lines, select the road segment containing the fitted lane lines and whose angle with the road segment with missing lane lines in the road direction meets the preset angle condition, and use it as the target road segment.

7. An apparatus for constructing a map, characterized in that, include: The determination module is used to determine the relative pose of the specified acquisition device with respect to the lane lines involved in the acquired image data, as well as the depth value of the lane lines involved in the image data, and to determine the positioning data of the acquisition device in the absolute coordinate system when acquiring the image data. The parameter determination module is used to determine, based on the relative pose, the depth value, and the positioning data, a parameter that characterizes the spatial relationship between the image position of the lane line in the image data and the actual position of the lane line in the absolute coordinate system, as a transformation parameter. The mapping module is used to map the lane lines tracked from the image data to a preset public space according to the transformation parameters. The fitting module is used to fit the lane lines mapped to the public space to obtain the fitted lane lines. A construction module is used to build a map based on the fitted lane lines; The transformation parameters include: rotation parameters, translation parameters, and scale parameters. The rotation parameters and translation parameters are used to realize the mutual conversion between the relative pose and the positioning data in space. The scale parameters are used to characterize the relationship between the scale of the lane lines involved in the image data in the image data and the actual scale of the lane lines involved in the image data in the absolute coordinate system. Based on the relative pose, the depth value, and the positioning data, parameters are determined to characterize the spatial relationship between the image position of the lane line in the image data and the actual position of the lane line in the absolute coordinate system, specifically including: The transformation parameters are determined according to the following formula: in, The location data, The scale parameter is... The rotation parameters are... The translation parameters are... The position of the lane line in the coordinate system of the specified acquisition device is determined based on the relative pose and the depth value.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 6.

9. An electronic 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 program, it implements the method described in any one of claims 1 to 6.

Images