CN110008891B - Pedestrian detection positioning method and device, vehicle-mounted computing equipment and storage medium - Google Patents
Pedestrian detection positioning method and device, vehicle-mounted computing equipment and storage medium Download PDFInfo
- Publication number
- CN110008891B CN110008891B CN201910252786.9A CN201910252786A CN110008891B CN 110008891 B CN110008891 B CN 110008891B CN 201910252786 A CN201910252786 A CN 201910252786A CN 110008891 B CN110008891 B CN 110008891B
- Authority
- CN
- China
- Prior art keywords
- area
- positioning
- unmanned vehicle
- identification
- obstacle
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/06—Systems determining position data of a target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Electromagnetism (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a pedestrian detection positioning method, a pedestrian detection positioning device, vehicle-mounted computing equipment and a storage medium, and relates to the field of unmanned vehicle driving. The method comprises the following steps: acquiring radar data and image data of an area in front of the unmanned vehicle; dividing an area in front of the unmanned vehicle into a plurality of positioning areas based on radar data; dividing an area in front of the unmanned vehicle into a plurality of identification areas based on the image data; the positioning area and the identification area have a corresponding relation; judging a positioning area with an obstacle based on the radar data; acquiring an identification area corresponding to a positioning area with an obstacle; and determining the identification area of which the contained barrier is the pedestrian target according to the acquired image data corresponding to the identification area so as to realize pedestrian detection and positioning. According to the invention, through the corresponding relation between the positioning area and the identification area, the area in front of the unmanned vehicle does not need to be comprehensively identified, the range of pedestrian identification is reduced, and the pedestrian detection and positioning efficiency is improved.
Description
Technical Field
The invention relates to the technical field of unmanned vehicles, in particular to a pedestrian detection positioning method, a pedestrian detection positioning device, vehicle-mounted computing equipment and a storage medium.
Background
With the continuous progress of social economy and science and technology, people are more and more urgent to the demand of unmanned products, especially the application of unmanned electric vehicles in public places such as scenic spots, gardens and the like, but the pedestrian safety is the first priority, so the pedestrian detection and positioning function based on the unmanned sightseeing electric vehicle is very important.
At present, patent CN109165542A discloses a pedestrian detection method based on a simplified convolutional neural network, and patent CN109117717A discloses an urban pedestrian detection method, but both methods only adopt an image recognition method for detection, and do not locate a pedestrian detection result, which is not suitable for autonomous pedestrian obstacle avoidance of an unmanned electric vehicle.
Therefore, it is a problem to be solved by the present invention to develop a method for pedestrian detection and positioning.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide a method and an apparatus for pedestrian detection and location, a vehicle-mounted computing device and a storage medium, which are used to add a pedestrian detection and location function to an unmanned electric vehicle in public environments such as scenic spots and parks.
The invention provides a pedestrian detection and positioning method, which comprises the following steps:
acquiring radar data and image data of an area in front of the unmanned vehicle;
dividing the area ahead of the unmanned vehicle into a plurality of positioning areas based on the radar data;
dividing the unmanned vehicle driving front area into a plurality of identification areas based on the image data; wherein the positioning area and the identification area have a corresponding relationship;
judging a positioning area with an obstacle based on the radar data;
acquiring an identification area corresponding to a positioning area with an obstacle;
and determining the contained identification area of which the obstacle is a pedestrian target according to the acquired image data corresponding to the identification area so as to realize pedestrian detection and positioning.
Preferably, the step of acquiring radar data and image data of an area ahead of the unmanned vehicle includes:
acquiring radar data of an area in front of the unmanned vehicle by using a first-line laser radar sensor; the radar data comprise a group of polar coordinate system coordinate points collected by the radar sensor, and each coordinate point consists of an angle and a distance between the coordinate point and the unmanned vehicle;
and acquiring image data of the area in front of the unmanned vehicle by using a monocular camera.
Preferably, the correspondence relationship between the positioning area and the identification area specifically includes:
dividing the area ahead of the unmanned vehicle into at least one positioning area corresponding to different directions based on the radar data and the view angle;
dividing the unmanned vehicle driving front area into at least one identification area corresponding to different directions based on the image data and the image width;
and establishing a corresponding relation between the positioning areas and the identification areas with the same direction.
Preferably, the step of determining a location area where an obstacle exists based on the radar data includes:
based on the radar data, any two coordinate points p in the same positioning area are subjected to positioningi(θi,di) And pj(θj,dj) Clustering is carried out to obtain all barrier classes;
and determining a positioning area where the obstacle is located.
Preferably, any two coordinate points p of the same positioning region are determined based on the radar datai(θi,di) And pj(θj,dj) The specific steps of clustering and obtaining all the obstacle classes include:
judging any two coordinate points p of the same positioning areai(θi,di) And pj(θj,dj) Whether or not the condition | θ is satisfiedi-θjLess than or equal to 3 and | di-dj|≤0.05；
If the condition can be met, the two coordinate points can be clustered, and the two coordinate points are marked as an obstacle;
if the condition cannot be satisfied, the two coordinate points cannot be clustered.
The embodiment of the present invention further provides a pedestrian detection positioning device, including:
the data acquisition unit is used for acquiring radar data and image data of an area in front of the unmanned vehicle;
a positioning area dividing unit configured to divide an area ahead of the unmanned vehicle into a plurality of positioning areas based on the radar data;
an identification area dividing unit configured to divide the area ahead of the unmanned vehicle into a plurality of identification areas based on the image data; wherein the positioning area and the identification area have a corresponding relationship;
a judging unit, configured to judge, based on the radar data, a positioning area where an obstacle exists;
the corresponding unit is used for acquiring an identification area corresponding to the positioning area with the obstacle;
and the positioning unit is used for determining the identification area containing the obstacle as the pedestrian target according to the acquired image data corresponding to the identification area so as to realize pedestrian detection and positioning.
Preferably, the data acquisition unit includes:
the radar data acquisition module is used for acquiring radar data of an area in front of the unmanned vehicle by using a first-line laser radar sensor; the radar data comprise a group of polar coordinate system coordinate points acquired by the radar sensor, and each coordinate point consists of an angle and a distance between the coordinate point and an unmanned vehicle;
and the image data acquisition module is used for acquiring the image data of the area in front of the unmanned vehicle by using the monocular camera.
Preferably, the obstacle determination unit includes:
a clustering module for clustering any two coordinate points p in the same positioning region based on the radar datai(θi,di) And pj(θj,dj) Clustering to obtain all barrier classes;
and the area determining module is used for determining a positioning area where the obstacle is located.
The embodiment of the invention also provides vehicle-mounted computing equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the pedestrian detection positioning method.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the program is executed by a processor to implement the steps of the above-mentioned pedestrian detection and positioning method.
According to the pedestrian detection positioning method and device, the vehicle-mounted computing equipment and the storage medium, the radar data and the image data of the area in front of the driving of the unmanned vehicle are obtained, the positioning area is divided based on the radar data, the identification area is divided based on the image data, and the positioning area and the identification area are in corresponding relation. Therefore, when the radar sensor detects an obstacle in a certain positioning area, the vehicle-mounted computing device only needs to find the identification area corresponding to the positioning area with the obstacle according to the corresponding relation between the positioning area and the identification area, analyze the image data of the identification area through an image analysis technology, determine whether the obstacle in the identification area is a pedestrian, and position the pedestrian if the obstacle is the pedestrian. The pedestrian detection and positioning method provided by the invention can reduce the range of pedestrian identification, does not need to identify all areas in front of the unmanned vehicle, and improves the efficiency of pedestrian detection and positioning. The pedestrian detection and positioning method provided by the embodiment can be applied to unmanned electric vehicles in public place environments such as scenic spots and gardens, can well solve the problem of real-time pedestrian detection and positioning of the unmanned electric vehicles in the public place environments such as scenic spots and gardens, ensures the safety of pedestrians, has high real-time performance, and meets the requirements of practical application.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart of a pedestrian detection and positioning method according to a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of a pedestrian detection and positioning method device according to a second embodiment of the present invention.
Icon: 201-a data acquisition unit; 202-positioning area division unit; 203-identification area division unit; 204-a judging unit; 205-corresponding unit; 206-positioning unit.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, a first embodiment of the present invention provides a pedestrian detection and location method, which can be executed by an onboard computing device, such as an onboard computer configured on an unmanned vehicle, and has control and computing capabilities, and specifically includes at least the following steps:
and S101, acquiring radar data and image data of an area in front of the unmanned vehicle.
During the driving process of the unmanned vehicle, data of a region in front of the unmanned vehicle is collected according to a sensor arranged on the unmanned vehicle, for example, radar data and image data are collected by a camera, a laser radar and the like, the radar data is used for confirming the existence of an obstacle in the region in front of the unmanned vehicle, the image data is used for confirming whether the obstacle is a pedestrian, and the two data are combined, so that the pedestrian information in the region in front of the unmanned vehicle can be accurately and effectively detected. It should be noted that, in this embodiment, the driving front area of the unmanned vehicle refers to all areas that can be detected by the head front sensor of the unmanned vehicle.
In this embodiment, in a preferred embodiment of the present invention, the step of acquiring radar data and image data of an area ahead of the unmanned vehicle includes:
acquiring radar data of an area in front of the unmanned vehicle by using a first-line laser radar sensor; the radar data comprise a group of polar coordinate system coordinate points collected by the radar sensor, and each coordinate point consists of an angle and a distance between the coordinate point and the unmanned vehicle;
and acquiring image data of the area in front of the unmanned vehicle by using a monocular camera.
Specifically, in this embodiment, the first-line lidar sensor and the monocular camera have certain installation requirements, so as to ensure the accuracy of data acquisition. A ray of laser radar sensor horizontal installation is in the middle of the automobile body front portion of unmanned car, requires that the radar sensor is not sheltered from by other objects, and the mounting height is in 0.4 ~ 0.6 m. The monocular camera is also horizontally arranged in the middle of the front part of the unmanned vehicle body, the lens of the monocular camera is required to be pushed to the front lower part and is not shielded by other objects, and the installation height is within 1.5-2 m. And finally, the alignment of the line of laser radar sensors and the central axis of the visual field of the monocular camera is ensured, so that the division and the correspondence of a positioning area and a recognition area in the subsequent steps are facilitated, and the error is reduced.
In this embodiment, the radar data collected by the line lidar sensor is a set of polar coordinate system coordinate points, which may be P { P }1,p2,p3,...,pk,...,pnEach of said coordinate points consisting of an angle and a distance from the unmanned vehicle, the kth coordinate point may be denoted as pk(θk,dk) Wherein the angle thetakIn degrees, distance dkIn meters. The size of the image data collected by the monocular camera is h multiplied by w, h represents the height of the image, and w represents the width of the image, and the unit is pixel.
S102, dividing the area in front of the unmanned vehicle into a plurality of positioning areas based on the radar data.
S103, dividing the area in front of the unmanned vehicle into a plurality of identification areas based on the image data; wherein the positioning area and the identification area have a corresponding relationship.
S104, judging a positioning area with an obstacle based on the radar data;
s105, acquiring an identification area corresponding to the positioning area with the obstacle;
and S106, determining the identification area containing the obstacle as the pedestrian target according to the acquired image data corresponding to the identification area so as to realize pedestrian detection and positioning.
Specifically, in this embodiment, the area ahead of the unmanned vehicle is divided into the positioning areas based on the radar data, and then the area ahead of the unmanned vehicle is divided into the identification areas based on the image data, where the positioning areas and the identification areas have a corresponding relationship. Therefore, when the radar sensor detects an obstacle in a certain positioning area, the vehicle-mounted computing device only needs to find the identification area corresponding to the positioning area with the obstacle according to the corresponding relation between the positioning area and the identification area, analyzes the image data of the identification area through the image analysis technology, confirms whether the obstacle in the identification area is a pedestrian, and positions the pedestrian if the obstacle is the pedestrian. The pedestrian detection positioning method reduces the range of pedestrian identification, does not need to identify pedestrians in the whole area in front of the unmanned vehicle, and improves the efficiency of pedestrian detection positioning.
The pedestrian detection and positioning method can be applied to the unmanned electric vehicle in public place environments such as scenic spots and parks, can well solve the problem of real-time pedestrian detection and positioning of the unmanned electric vehicle in the public place environments such as scenic spots and parks, ensures the safety of pedestrians, has high real-time performance, and meets the requirements of practical application. In the invention, in order to guarantee the safety of pedestrians and vehicles, the driving speed of the unmanned vehicle applying the pedestrian detection and positioning method is lower than 50 km/h according to the environmental requirements of public places such as scenic spots, gardens and the like.
It should be noted that, the corresponding relationship between the positioning area and the identification area may be that one positioning area corresponds to one identification area, one positioning area corresponds to multiple identification areas, or multiple positioning areas correspond to one identification area, which is not limited herein, and the corresponding relationship may be set according to actual requirements.
Preferably, on the basis of the above embodiment, in a preferred embodiment of the present invention, the step of determining that the positioning area and the identification area have a correspondence specifically includes:
dividing the area ahead of the unmanned vehicle into at least one positioning area corresponding to different directions based on the radar data and the view angle;
dividing the unmanned vehicle driving front area into at least one identification area corresponding to different directions based on the image data and the image width;
and establishing a corresponding relation between the positioning areas and the identification areas with the same direction.
Specifically, in this embodiment, the area in front of the unmanned vehicle is divided into the positioning area and the identification area according to different directions, so that the positioning area and the identification area in the same direction are in one-to-one correspondence, and the accuracy of area correspondence is enhanced. For example, in a preferred embodiment of the present invention, the area in front of the unmanned vehicle is divided into three positioning areas based on radar data, and the angle range of the field of view of each positioning area is 60 °, which are a left positioning area, a middle positioning area, and a right positioning area. The area ahead of the unmanned vehicle is divided into three identification areas based on radar data, and each identification area is divided into a left identification area, a middle identification area and a right identification area on average according to the width of an image. The left positioning area corresponds to the left recognition area, the middle positioning area corresponds to the middle recognition area, and the right positioning area corresponds to the right recognition area. In such a way, the area is partitioned based on that the width of the picture shot by the monocular camera is the view angle of the camera and is consistent with the view angle of the radar, so that the positioning area and the identification area in the same direction can better correspond to each other, and the error of the corresponding relation is reduced. And the embodiment further reduces the error of the corresponding relation according to the installation position of the radar sensor and the monocular camera, so that the corresponding relation between the positioning area and the identification area is more accurate, and the pedestrian identification and positioning in the subsequent steps are facilitated.
Preferably, on the basis of the above embodiment, in a preferred embodiment of the present invention, the step of determining, based on the radar data, a location area where an obstacle exists includes:
based on the radar data, any two coordinate points p in the same positioning area are determinedi(θi,di) And pj(θj,dj) Clustering is carried out to obtain all barrier classes;
and determining a positioning area where the obstacle is located.
Specifically, in this embodiment, the vehicle-mounted computing device clusters any two coordinate points of the same positioning area through a clustering algorithm, if the two coordinate points can be clustered, the two coordinate points are very close to each other, and may be two coordinate points obtained by scanning on the same obstacle, so that the two coordinate points can be marked as an obstacle, and finally all positioning areas can be traversed and calculated to obtain all obstacle types. The clustering algorithm may be implemented by the prior art, and is not described herein in detail. In the embodiment, the obstacle is detected in the largest range as possible by determining the obstacle type through the two coordinate points, so that the condition of missed detection is avoided.
Preferably, on the basis of the above-described embodiments, in the inventionIn a preferred embodiment, based on the radar data, any two coordinate points p in the same positioning area are determinedi(θi,di) And pj(θj,dj) The specific steps of clustering and obtaining all the obstacle classes include:
judging any two coordinate points p of the same positioning areai(θi,di) And pj(θj,dj) Whether or not the condition | θ is satisfiedi-θjLess than or equal to 3 and | di-dj|≤0.05；
If the condition can be met, the two coordinate points can be clustered, and the two coordinate points are marked as an obstacle;
if the condition cannot be satisfied, the two coordinate points cannot be clustered.
In this embodiment, the clustering is performed by determining the angle and position relationship between two coordinate points according to radar data, without excessively complex algorithm calculation, so that the clustering process is faster and simpler.
Preferably, on the basis of the foregoing embodiment, in a preferred embodiment of the present invention, the specific step of determining, according to the acquired image data corresponding to the identification area, the identification area including the obstacle as the pedestrian target to achieve pedestrian detection and positioning includes:
acquiring image data of the identification area;
detecting the image of the obstacle according to the image data and an image analysis technology;
when the obstacle is a pedestrian, marking the identification area where the obstacle is located as a pedestrian area;
and positioning the pedestrian according to the relative position of the pedestrian area and the unmanned vehicle.
Specifically, in this embodiment, the vehicle-mounted computing device may find the identification area where the obstacle exists by determining which positioning areas have the obstacle, and then according to the corresponding relationship between the positioning areas and the identification areas, and may obtain the image data of the identification area. And detecting the pedestrian in the region by utilizing an image analysis technology, such as a classical image processing method based on HOG characteristics, and judging whether the obstacle is a pedestrian. And the pedestrian detection can be omitted in a positioning area without obstacles, so that the range of pedestrian identification is reduced, and the efficiency is improved.
In this embodiment, when the obstacle is determined to be a pedestrian, the identification area where the obstacle is located is marked as a pedestrian area, that is, the identification area has a pedestrian. And finally, the vehicle-mounted computing equipment positions the pedestrians through the relative positions of the pedestrian area and the unmanned vehicle, so that the unmanned vehicle avoids the pedestrians, and the safety of the pedestrians is guaranteed. For example, in a preferred embodiment of the present invention, the unmanned vehicle driving front area is divided into three identification areas based on radar data, each identification area is divided into a left identification area, a middle identification area and a right identification area on average according to the width of an image, the three orientations correspond to the positional relationship between the unmanned vehicle driving front area and the unmanned vehicle, and the three identification areas correspond to the three positional relationships of the left side, the right side and the right side in front of the unmanned vehicle. Thus, if a pedestrian is detected by the left recognition area, the pedestrian is positioned to the front left side of the unmanned vehicle; if the pedestrian is detected in the middle recognition area, positioning the pedestrian right in front of the unmanned vehicle; if the pedestrian is detected in the right recognition area, the pedestrian is positioned on the right side in front of the unmanned vehicle, the pedestrian is quickly positioned by the aid of the method, and the unmanned vehicle can conveniently avoid the pedestrian. The above is a preferred embodiment of the present invention, which can design the position relationship between the identification area and the vehicle autonomously according to the requirement, thereby achieving the effect of positioning the pedestrian.
Referring to fig. 2, a second embodiment of the present invention provides a pedestrian detection positioning apparatus, including:
a data acquisition unit 201 for acquiring radar data and image data of an area ahead of the unmanned vehicle;
a positioning area dividing unit 202 configured to divide an area ahead of the unmanned vehicle into a plurality of positioning areas based on the radar data;
an identification region dividing unit 203 for dividing the unmanned vehicle traveling front region into a plurality of identification regions based on the image data; wherein the positioning area and the identification area have a corresponding relationship;
a determining unit 204, configured to determine, based on the radar data, a positioning area where an obstacle exists;
a corresponding unit 205, configured to acquire an identification area corresponding to a positioning area where an obstacle exists;
and the positioning unit 206 is configured to determine, according to the acquired image data corresponding to the identification area, an identification area in which the obstacle is a pedestrian target, so as to implement pedestrian detection and positioning.
Preferably, the data acquisition unit 201 includes:
the radar data acquisition module is used for acquiring radar data of an area in front of the unmanned vehicle by using a first-line laser radar sensor; the radar data comprise a group of polar coordinate system coordinate points collected by the radar sensor, and each coordinate point consists of an angle and a distance between the coordinate point and the unmanned vehicle;
and the image data acquisition module is used for acquiring the image data of the area in front of the unmanned vehicle by using the monocular camera.
Preferably, the correspondence relationship between the positioning area and the identification area specifically includes:
dividing the area ahead of the unmanned vehicle into at least one positioning area corresponding to different directions based on the radar data and the view angle;
dividing the unmanned vehicle driving front area into at least one identification area corresponding to different directions based on the image data and the image width;
and establishing a corresponding relation between the positioning areas and the identification areas with the same direction.
Preferably, the obstacle determination unit 204 includes:
a clustering module for clustering any two coordinate points p in the same positioning region based on the radar datai(θi,di) And pj(θj,dj) Clustering is carried out to obtain all barrier classes;
and the area determining module is used for determining a positioning area where the obstacle is located.
Preferably, the clustering module is configured to:
judging any two coordinate points p of the same positioning areai(θi,di) And pj(θj,dj) Whether or not the condition | θ is satisfiedi-θjLess than or equal to 3 and | di-dj|≤0.05；
If the condition can be met, the two coordinate points can be clustered, and the two coordinate points are marked as an obstacle;
if the condition cannot be satisfied, the two coordinate points cannot be clustered.
Preferably, the positioning unit 206 includes:
the acquisition module is used for acquiring the image data of the identification area;
the detection module is used for carrying out image detection on the obstacle according to the image data and an image analysis technology;
the marking module is used for marking the identification area where the obstacle is located as a pedestrian area when the obstacle is a pedestrian;
and the positioning module is used for positioning the pedestrian according to the relative position of the pedestrian area and the unmanned vehicle.
The third embodiment of the present invention also provides an in-vehicle computing device, which includes a memory, a processor, and a computer program stored on the memory and operable on the processor, and when the processor executes the program, the pedestrian detection positioning method of the first embodiment is implemented.
Embodiments of the present invention also provide a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the steps of the pedestrian detection positioning method of the first embodiment.
Illustratively, the computer program of embodiments of the present invention may be partitioned into one or more modules that are stored in the memory and executed by the processor to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of performing certain functions, the instruction segments being used to describe the execution of the computer program in the implementation server device. For example, the device described in the second embodiment of the present invention.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an APPlication Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor is a control center of the pedestrian detection and positioning method, and various interfaces and lines are used to connect the whole parts for implementing the pedestrian detection and positioning method.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the pedestrian detection positioning method by running or executing the computer program and/or module stored in the memory and calling data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, a text conversion function, etc.), and the like; the storage data area may store data (such as audio data, text message data, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein, the module for realizing the service device can be stored in a computer readable storage medium if it is realized in the form of software functional unit and sold or used as a stand-alone product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, and software distribution medium, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A pedestrian detection positioning method is characterized by comprising the following steps:
acquiring radar data and image data of an area in front of the unmanned vehicle;
dividing the area in front of the unmanned vehicle into a plurality of positioning areas based on the radar data;
dividing the unmanned vehicle driving front area into a plurality of identification areas based on the image data; the positioning area and the identification area have a corresponding relation;
judging a positioning area with an obstacle based on the radar data;
acquiring an identification area corresponding to a positioning area with an obstacle;
determining the identification area containing the obstacle as a pedestrian target according to the acquired image data corresponding to the identification area so as to realize pedestrian detection and positioning;
wherein the content of the first and second substances,
the correspondence relationship between the positioning area and the identification area specifically includes:
dividing the area ahead of the unmanned vehicle into at least one positioning area corresponding to different directions based on the radar data and the view angle;
dividing the unmanned vehicle driving front area into at least one identification area corresponding to different directions based on the image data and the image width;
and establishing a corresponding relation between the positioning areas and the identification areas with the same direction.
2. The pedestrian detection and positioning method according to claim 1, wherein the step of acquiring radar data and image data of an area ahead of the unmanned vehicle comprises:
acquiring radar data of an area in front of the unmanned vehicle by using a first-line laser radar sensor; the radar data comprise a group of polar coordinate system coordinate points acquired by the radar sensor, and each coordinate point consists of an angle and a distance between the coordinate point and an unmanned vehicle;
and acquiring image data of the area in front of the unmanned vehicle by using a monocular camera.
3. The pedestrian detection positioning method according to claim 2, wherein the step of determining a positioning area where an obstacle exists based on the radar data includes:
based on the radar data, any two coordinate points p in the same positioning area are subjected to positioningi(θi,di) And pj(θj,dj) Clustering to obtain all barrier classes;
and determining a positioning area where the obstacle is located.
4. The pedestrian detection positioning method according to claim 3, characterized in that any two coordinate points p of the same positioning area are subjected to positioning based on the radar datai(θi,di) And pj(θj,dj) The specific steps of clustering and obtaining all the obstacle classes include:
judging any two coordinate points p of the same positioning areai(θi,di) And pj(θj,dj) Whether or not the condition | θ is satisfiedi-θjLess than or equal to 3 and | di-dj|≤0.05；
If the condition can be met, the two coordinate points can be clustered, and the two coordinate points are marked as an obstacle;
if the condition cannot be satisfied, the two coordinate points cannot be clustered.
5. A pedestrian detection positioning device, comprising:
the data acquisition unit is used for acquiring radar data and image data of an area in front of the unmanned vehicle;
a positioning area dividing unit configured to divide an area ahead of the unmanned vehicle into a plurality of positioning areas based on the radar data;
an identification area dividing unit configured to divide the area ahead of the unmanned vehicle into a plurality of identification areas based on the image data; the positioning area and the identification area have a corresponding relation;
a determination unit configured to determine a location area where an obstacle exists based on the radar data;
the corresponding unit is used for acquiring an identification area corresponding to the positioning area with the obstacle;
the positioning unit is used for determining the identification area containing the obstacle as the pedestrian target according to the acquired image data corresponding to the identification area so as to realize pedestrian detection and positioning;
wherein the content of the first and second substances,
the correspondence relationship between the positioning area and the identification area specifically includes:
dividing the area ahead of the unmanned vehicle into at least one positioning area corresponding to different directions based on the radar data and the view angle;
dividing the unmanned vehicle driving front area into at least one identification area corresponding to different directions based on the image data and the image width;
and establishing a corresponding relation between the positioning areas and the identification areas with the same direction.
6. The pedestrian detection positioning apparatus according to claim 5, wherein the data acquisition unit includes:
the radar data acquisition module is used for acquiring radar data of an area in front of the unmanned vehicle by using a first-line laser radar sensor; the radar data comprise a group of polar coordinate system coordinate points acquired by the radar sensor, and each coordinate point consists of an angle and a distance between the coordinate point and an unmanned vehicle;
and the image data acquisition module is used for acquiring the image data of the area in front of the unmanned vehicle by using the monocular camera.
7. The pedestrian detection positioning device according to claim 6, wherein the determination unit includes:
a clustering module for clustering any two coordinate points p in the same positioning region based on the radar datai(θi,di) And pj(θj,dj) Clustering to obtain all barrier classes;
and the area determining module is used for determining a positioning area where the obstacle is located.
8. An on-vehicle computing device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor implements the pedestrian detection and positioning method according to claims 1 to 4 when executing the program.
9. A computer-readable storage medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the steps of the pedestrian detection and positioning method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910252786.9A CN110008891B (en) | 2019-03-29 | 2019-03-29 | Pedestrian detection positioning method and device, vehicle-mounted computing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910252786.9A CN110008891B (en) | 2019-03-29 | 2019-03-29 | Pedestrian detection positioning method and device, vehicle-mounted computing equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110008891A CN110008891A (en) | 2019-07-12 |
| CN110008891B true CN110008891B (en) | 2022-07-08 |
Family
ID=67169039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910252786.9A Active CN110008891B (en) | 2019-03-29 | 2019-03-29 | Pedestrian detection positioning method and device, vehicle-mounted computing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110008891B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114866577A (en) * | 2019-07-19 | 2022-08-05 | 西安艾润物联网技术服务有限责任公司 | ETC-based vehicle fee payment method and computer storage medium |
| CN110580046B (en) * | 2019-09-12 | 2022-08-16 | 吉利汽车研究院（宁波）有限公司 | Control method and system for unmanned sightseeing vehicle |
| CN111178215B (en) * | 2019-12-23 | 2024-03-08 | 深圳成谷科技有限公司 | Sensor data fusion processing method and device |
| CN111144315A (en) * | 2019-12-27 | 2020-05-12 | 北京三快在线科技有限公司 | Target detection method and device, electronic equipment and readable storage medium |
| CN114842441A (en) * | 2022-06-30 | 2022-08-02 | 小米汽车科技有限公司 | Model performance determination method and device, electronic device and readable storage medium |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102508246B (en) * | 2011-10-13 | 2013-04-17 | 吉林大学 | Method for detecting and tracking obstacles in front of vehicle |
| FR3014229B1 (en) * | 2013-12-02 | 2017-02-03 | Commissariat Energie Atomique | RECOGNITION OF SHAPES BY IMAGE CORRECTION |
| CN104573646B (en) * | 2014-12-29 | 2017-12-12 | 长安大学 | Chinese herbaceous peony pedestrian detection method and system based on laser radar and binocular camera |
| KR102366402B1 (en) * | 2015-05-21 | 2022-02-22 | 엘지전자 주식회사 | Driver assistance apparatus and control method for the same |
| US10145951B2 (en) * | 2016-03-30 | 2018-12-04 | Aptiv Technologies Limited | Object detection using radar and vision defined image detection zone |
| TW201832710A (en) * | 2017-03-14 | 2018-09-16 | 聯潤科技股份有限公司 | Partition-cleaning method of self-propelled cleaning device and self-propelled cleaning device using the method capable of increasing the cleaning efficiency of the self-propelled cleaning device |
| CN109426264A (en) * | 2017-08-30 | 2019-03-05 | 苏州宝时得电动工具有限公司 | From mobile device and its control method of movement routine |
| CN107991671A (en) * | 2017-11-23 | 2018-05-04 | 浙江东车智能科技有限公司 | A kind of method based on radar data and vision signal fusion recognition risk object |
| CN109100741B (en) * | 2018-06-11 | 2020-11-20 | 长安大学 | Target detection method based on 3D laser radar and image data |
| CN109443369A (en) * | 2018-08-20 | 2019-03-08 | 北京主线科技有限公司 | The method for constructing sound state grating map using laser radar and visual sensor |
| CN109271944B (en) * | 2018-09-27 | 2021-03-12 | 百度在线网络技术（北京）有限公司 | Obstacle detection method, obstacle detection device, electronic apparatus, vehicle, and storage medium |
-
2019
- 2019-03-29 CN CN201910252786.9A patent/CN110008891B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110008891A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008891B (en) | Pedestrian detection positioning method and device, vehicle-mounted computing equipment and storage medium | |
| US10628690B2 (en) | Systems and methods for automated detection of trailer properties | |
| CN106991389B (en) | Device and method for determining road edge | |
| CN110796007B (en) | Scene recognition method and computing device | |
| US20200218908A1 (en) | Real-time simultaneous detection of lane marker and raised pavement marker for optimal estimation of multiple lane boundaries | |
| CN110632617B (en) | Laser radar point cloud data processing method and device | |
| DE112018004507T5 (en) | INFORMATION PROCESSING DEVICE, MOTION DEVICE AND METHOD AND PROGRAM | |
| CN110858405A (en) | Attitude estimation method, device and system of vehicle-mounted camera and electronic equipment | |
| CN110696826B (en) | Method and device for controlling a vehicle | |
| CN108291814A (en) | For putting the method that motor vehicle is precisely located, equipment, management map device and system in the environment | |
| CN111754798A (en) | Method for realizing detection of vehicle and surrounding obstacles by fusing roadside laser radar and video | |
| CN108399360B (en) | Continuous obstacle detection method, device and terminal | |
| CN113435237A (en) | Object state recognition device, recognition method, recognition program, and control device | |
| CN113255444A (en) | Training method of image recognition model, image recognition method and device | |
| CN111325187A (en) | Lane position identification method and device | |
| CN114550142A (en) | Parking space detection method based on fusion of 4D millimeter wave radar and image recognition | |
| CN103577790B (en) | road turn type detection method and device | |
| CN108693517B (en) | Vehicle positioning method and device and radar | |
| CN112183206B (en) | Traffic participant positioning method and system based on road side monocular camera | |
| CN110727269B (en) | Vehicle control method and related product | |
| CN107452230B (en) | Obstacle detection method and device, terminal equipment and storage medium | |
| CN116635919A (en) | Object tracking device and object tracking method | |
| CN112861657A (en) | Unmanned vehicle calling and parking method, terminal equipment and storage medium | |
| CN115601435B (en) | Vehicle attitude detection method, device, vehicle and storage medium | |
| CN116206483B (en) | Parking position determining method, electronic device and computer readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |