CN113049001B - Evaluation system and method for crowdsourcing map construction - Google Patents
Evaluation system and method for crowdsourcing map construction Download PDFInfo
- Publication number
- CN113049001B CN113049001B CN201911370416.1A CN201911370416A CN113049001B CN 113049001 B CN113049001 B CN 113049001B CN 201911370416 A CN201911370416 A CN 201911370416A CN 113049001 B CN113049001 B CN 113049001B
- Authority
- CN
- China
- Prior art keywords
- imu
- synchronous
- detected
- data
- gps information
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 55
- 238000011156 evaluation Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000001360 synchronised effect Effects 0.000 claims abstract description 109
- 230000005540 biological transmission Effects 0.000 claims description 35
- 238000013500 data storage Methods 0.000 claims description 9
- 238000012358 sourcing Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 238000012795 verification Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000010835 comparative analysis Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000013078 crystal Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C25/00—Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C25/00—Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass
- G01C25/005—Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass initial alignment, calibration or starting-up of inertial devices
Abstract
The embodiment of the invention discloses an evaluation system and method for crowdsourcing map construction. The high-precision consumption level IMU and the high-precision GPS, the consumption level IMU to be evaluated and the consumption level GPS can be integrated on one device, high-precision map construction and consumption level map construction are simultaneously carried out, then the comparison analysis is carried out on the effects of the two maps after construction, whether the consumption level IMU, the consumption level GPS and a map construction algorithm meet the requirements or not can be obtained, and compared with IMU inertial navigation, the consumption level IMU is low in price, so that the evaluation cost can be reduced. And two groups of data are collected simultaneously through one set of equipment, all the data are synchronized through one time source, and the comparison and verification of a later algorithm are facilitated. Compared with inertial navigation of the IMU, the consumption-level IMU is small in size, so that the built IMU evaluation system is compact in structure and can be used for large-scale collection. The high-precision consumption-level IMU is embedded into the camera in a modular mode, and other IMU sensors are convenient to replace in the later period for comparison.
Description
Technical Field
The invention relates to the technical field of map construction, in particular to an evaluation system and method for crowdsourcing map construction.
Background
In the running process of the unmanned vehicle, the unmanned vehicle needs to detect lane lines, pedestrians, other vehicles and the like on the road, so that the map can be constructed according to the detection result, and the position of the vehicle is determined according to the constructed map. In particular, different sensors, such as IMU (Inertial measurement unit ) and GPS (Global Positioning System, global positioning system), can be installed in the vehicle and mapped by means of a mapping algorithm.
IMUs can be classified into IMU inertial navigation and consumer level IMUs. IMU inertial navigation is a high-precision sensor, mainly used for establishing basic data with higher precision, but has high price and large volume. The consumption-level IMU has lower price and small volume.
In general, a consumer IMU is usually installed in a vehicle, data is collected through the consumer IMU and a consumer GPS, and map construction is performed through a map construction algorithm. The accuracy of the consumption level IMU, the consumption level GPS, and the map construction algorithm all affect the accuracy of the crowd-sourced map construction result. The known evaluation method for crowdsourcing map construction mainly detects the precision of each device and algorithm by installing IMU inertial navigation high-precision devices on a vehicle, but the cost of the method is higher. Therefore, in order to reduce the cost of evaluation, an evaluation method is demanded.
Disclosure of Invention
The invention provides an evaluation system and an evaluation method for crowdsourcing map construction, which are used for reducing the evaluation cost. The specific technical scheme is as follows.
In a first aspect, an embodiment of the present invention provides an evaluation system for crowd sourcing map construction, the system including: a camera, a consumer-level global positioning system GPS, a reference GPS, a synchronization device, an online computing device, a data acquisition device, and an offline computing device; the camera includes: the system comprises a photosensitive element, a consumption level inertial measurement unit IMU to be measured and a reference consumption level IMU; the precision of the consumption level IMU to be detected is smaller than that of the reference consumption level IMU; the precision of the consumer grade GPS is smaller than that of the reference GPS;
the photosensitive element is used for collecting a target image of the surrounding environment of the unmanned vehicle and sending the target image to the synchronous equipment;
the consumption-level IMU to be detected is used for collecting IMU data to be detected and sending the IMU data to be detected to the synchronous equipment;
the consumption-level GPS is used for collecting GPS information to be detected and sending the GPS information to be detected to the synchronous equipment;
the reference consumption level IMU is used for acquiring reference IMU data and sending the reference IMU data to the synchronous equipment;
the synchronization device is configured to synchronize the target image, the IMU data to be detected, the GPS information to be detected, and the reference IMU data to obtain a synchronous target image, synchronous IMU data to be detected, synchronous GPS information to be detected, and synchronous reference IMU data; the synchronous target image, the synchronous IMU data to be detected and the synchronous GPS information to be detected are sent to the online computing equipment, and the synchronous target image and the synchronous reference IMU data are sent to the data acquisition equipment;
the on-line computing device is used for computing a map result to be detected in real time according to the synchronous target image, the synchronous IMU data to be detected and the synchronous GPS information to be detected;
the reference GPS is used for acquiring reference GPS information and transmitting the reference GPS information to the data acquisition equipment;
the off-line computing device is used for acquiring the synchronous target image, the synchronous reference IMU data and the reference GPS information from the data acquisition device and acquiring the map result to be detected from the on-line computing device; and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be detected with the reference map result to obtain an evaluation result of crowdsourcing map construction.
Optionally, the method further comprises: the cloud storage device comprises a data sending device and a cloud storage device;
the online computing equipment is also used for sending the map result to be detected to the data sending equipment;
the data sending device is used for sending the map result to be detected to the cloud storage device;
the offline computing device is specifically configured to obtain the synchronization target image, the synchronization reference IMU data, and the reference GPS information from the data acquisition device, and obtain the map result to be detected from the cloud storage device; and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be tested with the reference map result to obtain an evaluation result of the consumption-level IMU to be tested.
Optionally, the data sending device is specifically configured to detect whether the current network transmission speed is greater than a preset speed threshold, and send the map result to be tested to the cloud storage device when the current network transmission speed is greater than the preset speed threshold; and when the current network transmission speed is not greater than the preset speed threshold, caching the map result to be tested to the local, periodically detecting whether the current network transmission speed is greater than the preset speed threshold, and when the current network transmission speed is greater than the preset speed threshold, sending the map result to be tested to the cloud storage device.
Optionally, the method further comprises: a data storage device;
the data storage device is used for receiving the synchronous target image, the synchronous reference IMU data and the reference GPS information which are sent by the data acquisition device; storing the synchronous target image, the synchronous reference IMU data and the reference GPS information to a magnetic disk;
the offline computing device is specifically configured to obtain the synchronization target image, the synchronization reference IMU data, and the reference GPS information from the disk, and obtain the map result to be tested from the cloud storage device; and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be tested with the reference map result to obtain an evaluation result of the consumption-level IMU to be tested.
Optionally, the data storage device is specifically configured to encrypt the synchronization target image, the synchronization reference IMU data, and the reference GPS information, and store the encrypted synchronization target image, the encrypted synchronization reference IMU data, and the encrypted reference GPS information to a disk.
In a second aspect, an embodiment of the present invention provides an evaluation method for crowd-sourced map construction, where the method is applied to an evaluation system for crowd-sourced map construction, and the method includes:
collecting target images of surrounding environments of the unmanned vehicle, IMU data to be detected, GPS information to be detected, reference IMU data and reference GPS information; the method comprises the steps that IMU data to be detected are collected through a consumption level IMU to be detected of the system, reference IMU data are collected through a reference consumption level IMU of the system, GPS information to be detected is collected through a global positioning system to be detected of the system, reference GPS information is collected through a reference GPS of the system, and the accuracy of the consumption level IMU to be detected is smaller than that of the reference consumption level IMU; the precision of the consumer grade GPS is smaller than that of the reference GPS;
synchronizing the target image, the IMU data to be detected, the GPS information to be detected and the reference IMU data to obtain a synchronous target image, synchronous IMU data to be detected, synchronous GPS information to be detected and synchronous reference IMU data;
calculating a map result to be measured in real time according to the synchronous target image, the synchronous IMU data to be measured and the synchronous GPS information to be measured;
and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be detected with the reference map result to obtain an evaluation result of crowdsourcing map construction.
Optionally, the method further comprises:
and sending the map result to be measured to cloud storage equipment.
Optionally, the step of sending the map to be measured result to a cloud storage device includes:
detecting whether the current network transmission speed is greater than a preset speed threshold value;
when the current network transmission speed is greater than a preset speed threshold, sending the map result to be tested to the cloud storage equipment;
and when the current network transmission speed is not greater than the preset speed threshold, caching the map result to be tested to the local, periodically detecting whether the current network transmission speed is greater than the preset speed threshold, and when the current network transmission speed is greater than the preset speed threshold, sending the map result to be tested to the cloud storage device.
Optionally, the method further comprises:
and storing the synchronous target image, the synchronous reference IMU data and the reference GPS information to a magnetic disk.
Optionally, the step of storing the synchronization target image, the synchronization reference IMU data, and the reference GPS information to a disk includes:
and encrypting the synchronous target image, the synchronous reference IMU data and the reference GPS information, and storing the encrypted synchronous target image, the synchronous reference IMU data and the encrypted reference GPS information into a magnetic disk.
As can be seen from the above, the evaluation system and the method for crowdsourcing map construction provided by the embodiments of the present invention can integrate a high-precision consumption level IMU and a high-precision GPS, and a consumption level IMU and a consumption level GPS to be evaluated on one device, and perform high-precision map construction and consumption level map construction simultaneously, and then perform comparative analysis on the effects of the two maps, so as to obtain whether the consumption level IMU, the consumption level GPS, and the map construction algorithm meet the requirements, and compared with IMU inertial navigation, the consumption level IMU has a lower price, thereby being capable of reducing the evaluation cost. And two groups of data are collected simultaneously through one set of equipment, all the data are synchronized through one time source, and the comparison and verification of a later algorithm are facilitated. Compared with inertial navigation of the IMU, the consumption-level IMU is small in size, so that the built IMU evaluation system is compact in structure and can be used for large-scale collection. The high-precision consumption-level IMU is embedded into the camera in a modular mode, and other IMU sensors are convenient to replace in the later period for comparison. Of course, it is not necessary for any one product or method of practicing the invention to achieve all of the advantages set forth above at the same time.
The innovation points of the embodiment of the invention include:
1. and integrating the high-precision consumption level IMU and the high-precision GPS, the consumption level IMU to be evaluated and the consumption level GPS on one device, simultaneously carrying out high-precision map construction and consumption level map construction, and then carrying out comparison analysis on the effects of the two maps, so as to obtain whether the consumption level IMU, the consumption level GPS and a map construction algorithm meet the requirements or not. And two groups of data are collected simultaneously through one set of equipment, all the data are synchronized through one time source, and the comparison and verification of a later algorithm are facilitated. Compared with inertial navigation of the IMU, the consumption-level IMU is small in size, so that the built IMU evaluation system is compact in structure and can be used for large-scale collection. The high-precision consumption-level IMU is embedded into the camera in a modular mode, and other IMU sensors are convenient to replace in the later period for comparison.
2. The map result to be measured is sent to the cloud storage equipment for storage, so that the resource occupation of the online computing equipment can be reduced, and the computing capacity of the online computing equipment is improved; and the safety of the map result to be detected can be improved by storing the map result to the cloud storage device.
3. The map result to be measured is cached to the local when the signal is bad, and is sent to the cloud storage equipment when the signal is good, so that the conditions of data loss and the like caused by poor signal can be avoided, and the safety of the map result transmission to be measured is improved.
4. The data used for constructing the reference map result is stored in the disk, so that the resource occupation of the offline computing equipment can be reduced, and the computing capacity of the offline computing equipment is improved; in addition, the data can be stored in the disk, so that the safety of the data can be improved.
5. The data is stored after being encrypted, so that the safety of the data can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is apparent that the drawings in the following description are only some embodiments of the invention. Other figures may be derived from these figures without inventive effort for a person of ordinary skill in the art.
Fig. 1 is a schematic structural diagram of an evaluation system for crowd-sourced map construction according to an embodiment of the present invention;
fig. 2 is a schematic diagram of another structure of an evaluation system for crowd-sourced map construction according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another structure of an evaluation system for crowd-sourced map construction according to an embodiment of the present invention;
fig. 4 is a schematic flow chart of an evaluation method for crowd-sourced map construction according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. A process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed but may alternatively include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses an evaluation system and an evaluation method for crowdsourcing map construction, which can reduce the evaluation cost. The following describes embodiments of the present invention in detail.
As shown in fig. 1, an evaluation system for crowd-sourced map construction provided in an embodiment of the present invention may include: camera 110, consumer-grade GPS120, reference GPS130, synchronization device 140, online computing device 150, data acquisition device 160, and offline computing device 170. Wherein, the camera 110 may include: a photosensitive element 111, a to-be-measured consumption level IMU112, and a reference consumption level IMU113; the accuracy of the to-be-measured consumption level IMU112 is less than the accuracy of the reference consumption level IMU113; the accuracy of the consumer grade GPS120 is less than the accuracy of the reference GPS130.
The IMU112 of the consumer level to be tested is the IMU to be evaluated, which is the IMU of the consumer level. The reference consumption level IMU113 is also a consumption level IMU, and the accuracy of the reference consumption level IMU113 is higher than the to-be-measured consumption level IMU112. The consumption-level IMU has the characteristics of low cost and small volume, so that the cost of IMU evaluation can be reduced, and the method is suitable for large-scale acquisition. The consumer grade GPS120 is a GPS that needs to be evaluated, and has a lower accuracy than the reference GPS130.
The consumption level IMU112 and the reference consumption level IMU113 to be detected are integrated in the camera 110, the consumption level GPS120 and the reference GPS130 are used for simultaneously acquiring data through the sensors, and the reference map is constructed according to the acquired data of the reference consumption level IMU113 and the reference GPS130, so that the precision is higher than that of the map to be detected calculated in real time according to the acquired data of the consumption level IMU112 and the consumption level GPS120, and the precision of the sensors and the map construction algorithm can be determined by comparing the map to be detected with the reference map.
The photosensitive element 111 is used for acquiring a target image of the surrounding environment of the unmanned vehicle and transmitting the target image to the synchronization device 140. The consumption level IMU112 to be tested is configured to collect IMU data to be tested and send the IMU data to be tested to the synchronization device 140. The consumer-level GPS120 is configured to collect GPS information to be measured and send the GPS information to be measured to the synchronization device 140. The reference consumer-level IMU113 is configured to collect reference IMU data and send the reference IMU data to the synchronization device 140. The reference GPS130 is used for acquiring reference GPS information and transmitting the reference GPS information to the data acquisition device 160.
The IMU data to be measured is the current acceleration, direction, pitch angle, etc. of the unmanned vehicle collected by the consumer-level IMU112 to be measured. The reference IMU data is the current acceleration, direction, pitch angle, etc. of the unmanned vehicle acquired by the reference consumer level IMU 113. The GPS information to be measured is the three-dimensional coordinates of the unmanned vehicle currently in the preset coordinate system, as well as speed, direction, elevation data, etc. acquired by the consumer GPS 120. The reference GPS information is the three-dimensional coordinates of the unmanned vehicle currently in the preset coordinate system, and the speed, direction, elevation data, etc. acquired by the reference GPS130. The preset coordinate system may be a vehicle coordinate system, a world coordinate system, or the like, which is not limited in the embodiment of the present invention.
The photosensitive element 111, the consumption level IMU112 to be measured, the consumption level GPS120, the reference consumption level IMU113, and the reference GPS130 may be time-synchronized in advance. Also, the photosensitive element 111, the to-be-measured consumption level IMU112, the consumption level GPS120, the reference consumption level IMU113, and the reference GPS130 may periodically perform data acquisition according to the same period (e.g., 1 ms, 2 ms, 5 ms, etc.).
That is, according to the design concept, the photosensitive element 111, the consumption level IMU112 to be measured, the consumption level GPS120, the reference consumption level IMU113, and the reference GPS130 can perform data collection at the same time in each period. However, in practical applications, due to differences of crystal oscillators of the devices, the photosensitive elements 111, the IMU112, the GPS120, the IMU113, and the GPS130 may not be completely synchronized. This will affect the accuracy of the mapping results and thus the accuracy of the IMU assessment.
In the embodiment of the invention, in order to ensure the evaluation accuracy of the IMU, the synchronization device 140 may synchronize the target image, the IMU data to be tested, the GPS information to be tested, and the reference IMU data to obtain the synchronization target image, the IMU data to be tested, the GPS information to be tested, and the reference IMU data. The reference GPS information collected by the reference GPS130 itself carries a time parameter and thus does not need to be synchronized by the synchronization device 140.
In an embodiment of the present invention, to ensure the computation rate, the map construction may be performed based on the online computing device 150 and the offline computing device 170, respectively. Also, to ensure the computing power of the offline computing device 170, to reduce the resource occupation of the offline computing device 170, data may be transmitted to the offline computing device 170 through the data acquisition device 160.
Specifically, the synchronization device 140 may send the synchronization target image, the IMU data to be detected in synchronization, and the GPS information to be detected in synchronization to the online computing device 150, so as to calculate the map result to be detected in real time through the online computing device; the synchronization target image and the synchronization reference IMU data may be sent to the data acquisition device 160 for transmission of the data by the data acquisition device 160 to the offline computing device 170, and the offline computing device 170 may construct the reference map results.
The online computing device 150 is configured to calculate a map result to be measured in real time according to the synchronization target image, the synchronization IMU data to be measured, and the synchronization GPS information to be measured. Specifically, the online computing device 150 may calculate the map result to be measured in real time according to any known map construction algorithm, which is not limited in the embodiment of the present invention.
The offline computing device 170 is configured to obtain the synchronization target image, the synchronization reference IMU data, and the reference GPS information from the data acquisition device 160, and obtain the map result to be measured from the online computing device 150. And constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information. Specifically, the offline computing device 170 may construct a reference map result according to any known map construction algorithm, which is not limited in this embodiment of the present invention.
After obtaining the reference map result, the offline computing device 170 may compare the map result to be tested with the reference map result to obtain an evaluation result of crowd-sourced map construction. For example, the similarity between the map result to be measured and the reference map result can be calculated and used as the evaluation result of crowdsourcing map construction.
From the above, it can be seen that the IMU evaluation system for an unmanned vehicle provided by the embodiment of the invention can integrate a high-precision consumption level IMU and a high-precision GPS, and a consumption level IMU and a consumption level GPS to be evaluated on one device, and simultaneously perform high-precision map construction and consumption level map construction, and then perform comparative analysis on the effects of the two maps, so as to obtain whether the consumption level IMU, the consumption level GPS and a map construction algorithm meet the requirements, and compared with IMU inertial navigation, the consumption level IMU has lower price, thereby being capable of reducing the evaluation cost. And two groups of data are collected simultaneously through one set of equipment, all the data are synchronized through one time source, and the comparison and verification of a later algorithm are facilitated. Compared with inertial navigation of the IMU, the consumption-level IMU is small in size, so that the built IMU evaluation system is compact in structure and can be used for large-scale collection. The high-precision consumption-level IMU is embedded into the camera in a modular mode, and other IMU sensors are convenient to replace in the later period for comparison.
It will be appreciated that how much of the resources stored in the online computing device 150 will affect its computing power. For example, when fewer resources are stored in the online computing device 150, its computing power is greater; when more resources are stored in the online computing device 150, its computing power is weaker.
As an implementation manner of the embodiment of the present invention, as shown in fig. 2, the system may further include: a data transmission device 180 and a cloud storage device 190.
The online computing device 150 may send the map result to be measured to the data sending device 180 after calculating the map result to be measured in real time. The data transmitting device 180 may transmit the map result to be measured to the cloud storage device 190 to store the map result to be measured to the cloud storage device 190.
The cloud storage device 190 may be, for example, a cloud storage device such as a hundred degree cloud, which is not limited in the embodiment of the present invention.
Accordingly, the offline computing device 170 may acquire the synchronization target image, the synchronization reference IMU data, and the reference GPS information from the data acquisition device 160, and acquire the map result to be measured from the cloud storage device 190; and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be tested with the reference map result to obtain an evaluation result of crowdsourcing map construction.
The map result to be measured is sent to the cloud storage device 190 for storage, so that the resource occupation of the online computing device 150 can be reduced, and the computing capacity of the online computing device 150 can be improved; and, the security of the map result to be measured can be improved by storing the map result in the cloud storage device 190.
In one implementation, to ensure the security of data transmission, the data sending device 180 may detect whether the current network transmission speed is greater than a preset speed threshold, and send the map result to be tested to the cloud storage device 190 when the current network transmission speed is greater than the preset speed threshold; and when the current network transmission speed is not greater than the preset speed threshold, caching the map result to be tested to the local, periodically detecting whether the current network transmission speed is greater than the preset speed threshold, and when the current network transmission speed is greater than the preset speed threshold, sending the map result to be tested to the cloud storage device 190.
The map result to be measured is cached to the local when the signal is bad, and is sent to the cloud storage device 190 when the signal is good, so that the situation of data loss and the like caused by poor signal can be avoided, and the safety of the map result transmission to be measured is improved.
As an implementation manner of the embodiment of the present invention, as shown in fig. 3, the system may further include: a data storage device 100.
The data storage device 100 may receive the synchronization target image, the synchronization reference IMU data, and the reference GPS information transmitted from the data acquisition device 160; and storing the synchronization target image, the synchronization reference IMU data, and the reference GPS information to the disk.
Accordingly, the offline computing device 170 may acquire the synchronization target image, the synchronization reference IMU data, and the reference GPS information from the disk, and acquire the map result to be measured from the cloud storage device 190; and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be tested with the reference map result to obtain an evaluation result of crowdsourcing map construction.
Storing the data used to construct the reference map results to disk can reduce the resource occupation of the offline computing device 170 and improve the computing capacity of the offline computing device 170; in addition, the data can be stored in the disk, so that the safety of the data can be improved.
In one implementation, the data storage device 100 may encrypt the synchronization target image, the synchronization reference IMU data, and the reference GPS information and store the encrypted synchronization target image, the synchronization reference IMU data, and the reference GPS information to the disk. The data is stored after being encrypted, so that the safety of the data can be improved.
Fig. 4 is a flowchart of an evaluation method for crowd-sourced map construction, which is provided by an embodiment of the present invention, and the method is applied to an evaluation system for crowd-sourced map construction, and includes the following steps.
S410: collecting target images of surrounding environments of the unmanned vehicle, IMU data to be detected, GPS information to be detected, reference IMU data and reference GPS information; the method comprises the steps that IMU data to be measured are collected through a consumption level IMU to be measured of a system, reference IMU data are collected through a reference consumption level IMU of the system, GPS information to be measured is collected through a consumption level GPS of the system, reference GPS information is collected through a reference GPS of the system, and accuracy of the consumption level IMU to be measured is smaller than that of the reference consumption level IMU; the accuracy of the consumer grade GPS is less than the accuracy of the reference GPS.
S420: and synchronizing the target image, the IMU data to be detected, the GPS information to be detected and the reference IMU data to obtain a synchronous target image, the IMU data to be detected, the GPS information to be detected and the reference IMU data.
S430: and calculating a map result to be measured in real time according to the synchronous target image, the synchronous IMU data to be measured and the synchronous GPS information to be measured.
S440: and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be tested with the reference map result to obtain an evaluation result of crowdsourcing map construction.
From the above, it can be seen that the IMU evaluation method for an unmanned vehicle provided by the embodiment of the invention can integrate a high-precision consumption level IMU and a high-precision GPS, and a consumption level IMU and a consumption level GPS to be evaluated on one device, and simultaneously perform high-precision map construction and consumption level map construction, and then perform comparative analysis on the effects of the two maps, so as to obtain whether the consumption level IMU, the consumption level GPS and a map construction algorithm meet the requirements, and compared with IMU inertial navigation, the consumption level IMU has lower price, thereby being capable of reducing the evaluation cost. And two groups of data are collected simultaneously through one set of equipment, all the data are synchronized through one time source, and the comparison and verification of a later algorithm are facilitated. Compared with inertial navigation of the IMU, the consumption-level IMU is small in size, so that the built IMU evaluation system is compact in structure and can be used for large-scale collection. The high-precision consumption-level IMU is embedded into the camera in a modular mode, and other IMU sensors are convenient to replace in the later period for comparison.
As an implementation of the embodiment of the present invention, the method further includes:
and sending the map result to be measured to cloud storage equipment.
As an implementation manner of the embodiment of the present invention, the step of sending the map result to be measured to the cloud storage device includes:
detecting whether the current network transmission speed is greater than a preset speed threshold value;
when the current network transmission speed is greater than a preset speed threshold, sending a map result to be tested to cloud storage equipment;
when the current network transmission speed is not greater than a preset speed threshold, caching the map result to be tested to the local, periodically detecting whether the current network transmission speed is greater than the preset speed threshold, and when the current network transmission speed is greater than the preset speed threshold, sending the map result to be tested to the cloud storage device.
As an implementation of the embodiment of the present invention, the method further includes:
the synchronization target image, the synchronization reference IMU data, and the reference GPS information are stored to the disk.
As one implementation of the embodiment of the present invention, the step of storing the synchronization target image, the synchronization reference IMU data, and the reference GPS information to the disk includes:
and encrypting the synchronous target image, the synchronous reference IMU data and the reference GPS information, and storing the encrypted synchronous target image, the synchronous reference IMU data and the reference GPS information into a magnetic disk.
The method embodiment corresponds to the system embodiment, and has the same technical effects as the system embodiment, and the specific description refers to the system embodiment. The method embodiments are based on system embodiments, and specific descriptions may be referred to in the system embodiments, which are not described herein.
Those of ordinary skill in the art will appreciate that: the drawing is a schematic diagram of one embodiment and the modules or flows in the drawing are not necessarily required to practice the invention.
Those of ordinary skill in the art will appreciate that: the devices in the system in the embodiments may be distributed in the devices in the embodiments according to the embodiment descriptions, or may be located in one or more devices different from the present embodiment with corresponding changes. The devices of the foregoing embodiments may be combined into one device, or may be further split into multiple sub-devices.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An evaluation system for crowd sourcing map construction, the system comprising: a camera, a consumer-level global positioning system GPS, a reference GPS, a synchronization device, an online computing device, a data acquisition device, and an offline computing device; the camera includes: the system comprises a photosensitive element, a consumption level inertial measurement unit IMU to be measured and a reference consumption level IMU; the precision of the consumption level IMU to be detected is smaller than that of the reference consumption level IMU; the precision of the consumer grade GPS is smaller than that of the reference GPS;
the photosensitive element is used for collecting target images of the surrounding environment of the unmanned vehicle and sending the target images to the synchronous equipment;
the consumption-level IMU to be detected is used for collecting IMU data to be detected and sending the IMU data to be detected to the synchronous equipment;
the consumption-level GPS is used for collecting GPS information to be detected and sending the GPS information to be detected to the synchronous equipment;
the reference consumption level IMU is used for acquiring reference IMU data and sending the reference IMU data to the synchronous equipment;
the synchronization device is configured to synchronize the target image, the IMU data to be detected, the GPS information to be detected, and the reference IMU data to obtain a synchronous target image, synchronous IMU data to be detected, synchronous GPS information to be detected, and synchronous reference IMU data; the synchronous target image, the synchronous IMU data to be detected and the synchronous GPS information to be detected are sent to the online computing equipment, and the synchronous target image and the synchronous reference IMU data are sent to the data acquisition equipment;
the on-line computing device is used for computing a map result to be detected in real time according to the synchronous target image, the synchronous IMU data to be detected and the synchronous GPS information to be detected;
the reference GPS is used for acquiring reference GPS information and transmitting the reference GPS information to the data acquisition equipment;
the off-line computing device is used for acquiring the synchronous target image, the synchronous reference IMU data and the reference GPS information from the data acquisition device and acquiring the map result to be detected from the on-line computing device; and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be detected with the reference map result to obtain an evaluation result of crowdsourcing map construction.
2. The system of claim 1, further comprising: the cloud storage device comprises a data sending device and a cloud storage device;
the online computing equipment is also used for sending the map result to be detected to the data sending equipment;
the data sending device is used for sending the map result to be detected to the cloud storage device;
the offline computing device is specifically configured to obtain the synchronization target image, the synchronization reference IMU data, and the reference GPS information from the data acquisition device, and obtain the map result to be detected from the cloud storage device; and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be tested with the reference map result to obtain an evaluation result of the consumption-level IMU to be tested.
3. The system of claim 2, wherein the system further comprises a controller configured to control the controller,
the data sending device is specifically configured to detect whether a current network transmission speed is greater than a preset speed threshold, and send the map result to be detected to the cloud storage device when the current network transmission speed is greater than the preset speed threshold; and when the current network transmission speed is not greater than the preset speed threshold, caching the map result to be tested to the local, periodically detecting whether the current network transmission speed is greater than the preset speed threshold, and when the current network transmission speed is greater than the preset speed threshold, sending the map result to be tested to the cloud storage device.
4. The system of claim 2, further comprising: a data storage device;
the data storage device is used for receiving the synchronous target image, the synchronous reference IMU data and the reference GPS information which are sent by the data acquisition device; storing the synchronous target image, the synchronous reference IMU data and the reference GPS information to a magnetic disk;
the offline computing device is specifically configured to obtain the synchronization target image, the synchronization reference IMU data, and the reference GPS information from the disk, and obtain the map result to be tested from the cloud storage device; and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be tested with the reference map result to obtain an evaluation result of the consumption-level IMU to be tested.
5. The system of claim 4, wherein the system further comprises a controller configured to control the controller,
the data storage device is specifically configured to encrypt the synchronization target image, the synchronization reference IMU data, and the reference GPS information, and store the encrypted synchronization target image, the encrypted synchronization reference IMU data, and the encrypted reference GPS information to a disk.
6. An evaluation method for crowd sourcing map construction, characterized in that the method is applied to an evaluation system for crowd sourcing map construction according to any one of claims 1-5, the method comprising:
collecting target images of surrounding environments of the unmanned vehicle, IMU data to be detected, GPS information to be detected, reference IMU data and reference GPS information; the method comprises the steps that IMU data to be detected are collected through a consumption level IMU to be detected of the system, reference IMU data are collected through a reference consumption level IMU of the system, GPS information to be detected is collected through a global positioning system to be detected of the system, reference GPS information is collected through a reference GPS of the system, and the accuracy of the consumption level IMU to be detected is smaller than that of the reference consumption level IMU; the precision of the consumer grade GPS is smaller than that of the reference GPS;
synchronizing the target image, the IMU data to be detected, the GPS information to be detected and the reference IMU data to obtain a synchronous target image, synchronous IMU data to be detected, synchronous GPS information to be detected and synchronous reference IMU data;
calculating a map result to be measured in real time according to the synchronous target image, the synchronous IMU data to be measured and the synchronous GPS information to be measured;
and constructing a reference map result according to the synchronous target image, the synchronous reference IMU data and the reference GPS information, and comparing the map result to be detected with the reference map result to obtain an evaluation result of crowdsourcing map construction.
7. The method as recited in claim 6, further comprising:
and sending the map result to be measured to cloud storage equipment.
8. The method of claim 7, wherein the step of sending the map under test results to a cloud storage device comprises:
detecting whether the current network transmission speed is greater than a preset speed threshold value;
when the current network transmission speed is greater than a preset speed threshold, sending the map result to be tested to the cloud storage equipment;
and when the current network transmission speed is not greater than the preset speed threshold, caching the map result to be tested to the local, periodically detecting whether the current network transmission speed is greater than the preset speed threshold, and when the current network transmission speed is greater than the preset speed threshold, sending the map result to be tested to the cloud storage device.
9. The method as recited in claim 7, further comprising:
and storing the synchronous target image, the synchronous reference IMU data and the reference GPS information to a magnetic disk.
10. The method of claim 9, wherein storing the synchronization target image, the synchronization reference IMU data, and the reference GPS information to disk comprises:
and encrypting the synchronous target image, the synchronous reference IMU data and the reference GPS information, and storing the encrypted synchronous target image, the synchronous reference IMU data and the encrypted reference GPS information into a magnetic disk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911370416.1A CN113049001B (en) | 2019-12-26 | 2019-12-26 | Evaluation system and method for crowdsourcing map construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911370416.1A CN113049001B (en) | 2019-12-26 | 2019-12-26 | Evaluation system and method for crowdsourcing map construction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113049001A CN113049001A (en) | 2021-06-29 |
| CN113049001B true CN113049001B (en) | 2023-11-24 |
Family
ID=76505690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911370416.1A Active CN113049001B (en) | 2019-12-26 | 2019-12-26 | Evaluation system and method for crowdsourcing map construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113049001B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017172778A1 (en) * | 2016-03-28 | 2017-10-05 | Sri International | Collaborative navigation and mapping |
| WO2018106311A2 (en) * | 2016-09-22 | 2018-06-14 | The Regents Of The University Of California | Signals of opportunity aided inertial navigation |
| CN108759845A (en) * | 2018-07-05 | 2018-11-06 | 华南理工大学 | A kind of optimization method based on inexpensive multi-sensor combined navigation |
| CN108955702A (en) * | 2018-05-07 | 2018-12-07 | 西安交通大学 | Based on the lane of three-dimensional laser and GPS inertial navigation system grade map creation system |
| CN109405824A (en) * | 2018-09-05 | 2019-03-01 | 武汉契友科技股份有限公司 | A kind of multi-source perceptual positioning system suitable for intelligent network connection automobile |
| WO2019153245A1 (en) * | 2018-02-09 | 2019-08-15 | Baidu.Com Times Technology (Beijing) Co., Ltd. | Systems and methods for deep localization and segmentation with 3d semantic map |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9798928B2 (en) * | 2013-07-17 | 2017-10-24 | James L Carr | System for collecting and processing aerial imagery with enhanced 3D and NIR imaging capability |
-
2019
- 2019-12-26 CN CN201911370416.1A patent/CN113049001B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017172778A1 (en) * | 2016-03-28 | 2017-10-05 | Sri International | Collaborative navigation and mapping |
| WO2018106311A2 (en) * | 2016-09-22 | 2018-06-14 | The Regents Of The University Of California | Signals of opportunity aided inertial navigation |
| WO2019153245A1 (en) * | 2018-02-09 | 2019-08-15 | Baidu.Com Times Technology (Beijing) Co., Ltd. | Systems and methods for deep localization and segmentation with 3d semantic map |
| CN108955702A (en) * | 2018-05-07 | 2018-12-07 | 西安交通大学 | Based on the lane of three-dimensional laser and GPS inertial navigation system grade map creation system |
| CN108759845A (en) * | 2018-07-05 | 2018-11-06 | 华南理工大学 | A kind of optimization method based on inexpensive multi-sensor combined navigation |
| CN109405824A (en) * | 2018-09-05 | 2019-03-01 | 武汉契友科技股份有限公司 | A kind of multi-source perceptual positioning system suitable for intelligent network connection automobile |
Non-Patent Citations (3)
| Title |
|---|
| 基于GPS与图像融合的智能车辆高精度定位算法;李承;胡钊政;胡月志;吴华伟;;交通运输系统工程与信息(第03期);全文 * |
| 基于消费级无人机的小范围高精度倾斜摄影测量;刘龙威;徐洪飞;魏瑄;;测绘技术装备(第04期);全文 * |
| 面向三维城市建模的多点云数据融合方法综述;朱庆;李世明;胡翰;钟若飞;吴波;谢林甫;;武汉大学学报(信息科学版)(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113049001A (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7186607B2 (en) | Method, apparatus and computer readable storage medium for updating electronic maps | |
| CN107024215B (en) | Tracking objects within a dynamic environment to improve localization | |
| CN106575475B (en) | Apparatus for management of information, vehicle and approaches to IM | |
| CN110617821B (en) | Positioning method, positioning device and storage medium | |
| US11002553B2 (en) | Method and device for executing at least one measure for increasing the safety of a vehicle | |
| CN104790283A (en) | Quick road surface roughness detection system based on vehicle-mounted accelerometer | |
| CN103150786A (en) | Non-contact type unmanned vehicle driving state measuring system and measuring method | |
| EP3842735A1 (en) | Position coordinates estimation device, position coordinates estimation method, and program | |
| CN110851545A (en) | Map drawing method, device and equipment | |
| CN103162689A (en) | Auxiliary vehicle positioning system and auxiliary positioning method of vehicle | |
| CN109564095B (en) | Method and apparatus for using virtual probe points for routing or navigation purposes | |
| CN109405827B (en) | Terminal positioning method and device | |
| CN112455502B (en) | Train positioning method and device based on laser radar | |
| CN102980589A (en) | Method and device for automatically computing vehicle pulse factor via GPS (global positioning system) speed | |
| CN105509764A (en) | Vehicle-mounted integrated terminal used for intelligent driving test | |
| JP2019184607A (en) | Method for satellite-based determination of vehicle position | |
| US11938945B2 (en) | Information processing system, program, and information processing method | |
| KR102217422B1 (en) | Driving license test processing device | |
| CN110515110B (en) | Method, device, equipment and computer readable storage medium for data evaluation | |
| CN111947669A (en) | Method for using feature-based positioning maps for vehicles | |
| Gupta et al. | Road grade estimation using crowd-sourced smartphone data | |
| CN101504289A (en) | Method for implementing vertical height positioning by acceleration sensing in satellite positioning system | |
| TW202018256A (en) | Multiple-positioning-system switching and fusion calibration method and device thereof capable of setting different positioning information weights to fuse the positioning information generated by different devices and calibrate the positioning information | |
| CN113049001B (en) | Evaluation system and method for crowdsourcing map construction | |
| Forno et al. | Techniques for improving localization applications running on low-cost IoT devices |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211123 Address after: 215100 floor 23, Tiancheng Times Business Plaza, No. 58, qinglonggang Road, high speed rail new town, Xiangcheng District, Suzhou, Jiangsu Province Applicant after: MOMENTA (SUZHOU) TECHNOLOGY Co.,Ltd. Address before: Room 601-a32, Tiancheng information building, No. 88, South Tiancheng Road, high speed rail new town, Xiangcheng District, Suzhou City, Jiangsu Province Applicant before: MOMENTA (SUZHOU) TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |