WO2023103882A1 - 道路作业区域预警方法及装置 - Google Patents

道路作业区域预警方法及装置 Download PDF

Info

Publication number
WO2023103882A1
WO2023103882A1 PCT/CN2022/135973 CN2022135973W WO2023103882A1 WO 2023103882 A1 WO2023103882 A1 WO 2023103882A1 CN 2022135973 W CN2022135973 W CN 2022135973W WO 2023103882 A1 WO2023103882 A1 WO 2023103882A1
Authority
WO
WIPO (PCT)
Prior art keywords
lane
warning device
road
image
vehicle
Prior art date
Application number
PCT/CN2022/135973
Other languages
English (en)
French (fr)
Inventor
王东伟
雍智凡
Original Assignee
北京罗克维尔斯科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京罗克维尔斯科技有限公司 filed Critical 北京罗克维尔斯科技有限公司
Publication of WO2023103882A1 publication Critical patent/WO2023103882A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/06—Road conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B60W2050/143—Alarm means

Definitions

  • the present disclosure relates to the technical field of traffic safety, in particular to a method, device, equipment and storage medium for an early warning of a road work area.
  • an assisted driving module can be configured on the vehicle to assist the user in driving the vehicle through the assisted driving module.
  • the current assisted driving module has imperfect functions and cannot accurately predict the working area on the road, so that the driving user cannot avoid the working area in time. Therefore, the safety of the driving user and the personnel in the working area cannot be guaranteed, nor can the safety of the driving user. driving experience.
  • the present disclosure provides a road work area early warning method, device, equipment and storage medium.
  • the present disclosure provides a method for early warning of a road work area, the method comprising:
  • early warning information is generated, and the early warning information is used to warn the road work area.
  • the present disclosure provides an early warning device for a road work area, the device comprising:
  • the road image acquisition module is configured to acquire the road image of the target vehicle in the forward direction
  • the lane range determination module is configured to perform road detection on the road image to obtain the lane range of the relevant lane of the target vehicle;
  • the position determination module of the warning device is configured to detect the warning device on the road image to obtain the position of the warning device;
  • the early warning information generation module is configured to generate early warning information in response to the position of the warning device falling within the range of the lane, and the early warning information is used to warn the road work area.
  • the embodiment of the present disclosure also provides a road work area early warning device, the device includes:
  • processors one or more processors
  • the one or more processors realize the road work area early warning method provided in the first aspect.
  • an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the road work area early warning method provided in the first aspect is implemented.
  • an embodiment of the present disclosure further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the road work area early warning method provided in the first aspect is implemented.
  • the road work area warning method, device, equipment and storage medium of the embodiments of the present disclosure can perform road detection on the road image after acquiring the road image of the target vehicle in the forward direction, and obtain the lane range of the relevant lane of the target vehicle, And detect the warning device on the road image to obtain the position of the warning device, so that further based on the lane range of the relevant lane of the target vehicle and the position of the warning device, accurately determine whether the position of the warning device falls within the range of the lane, and respond to the warning device
  • the position falls within the range of the lane, generate early warning information, and use the early warning information to warn the road work area, so that the road image can be analyzed in real time to accurately predict the road work area, and in the case of predicting the road work area , to send early warning information to the user, so that the user can avoid the work area in time after obtaining the early warning information, ensuring the safety of the driving user and the personnel in the work area, and further ensuring the driving experience of the driving user.
  • Fig. 1 is a schematic flow chart of a road work area early warning method provided by the embodiment of the present invention
  • FIG. 2 is a schematic flowchart of another road work area early warning method provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic flowchart of another method for early warning of a road work area provided by an embodiment of the present disclosure
  • Fig. 4 is a schematic flow chart of another road work area early warning method provided by an embodiment of the present disclosure.
  • FIG. 5 is a logical schematic diagram of a road work area early warning method provided by an embodiment of the present disclosure
  • FIG. 6 is a logical schematic diagram of another road work area early warning method proposed by an embodiment of the present disclosure.
  • FIG. 7 is a logical schematic diagram of yet another early warning method for a road work area proposed by an embodiment of the present disclosure.
  • FIG. 8 is a logical schematic diagram of yet another early warning method for a road work area proposed by an embodiment of the present disclosure.
  • FIG. 9 is a schematic structural diagram of an early warning device for a road work area provided by an embodiment of the present disclosure.
  • Fig. 10 is a schematic structural diagram of an early warning device for a road work area provided by an embodiment of the present disclosure.
  • an assisted driving module can be configured on the vehicle.
  • the assisted driving module can provide users with assisted driving functions and help users relieve driving fatigue. However, it also has the disadvantage of reducing the user's driving alertness.
  • the current assisted driving module functions usually rely on convolutional neural networks to detect elements such as lane lines and vehicles. Due to the serious long-tail problem of the convolutional neural network, if there is a road work area on the road ahead of the vehicle, and the road in the work area is covered with cones, the convolutional neural network cannot recognize the road work area, so that the driving user cannot timely The work area is found and the work area cannot be avoided in time. Therefore, the safety of the driving user and the personnel in the work area cannot be guaranteed, nor can the driving experience of the driving user be guaranteed.
  • embodiments of the present disclosure provide a road work area early warning method, device, equipment and storage medium capable of identifying road work areas.
  • Fig. 1 shows a schematic flowchart of a method for early warning of a road work area provided by an embodiment of the present disclosure.
  • the road work area early warning method shown in FIG. 1 may be executed by an electronic device or a server.
  • the electronic equipment may include, but not limited to, mobile terminals such as smartphones, notebook computers, tablet computers (PAD), portable multimedia players (PMP), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as desktop computers.
  • the server may be a cloud server or a server cluster or other device with storage and computing functions.
  • the road work area early warning method may include the following steps S110 to S140.
  • the electronic device can acquire the road image of the target vehicle in the forward direction in real time, so as to use the road image in the forward direction to identify the road work area in the forward direction, and perform Early warning for road work areas.
  • the forward direction may be the traveling direction of the target vehicle.
  • the road image may be road condition information within a preset distance including the heading direction.
  • the road condition information may include at least one of lane line information in front of the target vehicle, driving information of the vehicle in front, and warning device information.
  • the preset distance may be an area such as 100 meters, 200 meters, 500 meters, etc., which is not limited here.
  • the front image acquisition device can be pre-configured on the target vehicle. During the driving process of the target vehicle, the front image acquisition device can be used to collect the road image in the forward direction in real time, and send the road image to The electronic equipment enables the electronic equipment to obtain the road image collected by the front image collection device.
  • the front image acquisition device may be a monocular camera, a binocular camera, a depth camera, a camera, etc., which is not limited here.
  • S120 Perform road detection on the road image to obtain a lane range of a relevant lane of the target vehicle.
  • road detection may be performed on the road image to determine the lane range of the relevant lane of the target vehicle.
  • the relevant lanes of the target vehicle may include a first lane on which the target vehicle travels and a second lane adjacent to the first lane.
  • the first lane may be a main lane
  • the second lane may include left and right lanes of the main lane.
  • the lane range may be determined according to the lane line range on the relevant lane.
  • the range of lanes may include a first lane and a second lane adjacent to the first lane.
  • the range of lanes may include lane lines corresponding to the first lane.
  • the range of lanes may be a first lane, a second lane adjacent to the first lane, and a lane line corresponding to each lane.
  • S120 may specifically include the following steps S1201 to S1203.
  • the electronic device can input the road image into the pre-trained image segmentation model to obtain the lane line image, and determine the pixel value corresponding to the lane point in the lane line image, according to the pixel value corresponding to the lane point and the pre-set
  • the calibration parameters of the image acquisition device determine the position of the lane point in the vehicle coordinate system, and then determine the lane range of the relevant lane of the target vehicle according to the position of the lane point.
  • the lane line image can be segmented from the road image, and the position of the lane point can be accurately determined based on the pixel value corresponding to the lane point in the lane line image and the calibration parameters of the front-end image acquisition device, This makes it possible to accurately determine the lane range of the relevant lane further based on the position of the lane point.
  • the electronic device after the electronic device acquires the road image, it may detect the warning device on the road image, so as to determine the position of the warning device.
  • the warning device may be a device for warning the working area.
  • the warning device may include devices such as a cone, a warning sign, a pile bucket, and a cylinder, which are not limited here.
  • S130 may specifically include the following steps S1301 to S1302.
  • the electronic device can input the road image into the pre-trained image segmentation model to obtain the warning device image, and determine the pixel value corresponding to the warning device in the warning device image, according to the pixel value corresponding to the warning device and the pre-set
  • the calibration parameters of the image acquisition device determine the position of the warning device in the vehicle coordinate system.
  • the image of the warning device can be segmented from the road image, and based on the pixel value corresponding to the warning device in the image of the warning device and the calibration parameters of the front-end image acquisition device, the value of the warning device can be accurately determined. Location.
  • the electronic device determines the lane range of the relevant lane and the position of the warning device, it can be determined whether the position of the warning device falls within the range of the lane according to the position of the warning device and the range of the lane, and if so, then Early warning information is generated and issued, so that the early warning information is used to warn the road work area, and if it does not fall, no early warning information is generated.
  • the location of the warning device in response to the location of the warning device being within a lane of the associated lane, it is determined that the location of the warning device falls within the bounds of the lane.
  • the position of the warning device in response to the position of the warning device being located on the lane line of the first lane in the relevant lanes, it is determined that the position of the warning device falls within the range of the lane.
  • the location of the warning device in response to the location of the warning device being within a lane of the associated lane, and the location of the warning device being located on a lane line of a first lane of the associated lanes, it is determined that the location of the warning device falls within the range of the lane.
  • the warning information may include information such as the lane where the work area is located, the distance between the work area and the target vehicle, etc., which is not limited here.
  • road detection can be performed on the road image to obtain the lane range of the relevant lane of the target vehicle, and the warning device can be detected on the road image to obtain the warning device.
  • early warning information is generated to Use the early warning information to warn the road work area, so that the road image can be analyzed in real time to accurately predict the road work area, and when the road work area is predicted, an early warning message is sent to the user, so that the user can obtain the early warning information
  • avoiding the work area in time ensures the safety of the driving user and the personnel in the work area, and further ensures the driving experience of the driving user.
  • different methods may be used to determine the lane range of the relevant lane of the target vehicle and the position of the warning device.
  • the lane range may be determined according to the road image.
  • S120 may specifically include the following steps S1201 to S1202.
  • the fitted lane line can be obtained by fitting the lane points collected from the road image.
  • S1201 may specifically include the following steps S12011 to S12013.
  • the electronic device can input the road image into a pre-trained image segmentation model to perform lane line detection on the road image to obtain the lane line image, and then, according to the shooting calibration parameters corresponding to the road image, Project the lane line image to the vehicle coordinate system of the target vehicle to obtain the lane line projection points.
  • the preset fitting parameters fit the lane line projection points corresponding to the target lane to obtain the curve equation, and use the obtained curve equation as Fitted lane lines.
  • the image segmentation model may be a convolutional neural network, a deep learning network, etc., which is not limited here.
  • the shooting calibration parameters corresponding to the road image shooting may include internal parameters and external parameters of the front image acquisition device on the target vehicle.
  • the electronic device can use the shooting calibration parameters corresponding to the road image taken as the mapping relationship between the image coordinate system and the vehicle coordinate system, and based on the mapping relationship, project the lane line image to the vehicle coordinate system of the target vehicle , to get the projection point of the lane line.
  • the preset fitting parameters may include fitting coefficients used to obtain each order of the curve equation.
  • the curve equation may be a cubic equation, so that the obtained fitted lane line is a cubic fitted curve.
  • S1202 may specifically include the following steps S12021 to S12022.
  • the position of the target vehicle can be determined according to the real-time coordinates of the target vehicle in the vehicle coordinate system.
  • the position of the fitting point can be determined according to the coordinates of the fitting point in the vehicle coordinate system.
  • the electronic device can determine the real-time coordinates of the target vehicle in the vehicle coordinate system according to the positioning information collected by the positioning device on the target vehicle and the vehicle coordinate system, obtain the position of the target vehicle, and determine The lane that the target vehicle is driving, that is, determine the first lane and the second lane adjacent to the first lane; at the same time, determine the positions of all fitting points on the fitting lane line according to the coordinates of the fitting points in the vehicle coordinate system , to obtain the lane line range of each lane line on the relevant lane; then, according to the lane on which the target vehicle is driving and the lane line range of each lane line on the relevant lane, determine the lane range of the relevant lane of the target vehicle.
  • the lane line detection can be performed on the road image to obtain the lane line image, and according to the lane line image and the shooting calibration parameters corresponding to the road image, the lane line projection point can be determined, and the lane line The line projection points are fitted to obtain the fitted lane line, so as to further accurately determine the lane range based on the position of the target vehicle and the position of the fitting point on the fitted lane line.
  • the position of the warning device can be determined according to the road image.
  • S130 may specifically include the following steps S1301 to S1302.
  • S1302. Determine the position of the warning device based on the image of the warning device.
  • S1301 may specifically include the following step S13011.
  • the warning device image may be a warning device detection frame.
  • the image segmentation model may be a convolutional neural network, a deep learning network, etc., which is not limited here.
  • S1302 may specifically include the following steps S13021 to S13023.
  • the electronic device can project the image of the warning device to the vehicle coordinate system of the target vehicle according to the shooting calibration parameters corresponding to the road image to obtain the projected point of the warning device, and then select from the projected points of the warning device.
  • the lower left corner projection point and the lower right corner projection point are based on the projection positions corresponding to the lower left corner projection point and the lower right corner projection point respectively, calculate the midpoint of the lower left corner projection point and the lower right corner projection point, and project the lower left corner projection point and the lower right corner projection point
  • the midpoint of the point is used as the position of the warning device.
  • the midpoint of the bottom-left projection point and the bottom-right projection point may be denoted as cone_vcs_c[k].
  • the embodiment of the present disclosure it is possible to detect the warning device on the road image, obtain the warning device image, and determine the projection point of the warning device in the vehicle coordinate system according to the warning device image and the shooting calibration parameters corresponding to the road image. , accurately determine the position of the warning device according to the projection points of the lower left corner and the lower right corner of the projection points of the warning device.
  • the position of the warning device before generating the warning information, it may be determined whether the position of the warning device falls within the range of the lane according to the maximum distance between the warning device and the fitted lane line corresponding to any lane, or, according to the first Each side corresponding to the lane fits the number of warning devices on the lane line, and determines whether the position of the warning device falls within the range of the lane.
  • the position of the warning device falls within the range of the lane according to the maximum distance between the warning device and the fitted lane line corresponding to any lane.
  • Fig. 2 shows a schematic flowchart of another road work area early warning method provided by an embodiment of the present disclosure.
  • the road work area early warning method may include the following steps S210 to S270.
  • S210 is similar to S110, and details are not described here.
  • the method may further include the following step S2301.
  • the electronic device can acquire multiple consecutive frames of road images, and calculate the two adjacent fitted lanes according to the positions of the lane points on the adjacent two fitted lane lines in the fitted lane lines corresponding to each frame of road image. The distance between the lines is then calculated based on the distance obtained from all frame road images to calculate the average of the distance, and the average of the distance is used as the width of each lane.
  • the width of each lane may be represented as lane_width_avr_[j].
  • S240 Perform warning device detection on the road image to obtain the location of the warning device.
  • the S240 is similar to the S130 and will not be described in detail here.
  • the lane range may include a first lane and a second lane adjacent to the first lane, and the first lane is a lane on which the target vehicle is driving.
  • the electronic device can acquire multiple consecutive frames of road images, and determine the fitted lane line of any lane of the relevant lane for the fitted lane line corresponding to each frame of road image, and then according to the position of the warning device and any The fitted lane line corresponding to the lane, calculate the maximum distance between the warning device and the fitted lane line corresponding to any lane, so the maximum distance can be calculated based on each frame of road image, and then the maximum distance calculated based on all frame road images , calculate the maximum distance average, and use the maximum distance average as the maximum distance between the warning device and the fitted lane line corresponding to any lane.
  • any lane has a left fitting lane line and a right fitting lane line at the same time, then according to the position of the warning device and the fitting lane line corresponding to any lane, calculate the warning device and any lane respectively.
  • the distance between the fitted lane line on the left side and the fitted lane line on the right side of take the maximum distance from the two calculated distances as the maximum distance between the warning device and the fitted lane line corresponding to any lane.
  • the distance between the warning device and the fitting lane line on the left side is calculated according to the position of the warning device and the fitting lane line on the left side corresponding to any lane , at the same time, according to the width of any lane and the corresponding left fitting lane line of any lane, the distance between the warning device and the right fitting lane line can be calculated, and the maximum distance can be taken from the two calculated distances as The maximum distance between the warning device and the fitted lane line corresponding to any lane.
  • the distance between the warning device and the fitting lane line on the right side is calculated according to the position of the warning device and the fitting lane line on the right side corresponding to any lane , at the same time, according to the width of any lane and the right fitting lane line corresponding to any lane, the distance between the warning device and the left fitting lane line can be calculated, and the maximum distance can be taken from the two calculated distances as The maximum distance between the warning device and the fitted lane line corresponding to any lane.
  • the maximum distance between the warning device and the fitted lane line corresponding to any lane may be expressed as cone_lane_dis[k][j].
  • the electronic device calculates the maximum distance, it compares the maximum distance with a preset distance threshold, and if the maximum distance is smaller than the preset distance threshold, it means that the warning device falls into the first lane or the second lane, then It can be determined that the position of the warning device falls within the range of the lane, otherwise, it means that the position of the warning device does not fall within the first lane or the second lane, and it can be determined that the position of the warning device does not fall within the range of the lane.
  • the preset distance threshold may be a predetermined maximum distance for judging whether the position of the warning device falls within the range of the lane.
  • the relevant lane falling into the warning device may be represented as lane_cone_occ[j].
  • the warning when the range of lanes includes the first lane and the second lane adjacent to the first lane, and the first lane is the lane on which the target vehicle is driving, the warning can be determined based on multiple frames of images
  • the maximum distance between the fitted lane line corresponding to the device and any lane can accurately determine whether the position of the warning device falls into the first lane or the second lane, so as to accurately determine whether the position of the warning device falls within the range of the lane, and eliminate In order to detect noise, the accuracy of early warning signals is improved.
  • the S270 is similar to the S140, so details are not described here.
  • the position of the warning device falls within the range of the lane according to the number of warning devices on the fitted lane line on each side corresponding to the first lane.
  • Fig. 3 shows a schematic flowchart of another road work area early warning method provided by an embodiment of the present disclosure.
  • the road work area early warning method may include the following steps S310 to S370.
  • S310 is similar to S110, and details are not described here.
  • S320 Perform lane line detection on the road image to obtain fitted lane lines contained in the road image.
  • S320 and S330 are similar to S220 and S230, and details are not described here.
  • the S340 is similar to the S130, and details are not described here.
  • the lane range may include a fitting lane line corresponding to the first lane, and the first lane is a lane on which the target vehicle is driving.
  • the electronic device can acquire multiple consecutive frames of road images, and for the first lane corresponding to each frame of road images, it can be determined based on the position of the warning device that it falls on the fitted lane line on each side corresponding to the first lane The number of warning devices in order to obtain the number of warning devices on the left fitting lane line or the right fitting lane line of the first lane, thus, based on each frame of road image, the corresponding The number of warning devices on each side of the fitted lane line of , and then, based on the number of warning devices on each side of the fitted lane line corresponding to the first lane obtained from all frame road images, the average value of the number of warning devices is calculated, and the warning The mean value of the number of devices is used as the number of warning devices falling on the fitted lane line on each side corresponding to the first lane.
  • the electronic device may acquire the preset line pressure threshold of the fitted lane line of the first lane; If the distance between the positions of the joint lane lines is less than the preset line pressure threshold, it is determined that the warning device falls on the fitted lane line on the left side of the first lane, and the warning device falls on the fitted lane line on the left side of the first lane Quantity; in response to the distance between the position of the warning device and the position of the fitted lane line on the right side of the first lane is less than the preset line pressure threshold, determine that the warning device falls on the fitted lane line on the right side of the first lane, and determine The number of warning devices that fall on the fitted lane line to the right of the first lane.
  • the preset line-breaking threshold may be a distance threshold for judging whether the warning device is breaking the line.
  • the number of warning devices falling on the fitted lane line on each side corresponding to the first lane may be expressed as cone_on_line_[j].
  • the preset pressure line threshold may be expressed as delta.
  • the electronic device determines the number of warning devices, it compares the number of warning devices on at least one side of the fitted lane line with the threshold value of the number of warning devices. If the number of warning devices on at least one side of the fitted lane line is is greater than the number threshold of the warning device, indicating that the warning device falls on the left or right fitting lane line of the first lane, it can be determined that the position of the warning device falls within the range of the lane; otherwise, it means that the warning device is not If it is pressed against the lane line of the first lane, it can be determined that the position of the warning device does not fall within the range of the lane.
  • the number threshold of warning devices may be a predetermined minimum number for judging whether the positions of the warning devices fall within the lane range.
  • the warning device in response to the number of warning devices on the fitting lane line on the left side of the first lane being greater than the number threshold of warning devices, it may be determined that the warning device falls within the left lane of the first lane.
  • the warning device in response to the number of warning devices on the fitting lane line on the right side of the first lane being greater than the number threshold of warning devices, it may be determined that the warning device falls within the right lane of the first lane.
  • the warning device in response to the number of warning devices on the right fitting lane of the first lane being greater than the threshold number of warning devices, and the number of warning devices on the left fitting lane of the first lane being greater than the number of warning devices The quantity threshold value of , it can be determined that the warning device falls in the right lane and the left lane of the first lane.
  • the right lane and/or the left lane falling into the first lane of the warning device may be represented as lane_cone_occ[j].
  • the number of warning devices on at least one side of the fitted lane line and the number of warning devices Threshold comparison can accurately determine whether the position of the warning device falls into the left or right lane of the first lane, so as to accurately determine whether the position of the warning device falls within the range of the lane. Since the range of the lane can be determined based on multiple frames of images, Detection noise is thus eliminated, increasing the accuracy of early warning signals.
  • the position of the warning device falls within the range of the lane according to different methods, which improves the flexibility of judging whether the position of the warning device falls within the range of the lane, and can adapt to different judgment scenarios.
  • the early warning information in order to reduce the false alarm rate of the early warning, after it is determined that the position of the warning device falls within the range of the lane, the early warning information may also be generated in combination with other conditions.
  • Fig. 4 shows a schematic flowchart of another road work area early warning method provided by an embodiment of the present disclosure.
  • the road work area early warning method may include the following steps S410 to S460.
  • S410 is similar to S110 , so details are not described here.
  • S420 and S430 are similar to S220 and S230, so details are not described here.
  • the S440 is similar to the S130, so details are not described here.
  • the determination of an effective lane in the relevant lanes in S450 may specifically include the following steps S4501 to S4502.
  • the number of lane points collected may be the number of actual lane points collected.
  • the threshold number of lane collection points may be a preset minimum number for judging whether any lane is a valid lane.
  • the electronic device may acquire the number of lane points collected corresponding to the fitted lane line corresponding to any lane, and compare the number of lane points collected with the threshold number of lane collection points, and then If the number of lane point collection is greater than the threshold of the number of lane collection points, it means that there are more actual lane points on any lane, and a more accurate fitting lane line can be obtained based on the actual lane points, that is, any lane in the relevant lanes can be determined is a valid lane, otherwise, if the number of lane points collected is less than the threshold of the number of lane points collected, it means that there are few actual lane points on any lane, and it is difficult to obtain a more accurate fitting lane line based on the actual lane points, that is, to determine the relevant lane Any lane in is an invalid lane.
  • a valid lane may be denoted as lane_valid[j].
  • calculating the width of each lane in the relevant lanes in S450 may specifically include the following steps:
  • the electronic device may select lane points at the same position in one direction from the fitted lane line on the left side and the fitted lane line on the right side of each lane, Based on the position of these lane points in the other direction, calculate the width of each lane.
  • the position in one direction may be the abscissa or ordinate of the lane point in the vehicle coordinate system.
  • obtaining the driving speed of the vehicle in front on each lane in the relevant lanes in S450 may specifically include the following steps S4504 to S4506.
  • S4506. Determine the driving speed of the vehicle in front according to the real-time position of the vehicle in front, the real-time position of the target vehicle and the speed of the target vehicle.
  • the electronic device may input the road image into a pre-trained image segmentation model, so as to detect the vehicle ahead on the road image, and obtain an image of the vehicle ahead and a ground line of the vehicle ahead.
  • the front vehicle image may be a front vehicle detection frame.
  • the ground line of the vehicle in front may be the vehicle center of the vehicle in front, and is used to determine the lane to which the vehicle in front belongs.
  • the ground line of the preceding vehicle can be expressed as: veh[m].
  • the electronic device can project the image of the vehicle in front and the ground line of the vehicle in front to the vehicle coordinate system of the target vehicle according to the shooting calibration parameters corresponding to the road image to obtain the real-time position of the vehicle in front, and further base on the vehicle in front Real-time position, determine the driving speed of the vehicle ahead.
  • the electronic device can determine the relative position of the vehicle in front and the target vehicle in real time according to the real-time position of the vehicle in front and the real-time position of the target vehicle, and determine the driving speed of the vehicle in front according to the speed and relative position of the target vehicle.
  • the width of the relevant lane of falling into the warning device is greater than the preset width threshold, and the driving speed of the vehicle ahead on the relevant lane of falling into the warning device is less than the preset speed Threshold, generate early warning information, and the early warning information is used to warn the road work area.
  • the vehicle speed is lower than that of a normal driving vehicle.
  • the preset speed threshold may be the speed used to determine whether the vehicle in front is a normal driving vehicle.
  • the preset speed threshold may be expressed as vel_speed_vel.
  • the electronic device determines that the position of the warning device falls within the range of the lane
  • the width of the relevant lane falling into the warning device is greater than the preset width threshold
  • the driving speed of the vehicle ahead on the relevant lane falling into the warning device is less than the preset speed threshold
  • the relevant lanes falling into the warning device may be represented as lane_vehicles_occ[j].
  • the relevant lane where the warning device falls is the lane that needs to be warned, and it is determined that the relevant lane where the warning device falls is sufficiently wide.
  • early warning information is generated to combine with more information for road operation area early warning. Therefore, the false alarm rate of early warning is reduced, and the user's driving experience is further improved experience.
  • the electronic device determines that the position of the warning device falls within the range of the lane, it can also be combined that the relevant lane falling into the warning device is an effective lane, the width of the relevant lane falling into the warning device is greater than the preset width threshold, Moreover, if the driving speed of the vehicle ahead falling into the relevant lane of the warning device is lower than one or any two conditions in the preset speed threshold, warning information is generated, which improves the flexibility of judging whether to generate warning information.
  • Fig. 5 shows a schematic diagram of a road work area early warning method provided by an embodiment of the present disclosure.
  • the road work area early warning method may include the following steps S510 to S530.
  • the S510 is similar to the S110 and will not be repeated here.
  • obtaining the lane line image based on the road image in S520 may specifically include the following steps S5201 to S5203. S5201. Input a road image into a pre-trained image segmentation model to obtain a lane line image.
  • obtaining the warning device image based on the road image in S520 may specifically include the following steps: S5202. Input the road image into the pre-trained image segmentation model to obtain the warning device image image.
  • obtaining the vehicle image in front and the ground line of the vehicle in front based on the road image in S520 may specifically include the following steps: S5203, inputting the road image to a pre-trained image segmentation model
  • the front vehicle detection is carried out on the road image, and the front vehicle image and the front vehicle grounding line are obtained.
  • the lane line image, the warning device image, the front vehicle image and the front vehicle grounding line are fused to generate early warning information.
  • S530 may specifically include the following steps S5301 to S5304.
  • FIG. 6 shows a schematic diagram of another road work area early warning method proposed by the embodiment of the present disclosure.
  • S5301 may specifically include the following steps S53011 to S53014.
  • S53011 may specifically include: projecting the lane line image onto the vehicle coordinate system of the target vehicle according to the shooting calibration parameters corresponding to the road image to obtain the lane line projection point; according to the preset fitting parameters, corresponding to the target lane The lane line projection points are fitted to obtain the fitted lane line.
  • the lane range may include the first lane, the second lane, and the left lane line and the right lane line on the first lane and the second lane.
  • FIG. 7 shows a schematic diagram of another road work area early warning method proposed by the embodiment of the present disclosure.
  • S5302 may specifically include the following steps S53021 to S53023.
  • the range of lanes includes a first lane and a second lane adjacent to the first lane, and the first lane is the lane on which the target vehicle travels;
  • S53022 may specifically include: for any lane in the relevant lanes, based on the position of the warning device, calculating the maximum distance between the warning device and the fitted lane line corresponding to any lane; in response to the maximum distance being less than the preset distance threshold , it is determined that the position of the warning device falls within the range of the lane, specifically, it can be determined that the position of the warning device falls within any of the relevant lanes, otherwise, it is determined that the position of the warning device does not fall within any of the relevant lanes.
  • the lane range includes the fitting lane line corresponding to the first lane, and the first lane is the lane on which the target vehicle is driving.
  • S53023 may specifically include: for the first lane, based on the positions of the warning devices, determining the number of warning devices falling on each side of the fitted lane line corresponding to the first lane; If the number of warning devices is greater than the threshold value of the number of warning devices, it is determined that the position of the warning device falls within the lane range. Specifically, it can be determined that the position of the warning device falls on the fitted lane line of the first lane; otherwise, it is determined that the position of the warning device does not fall within the range of the lane.
  • the fitted lane line of a lane is based on the positions of the warning devices, determining the number of warning devices falling on each side of the fitted lane line corresponding to the first lane. If the number of warning devices is greater than the threshold value of the number of warning devices, it is determined that the position of the warning device falls within the lane range. Specifically, it can be determined that the position of the warning device falls on the fitted lane line of the first lane; otherwise, it is determined that the position of
  • FIG. 8 shows a schematic diagram of another road work area early warning method proposed by the embodiment of the present disclosure.
  • S5303 may specifically include the following steps S53031 to S53032.
  • S53032 Determine the driving speed of the vehicle in front according to the real-time position of the vehicle in front, the real-time position of the target vehicle and the speed of the target vehicle.
  • the road work area early warning device may be an electronic device or a server.
  • the electronic equipment may include but not limited to mobile terminals such as smart phones, notebook computers, tablet computers (PAD), portable multimedia players (PMP), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and mobile terminals such as desktop computers, etc.
  • the server may be a cloud server or a server cluster or other device with storage and computing functions.
  • Fig. 9 shows a schematic structural diagram of an early warning device for a road work area provided by an embodiment of the present disclosure.
  • the road work area warning device 900 may include: a road image acquisition module 910 , a lane range determination module 920 , a warning device location determination module 930 and a warning information generation module 940 .
  • the road image acquiring module 910 may be configured to acquire the road image of the target vehicle in the forward direction.
  • the lane range determination module 920 may be configured to perform road detection on the road image to obtain the lane range of the relevant lane of the target vehicle.
  • the location determination module 930 of the warning device may be configured to detect the warning device on the road image to obtain the location of the warning device.
  • the early warning information generating module 940 may be configured to generate early warning information in response to the position of the warning device falling within the range of the lane, and the early warning information is used to warn the road work area.
  • road detection can be performed on the road image to obtain the lane range of the relevant lane of the target vehicle, and the warning device can be detected on the road image to obtain the warning device.
  • early warning information is generated to Use the early warning information to warn the road work area, so that the road image can be analyzed in real time to accurately predict the road work area, and when the road work area is predicted, an early warning message is sent to the user, so that the user can obtain the early warning information
  • avoiding the work area in time ensures the safety of the driving user and the personnel in the work area, and further ensures the driving experience of the driving user.
  • the lane range determination module 920 may include: a fitted lane line generation unit and a lane range determination unit.
  • the fitting lane line generation unit may be configured to detect the lane line on the road image to obtain the fitted lane line contained in the road image.
  • the lane range determination unit may be configured to determine the lane range of the relevant lane of the target vehicle based on the fitted lane line.
  • the fitting lane line generation unit may also be configured to detect the lane line on the road image to obtain the lane line image; project the lane line image to the In the vehicle coordinate system of the target vehicle, the lane line projection points are obtained; according to the preset fitting parameters, the lane line projection points corresponding to the target lane are fitted to obtain the fitted lane line.
  • the lane range determination unit may also be configured to determine the position of the target vehicle and the positions of all fitting points on the fitted lane line respectively; based on the position of the target vehicle and all fitting points on the fitted lane line, The position of the point determines the lane extent of the relevant lane of the target vehicle.
  • the warning device position determination module 930 may include: a warning device image determination unit and a warning device position determination unit.
  • the warning device image determination unit may be configured to detect the warning device on the road image to obtain the warning device image.
  • the position determining unit of the warning device may be configured to determine the position of the warning device based on the image of the warning device.
  • the position determination unit of the warning device may also be configured to project the image of the warning device into the vehicle coordinate system of the target vehicle according to the shooting calibration parameters corresponding to the road image taken, to obtain the projected point of the warning device ;Select the target projection point from the warning device projection points, the target projection point includes the lower left corner projection point and the lower right corner projection point of the warning device image; use the midpoint of the lower left corner projection point and the lower right corner projection point as the position of the warning device.
  • the lane range includes a first lane and a second lane adjacent to the first lane, and the first lane is a lane on which the target vehicle is driving.
  • the road work area early warning device may also include: a maximum distance calculation module and a first fall determination module.
  • the maximum distance calculation module can be configured to calculate the maximum distance between the warning device and the fitted lane line corresponding to any lane based on the position of the warning device for any lane in the relevant lanes.
  • the first falling-in determination module may be configured to determine that the position of the warning device falls within the range of the lane in response to the maximum distance being less than a preset distance threshold.
  • the lane range includes a fitted lane line corresponding to the first lane, and the first lane is a lane on which the target vehicle is driving.
  • the road work area early warning device may also include: a warning device quantity determination module and a second fall-in determination module.
  • the module for determining the number of warning devices may be configured to determine the number of warning devices falling on the fitted lane line on each side corresponding to the first lane based on the positions of the warning devices for the first lane.
  • the second falling-in determination module may be configured to determine that the position of the warning device falls within the range of the lane in response to the number of warning devices on at least one side of the fitted lane line being greater than the number threshold of warning devices.
  • the road work area early warning device may further include: an effective lane determination module, a width calculation module and a driving speed acquisition module.
  • the effective lane determination module can be configured to determine the effective lane in the relevant lanes.
  • a width calculation module may be configured to calculate the width of each of the relevant lanes.
  • the driving speed obtaining module may be configured to obtain the driving speed of the vehicle in front on each lane in the relevant lanes.
  • the early warning information generation module 940 can also be configured to respond to the relevant lane falling into the warning device as an effective lane, the width of the relevant lane falling into the warning device is greater than the preset width threshold, and the relevant lane falling into the warning device When the driving speed of the vehicle ahead is lower than the preset speed threshold, an early warning message is generated.
  • the effective lane determination module can also be configured to, for any lane in the relevant lanes, obtain the number of lane point collections corresponding to the fitted lane line of any lane; The threshold of the number of collection points is used to determine any one of the relevant lanes as a valid lane.
  • the width calculation module may also be configured to, for each lane in the relevant lanes, calculate the width.
  • the driving speed acquisition module may also be configured to detect the vehicle in front of the road image to obtain the vehicle image in front and the ground line of the vehicle in front;
  • the shooting calibration parameters corresponding to the shooting road image the front vehicle image and the front vehicle grounding line are projected to the vehicle coordinate system of the target vehicle to obtain the real-time position of the front vehicle;
  • the real-time position of the vehicle in front the real-time position of the target vehicle and the speed of the target vehicle, the driving speed of the vehicle in front is determined.
  • the road work area early warning device 900 shown in FIG. 9 can execute each step in the method embodiment shown in FIG. 1 to FIG. 8 , and realize each step in the method embodiment shown in FIG. 1 to FIG. The process and effect will not be repeated here.
  • An embodiment of the present disclosure also provides a warning device for a road work area, which includes: one or more processors; a storage device for storing one or more programs, when one or more programs are processed by one or more The processor is executed, so that one or more processors realize the road work area early warning method provided by the embodiment of the present disclosure.
  • Fig. 10 shows a schematic structural diagram of an early warning device for a road work area provided by an embodiment of the present disclosure.
  • the data collection device may include a processor 1001 and a memory 1002 storing computer program instructions.
  • processor 1001 may include a central processing unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
  • CPU central processing unit
  • ASIC Application Specific Integrated Circuit
  • Memory 1002 may include mass storage for information or instructions.
  • the memory 1002 may include a hard disk drive (Hard Disk Drive, HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (Universal Serial Bus, USB) drive or two or more A combination of the above.
  • Storage 1002 may include removable or non-removable (or fixed) media, where appropriate.
  • the memory 1002 may be internal or external to the integrated gateway device.
  • memory 1002 is a non-volatile solid-state memory.
  • the memory 1002 includes a read-only memory (Read-Only Memory, ROM).
  • the ROM can be a mask programmed ROM, a programmable ROM (Programmable ROM, PROM), an erasable PROM (Electrical Programmable ROM, EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM) ), electrically rewritable ROM (Electrically Alterable ROM, EAROM) or flash memory, or a combination of two or more of these.
  • the processor 1001 reads and executes the computer program instructions stored in the memory 1002 to execute the steps of the road work area early warning method provided by the embodiment of the present disclosure.
  • the road work area warning device may further include a transceiver 1003 and a bus 1004 .
  • a processor 1001 a memory 1002 and a transceiver 1003 are connected through a bus 1004 to complete mutual communication.
  • Bus 1004 includes hardware, software, or both.
  • a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Super Transmission (Hyper Transport, HT) interconnection, Industrial Standard Architecture (Industrial Standard Architecture, ISA) bus, Infinity Bandwidth interconnection, Low Pin Count (Low Pin Count, LPC) bus, memory bus, Micro Channel Architecture (Micro Channel Architecture) , MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (Serial Advanced Technology Attachment, SATA) bus, Video Electronics Standards Association local (Video Electronics Standards Association Local Bus, VLB) bus or other suitable bus or a combination of two or more of these.
  • Bus 1004 may comprise one or more buses, where appropriate.
  • the embodiment of the present disclosure also provides a computer-readable storage medium, which can store a computer program, and when the computer program is executed by the processor, the processor can realize the road work area early warning method provided by the embodiment of the present disclosure.
  • the above-mentioned storage medium may, for example, include a memory 1002 of computer program instructions, and the above-mentioned instructions can be executed by the processor 1001 of the battery internal resistance detection device to complete the battery internal resistance detection method provided by the embodiment of the present disclosure.
  • the storage medium can be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium can be ROM, random access memory (Random Access Memory, RAM), compact disc read-only memory (Compact Disc ROM) , CD-ROM), tapes, floppy disks and optical data storage devices, etc.
  • An embodiment of the present disclosure further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method for early warning of a road work area provided by the embodiment of the present disclosure is implemented.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Image Analysis (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种道路作业区域预警方法、装置、设备及存储介质。该方法包括：获取目标车辆在前进方向上的道路图像；对道路图像进行道路检测，得到目标车辆的相关车道的车道范围；对道路图像进行警示装置检测，得到警示装置的位置；响应于警示装置的位置落入车道范围内，生成预警信息，预警信息用于警示道路作业区域。

Description

道路作业区域预警方法及装置
相关申请的交叉引用
本申请基于申请号为202111480429.1、申请日为2021年12月06日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及交通安全技术领域，尤其涉及一种道路作业区域预警方法、装置、设备及存储介质。
背景技术
随着汽车技术的不断提高以及公路运输行业的发展，越来越多的用户选择驾驶汽车出行，并且，出行安全性也是用户一直关心的问题。
为了提高出行安全性，车辆上可以配置辅助驾驶模块，以通过辅助驾驶模块辅助用户驾驶车辆。但是目前的辅助驾驶模块功能不完善，无法准确的预测公路上的作业区域，使得驾驶用户不能及时避开作业区域，因此，不能保证驾驶用户和作业区域人员的安全性，也不能保证驾驶用户的驾驶体验。
发明内容
为了解决上述技术问题或者至少部分地解决上述技术问题，本公开提供了一种道路作业区域预警方法、装置、设备及存储介质。
在第一方面，本公开提供了一种道路作业区域预警方法，该方法包括：
获取目标车辆在前进方向上的道路图像；
对道路图像进行道路检测，得到目标车辆的相关车道的车道范围；
对道路图像进行警示装置检测，得到警示装置的位置；
响应于警示装置的位置落入车道范围内，生成预警信息，预警信息用于警示道路作业区域。
在第二方面，本公开提供了一种道路作业区域预警装置，该装置包括：
道路图像获取模块，配置于获取目标车辆在前进方向上的道路图像；
车道范围确定模块，配置于对道路图像进行道路检测，得到目标车辆的相关车道的车道范围；
警示装置的位置确定模块，配置于对道路图像进行警示装置检测，得到警示装置的位置；
预警信息生成模块，配置于响应于警示装置的位置落入车道范围内，生成预警信息，预警信息用于警示道路作业区域。
在第三方面，本公开实施例还提供了一种道路作业区域预警设备，该设备包括：
一个或多个处理器；
存储装置，用于存储一个或多个程序，
当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现第一方面所提供的道路作业区域预警方法。
在第四方面，本公开实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现第一方面所提供的道路作业区域预警方法。
在第五方面，本公开实施例还提供了一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现第一方面所提供的道路作业区域预警方法。
本公开实施例的一种道路作业区域预警方法、装置、设备及存储介质，在获取目标车辆在前进方向上的道路图像，能够对道路图像进行道路检测，得到目标车辆的相关车 道的车道范围，以及对道路图像进行警示装置检测，得到警示装置的位置，使得进一步基于目标车辆的相关车道的车道范围和警示装置的位置，准确的确定警示装置的位置是否落入车道范围内，响应于警示装置的位置落入车道范围内，生成预警信息，以利用预警信息警示道路作业区域，由此，可以对道路图像进行实时分析，以准确的预测道路作业区域，并在预测到道路作业区域的情况下，向用户发出预警信息，使得用户获取到预警信息之后，及时避开作业区域，保证了驾驶用户和作业区域人员的安全性，也进一步保证了驾驶用户的驾驶体验。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本开实施例提供的一种道路作业区域预警方法的流程示意图；
图2为本公开实施例提供的另一种道路作业区域预警方法的流程示意图；
图3为本公开实施例提供的又一种道路作业区域预警方法的流程示意图；
图4为本公开实施例提供的又一种道路作业区域预警方法的流程示意图；
图5为本公开实施例提供的一种道路作业区域预警方法的逻辑示意图；
图6为本公开实施例提出了另一种道路作业区域预警方法的逻辑示意图；
图7为本公开实施例提出了又一种道路作业区域预警方法的逻辑示意图；
图8为本公开实施例提出了再一种道路作业区域预警方法的逻辑示意图；
图9为本公开实施例提供的一种道路作业区域预警装置的结构示意图；
图10为本公开实施例提供的一种道路作业区域预警设备的结构示意图。
具体实施方式
为了能够更清楚地理解本公开的上述目的、特征和优点，下面将对本公开的方案进行进一步描述。需要说明的是，在不冲突的情况下，本公开的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本公开，但本公开还可以采用其他不同于在此描述的方式来实施；显然，说明书中的实施例只是本公开的一部分实施例，而不是全部的实施例。
用户驾驶车辆在高速公路上行驶时，高速公路上的车速较快，如果用户长时间驾驶容易产生疲劳，使得用户出行安全性得不到保证。为了提高车辆的出行安全性，车辆上可以配置辅助驾驶模块，辅助驾驶模块可以为用户提供辅助驾驶功能，帮助用户缓解驾驶疲劳，然而，同时也存在降低用户驾驶警觉性的弊端。
但是，目前的辅助驾驶模块功能通常依赖于卷积神经网络检测车道线、车辆等要素。由于卷积神经网络存在严重的长尾问题，如果车辆驾驶前方的道路上存在道路作业区域，作业区域的路面上布满锥桶，卷积神经网络无法识别到道路作业区域，使得驾驶用户不能及时发现作业区域以及不能及时避开作业区域，因此，不能保证驾驶用户和作业区域人员的安全性，也不能保证驾驶用户的驾驶体验。
为了解决上述问题，本公开实施例提供了一种能够识别道路作业区域的道路作业区域预警方法、装置、设备及存储介质。
下面，首先结合图1至图8对本公开实施例提供的道路作业区域预警方法进行说明。
图1示出了本公开实施例提供的一种道路作业区域预警方法的流程示意图。
在本公开一些实施例中，图1所示的道路作业区域预警方法可以由电子设备或服务 器执行。该电子设备可以包括但不限于诸如智能手机、笔记本电脑、平板电脑(PAD)、便携式多媒体播放器(PMP)、车载终端(例如车载导航终端)等的移动终端，以及诸如台式计算机等的固定终端。服务器可以是云服务器或者服务器集群等具有存储及计算功能的设备。
如图1所示，该道路作业区域预警方法可以包括如下步骤S110至步骤S140。
S110、获取目标车辆在前进方向上的道路图像。
在本公开实施例中，在目标车辆驾驶的过程中，电子设备可以实时获取目标车辆在前进方向上的道路图像，以利用前进方向上的道路图像，识别前进方向上的道路作业区域，以及进行道路作业区域预警。
在本公开实施例中，前进方向可以是目标车辆的行驶方向。
在本公开实施例中，道路图像可以是包括前进方向的预设距离内的路况信息。
在一些实施例中，路况信息可以包括目标车辆前方的车道线信息、前方车辆的行驶信息以及警示装置信息中的至少一种。
其中，预设距离可以是100米、200米、500米等区域，在此不做限定。
在一些实施例中，可以预先在目标车辆上配置前置图像采集装置，在目标车辆驾驶的过程中，可以利用前置图像采集装置，实时采集前进方向上的道路图像，并将道路图像发送至电子设备，使得电子设备获取前置图像采集装置采集的道路图像。
在一些实施例中，前置图像采集装置可以是单目相机、双目相机、深度相机以及摄像头等装置，在此不做限制。
S120、对道路图像进行道路检测，得到目标车辆的相关车道的车道范围。
在本公开实施例中，在电子设备获取到道路图像之后，可以对道路图像进行道路检测，以确定目标车辆的相关车道的车道范围。
在本公开实施例中，目标车辆的相关车道可以包括目标车辆所行驶的第一车道和与第一车道相邻的第二车道。在一些实施例中，第一车道可以为主车道，第二车道可以包括主车道的左车道和右车道。
在本公开实施例中，车道范围可以根据相关车道上的车道线范围确定。
在一些实施例中，车道范围可以包括第一车道和与第一车道相邻的第二车道。
在另一些实施例中，车道范围可以包括第一车道对应的车道线。
在又一些实施例中，车道范围可以第一车道和与第一车道相邻的第二车道，以及每个车道对应的车道线。
在本公开实施例中，在一些实施例中，S120具体可以包括如下步骤S1201至S1203。
S1201、对道路图像进行图像分割，得到车道线图像；
S1202、基于车道分割图像中车道点对应的像素值，确定车道点位置，车道点位置为车道点在车辆坐标系下的位置；
S1203、基于车道点位置，确定目标车辆的相关车道的车道范围。
在一些实施例中，电子设备可以将道路图像输入预先训练好的图像分割模型中，得到车道线图像，并确定车道线图像中车道点对应的像素值，根据车道点对应的像素值和前置图像采集装置的标定参数，确定车辆坐标系下的车道点位置，然后根据车道点位置，确定目标车辆的相关车道的车道范围。
由此，在本公开实施例中，可以从道路图像中分割出车道线图像，并基于车道线图像中车道点对应的像素值以及前置图像采集装置的标定参数，准确的确定车道点位置，使得进一步基于车道点位置准确的确定相关车道的车道范围。
S130、对道路图像进行警示装置检测，得到警示装置的位置。
在本公开实施例中，在电子设备获取到道路图像之后，可以对道路图像进行警示装置检测，以确定警示装置的位置。
在本公开实施例中，警示装置可以是用于警示作业区域的装置。
在一些实施例中，警示装置可以包括锥桶、警示牌、桩桶以及圆筒等装置，在此不做限制。
在本公开实施例中，在一些实施例中，S130具体可以包括如下步骤S1301至S1302.
S1301、对道路图像进行图像分割，得到警示装置图像；
S1302、基于警示装置图像中的警示装置对应的像素值，确定警示装置的位置，警示装置的位置为警示装置在车辆坐标系下的位置。
在一些实施例中，电子设备可以将道路图像输入预先训练好的图像分割模型中，得到警示装置图像，并确定警示装置图像中警示装置对应的像素值，根据警示装置对应的像素值和前置图像采集装置的标定参数，确定车辆坐标系下的警示装置的位置。
由此，在本公开实施例中，可以从道路图像中分割出警示装置图像，并基于警示装置图像中警示装置对应的像素值，以及前置图像采集装置的标定参数，准确的确定警示装置的位置。
S140、响应于警示装置的位置落入车道范围内，生成预警信息，预警信息用于警示道路作业区域。
在本公开实施例中，在电子设备确定相关车道的车道范围和警示装置的位置之后，可以根据警示装置的位置和车道范围，判断警示装置的位置是否落入车道范围内，如果落入，则生成预警信息，并发出预警信息，使得利用预警信息警示道路作业区域，如果没有落入，则不生成预警信息。
在一些实施例中，响应于警示装置的位置位于相关车道的车道内，确定警示装置的位置落入车道范围内。
在另一些实施例中，响应于警示装置的位置位于相关车道中第一车道的车道线上，确定警示装置的位置落入车道范围内。
在又一些实施例中，响应于警示装置的位置位于相关车道的车道内，并且，警示装置的位置位于相关车道中第一车道的车道线上，确定警示装置的位置落入车道范围内。
在一些实施例中，警示信息可以包括作业区域所在的车道、作业区域与目标车辆的距离等信息，在此不做限制。
在本公开实施例中，在获取目标车辆在前进方向上的道路图像，能够对道路图像进行道路检测，得到目标车辆的相关车道的车道范围，以及对道路图像进行警示装置检测，得到警示装置的位置，使得进一步基于目标车辆的相关车道的车道范围和警示装置的位置，准确的确定警示装置的位置是否落入车道范围内，响应于警示装置的位置落入车道范围内，生成预警信息，以利用预警信息警示道路作业区域，由此，可以对道路图像进行实时分析，以准确的预测道路作业区域，并在预测到道路作业区域的情况下，向用户发出预警信息，使得用户获取到预警信息之后，及时避开作业区域，保证了驾驶用户和作业区域人员的安全性，也进一步保证了驾驶用户的驾驶体验。在本公开另一种实施方式中，可以采用不同的方式确定目标车辆的相关车道的车道范围和警示装置的位置。
在本公开实施例中，可以根据道路图像，确定车道范围。
在本公开实施例中，在一些实施例中，S120具体可以包括如下步骤S1201至S1202。
S1201、对道路图像进行车道线检测，得到道路图像所包含的拟合车道线；
S1202、基于拟合车道线，确定目标车辆的相关车道的车道范围。
其中，拟合车道线可以对从道路图像中采集到的车道点进行拟合得到。
针对S1201，在一些实施例中，S1201具体可以包括如下步骤S12011至S12013。
S12011、对道路图像进行车道线检测，得到车道线图像；
S12012、根据用于拍摄道路图像对应的拍摄标定参数，将车道线图像投影至目标车辆的车辆坐标系下，得到车道线投影点；
S12013、按照预设拟合参数，对目标车道对应的车道线投影点进行拟合，得到拟合车道线。
在一些实施例中，电子设备可以将道路图像输入预先训练好的图像分割模型中，以对道路图像进行车道线检测，得到车道线图像，然后，根据用于拍摄道路图像对应的拍摄标定参数，将车道线图像投影至目标车辆的车辆坐标系下，得到车道线投影点，按照预设拟合参数，对目标车道对应的车道线投影点进行拟合，得到曲线方程，将得到的曲线方程作为拟合车道线。
在一些实施例中，图像分割模型可以是卷积神经网络、深度学习网络等，在此不做限制。
在一些实施例中，用于拍摄道路图像对应的拍摄标定参数可以包括目标车辆上的前置图像采集装置的内参和外参。
在一些实施例中，电子设备可以将用于拍摄道路图像对应的拍摄标定参数作为图像坐标系和车辆坐标系的映射关系，基于该映射关系，将车道线图像投影至目标车辆的车辆坐标系下，得到车道线投影点。
在一些实施例中，预设拟合参数可以包括用于得到曲线方程的各阶次的拟合系数。曲线方程可以是三次方程，使得得到的拟合车道线为三次拟合曲线。
针对S1202，在一些实施例中，S1202具体可以包括如下步骤S12021至S12022。
S12021、分别确定目标车辆的位置和拟合车道线上所有拟合点的位置；
S12022、基于目标车辆的位置和拟合车道线上所有拟合点的位置，确定目标车辆的相关车道的车道范围。
其中，目标车辆的位置可以根据目标车辆在车辆坐标系下的实时坐标确定。
其中，拟合点的位置可以根据拟合点在车辆坐标系下的坐标确定。
在一些实施例中，电子设备可以根据目标车辆上的定位装置采集的定位信息和车辆坐标系，确定目标车辆在车辆坐标系下的实时坐标，得到目标车辆的位置，基于目标车辆的位置，确定目标车辆所行驶的车道，即确定第一车道和与第一车道相邻的第二车道；同时，根据拟合点在车辆坐标系下的坐标，确定拟合车道线上所有拟合点的位置，得到相关车道上每条车道线的车道线范围；然后，根据目标车辆所行驶的车道和相关车道上每条车道线的车道线范围，确定目标车辆的相关车道的车道范围。
由此，在本公开实施例中，可以对道路图像进行车道线检测，得到车道线图像，并根据车道线图像和用于拍摄道路图像对应的拍摄标定参数，确定车道线投影点，以及对车道线投影点进行拟合，得到拟合车道线，以进一步基于目标车辆的位置和拟合车道线上的拟合点的位置，准确的确定车道范围。
在本公开实施例中，可以根据道路图像，确定警示装置的位置。
在本公开实施例中，S130具体可以包括如下步骤S1301至S1302。
S1301、对道路图像进行警示装置检测，得到警示装置图像；和
S1302、基于警示装置图像，确定警示装置的位置。
针对S1301，在一些实施例中，S1301具体可以包括如下步骤S13011。
S13011、将道路图像输入预先训练好的图像分割模型中，利用图像分割模型对道路图像进行警示装置检测，得到警示装置图像。
其中，警示装置图像可以是警示装置检测框。
在一些实施例中，图像分割模型可以是卷积神经网络、深度学习网络等，在此不做限制。
针对S1302，在一些实施例中，S1302具体可以包括如下步骤S13021至S13023。
S13021、根据用于拍摄道路图像对应的拍摄标定参数，将警示装置图像投影至目标车辆的车辆坐标系下，得到警示装置投影点；
S13022、从警示装置投影点中选择目标投影点，目标投影点包括警示装置图像的左下角投影点和右下角投影点；
S13023、将左下角投影点和右下角投影点的中点，作为警示装置的位置。
在一些实施例中，电子设备可以根据用于拍摄道路图像对应的拍摄标定参数，将警示装置图像投影至目标车辆的车辆坐标系下，得到警示装置投影点，然后，从警示装置投影点中选择左下角投影点和右下角投影点，分别基于左下角投影点和右下角投影点对应的投影位置，计算左下角投影点和右下角投影点的中点，并将左下角投影点和右下角投影点的中点，作为警示装置的位置。
在一些实施例中，左下角投影点和右下角投影点的中点可以表示为cone_vcs_c[k]。
由此，在本公开实施例中，可以对道路图像进行警示装置检测，得到警示装置图像，并根据警示装置图像和用于拍摄道路图像对应的拍摄标定参数，确定车辆坐标系下警示装置投影点，根据警示装置投影点中的左下角投影点和右下角投影点，准确的确定警示装置的位置。在本公开又一种实施方式中，在生成预警信息之前，可以根据警示装置与任一车道对应的拟合车道线的最大距离，确定警示装置的位置是否落入车道范围，或者，根据第一车道对应的每侧拟合车道线上的警示装置数量，确定警示装置的位置是否落入车道范围。
在本公开一些实施例中，在生成预警信息之前，可以根据警示装置与任一车道对应的拟合车道线的最大距离，确定警示装置的位置是否落入车道范围。
图2示出了本公开实施例提供的另一种道路作业区域预警方法的流程示意图。
如图2所示，该道路作业区域预警方法可以包括如下步骤S210至步骤S270。
S210、获取目标车辆在前进方向上的道路图像。
其中，S210与S110相似，在此不做赘述。
S220、对道路图像进行车道线检测，得到道路图像所包含的拟合车道线。
S230、基于拟合车道线，确定目标车辆的相关车道的车道范围。
在本公开实施例中，在一些实施例中，在S230的同时，该方法还可以包括如下步骤S2301。
S2301、基于拟合车道线，计算相关车道中每条车道的宽度。
在一些实施例中，电子设备可以获取连续多帧道路图像，根据每帧道路图像对应的拟合车道线中相邻两条拟合车道线上车道点的位置，计算相邻两条拟合车道线之间的距离，然后，计算基于所有帧道路图像得到的距离计算距离的平均值，将距离的平均值作为每条车道的宽度。
在一些实施例中，每条车道的宽度可以表示为lane_width_avr_[j]。
S240、对道路图像进行警示装置检测，得到警示装置的位置。
其中，S240与S130相似，在此不做赘述。
S250、针对相关车道中的任一车道，基于警示装置的位置，计算警示装置与任一车道对应的拟合车道线的最大距离。
在本公开实施例中，车道范围可以包括第一车道和与第一车道相邻的第二车道，第一车道为目标车辆所行驶的车道。
在本公开实施例中，电子设备可以获取连续多帧道路图像，针对每帧道路图像对应的拟合车道线，确定相关车道的任意车道的拟合车道线，然后根据警示装置的位置和任一车道对应的拟合车道线，计算警示装置与任一车道对应的拟合车道线的最大距离，由此可以基于每帧道路图像计算得到最大距离，然后，基于所有帧道路图像计算得到的最大距离，计算最大距离均值，将最大距离均值，作为警示装置与任一车道对应的拟合车道线的最大距离。
在一些实施例中，任一车道同时存在左侧拟合车道线和右侧拟合车道线，则根据警示装置的位置和任一车道对应的拟合车道线，分别计算警示装置与任一车道的左侧拟合车道线和右侧拟合车道线的距离，从计算的两个距离中取距离的最大值，作为警示装置与任一车道对应的拟合车道线的最大距离。
在另一些实施例中，任一车道只存在左侧拟合车道线，则根据警示装置的位置和任 一车道对应的左侧拟合车道线，计算警示装置与左侧拟合车道线的距离，同时，可以根据任一车道的宽度和任一车道对应的左侧拟合车道线，计算警示装置与右侧拟合车道线的距离，从计算的两个距离中取距离的最大值，作为警示装置与任一车道对应的拟合车道线的最大距离。
在又一些实施例中，任一车道只存在右侧拟合车道线，则根据警示装置的位置和任一车道对应的右侧拟合车道线，计算警示装置与右侧拟合车道线的距离，同时，可以根据任一车道的宽度和任一车道对应的右侧拟合车道线，计算警示装置与左侧拟合车道线的距离，从计算的两个距离中取距离的最大值，作为警示装置与任一车道对应的拟合车道线的最大距离。
在一些实施例中，警示装置与任一车道对应的拟合车道线的最大距离可以表示为cone_lane_dis[k][j]。
S260、响应于最大距离小于预设的距离阈值，确定警示装置的位置落入车道范围。
在本公开实施例中，电子设备计算最大距离之后，将最大距离与预设的距离阈值比较，若最大距离小于预设的距离阈值，说明警示装置落入第一车道或第二车道内，则可以确定警示装置的位置落入车道范围，否则，说明警示装置未落入第一车道或第二车道内，则可以确定警示装置的位置未落入车道范围。
在本公开实施例中，预设的距离阈值可以是预先确定的用于判断警示装置的位置是否落入车道范围的最大距离。
在一些实施例中，落入警示装置的相关车道可以表示为lane_cone_occ[j]。
由此，在本公开实施例中，在车道范围包括第一车道和与第一车道相邻的第二车道，第一车道为目标车辆所行驶的车道的情况下，可以根据多帧图像确定警示装置与任一车道对应的拟合车道线的最大距离，准确的确定出警示装置的位置是否落入第一车道或第二车道内，以准确的确定警示装置的位置是否落入车道范围，消除了检测噪音，提高了预警信号的准确性。
S270、生成预警信息，预警信息用于警示道路作业区域。
其中，S270与S140相似，在此不做赘述。
在本公开另一些实施例中，在生成预警信息之前，可以根据第一车道对应的每侧拟合车道线上的警示装置数量，确定警示装置的位置是否落入车道范围。
图3示出了本公开实施例提供的又一种道路作业区域预警方法的流程示意图。
如图3所示，该道路作业区域预警方法可以包括如下步骤S310至步骤S370。
S310、获取目标车辆在前进方向上的道路图像。
其中，S310与S110相似，在此不做赘述。
S320、对道路图像进行车道线检测，得到道路图像所包含的拟合车道线。
S330、基于拟合车道线，确定目标车辆的相关车道的车道范围。
其中，S320和S330与S220和S230相似，在此不做赘述。
S340、对道路图像进行警示装置检测，得到警示装置的位置。
其中，S340与S130相似，在此不做赘述。
S350、针对第一车道，基于警示装置的位置，确定落在第一车道对应的每侧拟合车道线上的警示装置数量。
在本公开实施例中，车道范围可以包括第一车道对应的拟合车道线，第一车道为目标车辆所行驶的车道。
在本公开实施例中，电子设备可以获取连续多帧道路图像，针对每帧道路图像对应的第一车道，可以基于警示装置的位置，确定落在第一车道对应的每侧拟合车道线上的警示装置数量，以得到压在第一车道的左侧拟合车道线或右侧拟合车道线上的警示装置的数量，由此，可以基于每帧道路图像，得到落在第一车道对应的每侧拟合车道线上的警示装置数量，然后，基于所有帧道路图像得到的落在第一车道对应的每侧拟合车道线 上的警示装置数量，计算警示装置数量的均值，将警示装置数量的均值，作为落在第一车道对应的每侧拟合车道线上的警示装置数量。
在一些实施例中，对每帧道路图像对应的第一车道，电子设备可以获取第一车道的拟合车道线的预设压线阈值；响应于警示装置的位置与第一车道的左侧拟合车道线的位置之间的距离小于预设压线阈值，确定警示装置落在第一车道的左侧拟合车道线，并确定落在第一车道的左侧拟合车道线上的警示装置数量；响应于警示装置的位置与第一车道的右侧拟合车道线的位置之间的距离小于预设压线阈值，确定警示装置落在第一车道的右侧拟合车道线，并确定落在第一车道的右侧拟合车道线上的警示装置数量。
其中，预设压线阈值可以是用于判断警示装置是否压线的距离阈值。
在一些实施例中，落在第一车道对应的每侧拟合车道线上的警示装置数量可以表示为cone_on_line_[j]。
在一些实施例中，预设压线阈值可以表示为delta。
S360、响应于至少一侧拟合车道线上的警示装置数量大于警示装置的数量阈值，确定警示装置的位置落入车道范围。
在本公开实施例中，电子设备确定上述警示装置数量之后，将至少一侧拟合车道线上的警示装置数量与警示装置的数量阈值比较，若至少一侧拟合车道线上的警示装置数量大于警示装置的数量阈值，说明警示装置落在第一车道的左侧拟合车道线上或者右侧拟合车道线上，则可以确定警示装置的位置落入车道范围，否则，说明警示装置未压在第一车道的车道线上，则可以确定警示装置的位置未落入车道范围。
在本公开实施例中，警示装置的数量阈值可以是预先确定的用于判断警示装置的位置是否落入车道范围的最小数量。
在一些实施例中，响应于第一车道的左侧拟合车道线上的警示装置数量大于警示装置的数量阈值，可以确定警示装置落在第一车道的左车道内。
在另一些实施例中，响应于第一车道的右侧拟合车道线上的警示装置数量大于警示装置的数量阈值，可以确定警示装置落在第一车道的右车道内。
在又一些实施例中，响应于第一车道的右侧拟合车道线上的警示装置数量大于警示装置的数量阈值，且第一车道的左侧拟合车道线上的警示装置数量大于警示装置的数量阈值，可以确定警示装置落在第一车道的右车道和左车道内。
在一些实施例中，落入警示装置的第一车道的右车道和/或左车道可以表示为lane_cone_occ[j]。
由此，在本公开实施例中，在车道范围包括第一车道，第一车道为目标车辆所行驶的车道的情况下，将至少一侧拟合车道线上的警示装置数量与警示装置的数量阈值比较，可以准确的确定出警示装置的位置是否落入第一车道的左车道或者右车道内，以准确确定出警示装置的位置是否落入车道范围，由于车道范围可以根据多帧图像确定，因此消除了检测噪音，提高了预警信号的准确性。
S370、生成预警信息，预警信息用于警示道路作业区域。
综上，在生成预警信息之前，可以根据不同的方式，确定警示装置的位置是否落入车道范围，提高了警示装置的位置是否落入车道范围判断的灵活性，可以适应不同的判断场景。
在本公开再一种实施方式中，为了降低预警误报率，在确定警示装置的位置落入车道范围之后，还可以结合其他条件，生成预警信息。
图4示出了本公开实施例提供的再一种道路作业区域预警方法的流程示意图。
如图4所示，该道路作业区域预警方法可以包括如下步骤S410至步骤S460。
S410、获取目标车辆在前进方向上的道路图像。
其中，S410与S110相似，在此不做赘述。
S420、对道路图像进行车道线检测，得到道路图像所包含的拟合车道线。
S430、基于拟合车道线，确定目标车辆的相关车道的车道范围。
其中，S420和S430与S220和S230相似，在此不做赘述。
S440、对道路图像进行警示装置检测，得到警示装置的位置。
其中，S440与S130相似，在此不做赘述。
S450、响应于警示装置的位置落入车道范围内，确定相关车道中的有效车道、计算相关车道中每条车道的宽度、以及获取相关车道中每条车道上前方车辆的行驶速度。
在本公开实施例中，在一些实施例中，S450中的确定相关车道中的有效车道，具体可以包括如下步骤S4501至S4502。
S4501、针对相关车道中的任意一条车道，获取任意一条车道对应的拟合车道线的车道点采集数量；
S4502、响应于车道点采集数量大于车道采集点的数量阈值，则＝确定相关车道中的任意一条车道为有效车道。
其中，车道点采集数量可以是采集到的实际车道点的数量。
其中，车道采集点的数量阈值可以是预先设置的用于判断任意一条车道是否为有效车道的最小数量。
在一些实施例中，针对相关车道中的任意一条车道，电子设备可以获取任意一条车道对应的拟合车道线的车道点采集数量，并将车道点采集数量与车道采集点的数量阈值比较，在车道点采集数量大于车道采集点的数量阈值的情况下，说明任意一条车道上的实际车道点较多，基于实际车道点可以得到较准确的拟合车道线，即确定相关车道中的任意一条车道为有效车道，否则，车道点采集数量小于车道采集点的数量阈值，则说明任意一条车道上的实际车道点较少，基于实际车道点很难得到较准确的拟合车道线，即确定相关车道中的任意一条车道为无效车道。
在一些实施例中，有效车道可以表示为lane_valid[j]。
在本公开实施例中，在一些实施例中，S450中的计算相关车道中每条车道的宽度，具体可以包括如下步骤：
S4503、针对相关车道中的每条车道，基于每条车道的左侧的拟合车道线和右侧的拟合车道线，计算每条车道的宽度。
在一些实施例中，针对相关车道中的每条车道，电子设备可以从每条车道的左侧的拟合车道线和右侧的拟合车道线上选择在一个方向上位置相同的车道点，根据这些车道点在另一个方向上的位置，计算每条车道的宽度。
在一些实施例中，在一个方向上位置可以是车道点在车辆坐标系下的横坐标或者纵坐标。
在本公开实施例中，在一些实施例中，S450中的获取相关车道中每条车道上前方车辆的行驶速度，具体可以包括如下步骤S4504至S4506。
S4504、对道路图像进行前方车辆检测，得到前方车辆图像和前方车辆接地线；
S4505、根据用于拍摄道路图像对应的拍摄标定参数，将前方车辆图像和前方车辆接地线投影至目标车辆的车辆坐标系下，得到前方车辆的实时位置；
S4506、根据前方车辆的实时位置、目标车辆的实时位置和目标车辆的车速，确定前方车辆的行驶速度。
针对S4504，电子设备可以将道路图像输入预先训练好的图像分割模型中，以对道路图像进行前方车辆检测，得到前方车辆图像和前方车辆接地线。
其中，前方车辆图像可以是前方车辆检测框。
其中，前方车辆接地线可以为前方车辆的车辆中心，用于确定前方车辆所属的车道。
在一些实施例中，前方车辆接地线可以表示为：veh[m]。
针对S4505，电子设备可以根据用于拍摄道路图像对应的拍摄标定参数，将前方车辆图像和前方车辆接地线投影至目标车辆的车辆坐标系下，得到前方车辆的实时位置， 以进一步基于前方车辆的实时位置，确定前方车辆的行驶速度。
针对S4506，电子设备可以根据前方车辆的实时位置、目标车辆的实时位置，实时确定前方车辆与目标车辆的相对位置，并根据目标车辆的车速和相对位置，确定前方车辆的行驶速度。
S460、响应于落入警示装置的相关车道为有效车道、落入警示装置的相关车道的宽度大于预设的宽度阈值，且落入警示装置的相关车道上前方车辆的行驶速度小于预设的速度阈值，生成预警信息，预警信息用于警示道路作业区域。
需要说明的是，针对作业车辆来说，车速低于正常行驶的车辆。
基于上述原因，预设的速度阈值可以是用于确定前方车辆是否是正常行驶车辆的速度。
在一些实施例中，预设的速度阈值可以表示为vel_speed_vel。
在本公开实施例中，在电子设备确定警示装置的位置落入车道范围内之后，在确定落入警示装置的相关车道为有效车道、落入警示装置的相关车道的宽度大于预设的宽度阈值且落入警示装置的相关车道上前方车辆的行驶速度小于预设的速度阈值的情况下，说明落入警示装置的相关车道是需要进行警示的车道，并确定落入警示装置的相关车道足够宽，以及落入警示装置的相关车道未被正常行驶的车辆占用，因此，可以综合上述条件确定落入警示装置的相关车道上正在进行道路作业，可以生成警示信息。
在一些实施例中，落入警示装置的相关车道可以表示为lane_vehicles_occ[j]。
由此，在本公开实施例中，在确定警示装置的位置落入车道范围内之后，在落入警示装置的相关车道是需要进行警示的车道，并确定落入警示装置的相关车道足够宽，以及落入警示装置的相关车道未被正常行驶的车辆占用的情况下，生成预警信息，以结合更多的信息进行道路作业区域预警，因此，降低了预警误报率，进一步提高了用户的驾驶体验。
需要说明的是，在电子设备确定警示装置的位置落入车道范围内之后，也可以结合落入警示装置的相关车道为有效车道、落入警示装置的相关车道的宽度大于预设的宽度阈值、且落入警示装置的相关车道上前方车辆的行驶速度小于预设的速度阈值中的其中一种条件或者任意两种条件，生成警示信息，提高了判断是否生成警示信息的灵活性。
在本公开再一种实施方式中，可以对道路作业区域预警方法的整体逻辑进行解释。
图5示出了本公开实施例提供的一种道路作业区域预警方法的逻辑示意图。
如图5所示，该道路作业区域预警方法可以包括如下步骤S510至步骤S530。
S510、获取目标车辆在前进方向上的道路图像。
其中，S510与S110相似，在此不做赘述。
S520、基于道路图像，得到车道线图像、警示装置图像、前方车辆图像和前方车辆接地线。
在本公开实施例中，在一些实施例中，S520中的基于道路图像，得到车道线图像，具体可以包括如下步骤S5201至S5203。S5201、将道路图像输入至预先训练好的图像分割模型中，得到车道线图像。
其中，S5201具体可以参见前述描述，在此不做赘述。
在本公开实施例中，在一些实施例中，S520中的基于道路图像，得到警示装置图像，具体可以包括如下步骤：S5202、将道路图像输入至预先训练好的图像分割模型中，得到警示装置图像。
其中，S5202具体可以参见前述描述，在此不做赘述。
在本公开实施例中，在一些实施例中，S520中的基于道路图像，得到前方车辆图像和前方车辆接地线，具体可以包括如下步骤：S5203、对道路图像输入至预先训练好的图像分割模型中，以对道路图像进行前方车辆检测，得到前方车辆图像和前方车辆接 地线。
S530、基于用于拍摄道路图像对应的拍摄标定参数和自车运动信息，对车道线图像、警示装置图像、前方车辆图像和前方车辆接地线进行融合，生成预警信息。
在本公开实施例中，在一些实施例中，S530具体可以包括如下步骤S5301至S5304。
S5301、基于车道线图像和用于拍摄道路图像对应的拍摄标定参数，计算车道相关信息。
S5302、基于警示装置图像，计算警示装置相关信息。
S5303、基于前方车辆图像、前方车辆接地线、用于拍摄道路图像对应的拍摄标定参数，计算前方车辆相关信息。
S5304、响应于警示装置的位置在相关车道内或者落在第一车道的拟合车道线上，且相关车道的宽度大于预设的宽度阈值，且相关车道为有效车道以及前方车辆的行驶速度小于预设的速度阈值，生成预警信息。
在本公开实施例中，图6示出了本公开实施例提出了另一种道路作业区域预警方法的逻辑示意图。
如图6所示，S5301具体可以包括如下步骤S53011至步骤S53014。
S53011、对道路图像进行车道线检测，得到道路图像所包含的拟合车道线。
其中，S53011具体可以包括：根据用于拍摄道路图像对应的拍摄标定参数，将车道线图像投影至目标车辆的车辆坐标系下，得到车道线投影点；按照预设拟合参数，对目标车道对应的车道线投影点进行拟合，得到拟合车道线。
S53012、基于拟合车道线，确定目标车辆的相关车道的车道范围。
其中，车道范围可以包括第一车道、第二车道以及第一车道、第二车道上的左车道线和右车道线。
S53013、确定相关车道中的有效车道。
S53014、计算相关车道中每条车道的宽度。
在本公开实施例中，图7示出了本公开实施例提出了又一种道路作业区域预警方法的逻辑示意图。
如图7所示，S5302具体可以包括如下步骤S53021至步骤S53023。
S53021、基于警示装置图像，确定警示装置的位置。
S53022、确定警示装置的位置是否落入相关车道中的任一车道。
其中，车道范围包括第一车道和与第一车道相邻的第二车道，第一车道为目标车辆所行驶的车道；
相应的，S53022具体可以包括：针对相关车道中的任一车道，基于警示装置的位置，计算警示装置与任一车道对应的拟合车道线的最大距离；响应于最大距离小于预设的距离阈值，确定警示装置的位置落入车道范围，具体可以确定警示装置的位置落入相关车道中的任一车道，否则，确定警示装置的位置未落入相关车道中的任一车道。
S53023、确定警示装置的位置是否落在第一车道的拟合车道线上。
其中，车道范围包括第一车道对应的拟合车道线，第一车道为目标车辆所行驶的车道。
相应的，S53023具体可以包括：针对第一车道，基于警示装置的位置，确定落在第一车道对应的每侧拟合车道线上的警示装置数量；响应于至少一侧拟合车道线上的警示装置数量大于警示装置的数量阈值，确定警示装置的位置落入车道范围，具体可以确定警示装置的位置落在第一车道的拟合车道线上，否则，确定警示装置的位置未落在第一车道的拟合车道线上。
在本公开实施例中，图8示出了本公开实施例提出了再一种道路作业区域预警方法的逻辑示意图。
如图8所示，S5303具体可以包括如下步骤S53031至S53032。
S53031、根据用于拍摄道路图像对应的拍摄标定参数，将前方车辆图像和前方车辆接地线投影至目标车辆的车辆坐标系下，得到前方车辆的实时位置。
S53032、根据前方车辆的实时位置、目标车辆的实时位置和目标车辆的车速，确定前方车辆的行驶速度。
本公开实施例还提供了一种用于实现上述的道路作业区域预警方法的道路作业区域预警装置，下面结合图9进行说明。在本公开实施例中，该道路作业区域预警装置可以为电子设备或服务器。其中，该电子设备可以包括但不限于诸如智能手机、笔记本电脑、平板电脑(PAD)、便携式多媒体播放器(PMP)、车载终端(例如车载导航终端)等的移动终端，以及诸如台式计算机等的固定终端。服务器可以是云服务器或者服务器集群等具有存储及计算功能的设备。
图9示出了本公开实施例提供的一种道路作业区域预警装置的结构示意图。
如图9所示，道路作业区域预警装置900可以包括：道路图像获取模块910、车道范围确定模块920、警示装置的位置确定模块930和预警信息生成模块940。
道路图像获取模块910，可以配置于获取目标车辆在前进方向上的道路图像。
车道范围确定模块920，可以配置于对道路图像进行道路检测，得到目标车辆的相关车道的车道范围。
警示装置的位置确定模块930，可以配置于对道路图像进行警示装置检测，得到警示装置的位置。
预警信息生成模块940，可以配置于响应于警示装置的位置落入车道范围内，生成预警信息，预警信息用于警示道路作业区域。
在本公开实施例中，在获取目标车辆在前进方向上的道路图像，能够对道路图像进行道路检测，得到目标车辆的相关车道的车道范围，以及对道路图像进行警示装置检测，得到警示装置的位置，使得进一步基于目标车辆的相关车道的车道范围和警示装置的位置，准确的确定警示装置的位置是否落入车道范围内，响应于警示装置的位置落入车道范围内，生成预警信息，以利用预警信息警示道路作业区域，由此，可以对道路图像进行实时分析，以准确的预测道路作业区域，并在预测到道路作业区域的情况下，向用户发出预警信息，使得用户获取到预警信息之后，及时避开作业区域，保证了驾驶用户和作业区域人员的安全性，也进一步保证了驾驶用户的驾驶体验。
在本公开一些实施例中，车道范围确定模块920可以包括：拟合车道线生成单元和车道范围确定单元。
拟合车道线生成单元，可以配置于对道路图像进行车道线检测，得到道路图像所包含的拟合车道线。
车道范围确定单元，可以配置于基于拟合车道线，确定目标车辆的相关车道的车道范围。
在本公开一些实施例中，拟合车道线生成单元还可以配置于，对道路图像进行车道线检测，得到车道线图像；根据用于拍摄道路图像对应的拍摄标定参数，将车道线图像投影至目标车辆的车辆坐标系下，得到车道线投影点；按照预设拟合参数，对目标车道对应的车道线投影点进行拟合，得到拟合车道线。
在本公开一些实施例中，车道范围确定单元还可以配置于，分别确定目标车辆的位置和拟合车道线上所有拟合点的位置；基于目标车辆的位置和拟合车道线上所有拟合点的位置，确定目标车辆的相关车道的车道范围。
在本公开一些实施例中，警示装置的位置确定模块930可以包括：警示装置图像确定单元和警示装置的位置确定单元。
警示装置图像确定单元，可以配置于对道路图像进行警示装置检测，得到警示装置图像。
警示装置的位置确定单元，可以配置于基于警示装置图像，确定警示装置的位置。
在本公开一些实施例中，警示装置的位置确定单元还可以配置于，根据用于拍摄道路图像对应的拍摄标定参数，将警示装置图像投影至目标车辆的车辆坐标系下，得到警示装置投影点；从警示装置投影点中选择目标投影点，目标投影点包括警示装置图像的左下角投影点和右下角投影点；将左下角投影点和右下角投影点的中点，作为警示装置的位置。
在本公开一些实施例中，车道范围包括第一车道和与第一车道相邻的第二车道，第一车道为目标车辆所行驶的车道。
该道路作业区域预警装置还可以包括：最大距离计算模块和第一落入确定模块。
最大距离计算模块，可以配置于针对相关车道中的任一车道，基于警示装置的位置，计算警示装置与任一车道对应的拟合车道线的最大距离。
第一落入确定模块，可以配置于响应于最大距离小于预设的距离阈值，确定警示装置的位置落入车道范围。
在本公开一些实施例中，车道范围包括第一车道对应的拟合车道线，第一车道为目标车辆所行驶的车道。
该道路作业区域预警装置还可以包括：警示装置数量确定模块和第二落入确定模块。
警示装置数量确定模块，可以配置于针对第一车道，基于警示装置的位置，确定落在第一车道对应的每侧拟合车道线上的警示装置数量。
第二落入确定模块，可以配置于响应于至少一侧拟合车道线上的警示装置数量大于警示装置的数量阈值，确定警示装置的位置落入车道范围。
在本公开一些实施例中，该道路作业区域预警装置还可以包括：有效车道确定模块、宽度计算模块和行驶速度获取模块。
有效车道确定模块，可以配置于确定相关车道中的有效车道。
宽度计算模块，可以配置于计算相关车道中每条车道的宽度。
行驶速度获取模块，可以配置于获取相关车道中每条车道上前方车辆的行驶速度。
相应的，预警信息生成模块940还可以配置于，响应于落入警示装置的相关车道为有效车道、落入警示装置的相关车道的宽度大于预设的宽度阈值，且落入警示装置的相关车道上前方车辆的行驶速度小于预设的速度阈值，生成预警信息。
在本公开一些实施例中，有效车道确定模块还可以配置于，针对相关车道中的任意一条车道，获取任意一条车道对应的拟合车道线的车道点采集数量；响应于车道点采集数量大于车道采集点的数量阈值，确定相关车道中的任意一条车道为有效车道。
在本公开一些实施例中，宽度计算模块还可以配置于，针对相关车道中的每条车道，基于每条车道的左侧的拟合车道线和右侧的拟合车道线，计算每条车道的宽度。
在本公开一些实施例中，行驶速度获取模块还可以配置于，对道路图像进行前方车辆检测，得到前方车辆图像和前方车辆接地线；
根据用于拍摄道路图像对应的拍摄标定参数，将前方车辆图像和前方车辆接地线投影至目标车辆的车辆坐标系下，得到前方车辆的实时位置；
根据前方车辆的实时位置、目标车辆的实时位置和目标车辆的车速，确定前方车辆的行驶速度。
需要说明的是，图9所示的道路作业区域预警装置900可以执行图1至图8所示的方法实施例中的各个步骤，并且实现图1至图8所示的方法实施例中的各个过程和效果，在此不做赘述。
本公开实施例还提供了一种道路作业区域预警设备，该设备包括：一个或多个处理器；存储装置，用于存储一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现本公开实施例所提供的道路作业区域预警方法。
图10示出了本公开实施例提供的一种道路作业区域预警设备的结构示意图。
如图10所示，该数据采集设备可以包括处理器1001以及存储有计算机程序指令的 存储器1002。
具体地，上述处理器1001可以包括中央处理器(CPU)，或者特定集成电路(Application Specific Integrated Circuit，ASIC)，或者可以被配置成实施本申请实施例的一个或多个集成电路。
存储器1002可以包括用于信息或指令的大容量存储器。举例来说而非限制，存储器1002可以包括硬盘驱动器(Hard Disk Drive，HDD)、软盘驱动器、闪存、光盘、磁光盘、磁带或通用串行总线(Universal Serial Bus，USB)驱动器或者两个及其以上这些的组合。在合适的情况下，存储器1002可包括可移除或不可移除(或固定)的介质。在合适的情况下，存储器1002可在综合网关设备的内部或外部。在特定实施例中，存储器1002是非易失性固态存储器。在特定实施例中，存储器1002包括只读存储器(Read-Only Memory，ROM)。在合适的情况下，该ROM可以是掩模编程的ROM、可编程ROM(Programmable ROM，PROM)、可擦除PROM(Electrical Programmable ROM，EPROM)、电可擦除PROM(Electrically Erasable Programmable ROM，EEPROM)、电可改写ROM(Electrically Alterable ROM，EAROM)或闪存，或者两个或及其以上这些的组合。
处理器1001通过读取并执行存储器1002中存储的计算机程序指令，以执行本公开实施例所提供的道路作业区域预警方法的步骤。
在一个示例中，该道路作业区域预警设备还可包括收发器1003和总线1004。其中，如图10所示，处理器1001、存储器1002和收发器1003通过总线1004连接并完成相互间的通信。
总线1004包括硬件、软件或两者。举例来说而非限制，总线可包括加速图形端口(Accelerated Graphics Port，AGP)或其他图形总线、增强工业标准架构(Extended Industry Standard Architecture，EISA)总线、前端总线(Front Side BUS，FSB)、超传输(Hyper Transport，HT)互连、工业标准架构(Industrial Standard Architecture，ISA)总线、无限带宽互连、低引脚数(Low Pin Count，LPC)总线、存储器总线、微信道架构(Micro Channel Architecture，MCA)总线、外围控件互连(Peripheral Component Interconnect，PCI)总线、PCI-Express(PCI-X)总线、串行高级技术附件(Serial Advanced Technology Attachment，SATA)总线、视频电子标准协会局部(Video Electronics Standards Association Local Bus，VLB)总线或其他合适的总线或者两个或更多个以上这些的组合。在合适的情况下，总线1004可包括一个或多个总线。尽管本申请实施例描述和示出了特定的总线，但本申请考虑任何合适的总线或互连。
本公开实施例还提供了一种计算机可读存储介质，该存储介质可以存储有计算机程序，当计算机程序被处理器执行时，使得处理器实现本公开实施例所提供的道路作业区域预警方法。
上述的存储介质可以例如包括计算机程序指令的存储器1002，上述指令可由电池内阻检测设备的处理器1001执行以完成本公开实施例所提供的电池内阻检测方法。可选地，存储介质可以是非临时性计算机可读存储介质，例如，非临时性计算机可读存储介质可以是ROM、随机存取存储器(Random Access Memory，RAM)、光盘只读存储器(Compact Disc ROM，CD-ROM)、磁带、软盘和光数据存储设备等。
本公开实施例还提供了一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现本公开实施例所提供的道路作业区域预警方法。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有 的要素。
以上所述仅是本公开的具体实施方式，使本领域技术人员能够理解或实现本公开。对这些实施例的多种修改对本领域的技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本公开的精神或范围的情况下，在其它实施例中实现。因此，本公开将不会被限制于本文所述的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。

Claims (16)

  1. 一种道路作业区域预警方法，包括：
    获取目标车辆在前进方向上的道路图像；
    对所述道路图像进行道路检测，得到所述目标车辆的相关车道的车道范围；
    对所述道路图像进行警示装置检测，得到所述警示装置的位置；
    响应于所述警示装置的位置落入所述车道范围内，生成预警信息，所述预警信息用于警示道路作业区域。
  2. 根据权利要求1所述的方法，其中，所述对所述道路图像进行道路检测，得到所述目标车辆的相关车道的车道范围，包括：
    对所述道路图像进行车道线检测，得到所述道路图像所包含的拟合车道线；
    基于所述拟合车道线，确定所述目标车辆的相关车道的车道范围。
  3. 根据权利要求2所述的方法，其中，所述对所述道路图像进行车道线检测，得到所述道路图像所包含的拟合车道线，包括：
    对所述道路图像进行车道线检测，得到车道线图像；
    根据用于拍摄所述道路图像对应的拍摄标定参数，将所述车道线图像投影至所述目标车辆的车辆坐标系下，得到车道线投影点；
    按照预设拟合参数，对所述目标车道对应的车道线投影点进行拟合，得到所述拟合车道线。
  4. 根据权利要求2所述的方法，其中，所述基于所述拟合车道线，确定所述目标车辆的相关车道的车道范围，包括：
    分别确定所述目标车辆的位置和所述拟合车道线上所有拟合点的位置；
    基于所述目标车辆的位置和所述拟合车道线上所有拟合点的位置，确定所述目标车辆的相关车道的车道范围。
  5. 根据权利要求1所述的方法，其中，所述对所述道路图像进行警示装置检测，得到所述警示装置的位置，包括：
    对所述道路图像进行警示装置检测，得到警示装置图像；
    基于所述警示装置图像，确定所述警示装置的位置。
  6. 根据权利要求5所述的方法，其中，所述基于所述警示装置图像，确定所述警示装置的位置，包括：
    根据用于拍摄所述道路图像对应的拍摄标定参数，将所述警示装置图像投影至所述目标车辆的车辆坐标系下，得到警示装置投影点；
    从所述警示装置投影点中选择目标投影点，所述目标投影点包括警示装置图像的左下角投影点和右下角投影点；
    将所述左下角投影点和所述右下角投影点的中点，作为所述警示装置的位置。
  7. 根据权利要求2所述的方法，其中，所述车道范围包括第一车道和与所述第一车道相邻的第二车道，所述第一车道为所述目标车辆所行驶的车道；
    其中，在所述生成预警信息之前，所述方法还包括：
    针对所述相关车道中的任一车道，基于所述警示装置的位置，计算所述警示装置与所述任一车道对应的拟合车道线的最大距离；
    响应于所述最大距离小于预设的距离阈值，确定所述警示装置的位置落入所述车道 范围。
  8. 根据权利要求2所述的方法，其中，所述车道范围包括第一车道对应的拟合车道线，所述第一车道为所述目标车辆所行驶的车道；
    其中，在所述生成预警信息之前，所述方法还包括：
    针对所述第一车道，基于所述警示装置的位置，确定落在所述第一车道对应的每侧拟合车道线上的所述警示装置数量；
    响应于至少一侧拟合车道线上的所述警示装置数量大于警示装置的数量阈值，确定所述警示装置的位置落入所述车道范围。
  9. 根据权利要求2所述的方法，其中，在所述生成所述预警信息之前，所述方法还包括：
    确定所述相关车道中的有效车道；
    计算所述相关车道中每条车道的宽度；
    获取所述相关车道中每条车道上前方车辆的行驶速度；
    其中；所述响应于所述警示装置的位置落入所述车道范围内，生成预警信息，包括：
    响应于落入所述警示装置的相关车道为有效车道、落入所述警示装置的相关车道的宽度大于预设的宽度阈值，且落入所述警示装置的相关车道上前方车辆的行驶速度小于预设的速度阈值，生成所述预警信息。
  10. 根据权利要求9所述的方法，其中，所述确定所述相关车道中的有效车道，包括：
    针对所述相关车道中的任意一条车道，获取所述任意一条车道对应的拟合车道线的车道点采集数量；
    响应于所述车道点采集数量大于车道采集点的数量阈值，确定所述相关车道中的任意一条车道为有效车道。
  11. 根据权利要求9所述的方法，其中，所述计算所述相关车道中每条车道的宽度，包括：
    针对所述相关车道中的每条车道，基于所述每条车道的左侧的拟合车道线和右侧的拟合车道线，计算所述每条车道的宽度。
  12. 根据权利要求9所述的方法，其中，所述获取所述相关车道中每条车道上前方车辆的行驶速度，包括：
    对所述道路图像进行前方车辆检测，得到前方车辆图像和前方车辆接地线；
    根据用于拍摄所述道路图像对应的拍摄标定参数，将所述前方车辆图像和所述前方车辆接地线投影至所述目标车辆的车辆坐标系下，得到所述前方车辆的实时位置；
    根据所述前方车辆的实时位置、所述目标车辆的实时位置和所述目标车辆的车速，确定所述前方车辆的行驶速度。
  13. 一种道路作业区域预警装置，其中，包括：
    道路图像获取模块，配置于获取目标车辆在前进方向上的道路图像；
    车道范围确定模块，配置于对所述道路图像进行道路检测，得到所述目标车辆的相关车道的车道范围；
    警示装置的位置确定模块，配置于对所述道路图像进行警示装置检测，得到所述警示装置的位置；
    预警信息生成模块，配置于响应于所述警示装置的位置落入所述车道范围内，生成预警信息，所述预警信息用于警示道路作业区域。
  14. 一种道路作业区域预警设备，包括：
    处理器；
    存储器，用于存储可执行指令；
    其中，所述处理器用于从所述存储器中读取所述可执行指令，并执行所述可执行指令以实现上述权利要求1至12中任一项所述的道路作业区域预警方法。
  15. 一种计算机可读存储介质，其上存储有计算机程序，其中，所述存储介质存储有计算机程序，当所述计算机程序被处理器执行时，使得处理器实现上述权利要求1至12中任一项所述的道路作业区域预警方法。
  16. 一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现上述权利要求1至12中任一项所述的道路作业区域预警方法。
PCT/CN2022/135973 2021-12-06 2022-12-01 道路作业区域预警方法及装置 WO2023103882A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111480429.1 2021-12-06
CN202111480429.1A CN115447597A (zh) 2021-12-06 2021-12-06 道路作业区域预警方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023103882A1 true WO2023103882A1 (zh) 2023-06-15

Family

ID=84294655

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/135973 WO2023103882A1 (zh) 2021-12-06 2022-12-01 道路作业区域预警方法及装置

Country Status (2)

Country Link
CN (1) CN115447597A (zh)
WO (1) WO2023103882A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5931888A (en) * 1994-09-22 1999-08-03 Aisin Aw Co., Ltd. Navigation system for vehicles with alternative route searching capabilities
CN106256642A (zh) * 2015-06-03 2016-12-28 福特全球技术公司 基于摄像机获取的图像信息控制车辆部件的系统和方法
CN109532826A (zh) * 2017-09-21 2019-03-29 天津所托瑞安汽车科技有限公司 一种基于车道线视觉识别技术优化的雷达防碰撞预警方法
CN112109633A (zh) * 2019-06-19 2020-12-22 上海高德威智能交通系统有限公司 车道偏离预警方法、装置、设备、车辆及存储介质
CN113673438A (zh) * 2021-08-23 2021-11-19 上海商汤临港智能科技有限公司 一种碰撞预警的方法、装置、电子设备及存储介质
CN113688652A (zh) * 2020-05-18 2021-11-23 魔门塔(苏州)科技有限公司 一种异常驾驶行为的处理方法和装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5931888A (en) * 1994-09-22 1999-08-03 Aisin Aw Co., Ltd. Navigation system for vehicles with alternative route searching capabilities
CN106256642A (zh) * 2015-06-03 2016-12-28 福特全球技术公司 基于摄像机获取的图像信息控制车辆部件的系统和方法
CN109532826A (zh) * 2017-09-21 2019-03-29 天津所托瑞安汽车科技有限公司 一种基于车道线视觉识别技术优化的雷达防碰撞预警方法
CN112109633A (zh) * 2019-06-19 2020-12-22 上海高德威智能交通系统有限公司 车道偏离预警方法、装置、设备、车辆及存储介质
CN113688652A (zh) * 2020-05-18 2021-11-23 魔门塔(苏州)科技有限公司 一种异常驾驶行为的处理方法和装置
CN113673438A (zh) * 2021-08-23 2021-11-19 上海商汤临港智能科技有限公司 一种碰撞预警的方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN115447597A (zh) 2022-12-09

Similar Documents

Publication Publication Date Title
US11747809B1 (en) System and method for evaluating the perception system of an autonomous vehicle
WO2021042856A1 (zh) 一种车道中心线确定方法及装置
WO2013125404A1 (ja) 立体物検出装置
CN111595357B (zh) 可视化界面的显示方法、装置、电子设备和存储介质
CN104376297A (zh) 道路上的线型指示标志的检测方法和装置
CN112069944A (zh) 一种道路拥堵等级确定方法
CN111915883A (zh) 一种基于车载摄像的道路交通状况检测方法
US20180224296A1 (en) Image processing system and image processing method
EP4160346A1 (en) Method and device for identifying vehicle lane changing tendency
CN113297881B (zh) 一种目标检测方法及相关装置
WO2021259260A1 (zh) 一种制动等级的评估方法、装置、车辆和存储介质
CN113139607A (zh) 障碍物检测方法和装置
CN111856417B (zh) 车载毫米波雷达的性能分析方法、装置、终端及存储介质
WO2023088486A1 (zh) 车道线提取方法、装置、车辆及存储介质
WO2023103882A1 (zh) 道路作业区域预警方法及装置
CN109830123B (zh) 路口碰撞预警方法及系统
TW201536609A (zh) 障礙物偵測裝置
CN112990117B (zh) 基于智能驾驶系统的安装数据处理方法及装置
CN113257036A (zh) 一种车辆碰撞预警方法、装置、设备和存储介质
CN114596706B (zh) 路侧感知系统的检测方法及装置、电子设备和路侧设备
TWI621073B (zh) Road lane detection system and method thereof
JP5682302B2 (ja) 走行道路推定装置、方法およびプログラム
JP7468633B2 (ja) 状態推定方法、状態推定装置、及びプログラム
CN115027457A (zh) 碰撞检测方法、装置、车辆及存储介质
Sun et al. Toward the design of an efficient transparent traffic environment based on vehicular edge computing

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22903304

Country of ref document: EP

Kind code of ref document: A1