CN117854038A - Construction area acquisition method and device, electronic equipment and automatic driving vehicle - Google Patents
Construction area acquisition method and device, electronic equipment and automatic driving vehicle Download PDFInfo
- Publication number
- CN117854038A CN117854038A CN202311754360.6A CN202311754360A CN117854038A CN 117854038 A CN117854038 A CN 117854038A CN 202311754360 A CN202311754360 A CN 202311754360A CN 117854038 A CN117854038 A CN 117854038A
- Authority
- CN
- China
- Prior art keywords
- image data
- obstacle
- processed
- construction
- construction area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010276 construction Methods 0.000 title claims abstract description 297
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000011218 segmentation Effects 0.000 claims description 43
- 230000006870 function Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 13
- 230000004888 barrier function Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 12
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 4
- 230000004931 aggregating effect Effects 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 8
- 238000003709 image segmentation Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The disclosure provides a construction area acquisition method, a construction area acquisition device, electronic equipment, a readable storage medium and an automatic driving vehicle, and relates to the technical field of artificial intelligence such as image processing, deep learning, automatic driving and intelligent traffic. The construction area acquisition method comprises the following steps: acquiring image data to be processed and an initial construction area in the image data to be processed; determining at least one construction obstacle in the at least one obstacle according to the position information of the at least one obstacle in the image data to be processed and the initial construction area; and acquiring a target construction area in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed. The method and the device can improve the accuracy of the acquired construction area.
Description
Technical Field
The disclosure relates to the field of computer technology, and in particular to the technical field of artificial intelligence such as image processing, deep learning, automatic driving, intelligent traffic and the like. Provided are a construction area acquisition method, a construction area acquisition device, an electronic device, a readable storage medium and an automatic driving vehicle.
Background
In the field of autopilot, construction scenes belong to a special road condition scene. Because the construction area in the construction scene has the characteristics of irregular boundaries, complex characteristic structures and the like, the automatic driving vehicle has great challenges when passing through the construction area, and if the construction area cannot be accurately acquired, the automatic driving vehicle can be caused to drive into the construction area, so that the driving safety of the vehicle is influenced.
In the prior art, when a construction area is acquired, after a construction identifier is acquired, the structure and the size of the construction area are determined according to a preset rule and/or a preset condition, and then path planning is performed according to a determination result. However, in a real road scene, the shape and arrangement of the construction area are changed in many ways, and the construction area is determined only by rules and/or conditions, so that an accurate determination result of the construction area cannot be obtained, and the running safety of the automatic driving vehicle is further affected.
Disclosure of Invention
According to a first aspect of the present disclosure, there is provided a method for acquiring a construction area, including: acquiring image data to be processed and an initial construction area in the image data to be processed; determining at least one construction obstacle in the at least one obstacle according to the position information of the at least one obstacle in the image data to be processed and the initial construction area; and acquiring a target construction area in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed.
According to a second aspect of the present disclosure, there is provided an acquisition apparatus of a construction area, including: the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring image data to be processed and an initial construction area in the image data to be processed; a determining unit configured to determine at least one construction obstacle from among the at least one obstacle according to position information of the at least one obstacle in the image data to be processed and the initial construction area; and the processing unit is used for acquiring a target construction area in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described above.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method as described above.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method as described above.
According to a sixth aspect of the present disclosure, there is provided an autonomous vehicle comprising an electronic device according to the third aspect of the present disclosure.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;
FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure;
FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure;
fig. 5 is a block diagram of an electronic device used to implement a method of acquiring a construction area according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram according to a first embodiment of the present disclosure. As shown in fig. 1, the method for acquiring a construction area of the present embodiment specifically includes the following steps:
s101, acquiring image data to be processed and an initial construction area in the image data to be processed;
s102, determining at least one construction obstacle in at least one obstacle according to the position information of the at least one obstacle in the image data to be processed and the initial construction area;
s103, acquiring a target construction area in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed.
According to the method for acquiring the construction area, the initial construction area in the image data to be processed is acquired firstly, then at least one construction obstacle in the at least one obstacle is determined according to the position information of the at least one obstacle in the image data to be processed and the initial construction area, and finally the target construction area in the image data to be processed is acquired according to the position information of the at least one construction obstacle in the image data to be processed.
The present embodiment executes S101 to acquire image data to be processed, which is image data captured by a camera disposed on an autonomous vehicle.
If a plurality of cameras are disposed on the autopilot vehicle, in the embodiment, when S101 is executed, one piece of image data captured by the camera at a preset position (for example, the roof of the autopilot vehicle) may be obtained as the image data to be processed; multiple pieces of image data shot by all cameras can be obtained and used as image data to be processed; if a plurality of pieces of image data to be processed are acquired, the embodiment acquires the initial construction area in each piece of image data to be processed when executing S101.
In the embodiment, when S101 is executed to acquire the initial construction area in the image data to be processed, the implementation manner may be: inputting the image data to be processed into a construction area segmentation model; acquiring an initial construction area in the image data to be processed according to an output result of the construction area segmentation model; the construction region segmentation model in the embodiment is used for segmenting out a construction region in the image data.
That is, in this embodiment, the initial construction area in the image data to be processed is acquired by using the construction area segmentation model obtained by training in the image segmentation manner, so that the step of acquiring the initial construction area can be simplified, and the accuracy of the acquired initial construction area can be improved.
The present embodiment may further include the following when S101 is executed to input the image data to be processed into the construction region segmentation model: acquiring the image size of image data to be processed; and under the condition that the acquired image size is inconsistent with the preset size, the image size of the image data to be processed is adjusted to the preset size, and then the construction area segmentation model is input.
That is, the present embodiment unifies the image sizes of the image data input to the construction region division model so that the initial construction region acquired by the construction region division model is not affected by the image sizes, further improving the accuracy of the initial construction region acquired by the construction region division model.
The construction area segmentation model used in the execution of S101 in this embodiment may be obtained by training in the following manner: acquiring sample image data and a construction area marking result corresponding to the sample image data; inputting the acquired sample image data into an initial segmentation model, and acquiring a construction area prediction result output by the initial segmentation model, wherein a backbone network (backbone), a neck network (neg) and a passable area segmentation head (drivable area seg head) in the YOLOP model can be used as network structures of the initial segmentation model; and calculating a loss function value according to the construction region labeling result and the construction region prediction result, and adjusting parameters of the initial segmentation model according to the calculated loss function value to obtain a construction region segmentation model.
According to the embodiment, sample image data can be obtained from a sample image data set constructed in advance, so that an initial segmentation model is trained; the sample image data set in the present embodiment includes a plurality of pieces of sample image data, each piece of sample image data being image data including a construction area; the construction area in this embodiment may be a long-term construction area and a short-term construction area (i.e., a construction area where construction has already been started) located on the road, or may be a pre-construction diversion area located on the road.
When the sample image data set is constructed, a plurality of pieces of sample image data can be obtained in a graph searching mode, namely, the existing image data comprising a construction area is used as a search request, searching is carried out in a database, and the image data obtained by searching is obtained as sample image data; the image data marked with the construction tag for indicating that the construction area is included in the image data may also be acquired from the database as sample image data.
In this embodiment, after a plurality of pieces of sample image data are acquired, each piece of sample image data is labeled, specifically: marking the construction area in each piece of sample image data in a tracing mode.
In addition, the passable region in each sample image data can be marked, and further, in the training process of the construction region segmentation model, the parameters of the initial segmentation model are adjusted by combining the loss function value of the corresponding passable region and the loss function value of the corresponding construction region, so that the construction region segmentation model obtained by training can segment the construction region in the image data more accurately.
In the embodiment, when the step S101 of acquiring the initial construction area in the image data to be processed is performed, the initial construction area in the image data to be processed may also be acquired according to the construction identifier acquired from the image data to be processed and the preset area size; the present embodiment is not limited to the manner in which the initial construction area is acquired from the image data.
The present embodiment executes S102 to determine at least one construction obstacle from among the at least one obstacle according to the position information of the at least one obstacle in the image data to be processed and the initial construction area after executing S101 to acquire the initial construction area in the image data to be processed.
In the present embodiment, when S102 is executed, first, position information of at least one obstacle in image data to be processed is acquired, and then, according to the acquired position information and an initial construction area, it is determined whether the at least one obstacle is a construction obstacle.
In the embodiment, when S102 is executed to acquire the position information of at least one obstacle in the image data to be processed, the implementation manner may be as follows: detecting an obstacle of the image data to be processed; and acquiring at least one obstacle in the image data to be processed and the position information of the at least one obstacle in the image data to be processed according to the obstacle detection result.
The present embodiment may further employ the following manner when S102 is performed to acquire position information of at least one obstacle in image data to be processed: acquiring point cloud data of at least one obstacle; projecting point cloud data of at least one obstacle to image data to be processed, namely converting a three-dimensional obstacle into a two-dimensional obstacle in a projection mode; and acquiring the position information of at least one obstacle in the image data to be processed according to the projection result.
That is, in this embodiment, the position information of at least one obstacle in the image data to be processed may be acquired by using a method of detecting the obstacle in the image data or a method of projecting three-dimensional point cloud data of the obstacle, so that flexibility in acquiring the position information of the obstacle may be improved.
In the embodiment, when S102 is executed to determine at least one construction obstacle from the at least one obstacle according to the position information of the at least one obstacle in the image data to be processed and the initial construction area, the implementation manner may be: for each obstacle, acquiring the overlapping area of the obstacle and the initial construction area according to the position information of the obstacle in the image data to be processed and the initial construction area; under the condition that the acquired overlapping area is larger than a preset area threshold value, determining the obstacle as a construction obstacle; wherein the preset area threshold is a value greater than or equal to 0.
That is, the present embodiment determines, as a construction obstacle, an obstacle overlapping the initial construction area by means of the initial construction area acquired from the image data to be processed, and can improve the accuracy of the determined construction obstacle.
In addition, in the embodiment, when S102 is performed to determine at least one construction obstacle from the at least one obstacle according to the position information of the at least one obstacle in the image data to be processed and the initial construction area, the obstacle center coordinate may be determined first according to the position information of the obstacle, the area center coordinate may be determined according to the initial construction area, and then, in the case that it is determined that the distance between the obstacle center coordinate and the area center coordinate is less than or equal to the preset distance threshold, the obstacle may be determined to be the construction obstacle.
The present embodiment, after executing S102 to determine at least one construction obstacle of the at least one obstacle, executes S103 to acquire a target construction area in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed.
Because the boundary of the construction area is very irregular, the problem of boundary shake exists when the construction area is directly acquired from the image data by using an image processing method such as image segmentation, and under the condition that the boundary of the construction area shakes, the automatic driving vehicle cannot accurately plan a path according to the construction area, so that the driving safety of the automatic driving vehicle is affected.
Therefore, the embodiment combines the initial construction area obtained from the image data to be processed and the construction obstacle determined according to the initial construction area to obtain the target construction area in the image data to be processed, so that the obtained target construction area has a more stable boundary, the accuracy of the obtained target construction area is improved, and the running safety of the automatic driving vehicle is further improved.
In the embodiment, when S103 is executed to obtain the target construction area in the image data to be processed according to the position information of at least one construction barrier in the image data to be processed, the implementation manner may be as follows: according to the position information of at least one construction barrier in the image data to be processed, the at least one construction barrier is aggregated in the image data to be processed, and the embodiment can aggregate the at least one construction barrier with the distance between the barriers being less than or equal to a preset distance threshold; acquiring an aggregation area of at least one construction barrier in image data to be processed as a target construction area; one aggregation area in this embodiment corresponds to one target construction area.
For example, if there are two construction obstacles, if the distance between the two construction obstacles is less than or equal to the preset distance threshold, the embodiment executes S103 to aggregate the two construction obstacles to obtain an aggregate area as the target construction area; if the distance between the two construction obstacles is greater than the preset distance threshold, the embodiment performs S103 to aggregate the two construction obstacles respectively, so as to obtain two aggregate areas as target construction areas.
In the embodiment, when S103 is executed, a bounding box capable of bounding at least one construction obstacle may be obtained according to the position information of the at least one construction obstacle in the image data to be processed, and the obtained bounding box is taken as the target construction area; in this embodiment, a bounding box is used to enclose at least one construction obstacle whose distance between obstacles is less than or equal to a preset distance threshold, where a bounding box corresponds to a target construction area.
Fig. 2 is a schematic diagram according to a second embodiment of the present disclosure. A schematic diagram of an initial construction area obtained from image data to be processed according to the present embodiment is shown in fig. 2.
Fig. 3 is a schematic diagram according to a third embodiment of the present disclosure. A schematic diagram of a construction obstacle determined according to an initial construction area and a target construction area acquired according to the construction obstacle according to the present embodiment is shown in fig. 3; in fig. 3, the obstacle in the white box is a construction obstacle determined according to the initial construction area, the area in the black box is a target construction area obtained according to the construction obstacle, and two target construction areas are obtained in this embodiment; as can also be seen from fig. 3, when the target construction area is obtained according to the determined construction obstacle, the purpose of screening the initial construction area can also be achieved, that is, the initial construction area excluding the construction obstacle is filtered, so that a more accurate target construction area is obtained.
Fig. 4 is a schematic diagram according to a fourth embodiment of the present disclosure. As shown in fig. 4, the construction area acquisition apparatus 400 of the present embodiment includes:
an acquiring unit 401, configured to acquire image data to be processed and an initial construction area in the image data to be processed;
a determining unit 402 configured to determine at least one construction obstacle from among the at least one obstacle according to the initial construction area and position information of the at least one obstacle in the image data to be processed;
the processing unit 403 is configured to obtain a target construction area in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed.
The image data to be processed acquired by the acquisition unit 401 is image data captured by a camera disposed on the automated driving vehicle.
If a plurality of cameras are disposed on the autopilot vehicle, the acquiring unit 401 may acquire one piece of image data captured by the camera at a preset position (for example, the roof of the autopilot vehicle) as image data to be processed; multiple pieces of image data shot by all cameras can be obtained and used as image data to be processed; if a plurality of pieces of image data to be processed are acquired, the acquiring unit 401 acquires the initial construction area in each piece of image data to be processed, respectively.
The obtaining unit 401 may adopt the following implementation manners when obtaining the initial construction area in the image data to be processed: inputting the image data to be processed into a construction area segmentation model; and acquiring an initial construction area in the image data to be processed according to the output result of the construction area segmentation model.
That is, the acquisition unit 401 acquires the initial construction region in the image data to be processed by using the construction region segmentation model obtained by training in the image segmentation manner, and can simplify the acquisition step of the initial construction region and improve the accuracy of the acquired initial construction region.
The acquisition unit 401 may further include, when inputting image data to be processed into the construction region segmentation model, the following: acquiring the image size of image data to be processed; and under the condition that the acquired image size is inconsistent with the preset size, the image size of the image data to be processed is adjusted to the preset size, and then the construction area segmentation model is input.
That is, the acquisition unit 401 unifies the image sizes of the image data input to the construction region division model so that the initial construction region acquired by the construction region division model is not affected by the image sizes, further improving the accuracy of the initial construction region acquired by the construction region division model.
The construction area obtaining device 400 of the present embodiment further includes a training unit 404, configured to train to obtain a construction area segmentation model in the following manner: acquiring sample image data and a construction area marking result corresponding to the sample image data; inputting the acquired sample image data into an initial segmentation model, and acquiring a construction area prediction result output by the initial segmentation model; and calculating a loss function value according to the construction region labeling result and the construction region prediction result, and adjusting parameters of the initial segmentation model according to the calculated loss function value to obtain a construction region segmentation model.
The training unit 404 may acquire sample image data from a sample image dataset constructed in advance, and further train the initial segmentation model; the sample image data set in the present embodiment includes a plurality of pieces of sample image data, each piece of sample image data being image data including a construction area; the construction area in this embodiment may be a long-term construction area and a short-term construction area (i.e., a construction area where construction has already been started) located on the road, or may be a pre-construction diversion area located on the road.
When the training unit 404 constructs a sample image data set, a plurality of pieces of sample image data can be obtained in a graph searching mode, namely, the existing image data comprising a construction area is used as a search request, searching is carried out in a database, and the image data obtained by searching is obtained as sample image data; the image data marked with the construction tag for indicating that the construction area is included in the image data may also be acquired from the database as sample image data.
After acquiring a plurality of pieces of sample image data, the training unit 404 labels each piece of sample image data, specifically: marking the construction area in each piece of sample image data in a tracing mode.
In addition, the training unit 404 may further label the passable region in each sample image data, and further adjust parameters of the initial segmentation model by combining the loss function value of the corresponding passable region and the loss function value of the corresponding construction region in the training process of the construction region segmentation model, so that the construction region segmentation model obtained by training can segment the construction region in the image data more accurately.
When acquiring the initial construction area in the image data to be processed, the acquiring unit 401 may also acquire the initial construction area in the image data to be processed according to the construction identifier acquired from the image data to be processed and the size of the preset area; the present embodiment does not limit the manner in which the acquisition unit 401 acquires the initial construction area from the image data.
The present embodiment, after the initial construction area in the image data to be processed is acquired by the acquisition unit 401, determines at least one construction obstacle from among the at least one obstacle by the determination unit 402 based on the position information of the at least one obstacle in the image data to be processed and the initial construction area.
The determining unit 402 first acquires position information of at least one obstacle in the image data to be processed, and then determines whether the at least one obstacle is a construction obstacle according to the acquired position information and the initial construction area.
The determining unit 402 may adopt the implementation manner when acquiring the position information of at least one obstacle in the image data to be processed: detecting an obstacle of the image data to be processed; and acquiring at least one obstacle in the image data to be processed and the position information of the at least one obstacle in the image data to be processed according to the obstacle detection result.
The determination unit 402 may further employ, when acquiring the positional information of at least one obstacle in the image data to be processed, the following manner: acquiring point cloud data of at least one obstacle; projecting point cloud data of at least one obstacle to image data to be processed, namely converting a three-dimensional obstacle into a two-dimensional obstacle in a projection mode; and acquiring the position information of at least one obstacle in the image data to be processed according to the projection result.
That is, the determining unit 402 may acquire the position information of at least one obstacle in the image data to be processed in a manner of performing obstacle detection on the image data or in a manner of projecting three-dimensional point cloud data of the obstacle, which can promote flexibility in acquiring the position information of the obstacle.
The present determining unit 402 may determine, when determining at least one construction obstacle of the at least one obstacle according to the position information of the at least one obstacle in the image data to be processed and the initial construction area, as follows: for each obstacle, acquiring the overlapping area of the obstacle and the initial construction area according to the position information of the obstacle in the image data to be processed and the initial construction area; under the condition that the acquired overlapping area is larger than a preset area threshold value, determining the obstacle as a construction obstacle; wherein the preset area threshold is a value greater than or equal to 0.
That is, the determination unit 402 determines, as a construction obstacle, an obstacle overlapping the initial construction area by means of the initial construction area acquired from the image data to be processed, and can improve the accuracy of the determined construction obstacle.
In addition, when determining at least one construction obstacle from the at least one obstacle in the image data to be processed and the initial construction area, the determining unit 402 may also determine an obstacle center coordinate first from the position information of the obstacle, determine an area center coordinate from the initial construction area, and then determine that the obstacle is a construction obstacle if it is determined that the distance between the obstacle center coordinate and the area center coordinate is equal to or less than a preset distance threshold.
The present embodiment, after at least one construction obstacle among the at least one obstacle is determined by the determination unit 402, acquires a target construction area in the image data to be processed from the positional information of the at least one construction obstacle in the image data to be processed by the processing unit 403.
When the processing unit 403 obtains the target construction area in the image data to be processed according to the position information of at least one construction barrier in the image data to be processed, the implementation manner may be as follows: according to the position information of at least one construction barrier in the image data to be processed, aggregating the at least one construction barrier in the image data to be processed; and acquiring an aggregation area of at least one construction barrier in the image data to be processed as a target construction area.
The processing unit 403 may further acquire a bounding box capable of bounding the at least one construction obstacle according to the position information of the at least one construction obstacle in the image data to be processed, and take the acquired bounding box as the target construction area; the bounding box in this embodiment is used for bounding at least one construction obstacle with a distance between obstacles being less than or equal to a preset distance threshold.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
As shown in fig. 5, a block diagram of an electronic device of a construction area acquisition method according to an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 5, the apparatus 500 includes a computing unit 501 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, ROM502, and RAM503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Various components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, etc.; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508 such as a magnetic disk, an optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 501 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 501 performs the respective methods and processes described above, for example, the acquisition method of the construction area. For example, in some embodiments, the method of acquiring a construction zone may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 508.
In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM502 and/or the communication unit 509. When the computer program is loaded into the RAM503 and executed by the computing unit 501, one or more steps of the above-described acquisition method of the construction area may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the method of acquiring the construction area by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here can be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable construction area acquisition device such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram block or blocks to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can include or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a presentation device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for presenting information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (18)
1. The method for acquiring the construction area comprises the following steps:
acquiring image data to be processed and an initial construction area in the image data to be processed;
determining at least one construction obstacle in the at least one obstacle according to the position information of the at least one obstacle in the image data to be processed and the initial construction area;
and acquiring a target construction area in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed.
2. The method of claim 1, wherein the acquiring an initial construction area in the image data to be processed comprises:
inputting the image data to be processed into a construction area segmentation model;
and acquiring an initial construction area in the image data to be processed according to an output result of the construction area segmentation model.
3. The method of claim 1, wherein acquiring location information of at least one obstacle in the image data to be processed comprises:
detecting an obstacle for the image data to be processed;
and acquiring the position information of the at least one obstacle in the image data to be processed according to the obstacle detection result.
4. The method of claim 1, wherein acquiring location information of at least one obstacle in the image data to be processed comprises:
acquiring point cloud data of the at least one obstacle;
projecting point cloud data of the at least one obstacle to the image data to be processed;
and acquiring the position information of the at least one obstacle in the image data to be processed according to the projection result.
5. The method of claim 1, wherein the determining at least one of the at least one obstacle based on the initial construction area and the location information of the at least one obstacle in the image data to be processed comprises:
for each obstacle, acquiring the overlapping area of the obstacle and the initial construction area according to the position information of the obstacle in the image data to be processed and the initial construction area;
and under the condition that the overlapping area is larger than a preset area threshold value, determining the obstacle as a construction obstacle.
6. The method of claim 1, wherein the acquiring the target construction area in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed comprises:
aggregating the at least one construction obstacle in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed;
and acquiring an aggregation area of the at least one construction barrier in the image data to be processed as the target construction area.
7. The method of claim 2, further comprising,
acquiring sample image data and a construction area marking result corresponding to the sample image data;
inputting the sample image data into an initial segmentation model, and obtaining a construction area prediction result output by the initial segmentation model;
and calculating a loss function value according to the construction region labeling result and the construction region prediction result, and adjusting parameters of the initial segmentation model according to the loss function value to obtain the construction region segmentation model.
8. An acquisition device of a construction area, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring image data to be processed and an initial construction area in the image data to be processed;
a determining unit configured to determine at least one construction obstacle from among the at least one obstacle according to position information of the at least one obstacle in the image data to be processed and the initial construction area;
and the processing unit is used for acquiring a target construction area in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed.
9. The apparatus according to claim 8, wherein the acquisition unit, when acquiring an initial construction area in the image data to be processed, specifically performs:
inputting the image data to be processed into a construction area segmentation model;
and acquiring an initial construction area in the image data to be processed according to an output result of the construction area segmentation model.
10. The apparatus according to claim 8, wherein the determining unit, when acquiring position information of at least one obstacle in the image data to be processed, specifically performs:
detecting an obstacle for the image data to be processed;
and acquiring the position information of the at least one obstacle in the image data to be processed according to the obstacle detection result.
11. The apparatus according to claim 8, wherein the determining unit, when acquiring position information of at least one obstacle in the image data to be processed, specifically performs:
acquiring point cloud data of the at least one obstacle;
projecting point cloud data of the at least one obstacle to the image data to be processed;
and acquiring the position information of the at least one obstacle in the image data to be processed according to the projection result.
12. The apparatus according to claim 8, wherein the determining unit, when determining at least one construction obstacle of the at least one obstacle based on the initial construction area and the position information of the at least one obstacle in the image data to be processed, specifically performs:
for each obstacle, acquiring the overlapping area of the obstacle and the initial construction area according to the position information of the obstacle in the image data to be processed and the initial construction area;
and under the condition that the overlapping area is larger than a preset area threshold value, determining the obstacle as a construction obstacle.
13. The apparatus according to claim 8, wherein the processing unit, when acquiring the target construction area in the image data to be processed based on the position information of the at least one construction obstacle in the image data to be processed, specifically performs:
aggregating the at least one construction obstacle in the image data to be processed according to the position information of the at least one construction obstacle in the image data to be processed;
and acquiring an aggregation area of the at least one construction barrier in the image data to be processed as the target construction area.
14. The apparatus of claim 9, further comprising a training unit to perform:
acquiring sample image data and a construction area marking result corresponding to the sample image data;
inputting the sample image data into an initial segmentation model, and obtaining a construction area prediction result output by the initial segmentation model;
and calculating a loss function value according to the construction region labeling result and the construction region prediction result, and adjusting parameters of the initial segmentation model according to the loss function value to obtain the construction region segmentation model.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-7.
18. An autonomous vehicle comprising the electronic device of claim 15.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311754360.6A CN117854038A (en) | 2023-12-19 | 2023-12-19 | Construction area acquisition method and device, electronic equipment and automatic driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311754360.6A CN117854038A (en) | 2023-12-19 | 2023-12-19 | Construction area acquisition method and device, electronic equipment and automatic driving vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117854038A true CN117854038A (en) | 2024-04-09 |
Family
ID=90529719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311754360.6A Pending CN117854038A (en) | 2023-12-19 | 2023-12-19 | Construction area acquisition method and device, electronic equipment and automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117854038A (en) |
-
2023
- 2023-12-19 CN CN202311754360.6A patent/CN117854038A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112560862B (en) | Text recognition method and device and electronic equipment | |
| CN113378760A (en) | Training target detection model and method and device for detecting target | |
| CN113378693B (en) | Method and device for generating target detection system and detecting target | |
| CN114037966A (en) | High-precision map feature extraction method, device, medium and electronic equipment | |
| EP4145408A1 (en) | Obstacle detection method and apparatus, autonomous vehicle, device and storage medium | |
| CN113298910A (en) | Method, apparatus and storage medium for generating traffic sign line map | |
| CN115797736A (en) | Method, device, equipment and medium for training target detection model and target detection | |
| CN110866504A (en) | Method, device and equipment for acquiring marked data | |
| EP4080479A2 (en) | Method for identifying traffic light, device, cloud control platform and vehicle-road coordination system | |
| CN114429631B (en) | Three-dimensional object detection method, device, equipment and storage medium | |
| CN115761698A (en) | Target detection method, device, equipment and storage medium | |
| CN113762397B (en) | Method, equipment, medium and product for training detection model and updating high-precision map | |
| CN116434181A (en) | Ground point detection method, device, electronic equipment and medium | |
| CN115830268A (en) | Data acquisition method and device for optimizing perception algorithm and storage medium | |
| CN117854038A (en) | Construction area acquisition method and device, electronic equipment and automatic driving vehicle | |
| CN113361379B (en) | Method and device for generating target detection system and detecting target | |
| CN114049615B (en) | Traffic object fusion association method and device in driving environment and edge computing equipment | |
| CN117876992A (en) | Obstacle detection method, device, equipment and automatic driving vehicle | |
| CN117570961A (en) | Map real-time updating method, device and equipment based on stop line and storage medium | |
| CN117853614A (en) | Method and device for detecting change condition of high-precision map element and vehicle | |
| CN114579594A (en) | Information updating method and device, electronic equipment and storage medium | |
| CN117853724A (en) | Night low obstacle segmentation and model training method and automatic driving vehicle | |
| CN114359513A (en) | Method and device for determining position of obstacle and electronic equipment | |
| CN117570962A (en) | Map real-time updating method, device, equipment and storage medium based on lane lines | |
| CN113987098A (en) | High-precision map road boundary updating method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |