WO2020172842A1 - 车辆智能驾驶控制方法及装置、电子设备和存储介质 - Google Patents

车辆智能驾驶控制方法及装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2020172842A1
WO2020172842A1 PCT/CN2019/076441 CN2019076441W WO2020172842A1 WO 2020172842 A1 WO2020172842 A1 WO 2020172842A1 CN 2019076441 W CN2019076441 W CN 2019076441W WO 2020172842 A1 WO2020172842 A1 WO 2020172842A1
Authority
WO
WIPO (PCT)
Prior art keywords
target object
vehicle
detection frame
distance
module
Prior art date
Application number
PCT/CN2019/076441
Other languages
English (en)
French (fr)
Inventor
何园
朱海波
毛宁元
Original Assignee
深圳市商汤科技有限公司
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 深圳市商汤科技有限公司 filed Critical 深圳市商汤科技有限公司
Priority to SG11202108455PA priority Critical patent/SG11202108455PA/en
Priority to KR1020217026297A priority patent/KR20210115026A/ko
Priority to JP2021545946A priority patent/JP2022520544A/ja
Priority to PCT/CN2019/076441 priority patent/WO2020172842A1/zh
Publication of WO2020172842A1 publication Critical patent/WO2020172842A1/zh
Priority to US17/398,686 priority patent/US20210365696A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • 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
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
    • 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
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/53—Road markings, e.g. lane marker or crosswalk
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance
    • 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
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G06T2207/10021—Stereoscopic video; Stereoscopic image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10048—Infrared image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256—Lane; Road marking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/12—Bounding box
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/625—License plates

Definitions

  • the present disclosure relates to the field of image processing technology, and in particular to a method and device for intelligent driving control of a vehicle, electronic equipment and storage medium.
  • the camera loaded on the vehicle can be used to capture road information and conduct distance testing to realize functions such as automatic driving or assisted driving.
  • vehicles are densely occluded, and the position of the vehicle marked by the detection frame of the vehicle deviates greatly from the actual position, resulting in inaccurate traditional distance testing methods.
  • the present disclosure proposes a technical solution for vehicle intelligent driving control.
  • a vehicle intelligent driving control method including:
  • a vehicle intelligent driving control device including:
  • a video stream acquisition module which is used to collect a video stream of a road image of the scene where the vehicle is located via the on-board camera of the vehicle;
  • a drivable area determination module configured to detect a target object in the road image to obtain a detection frame of the target object; determine the drivable area of the vehicle in the road image;
  • a detection frame adjustment module configured to adjust the detection frame of the target object according to the drivable area
  • the control module is used for intelligent driving control of the vehicle according to the adjusted detection frame.
  • an electronic device including:
  • a memory for storing processor executable instructions
  • the processor is configured to execute any one of the methods described above.
  • a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the method described in any one of the above is implemented.
  • the video stream of the road image of the scene where the vehicle is collected is collected by the vehicle's on-board camera; the target object is detected in the road image, the detection frame of the target object; the vehicle is determined in the road image
  • the drivable area; the detection frame of the target object is adjusted according to the drivable area; the intelligent driving control of the vehicle is performed according to the adjusted detection frame.
  • the detection frame of the target object adjusted according to the drivable area can more accurately identify the position of the target object, which can be used to determine the actual position of the target object more accurately, so as to perform intelligent driving control of the vehicle more accurately.
  • Fig. 1 shows a flowchart of a vehicle intelligent driving control method according to an embodiment of the present disclosure
  • Fig. 2 shows a schematic diagram of a road drivable area in a vehicle intelligent driving control method according to an embodiment of the present disclosure
  • FIG. 3 shows a flowchart of step S20 of a method for controlling intelligent driving of a vehicle according to an embodiment of the present disclosure
  • step S20 shows a flowchart of step S20 of a method for controlling intelligent driving of a vehicle according to an embodiment of the present disclosure
  • FIG. 5 shows a flowchart of step S30 of a method for controlling intelligent driving of a vehicle according to an embodiment of the present disclosure
  • Fig. 6 shows a flowchart of step S40 of a method for controlling intelligent driving of a vehicle according to an embodiment of the present disclosure
  • FIG. 7 shows a flowchart of a method for controlling intelligent driving of a vehicle according to an embodiment of the present disclosure
  • FIG. 8 shows a block diagram of a vehicle intelligent driving control device according to an embodiment of the present disclosure
  • Fig. 9 is a block diagram showing an electronic device according to an exemplary embodiment
  • Fig. 10 is a block diagram showing an electronic device according to an exemplary embodiment.
  • Fig. 1 shows a flow chart of a vehicle intelligent driving control method according to an embodiment of the present disclosure.
  • the vehicle intelligent driving control method includes:
  • Step S10 Collect a video stream of a road image of the scene where the vehicle is located via the on-board camera of the vehicle.
  • the vehicle may be a passenger vehicle, a cargo vehicle, a toy vehicle, an unmanned vehicle, etc. in reality. It can also be a movable object such as a car model robot and a racing car in the virtual scene.
  • a vehicle-mounted camera can be set on the vehicle.
  • the vehicle-mounted camera can capture images from various vision sensors such as a monocular camera, an RGB camera, an infrared camera, and a binocular camera. Different shooting equipment can be selected according to needs, environment, current object type and cost. This disclosure does not limit this.
  • the corresponding functions of the on-board camera can be set on the vehicle to obtain road images of the environment where the vehicle is located. This disclosure does not limit this.
  • the road in the scene where the vehicle is located may include various types of roads such as urban roads and rural roads.
  • the video stream captured by the vehicle-mounted camera can include a video stream of any length.
  • Step S20 Detect a target object in the road image to obtain a detection frame of the target object; determine a drivable area of the vehicle in the road image.
  • the target object includes different object types such as vehicles, pedestrians, buildings, obstacles, and animals.
  • the target object can be a single or multiple target objects in one object type, or multiple target objects in multiple object types. For example, only a vehicle may be used as the target object, and the target object may be one vehicle or multiple vehicles. You can also target vehicles and pedestrians together.
  • the target objects are multiple vehicles and multiple pedestrians.
  • the set object type can be used as the target object, or the set object individual can be used as the target object.
  • image detection technology may be used to obtain the detection frame of the target object in the image taken by the vehicle-mounted camera.
  • the detection frame can be a rectangular frame or a frame of other shapes.
  • the size of the detection frame can be different according to the size of the image area occupied by the target object in the image.
  • the target object in the image includes three motor vehicles and two pedestrians.
  • five detection frames can be used to identify each target object in the image.
  • the drivable area may include an unoccupied area on the road for vehicles to travel.
  • the drivable area may include an unoccupied area on the road for vehicles to travel.
  • there are three motor vehicles on the road in front of the vehicle and the area on the road not occupied by the three motor vehicles is a drivable area.
  • the neural network model of the drivable area can be trained by using the sample images marked with the drivable area on the road.
  • the road image can be input to the trained driving area neural network model for processing to obtain the driving area in the road image.
  • FIG. 2 shows a schematic diagram of a road drivable area in a vehicle intelligent driving control method according to an embodiment of the present disclosure.
  • FIG. 2 shows a schematic diagram of a road drivable area in a vehicle intelligent driving control method according to an embodiment of the present disclosure.
  • the white rectangular frame is the detection frame of the car.
  • the area below the black line segment in Figure 2 is the driveable area of the vehicle.
  • one or more drivable areas can be determined in the road image. It is possible to determine a drivable area on the road without distinguishing between different lanes. It is also possible to distinguish the lanes and determine the drivable areas on each lane to obtain multiple drivable areas. The drivable area in Figure 2 does not distinguish lane lines.
  • Step S30 Adjust the detection frame of the target object according to the drivable area.
  • the accuracy of the actual position of the target object is critical to the intelligent driving control of the vehicle.
  • various target objects such as vehicles and pedestrians, on the road, and each target object is liable to be occluded with each other, resulting in a deviation between the detection frame of the occluded target object and the actual position of the target object.
  • the detection frame of the target object also deviates from the actual position of the target object due to the detection algorithm and other reasons.
  • the position of the detection frame of the target object can be adjusted to obtain a more accurate actual position of the target object for intelligent vehicle driving control.
  • the distance between the vehicle and the target object can be determined according to the center point on the bottom edge of the target object detection frame.
  • the bottom edge of the target object detection frame is the side of the detection frame close to the road.
  • the bottom edge of the target object detection frame is usually parallel to the road surface.
  • the position of the detection frame of the target object can be adjusted according to the position of the edge of the drivable area corresponding to the bottom edge of the target object detection frame.
  • the side where the tires of the car are located is the bottom edge of the detection frame, and the edge of the drivable area corresponding to the bottom edge of the detection frame is parallel to the bottom edge of the detection frame.
  • the horizontal position and/or vertical position of the detection frame of the target object can be adjusted according to the coordinates of the pixel points on the edge corresponding to the bottom edge of the detection frame. In order to make the position of the target object identified by the adjusted detection frame more consistent with the actual position of the target object.
  • Step S40 Perform intelligent driving control on the vehicle according to the adjusted detection frame.
  • the position of the target object identified by the detection frame of the target object adjusted according to the drivable area is more consistent with the actual position of the target object.
  • the actual position of the target object on the road can be determined according to the adjusted center point of the bottom edge of the detection frame of the target object.
  • the distance between the target object and the vehicle can be calculated according to the actual position of the target object and the actual position of the vehicle.
  • Intelligent driving control can include: automatic driving control or assisted driving control and switching between the two.
  • Intelligent driving control can include automatic navigation driving control, autonomous driving control, and manual intervention automatic driving control.
  • the distance between the target object and the vehicle in the driving direction of the vehicle in the intelligent driving control is very important for the driving control in the intelligent driving control.
  • the actual position of the target object can be determined according to the adjusted detection frame, and the corresponding intelligent driving control of the vehicle can be performed according to the actual position of the target object.
  • the present disclosure does not limit the control content and control method of intelligent driving control.
  • the video stream of the road image of the scene where the vehicle is located is collected by the vehicle’s on-board camera; the target object is detected in the road image, the detection frame of the target object; the vehicle’s availability is determined in the road image Driving area; adjusting the detection frame of the target object according to the drivable area; performing intelligent driving control on the vehicle according to the adjusted detection frame.
  • the detection frame of the target object adjusted according to the drivable area can more accurately identify the position of the target object, and can be used to more accurately determine the actual position of the target object, thereby more accurately controlling the intelligent driving of the vehicle.
  • step S20 in the method for controlling intelligent driving of a vehicle includes:
  • Step S21 Perform image segmentation on the road image to obtain the segmentation area where the target object in the road image is located.
  • the contour line of the target object can be identified in the sample image.
  • the first image segmentation neural network can be trained by using sample images that have identified the contour lines of the target object, so as to obtain the first image segmentation neural network that can be used for image segmentation.
  • the road image can be input to the trained first image segmentation neural network to obtain the segmentation area where each target object is located.
  • the target object is a vehicle
  • the segmented area of the vehicle is obtained by using the first image segmentation neural network as the silhouette of the vehicle itself.
  • the segmentation area of each target object obtained by using the first image segmentation neural network is a complete silhouette of each target area, and a complete segmentation area of the target object can be obtained.
  • the target object and the part of the road occupied by the target object can be identified together in the sample image.
  • the second image segmentation neural network can be trained by using sample images that identify the target object and the road surface occupied by the target object, and a second image segmentation neural network that can be used for image segmentation has been obtained.
  • the road image can be input to the second image segmentation neural network to obtain the segmentation area where each target object is located.
  • the target object is a vehicle
  • the segmented area of the vehicle obtained by using the second image segmentation neural network is the silhouette of the vehicle itself and the partial area of the road occupied by the vehicle.
  • the segmented area of the target object obtained by using the second image segmentation neural network includes the area of the road surface occupied by the target object, so that the drivable area obtained according to the segmentation result of the target object is more accurate.
  • Step S22 Perform lane line detection on the road image.
  • the lane line recognition neural network can be trained by using the sample images that mark the lane lines, and the trained lane line recognition neural network can be obtained.
  • the road image can be input to the trained lane line recognition neural network to recognize the lane line.
  • the lane lines may include various types of lane lines such as single solid lines and double solid lines. The present disclosure does not limit the types of lane lines.
  • Step S23 Determine the drivable area of the vehicle in the road image according to the detection result of the lane line and the segmented area.
  • the road area in the road image of the automobile market may be determined according to the lane line.
  • the area of the road area other than the divided area of the vehicle can be determined as a drivable area.
  • a road area can be determined in the road image according to the two outermost lane lines.
  • the segmented area of the vehicle can be removed from a determined road area to obtain a drivable area.
  • different lanes may be determined according to each lane line, and the road area corresponding to each lane may be determined in the road image. After removing the divided areas of the vehicle in each road area type, the drivable area corresponding to each lane area can be obtained.
  • the road image is segmented to obtain the segmentation area where the target object in the road image is; lane line detection is performed on the road image; the vehicle in the road image is determined according to the detection result of the lane line and the segmentation area Drivable area.
  • image segmentation obtains the segmented area where the target object is located
  • the road area is determined according to the lane line, and the drivable area obtained after removing the segmented area from the road area can accurately reflect the actual occupancy of the target object on the road and obtain the drivable
  • the area can be used to adjust the detection frame of the target object, so that the detection frame of the target object can more accurately identify the actual position of the target object for intelligent driving control of the vehicle.
  • FIG. 4 shows a flowchart of step S20 in the method for controlling intelligent driving of a vehicle according to an embodiment of the present disclosure.
  • step S20 in the method for controlling intelligent driving of a vehicle includes:
  • Step S24 Determine the overall projection area of the target object in the road image.
  • the overall projection area of the target object includes the projection area of the occluded part and the projection area of the unoccluded part of the target object.
  • the target object can be identified in the road image.
  • the target object can be identified based on the unoccluded part.
  • the part of the target object that is occluded can be supplemented according to the recognized part of the target object that is not occluded, and the preset actual aspect ratio of the target object.
  • the overall projection area of each target object on the road is determined in the road image.
  • Step S25 Perform lane line detection on the road image.
  • Step S26 Determine the drivable area of the vehicle in the road image according to the detection result of the lane line and the overall projection area.
  • the driveable area of the vehicle may be determined according to the overall projection area of each target object.
  • a road area can be determined in the road image based on the two outermost lane lines.
  • the overall projection area of each target object can be removed from the determined road area to obtain the driving area of the vehicle.
  • the drivable area determined according to the overall projection area of the target object can accurately reflect the actual position of each target object.
  • the target object is a vehicle
  • the detection frame of the target object is a detection frame of the head or tail of the vehicle.
  • the detection frame of the vehicle when the target object is an opposite vehicle, the detection frame of the vehicle may be the detection frame of the head of the vehicle.
  • the detection frame of the vehicle when the target object is a front vehicle, the detection frame of the vehicle may be the detection frame at the rear of the vehicle.
  • Fig. 5 shows a flowchart of step S30 in a method for controlling intelligent driving of a vehicle according to an embodiment of the present disclosure.
  • step S30 in the method for controlling intelligent driving of a vehicle includes:
  • Step S31 Determine the edge of the drivable area corresponding to the bottom edge of the detection frame as a reference edge.
  • the bottom side of the target object detection frame is the side of the detection frame where the side of the target object in contact with the road surface is located.
  • the edge of the drivable area corresponding to the bottom edge of the detection frame may be an edge of the drivable area parallel to the bottom edge of the detection frame.
  • the reference edge is the edge of the drivable area corresponding to the rear of the vehicle.
  • the edge of the drivable area corresponding to the bottom edge of the detection frame is the reference edge.
  • Step S32 Adjust the position of the detection frame of the target object in the road image according to the reference edge.
  • the position of the center point on the reference edge can be determined.
  • the detection frame can be adjusted so that the center point of the bottom edge of the detection frame coincides with the center point on the reference edge.
  • the position of the detection frame can also be adjusted according to the position of each pixel on the reference edge.
  • step S32 includes:
  • the position of the detection frame of the target object in the road image is adjusted in the height direction of the target object.
  • the width direction of the target object can be taken as the X-axis direction
  • the height direction of the target object can be taken as the Y-axis positive direction.
  • the height direction of the target object is the direction away from the ground.
  • the width direction of the target object is the direction parallel to the ground plane.
  • the edge of the drivable area in the road image can be jagged or other shapes.
  • the first coordinate value of each pixel on the reference edge in the Y-axis direction can be determined.
  • the first position average value of the first coordinate value of each pixel can be calculated, and the position of the detection frame in the height direction of the target object can be adjusted according to the calculated first position average value.
  • step S32 includes:
  • the position of the detection frame of the target object in the road image is adjusted in the width direction of the target object.
  • the second coordinate value of each pixel on the reference edge in the X-axis direction can be determined. After calculating the average value of each second coordinate value to obtain the second position average value, the position of the detection frame in the width direction of the target object is adjusted according to the second position average value.
  • only the position of the detection frame in the height direction or the width direction of the target object can be adjusted according to requirements, and the positions of the detection frame in the height direction and the width direction of the target object can also be adjusted at the same time.
  • the edge of the drivable area corresponding to the bottom edge of the detection frame is determined as a reference edge; the position of the detection frame of the target object in the road image is adjusted according to the reference edge .
  • the position of the detection frame adjusted according to the reference edge can make the position of the target object identified by the detection frame closer to the actual position.
  • Fig. 6 shows a flowchart of step S40 in a method for controlling intelligent driving of a vehicle according to an embodiment of the present disclosure.
  • step S40 in the method for controlling intelligent driving of a vehicle includes:
  • Step S41 Determine the detection aspect ratio of the target object according to the adjusted detection frame.
  • the road may have an uphill road and a downhill road.
  • the actual position of the target object can be determined according to the detection frame of the target object.
  • the detection aspect ratio of the target object is different from the normal aspect ratio when the target object is on a flat road. Therefore, in order to reduce or even avoid the deviation of the actual position of the target object, it can be determined according to The adjusted detection frame calculates the detection aspect ratio of the target object.
  • Step S42 in a case where the difference between the detected aspect ratio and the predetermined aspect ratio of the target object is greater than a difference threshold, determine a height adjustment value.
  • the detection aspect ratio of the target object may be compared with the actual aspect ratio to determine the height value used to adjust the position of the detection frame in the height direction.
  • the detected aspect ratio is greater than the actual aspect ratio, it can be considered that the position of the target object is higher than the plane where the vehicle is located, and the target object may be located on an uphill road.
  • the actual position of the target object can be adjusted according to the determined height value.
  • the detected aspect ratio When the detected aspect ratio is less than the actual aspect ratio, it can be considered that the position of the target object is lower than the plane where the vehicle is located, and the target object may be located on a downhill road.
  • the height adjustment value can be determined according to the difference between the detection aspect ratio and the actual aspect ratio, and the detection frame of the target object can be adjusted according to the determined height adjustment value.
  • the difference between the detected aspect ratio and the actual aspect ratio can be proportional to the height adjustment value.
  • Step S43 Perform intelligent driving control on the vehicle according to the height adjustment value and the detection frame.
  • the height adjustment value may be used to indicate the height value of the target object on the road relative to the plane where the vehicle is located.
  • the center point on the bottom edge of the detection frame can be used to determine the detection position of the target object.
  • the position can be adjusted to and detected according to the height, and the actual position of the target object on the road can be determined.
  • the detection aspect ratio of the target object is determined according to the adjusted detection frame; the difference between the detection aspect ratio and the predetermined aspect ratio of the target object is greater than the difference threshold In this case, the height adjustment value is determined; and the intelligent driving control of the vehicle is performed according to the height adjustment value and the detection frame.
  • the detection aspect ratio of the target object and the actual aspect ratio it can be determined whether the target object is located on the uphill road or the downhill road. It can avoid that the target object is located on the uphill road or downhill road. The position is deviated.
  • the step S40 includes:
  • multiple homography matrices of the vehicle-mounted camera are used to determine the actual position of the target object on the road, and the calibration distance range of each homography matrix is different.
  • the homography matrix can be used to express the perspective transformation between a plane in the real world and other images.
  • the homography matrix of the vehicle-mounted camera can be constructed based on the environment in which the vehicle is located, and multiple homography matrices with different calibration distance ranges can be determined according to requirements.
  • the distance between the target object and the vehicle can be determined by mapping the corresponding position of the ranging point in the image to the environment where the vehicle is located.
  • the homography matrix can be used to obtain the distance information between the distance measuring point and the target object in the image taken by the vehicle.
  • the homography matrix can be constructed based on the environment of the vehicle before ranging.
  • a monocular camera configured for an autonomous vehicle can be used to take a real road image, and a point set on the road image and a point set corresponding to the point set on the image on the real road can be used to construct a homography matrix.
  • Specific methods can include: 1. Establish a coordinate system: take the left front wheel of the autonomous vehicle as the origin, the right direction of the driver’s perspective as the positive direction of the X axis, and the forward direction as the positive direction of the Y axis. The car body coordinate system. 2. Select a point, select a point in the car body coordinate system, and get a selected point set.
  • the unit of each point is meter. According to requirements, you can also choose a point farther away. 3. Mark, mark the selected points on the real road surface to obtain the real point set. 4. Calibration, use the calibration board and calibration program to get the corresponding pixel position of the real point set in the captured image. 5. Generate a homography matrix according to the corresponding pixel positions.
  • a homography matrix can be constructed according to different distance ranges.
  • a homography matrix can be constructed with a distance range of 100 meters, or a homography matrix can be constructed with a range of 10 meters. The smaller the distance range, the higher the accuracy of the distance determined according to the homography matrix. Using multiple calibrated homography matrices, accurate actual distances of the target objects can be obtained.
  • multiple homography matrices are used to determine the actual position of the target object on the road, and the calibration distance range of each homography matrix is different. Through multiple homography matrices, a more accurate actual position of the target object can be obtained.
  • FIG. 7 shows a flowchart of a method for controlling intelligent driving of a vehicle according to an embodiment of the present disclosure. As shown in FIG. 7, the method for controlling intelligent driving of a vehicle further includes:
  • Step S50 Determine the dangerous area of the vehicle.
  • Step S60 Determine the danger level of the target object according to the actual position of the target object and the dangerous area.
  • Step S70 in the case that the danger level meets the danger threshold, send a danger level prompt message.
  • the set area in the forward direction of the vehicle may be determined as a dangerous area.
  • the area in front of the vehicle with a set length and set width can be determined as a dangerous area.
  • a sector area with a radius of 5 meters with the center of the front cover of the vehicle as the center is determined as a dangerous area, or an area with a length of 5 meters and a width of 3 meters in front of the vehicle is determined as a dangerous area.
  • the size and shape of the hazardous area can be determined according to requirements.
  • the risk level of the target object may be determined as a serious danger.
  • the target object's danger level can be determined as ordinary danger.
  • the target object's danger level can be determined as a common danger.
  • the target object's danger level can be determined as non-hazardous.
  • the corresponding danger level prompt information can be sent according to the danger level of the target object.
  • the hazard level prompt information can use voice, vibration, light, text and other different forms of expression. This disclosure does not limit the specific content and manifestation of the hazard level prompt information.
  • the determining the danger level of the target object according to the actual position of the target object and the dangerous area includes:
  • the first risk level of the target object is the highest risk level, determining the adjacent position of the target object in the adjacent images of the road image in the video stream;
  • the road image taken by the vehicle may be an image in a video stream.
  • the current road image and the image before the current road image can be used to determine the neighboring objects of the target object in the image before the current road image by using the method in the foregoing embodiment of the present disclosure.
  • the location is determined.
  • the coincidence degree of the target object in the current road image and the image before the current road image can also be calculated.
  • the adjacent positions of the target object can be determined. It can also calculate the historical distance between the target object and the vehicle in the image before the current road image, and calculate the distance difference between the historical distance and the target object and the vehicle in the current road image. When the distance difference is less than the distance threshold , You can determine the adjacent position of the target object.
  • the danger level of the target object can be determined according to the determined adjacent position and the actual position of the target object.
  • the first risk level of the target object is determined according to the actual position of the target object and the dangerous area; when the first risk level of the target object is the highest risk level, In the adjacent images of the road image in the video stream, the adjacent position of the target object is determined; and the danger level of the target object is determined according to the adjacent position and the actual position of the target object.
  • the danger level of the target object can be more accurately confirmed through the adjacent position of the target object in the adjacent image and the actual position of the target object.
  • the method further includes:
  • the collision time between the target object and the vehicle can be calculated based on the distance between the target object and the vehicle, the moving speed and direction of the target object, and the moving speed and direction of the vehicle.
  • the time threshold can be preset, and the collision warning information can be obtained according to the time threshold and the collision time.
  • the preset time threshold is 5 seconds.
  • the collision time between the target vehicle ahead and the current vehicle is calculated to be less than 5 seconds, it can be considered that if the target vehicle collides with the current vehicle, the driver of the vehicle may not be able to make timely processing If danger occurs, a collision warning message needs to be sent.
  • Different forms of expression such as sound, vibration, light and text can be used to send collision warning information. This disclosure does not limit the specific content and manifestation of the collision warning information.
  • the collision time is obtained according to the distance between the target object and the vehicle, the movement information of the target object, and the movement information of the vehicle; the collision warning information is determined according to the collision time and the time threshold; the collision warning information is sent.
  • the collision warning information obtained according to the actual distance between the target object and the vehicle and the movement information can be used in the field of safe driving in the intelligent driving of the vehicle to improve safety.
  • the sending the collision warning information includes:
  • the collision warning information is not sent.
  • the vehicle after the vehicle generates collision warning information for a target object, it can look up whether there is collision warning information for the target object in the transmission record of the sent collision warning information. If so, then Do not send, can improve user experience.
  • the sending the collision warning information includes:
  • the driving state information includes braking information and/or steering information
  • a collision when the vehicle moves according to the current movement information, the driver of the vehicle may perform operations such as braking, deceleration, and/or steering.
  • the braking information and steering information of the vehicle can be obtained according to the bus information of the vehicle.
  • the collision warning information may not be sent or stopped.
  • the bus information of the vehicle is acquired, and the bus information includes braking information and/or steering information; it is determined whether to send collision warning information according to the bus information. According to the bus information, it can be determined not to send or stop sending the collision warning information, making the sending of the collision warning information more humanized and improving the user experience.
  • the sending the collision warning information includes:
  • the driving state information includes braking information and/or steering information
  • the collision warning information is sent.
  • the driving state information can be obtained from the CAN (Controller Area Network, Controller Area Network) bus of the vehicle. According to the driving status information, it can be determined whether the vehicle has performed the braking and/or turn signal corresponding processing. Based on the driving status information, it can be determined that the vehicle driver or the intelligent driving system has performed the relevant processing. The collision warning information may not be sent to improve the user experience .
  • CAN Controller Area Network
  • Controller Area Network Controller Area Network
  • the target object is a vehicle
  • the method further includes:
  • the mutual occlusion between vehicles may cause the detection frame of the vehicle in front to be not the detection frame of the whole vehicle, or the distance between the two vehicles may cause the rear of the vehicle in front to be in the blind area of the on-board camera, which causes the vehicle to be on the road.
  • the image is not visible, or in other similar situations, the detection frame of the vehicle cannot accurately frame the position of the vehicle in front, because the distance between the target vehicle and the current vehicle calculated according to the detection frame has a large error.
  • the neural network can be used to identify the vehicle's license plate and/or vehicle logo detection frame, and the license plate and/or vehicle logo detection frame can be used to correct the distance between the target vehicle and the current vehicle.
  • the vehicle identification neural network can be trained using sample images of the license plate and/or logo of the vehicle.
  • the road image can be input to the trained vehicle identification neural network to obtain the license plate and/or logo of the vehicle.
  • the license plate at the rear of the preceding vehicle is framed by a rectangular frame.
  • the vehicle logo may be an identification of the vehicle type at the rear or the front of the vehicle, and the detection frame of the vehicle logo is not shown in FIG. 2.
  • Vehicle logos are usually placed near the license plate, such as above the adjacent license plate.
  • the reference distance of the target object that can be determined according to the detection result of the license plate and/or the vehicle logo may be different from the distance between the target object and the vehicle determined according to the tail of the target object or the whole.
  • the reference distance can be larger or smaller than the distance determined according to the rear of the target object or the whole.
  • the adjusting the distance between the target object and the vehicle according to the reference distance includes:
  • the distance between the target object and the vehicle is adjusted to the reference distance ,or
  • the license plate and/or logo of the vehicle may be used to determine the reference distance between the target object and the vehicle.
  • the difference threshold may be preset according to requirements. In the case that the difference between the reference distance and the distance between the target object and the vehicle is greater than the difference threshold, the difference between the target object and the vehicle may be Adjust the distance to the reference distance. When the difference between the reference distance and the calculated distance between the target object and the vehicle is large, the average value between the two distances can also be calculated, and the calculated average value is determined as the adjusted value between the target object and the vehicle. distance.
  • the identification information of the target object is detected in the road image
  • the identification information includes the license plate and/or the car logo
  • the reference distance of the target object is determined according to the identification information
  • the distance between the target object and the vehicle is adjusted according to the reference distance distance. Adjusting the adjusted distance between the target object and the vehicle according to the identification information of the target object can make the adjusted distance more accurate.
  • the adjusting the distance between the target object and the vehicle according to the reference distance includes:
  • adjusting the distance between the target object and the vehicle according to the reference distance includes directly adjusting the distance between the target object and the vehicle to the reference distance, or calculating the difference between the two.
  • the distance is greater than the distance between the target object and the vehicle, and the distance between the target object and the vehicle can be added to the difference. If the reference distance is less than the distance between the target object and the vehicle, the distance between the target object and the vehicle can be reduced. To the difference.
  • the present disclosure also provides vehicle intelligent driving control devices, electronic equipment, computer-readable storage media, and programs, all of which can be used to implement any of the vehicle intelligent driving control methods provided in the present disclosure.
  • vehicle intelligent driving control devices electronic equipment, computer-readable storage media, and programs, all of which can be used to implement any of the vehicle intelligent driving control methods provided in the present disclosure.
  • the corresponding technical solutions and descriptions and refer to methods Part of the corresponding records will not be repeated.
  • the writing order of the steps does not mean a strict execution order but constitutes any limitation on the implementation process.
  • the specific execution order of each step should be based on its function and possibility.
  • the inner logic is determined.
  • FIG. 8 shows a block diagram of a vehicle intelligent driving control device according to an embodiment of the present disclosure. As shown in FIG. 8, the vehicle intelligent driving control device includes:
  • the video stream acquisition module 10 is used to collect the video stream of the road image of the scene where the vehicle is located via the on-board camera of the vehicle;
  • the drivable area determination module 20 is configured to detect a target object in the road image to obtain a detection frame of the target object; determine the drivable area of the vehicle in the road image;
  • the detection frame adjustment module 30 is configured to adjust the detection frame of the target object according to the drivable area
  • the control module 40 is configured to perform intelligent driving control on the vehicle according to the adjusted detection frame.
  • the driveable area determination module includes:
  • An image segmentation sub-module configured to perform image segmentation on the road image to obtain a segmentation area in the road image where the target object is located;
  • the first lane line detection sub-module is used to perform lane line detection on the road image
  • the first drivable area determination sub-module is configured to determine the drivable area of the vehicle in the road image according to the detection result of the lane line and the segmented area.
  • the driveable area determination module includes:
  • the overall projection area determination sub-module is used to determine the overall projection area of the target object in the road image
  • the second lane line detection sub-module is used to perform lane line detection on the road image
  • the second drivable area determination sub-module is configured to determine the drivable area of the vehicle in the road image according to the detection result of the lane line and the overall projection area.
  • the target object is a vehicle
  • the detection frame of the target object is a detection frame of the head or tail of the vehicle.
  • the detection frame adjustment module includes:
  • a reference edge determination submodule configured to determine the edge of the drivable area corresponding to the bottom edge of the detection frame as a reference edge
  • the detection frame adjustment submodule is configured to adjust the position of the detection frame of the target object in the road image according to the reference edge.
  • the detection frame adjustment submodule is configured to:
  • the position of the detection frame of the target object in the road image is adjusted in the height direction of the target object.
  • the detection frame adjustment submodule is further used for:
  • the position of the detection frame of the target object in the road image is adjusted in the width direction of the target object.
  • control module includes:
  • the detection aspect ratio determination sub-module is configured to determine the detection aspect ratio of the target object according to the adjusted detection frame
  • a height adjustment value determination sub-module configured to determine a height adjustment value when the difference between the detected aspect ratio and the predetermined aspect ratio of the target object is greater than a difference threshold
  • the first control sub-module is configured to perform intelligent driving control of the vehicle according to the height adjustment value and the detection frame.
  • control module includes:
  • the actual position determination sub-module is used to determine the actual position of the target object on the road by using multiple homography matrices of the vehicle-mounted camera according to the adjusted detection frame, and the calibration distance range of each homography matrix is different;
  • the second control sub-module is used for intelligent driving control of the vehicle according to the actual position of the target object on the road.
  • the device further includes:
  • the dangerous area determination module is used to determine the dangerous area of the vehicle
  • a danger level determination module configured to determine the danger level of the target object according to the actual location of the target object and the dangerous area
  • the first prompt message sending module is configured to send the danger level prompt message when the danger level meets the danger threshold.
  • the risk level determination module includes:
  • the first danger level determination sub-module is configured to determine the first danger level of the target object according to the actual location of the target object and the dangerous area;
  • the adjacent position determining sub-module is used to determine the relative position of the target object in the adjacent images of the road image in the video stream when the first risk level of the target object is the highest risk level. Adjacent position
  • the second danger level determination sub-module is used to determine the danger level of the target object according to the adjacent position and the actual position of the target object.
  • the device further includes:
  • a collision time acquisition module configured to obtain the collision time according to the distance between the target object and the vehicle, the movement information of the target object, and the movement information of the vehicle;
  • a collision warning information determination module configured to determine collision warning information according to the collision time and time threshold
  • the second prompt information sending module is used to send the collision warning information.
  • the second prompt information sending module includes:
  • the second prompt message sending sub-module is used to send the collision warning information when there is no transmission record of the collision warning information of the target object in the sent collision warning information; and/or,
  • the collision warning information is not sent.
  • the second prompt information sending module includes:
  • a driving state information acquisition sub-module for acquiring driving state information of the vehicle, where the driving state information includes braking information and/or steering information;
  • the third prompt information sending sub-module is configured to send the collision warning information when it is determined according to the driving state information that the vehicle has not performed corresponding braking and/or steering treatments.
  • the device further includes a distance determining device, the distance determining device is used to determine the distance between the target object and the vehicle, and the distance determining device includes:
  • the license plate and vehicle mark detection sub-module is used to detect the license plate and/or vehicle mark of the vehicle in the road image
  • the reference distance determination sub-module is used to determine the reference distance of the target object according to the detection result of the license plate and/or vehicle logo;
  • the distance determining submodule is used to adjust the distance between the target object and the vehicle according to the reference distance.
  • the distance determining submodule is configured to:
  • the distance between the target object and the vehicle is adjusted to the reference distance ,or
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the embodiments of the present disclosure also provide a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above-mentioned method when executed by a processor.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium.
  • An embodiment of the present disclosure also provides an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured as the above method.
  • the electronic device can be provided as a terminal, server or other form of device.
  • Fig. 9 is a block diagram showing an electronic device 800 according to an exemplary embodiment.
  • the electronic device 800 may be a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and other terminals.
  • the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, and a sensor component 814 , And communication component 816.
  • the processing component 802 generally controls the overall operations of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • the processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the foregoing method.
  • the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components.
  • the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.
  • the memory 804 is configured to store various types of data to support operations in the electronic device 800. Examples of these data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc.
  • the memory 804 can be implemented by any type of volatile or non-volatile storage devices or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable and Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic Disk or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EPROM erasable and Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Magnetic Disk Magnetic Disk or Optical Disk.
  • the power supply component 806 provides power for various components of the electronic device 800.
  • the power supply component 806 may include a power management system, one or more power supplies, and other components associated with the generation, management, and distribution of power for the electronic device 800.
  • the multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 810 is configured to output and/or input audio signals.
  • the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive external audio signals.
  • the received audio signal may be further stored in the memory 804 or transmitted via the communication component 816.
  • the audio component 810 further includes a speaker for outputting audio signals.
  • the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module.
  • the peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include but are not limited to: home button, volume button, start button, and lock button.
  • the sensor component 814 includes one or more sensors for providing the electronic device 800 with various aspects of state evaluation.
  • the sensor component 814 can detect the on/off status of the electronic device 800 and the relative positioning of the components.
  • the component is the display and the keypad of the electronic device 800.
  • the sensor component 814 can also detect the electronic device 800 or the electronic device 800.
  • the position of the component changes, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800.
  • the sensor component 814 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact.
  • the sensor component 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.
  • the communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices.
  • the electronic device 800 can access a wireless network based on communication standards, such as WiFi, 2G, or 3G, or a combination thereof.
  • the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 816 further includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the electronic device 800 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field A programmable gate array (FPGA), controller, microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.
  • ASIC application specific integrated circuits
  • DSP digital signal processors
  • DSPD digital signal processing devices
  • PLD programmable logic devices
  • FPGA field A programmable gate array
  • controller microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.
  • a non-volatile computer-readable storage medium such as the memory 804 including computer program instructions, which can be executed by the processor 820 of the electronic device 800 to complete the foregoing method.
  • Fig. 10 is a block diagram showing an electronic device 1900 according to an exemplary embodiment.
  • the electronic device 1900 may be provided as a server.
  • the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932, for storing instructions executable by the processing component 1922, such as application programs.
  • the application program stored in the memory 1932 may include one or more modules each corresponding to a set of instructions.
  • the processing component 1922 is configured to execute instructions to perform the above-described methods.
  • the electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input output (I/O) interface 1958 .
  • the electronic device 1900 can operate based on an operating system stored in the memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.
  • a non-volatile computer-readable storage medium such as the memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to complete the foregoing method.
  • the present disclosure may be a system, method, and/or computer program product.
  • the computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for enabling a processor to implement various aspects of the present disclosure.
  • the computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, such as a printer with instructions stored thereon
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • flash memory flash memory
  • SRAM static random access memory
  • CD-ROM compact disk read-only memory
  • DVD digital versatile disk
  • memory stick floppy disk
  • mechanical encoding device such as a printer with instructions stored thereon
  • the computer-readable storage medium used here is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, light pulses through fiber optic cables), or through wires Transmission of electrical signals.
  • the computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing/processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • the network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing/processing device .
  • the computer program instructions used to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, or in one or more programming languages.
  • Source code or object code written in any combination, the programming language includes object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages.
  • Computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, executed as a stand-alone software package, partly on the user's computer and partly executed on a remote computer, or entirely on the remote computer or server carried out.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to access the Internet connection).
  • LAN local area network
  • WAN wide area network
  • an electronic circuit such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by using the status information of the computer-readable program instructions.
  • the computer-readable program instructions are executed to realize various aspects of the present disclosure.
  • These computer-readable program instructions can be provided to the processors of general-purpose computers, special-purpose computers, or other programmable data processing devices, thereby producing a machine such that when these instructions are executed by the processors of the computer or other programmable data processing devices , A device that implements the functions/actions specified in one or more blocks in the flowchart and/or block diagram is produced. It is also possible to store these computer-readable program instructions in a computer-readable storage medium. These instructions make computers, programmable data processing apparatuses, and/or other devices work in a specific manner, so that the computer-readable medium storing instructions includes An article of manufacture, which includes instructions for implementing various aspects of the functions/actions specified in one or more blocks in the flowchart and/or block diagram.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of an instruction, and the module, program segment, or part of an instruction contains one or more functions for implementing the specified logical function.
  • Executable instructions may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Automation & Control Theory (AREA)
  • Multimedia (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

一种车辆智能驾驶控制方法及装置、电子设备和存储介质。所述方法包括：经车辆的车载摄像头采集所述车辆所在场景的道路图像的视频流；在所述道路图像中检测目标对象，得到所述目标对象的检测框；在所述道路图像中确定所述车辆的可行驶区域；根据所述可行驶区域调整所述目标对象的检测框；根据调整后的检测框对所述车辆进行智能驾驶控制。根据可行驶区域调整后的目标对象的检测框，可以更加准确地标识目标对象的位置，可以用于更加准确的确定目标对象的实际位置，从而更加精准的对车辆进行智能驾驶控制。

Description

车辆智能驾驶控制方法及装置、电子设备和存储介质 技术领域
本公开涉及图像处理技术领域，尤其涉及一种车辆智能驾驶控制方法及装置、电子设备和存储介质。
背景技术
在道路中可以利用车辆上加载的摄像头拍摄道路信息，进行距离测试，以实现自动驾驶或辅助驾驶等功能。在道路中，车辆密集且相互遮挡严重，车辆的检测框标识的车辆位置与实际位置偏移较大，导致传统的距离测试方法不准确。
发明内容
本公开提出了一种车辆智能驾驶控制技术方案。
根据本公开的一方面，提供了一种车辆智能驾驶控制方法，包括：
经车辆的车载摄像头采集所述车辆所在场景的道路图像的视频流；
在所述道路图像中检测目标对象，得到所述目标对象的检测框；在所述道路图像中确定所述车辆的可行驶区域；
根据所述可行驶区域调整所述目标对象的检测框；
根据调整后的检测框对所述车辆进行智能驾驶控制。
根据本公开的一方面，提供了一种车辆智能驾驶控制装置，所述装置包括：
视频流获取模块，用于经车辆的车载摄像头采集所述车辆所在场景的道路图像的视频流；
可行驶区域确定模块，用于在所述道路图像中检测目标对象，得到所述目标对象的检测框；在所述道路图像中确定所述车辆的可行驶区域；
检测框调整模块，用于根据所述可行驶区域调整所述目标对象的检测框；
控制模块，用于根据调整后的检测框对所述车辆进行智能驾驶控制。
根据本公开的一方面，提供了一种电子设备，包括：
处理器；
用于存储处理器可执行指令的存储器；
其中，所述处理器被配置为：执行上述任意一项所述的方法。
根据本公开的一方面，提供了一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述任意一项所述的方法。
在本公开实施例中，经车辆的车载摄像头采集车辆所在场景的道路图像的视频流；在道路图像中检测目标对象，所述目标对象的检测框；在所述道路图像中确定所述车辆的可行驶区域；根据所述可行驶区域调整所述目标对象的检测框；根据调整后的检测框对所述车辆进行智能驾驶控制。根据可行驶区域调整后的目标对象的检测框，可以更加准确地标识目标对象的位置，可以用于更加准确的确定目标对象的实际位置，从而更加精准的对车辆进行智能驾驶控制。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。根据下面参考附图对示例性实施例的详细说明，本公开的其它特征及方面将变得清楚。
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，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。
图1示出根据本公开实施例的车辆智能驾驶控制方法的流程图；
图2示出根据本公开实施例的车辆智能驾驶控制方法中道路可行驶区域的示意图；
图3示出根据本公开实施例的车辆智能驾驶控制方法步骤S20的流程图；
图4示出根据本公开实施例的车辆智能驾驶控制方法步骤S20的流程图；
图5示出根据本公开实施例的车辆智能驾驶控制方法步骤S30的流程图；
图6示出根据本公开实施例的车辆智能驾驶控制方法步骤S40的流程图；
图7示出根据本公开实施例的车辆智能驾驶控制方法的流程图；
图8示出根据本公开实施例的车辆智能驾驶控制装置的框图；
图9是根据一示例性实施例示出的一种电子设备的框图；
图10是根据一示例性实施例示出的一种电子设备的框图。
具体实施方式
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
另外，为了更好地说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。
图1示出根据本公开实施例的车辆智能驾驶控制方法的流程图，如图1所示，所述车辆智能驾驶控制方法包括：
步骤S10，经车辆的车载摄像头采集所述车辆所在场景的道路图像的视频流。
在一种可能的实现方式中，车辆可以为现实中的载人车辆、载货车辆、玩具车辆、无人驾驶车辆等。也可以为虚拟场景中的车型机器人、赛车等可可以移动的对象。可以在车辆上设置车载摄像头，对于现实中的车辆，车载摄像头可以为单目摄像头、RGB摄像头、红外摄像头、双目摄像头等各种视觉传感器拍摄图像。可以根据需求、环境、当前对象的类型以及成本等，选用不同的拍摄设备。本公开对此不做限定。对于虚拟环境中的车辆，可在车辆上设置车载摄像头相应的功能，获取车辆所在环境的道路图像。本公开对此不做限定。车辆所在场景中的道路可以包括城市道路、乡村道路等各种类型的道路。车载摄像头拍摄的视频流可以包括任意时长的视频流。
步骤S20，在所述道路图像中检测目标对象，得到所述目标对象的检测框；在所述道路图像中确定所述车辆的可行驶区域。
在一种可能的实现方式中，目标对象包括车辆、行人、建筑物、障碍物、动物等不同的对象类型。目标对象可以是一个对象类型中的单个或多个目标对象，也可以是多个对象类型中的多个目标对象。例如，可以只将车辆作为目标对象，目标对象可以是一个车辆，可以是多个车辆。也可以将车辆和行人共同作为目标对象。目标对象是多个车辆和多个行人。根据需求，可以将设定的对象类型作为目标对象，也可以将设定的对象个体作为目标对象。
在一种可能的实现方式中，可以利用图像检测技术获取车载摄像头所拍摄的图像中目标对象的检测框。检测框可以是矩形框，也可以是其它形状的框。检测框的大小可以根据图像中目标对象所占的图像面积大小的不同而不同。例如，图像中的目标对象包括三辆机动车和两个行人。利用图像检测技术，可以在图像中利用五个检测框标识出各目标对象。
在一种可能的实现方式中，可行驶区域可以包括道路上未被占用的可供车辆行驶的区域。例如，车辆前方的道路上有三辆机动车，未被三辆机动车占用的道路上的区域为可行驶区域。可以利用标注了道路上可行驶区域的样本图像训练可行驶区域神经网络模型。可以将道路图像输入训练好的可行驶区域神经网络模型进行处理，得到道路图像中的可行驶区域。
图2示出根据本公开实施例的车辆智能驾驶控制方法中道路可行驶区域的示意图，如图2所示，车辆拍摄得到的道路图像中，车辆前方有两个轿车，图2中的两个白色矩形框为轿车的检测框。图2中的黑色线段下方的区域，为车辆的可行驶区域。
在一种可能的实现方式中，可以在道路图像中确定一个或多个可行驶区域。可以不区分不同车道，在道路上确定一个可行驶区域。也可以区分车道，在各车道上分别确定可行驶区域，得到多个可行驶区域。图2中的可行驶区域未区分车道线。
步骤S30，根据所述可行驶区域调整所述目标对象的检测框。
在一种可能的实现方式中，目标对象的实际位置的准确性对于车辆的智能驾驶控制来说至关重要。在道路上车辆、行人等各种目标对象的数量较多，各目标对象相互之间容易有遮挡，导致被遮挡的目标对象的检测框与目标对象的实际位置之间存在偏差。当目标对象未被遮挡时，目标对象的检测框由于检测算法等原因，也与目标对象的实际位置存在偏差。可以对目标对象的检测框的位置进行调整，从而得到更加准确的目标对象的实际位置以进行车辆智能驾驶控制。
在一种可能的实现方式中，可以根据目标对象检测框底边上的中心点，确定车辆与目标对象之间的距离。目标对象检测框的底边为检测框靠近道路一侧的边。目标对象检测框的底边通常与道路的路面平行。可以根据与目标对象检测框的底边对应的可行驶区域的边缘的位置，调整目标对象的检测框的位置。
如图2所示，轿车的轮胎所在的边为检测框的底边，与检测框的底边对应的可行驶区域的边缘与检测框的底边平行。可以根据与检测框的底边对应的边缘上的像素点的坐标，调整目标对象的检测框的横向位置和/或垂直位置。以使调整后的检测框所标识的目标对象的位置，与目标对象的实际位置更加吻合。
步骤S40，根据调整后的检测框对所述车辆进行智能驾驶控制。
在一种可能的实现方式中，根据可行驶区域调整后的目标对象的检测框所标识的目标对象的位置，与目标对象的实际位置更加吻合。可以根据调整后的目标对象的检测框的底边的中心点，确定目标对象在道路上的实际位置。可以根据目标对象的实际位置，以及车辆的实际位置，计算得到目标对象与车辆之间的距离。
智能驾驶控制可以包括：自动驾驶控制或辅助驾驶控制以及二者的切换。智能驾驶控制可以包括自动导航驾驶控制、自主驾驶控制和人工干预自动驾驶控制等。在智能驾驶控制中车辆行驶方向上的目标对象与车辆之间的距离，对于智能驾驶控制中的驾驶控制非常重要。可以根据调整后的检测框确定目标对象的实际位置，并根据目标对象的实际位置对车辆进行相应的智能驾驶控制。本公开对智能驾驶控制的控制内容及控制方式不进行限定。
在本实施例中，经车辆的车载摄像头采集车辆所在场景的道路图像的视频流；在道路图像中检测目标对象，所述目标对象的检测框；在所述道路图像中确定所述车辆的可行驶区域；根据所述可行驶区域调整所述目标对象的检测框；根据调整后的检测框对所述车辆进行智能驾驶控制。根据可行驶区域调整后的目标对象的检测框，可以更加准确地标识目标对象的位置，可以用于更加准确的确定目标对象的实际位置，从而更加精准的对车辆进行智能驾驶控制。
图3示出根据本公开实施例的车辆智能驾驶控制方法中步骤S20的流程图，如图3所示，所述车辆智能驾驶控制方法中步骤S20包括：
步骤S21，对所述道路图像进行图像分割，得到所述道路图像中所述目标对象所在的分割区域。
在一种可能的实现方式中，可以在样本图像中标识目标对象的轮廓线。当两个目标对象相互遮挡时，可以对各目标对象未被遮挡的部分的轮廓线进行标识。可以利用标识了目标对象轮廓线的样本图像训练第一图像分割神经网络，以得到可以用于图像分割的第一图像分割神经网络。可以将道路图像输入训练好的第一图像分割神经网络，得到各目标对象所在的分割区域。当目标对象为车辆时，利用第一图像分割神经网络得到车辆的分割区域为车辆自身的剪影。利用第一图像分割神经网络得到的各目标对象的分割区域，为各目标区域的完整剪影，可以得到完整的目标对象的分割区域。
在一种可能的实现方式中，可以在样本图像中将目标对象和目标对象所占的路面部分一起进行标识。当两个目标对象相互遮挡时，可以对各目标对象未被遮挡的部分的其所占的路面进行标识。可以利用标识了目标对象和目标对象所占路面的样本图像训练第二图像分割神经网络，已得到可以用于图像分割的第二图像分割神经网络。可以将将道路图像输入第二图像分割神经网络，得到各目标对象所在的分割区域。当目标对象为车辆时，利用第二图像分割神经网络得到车辆的分割区域为车辆自身的剪影以及车辆所占的路面部分区域。利用第二图像分割神经网络得到的目标对象的分割区域，包括了目标对象所占据的路面部分的区域，使得根据目标对象的分割结果得到的可行驶区域更加准确。
步骤S22，对所述道路图像进行车道线检测。
在一种可能的实现方式中，可以利用标识了车道线的样本图像训练车道线识别神经网络，已得到训练好的车道线识别神经网络。可以将道路图像输入训练好的车道线识别神经网络识别车道线。车道线可以包括单实线、双实线等各种类型的车道线。本公开对车道线的类型不进行限定。
步骤S23，根据所述车道线的检测结果和所述分割区域确定所述道路图像中所述车辆的可行驶区域。
在一种可能的实现方式中，可以根据车道线确定车市道路图像中的道路区域。可以将道路区域中除车辆的分割区 域以外的区域，确定为可行驶区域。
在一种可能的实现方式中，可以根据最外侧的两道车道线，在道路图像中确定一个道路区域。可以在确定出的一个道路区域中去除车辆的分割区域，得到一个可行驶区域。
在一种可能的实现方式中，可以根据各车道线确定不同的车道，在道路图像中确定与各车道分别对应的道路区域。可以在各道路区域种去除车辆的分割区域后，得到与各车道区域对应的可行驶区域。
在本实施例中，对道路图像进行图像分割，得到道路图像中目标对象所在的分割区域；对道路图像进行车道线检测；根据车道线的检测结果和分割区域确定所述道路图像中所述车辆的可行驶区域。图像分割得到目标对象所在的分割区域后，根据车道线确定道路区域，在道路区域中去除分割区域后得到的可行驶区域，能够准确地反应目标对象在道路中的实际占用情况，得到的可行驶区域能够用于调整目标对象的检测框，以使目标对象的检测框能够更加准确地标识该目标对象的实际位置，用于车辆智能驾驶控制。
图4示出根据本公开实施例的车辆智能驾驶控制方法中步骤S20的流程图，如图4所示，所述车辆智能驾驶控制方法中步骤S20包括：
步骤S24，确定所述目标对象在所述道路图像中的整体投影区域。
在一种可能的实现方式中，目标对象的整体投影区域，包括目标对象被遮挡部分的投影区域和未被遮挡部分的投影区域。可以在道路图像中识别目标对象。当目标对象被遮挡时，可以根据未被遮挡的部分识别目标对象。可以根据识别出的未被遮挡的部分目标对象，和预设的目标对象的实际长宽比等信息，补充得到被遮挡的部分目标对象。根据未被遮挡的部分目标对象，和补充的被遮挡的部分目标对象，在道路图像中确定各目标对象在道路上的整体投影区域。
步骤S25，对所述道路图像进行车道线检测。
在一种可能的实现方式中，同上述实施例步骤S22中的相关描述，不再赘述。
步骤S26，根据所述车道线的检测结果和所述整体投影区域确定所述道路图像中所述车辆的可行驶区域。
在一种可能的实现方式中，可以根据各目标对象的整体投影区域确定车辆的可行驶区域。可以根据最外侧的两道车道线，在道路图像中确定一个道路区域。可以在确定出的道路区域中去除各目标对象的整体投影区域，得到车辆的可行驶区域。
在本实施例中，确定目标对象在道路图像中的整体投影区域；对道路图像进行车道线检测；根据车道线的检测结果和整体投影区域确定道路图像中车辆的可行驶区域。根据目标对象的整体投影区域确定出的可行驶区域，可以准确地反应各目标对象的实际位置。
在一种可能的实现方式中，所述目标对象为车辆，所述目标对象的检测框为车辆头部或尾部的检测框。
在一种可能的实现方式中，当目标对象为对面的车辆时，车辆的检测框可以为车辆头部的检测框。当目标对象为前方的车辆时，车辆的检测框可以为车辆尾部的检测框。
图5示出根据本公开实施例的车辆智能驾驶控制方法中步骤S30的流程图，如图5所示，所述车辆智能驾驶控制方法中步骤S30包括：
步骤S31，将与所述检测框的底边对应的所述可行驶区域的边缘确定为参考边缘。
在一种可能的实现方式中，目标对象检测框的底边为目标对象与道路路面接触的一侧所在的检测框的边。与检测框的底边对应的可行驶区域的边缘，可以为与检测框的底边平行的可行驶区域的边缘。例如，当目标对象为前方的车辆时，参考边缘为车辆的尾部对应的可行驶区域的边缘。如图2所示，检测框的底边对应的可行驶区域的边缘为参考边缘。
步骤S32，根据所述参考边缘调整所述目标对象的检测框在所述道路图像中的位置。
在一种可能的实现方式中，可以确定参考边缘上的中心点的位置。可以将检测框调整至检测框底边的中心点与参考边缘上的中心点重合。也可以根据参考边缘上的各像素点的位置调整检测框的位置。
在一种可能的实现方式中，步骤S32，包括：
在图像坐标系中，确定所述参考边缘包括的像素点在所述目标对象高度方向的第一坐标值；
计算各所述第一坐标值的平均值得到第一位置平均值；
根据所述第一位置平均值，在所述目标对象高度方向调整所述目标对象的检测框在所述道路图像中的位置。
在一种可能的实现方式中，在图像坐标系中，可以以目标对象的宽度方向作为X轴方向，将目标对象的高度方向作为Y轴正向。目标对象的高度方向为远离地面的方向。目标对象的宽度方向为平行于地平面的方向。在道路图像中 可行驶区域的边缘可以呈锯齿状或其它形状。可以确定参考边缘上的各像素点在Y轴方向的第一坐标值。可以计算各像素点的第一坐标值的第一位置平均值，并根据计算得到的第一位置平均值调整检测框在目标对象高度方向的位置。
在一种可能的实现方式中，步骤S32，包括：
在图像坐标系中，确定所述参考边缘包括的像素点在所述目标对象宽度方向的第二坐标值；
计算各所述第二坐标值的平均值得到第二位置平均值；
根据所述第二位置平均值，在所述目标对象宽度方向调整所述目标对象的检测框在所述道路图像中的位置。
在一种可能的实现方式中，可以确定参考边缘上的各像素点在X轴方向的第二坐标值。计算各第二坐标值的平均值得到第二位置平均值后，根据第二位置平均值调整检测框在目标对象宽度方向的位置。
在一种可能的实现方式中，可以根据需求，只调整检测框在目标对象的高度方向或宽度方向的位置，也可以同时调整检测框在目标对象的高度方向和宽度方向的位置。
在本实施例中，将与所述检测框的底边对应的所述可行驶区域的边缘确定为参考边缘；根据所述参考边缘调整所述目标对象的检测框在所述道路图像中的位置。根据参考边缘调整的检测框的位置，可以使得检测框所标识的目标对象的位置更加接近实际位置。
图6示出根据本公开实施例的车辆智能驾驶控制方法中步骤S40的流程图，如图6所示，所述车辆智能驾驶控制方法中步骤S40包括：
步骤S41，根据调整后的检测框确定所述目标对象的检测宽高比。
在一种可能的实现方式中，道路可能有上坡道路和下坡道路。当目标对象位于上坡道路或下坡道路时，可根据目标对象的检测框确定出的目标对象的实际位置。当目标对象位于上坡道路或下坡道路时，目标对象的检测宽高比，与目标对象位于平面道路时正常的宽高比不同，因此为了减少甚至避免目标对象实际位置确定的偏差，可以根据调整后的检测框计算得到目标对象的检测宽高比。
步骤S42，在所述检测宽高比与所述目标对象的预定宽高比之间的差值大于差值阈值的情况下，确定高度调整值。
在一种可能的实现方式中，可以将目标对象的检测宽高比和实际宽高比进行比对，确定用于调整检测框在高度方向位置的高度值。在检测宽高比大于实际宽高比时，可以认为目标对象的位置高于车辆所在的平面，目标对象可能位于上坡道路。此时，可以根据确定出的高度值调整目标对象的实际位置。
在检测宽高比小于实际宽高比时，可以认为目标对象的位置低于车辆所在的平面，目标对象可能位于下坡道路。可以根据检测宽高比和实际宽高比之间的差值，确定高度调整值，并根据确定出的高度调整值调整目标对象的检测框。检测宽高比和实际宽高比之间的差值可以与高度调整值成正比。
步骤S43，根据所述高度调整值和所述检测框对所述车辆进行智能驾驶控制。
在一种可能的实现方式中，可以利用高度调整值表示目标对象在道路上相对于车辆所在平面的高度值。可以将检测框底边上的中心点确定目标对象的检测位置。可以根据高度调整至和检测确定位置，确定目标对象在道路上的实际位置。
在本实施例中，根据调整后的检测框确定所述目标对象的检测宽高比；在所述检测宽高比与所述目标对象的预定宽高比之间的差值大于差值阈值的情况下，确定高度调整值；根据所述高度调整值和所述检测框对所述车辆进行智能驾驶控制。可以根据目标对象的检测宽高比和实际宽高比，确定目标对象是否位于上坡道路或下坡道路，能够避免目标对象位于上坡道路或下坡道路时，根据目标对象检测框确定的实际位置产生偏差。
在一种可能的实现方式中，所述步骤S40，包括：
根据调整后的检测框，利用所述车载摄像头的多个单应矩阵确定所述目标对象在道路上的实际位置，各单应矩阵的标定距离范围不同。
在一种可能的实现方式中，单应矩阵可以用于表述真实世界中的一个平面和与其他图像之间的透视变换。可以利用基于车辆所处的环境构建车载摄像头的的单应矩阵(Homography matrix)，并根据需求确定多个不同标定距离范围的单应矩阵。可以将测距点在图像中对应的位置映射到车辆所处的环境中后，确定出目标对象与车辆之间的距离。利用单应矩阵可以得出车辆拍摄的图像中的测距点距离目标对象之间的距离信息。可以在测距前，基于车辆所处的环境构建单应矩阵。例如，可以利用自动驾驶车辆配置的单目摄像头拍摄真实的路面图像，利用路面图像上的点集，和图像上的点集在真实路面上对应的点集，构建单应矩阵。具体方法可以包括：1、建立坐标系：以自动驾驶车辆的左前轮为原点，以驾驶员的视角向右的方向为X轴的正方向，向前的方向为Y轴的正方向，建立车体坐标系。2、选点，选取 车体坐标系下的点，得到选点集。例如(0,5)、(0,10)、(0,15)、(1.85,5)、(1.85,10)、(1.85,15)，各点的单位为米。根据需求，也可以选取距离更远的点。3、标记、将选取的点在真实路面上进行标记，得到真实点集。4、标定，使用标定板和标定程序得到真实点集在拍摄图像中对应的像素位置。5、根据对应出的像素位置生成单应矩阵。
在一种可能的实现方式中，根据需求，可以根据不同的距离范围构建单应矩阵。例如，可以以100米的距离范围构建单应矩阵，也可以根据10米的范围构建单应矩阵。距离范围越小，根据单应矩阵确定出的距离的精度越高。利用标定好的多个单应矩阵，可以得到准确的目标对象的实际距离。
在本实施例中，根据调整后的检测框，利用多个单应矩阵确定目标对象在道路上的实际位置，各单应矩阵的标定距离范围不同。通过多个单应矩阵，可以得到更加准确的目标对象的实际位置。
图7示出根据本公开实施例的车辆智能驾驶控制方法的流程图，如图7所示，所述车辆智能驾驶控制方法还包括：
步骤S50，确定所述车辆的危险区域。
步骤S60，根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的危险等级。
步骤S70，在所述危险等级满足危险阈值的情况下，发送危险等级提示信息。
在一种可能的实现方式中，可以将车辆的前进方向上的设定区域确定为危险区域。在车辆行驶的方向上，可以将车辆前方设定长度和设定宽度的区域，确定为危险区域。例如，将车辆前方，以车辆前车盖正中心为圆心，半径为5米的扇形区域确定为危险区域，或将车辆正前方长度为5米，宽度为3米的区域确定为危险区域。可以根据需求确定危险区域的大小和形状。
在一种可能的实现方式中，当目标对象的实际位置位于危险区域以内时，可以将目标对象危险等级确定为严重危险。当目标对象的实际位置位于危险区域以外时，可以将目标对象危险等级确定为普通危险。
在一种可能的实现方式中，当目标对象的实际位置位于危险区域以外，且目标对象未被遮挡时，可以将目标对象危险等级确定为普通危险。
当目标对象的实际位置位于危险区域以外，且目标对象被遮挡时，可以将目标对象危险等级确定为无危险。
在一种可能的实现方式中，可以根据目标对象的危险等级，发送响应的危险等级提示信息。危险等级提示信息可以利用语音、震动、光、文字等不同的表现形式。本公开不限定危险等级提示信息的具体内容和表现形式。
在一种可能的实现方式中，所述根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的危险等级，包括：
根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的第一危险等级；
在所述目标对象的第一危险等级为最高危险等级的情况下，在所述视频流中所述道路图像的相邻图像中，确定所述目标对象的相邻位置；
根据所述相邻位置和所述目标对象的实际位置，确定所述目标对象的危险等级。
在一种可能的实现方式中，车辆所拍摄的道路图像可以是视频流中的一幅图像。当目标对象的危险等级被确定为严重危险时，可以根据当前道路图像和当前道路图像之前的图像，利用本公开上述实施例中的方法，对目标对象在当前道路图像之前的图像中的相邻位置进行确定。也可以计算当前道路图像和当前道路图像之前的图像中目标对象的重合度，当计算得到的重合度大于重合度阈值时，可以对目标对象的相邻位置进行确定。也可以计算当前道路图像之前的图像中该目标对象与车辆之间的历史距离，并计算该历史距离与当前道路图像中目标对象与车辆之间的距离差值，当距离差值小于距离阈值时，可以对目标对象的相邻位置进行确定。
可以根据确定出的相邻位置和目标对象的实际位置，确定目标对象的危险等级。
在本实施例中，根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的第一危险等级；在所述目标对象的第一危险等级为最高危险等级的情况下，在所述视频流中所述道路图像的相邻图像中，确定所述目标对象的相邻位置；根据所述相邻位置和所述目标对象的实际位置，确定所述目标对象的危险等级。可以通过相邻图像中目标对象的相邻位置和目标对象的实际位置，更加准确地确认目标对象的危险等级。
在一种可能的实现方式中，所述方法还包括：
根据所述目标对象与所述车辆之间的距离、所述目标对象的移动信息和所述车辆的移动信息，得到碰撞时间；
根据所述碰撞时间和时间阈值，确定碰撞预警信息；
发送所述碰撞预警信息。
在一种可能的实现方式中，可以根据目标对象距离车辆的距离，目标对象的移动速度和移动方向、车辆的移动速 度和移动方向，计算目标对象与车辆的碰撞时间。可以预设时间阈值，并根据时间阈值和碰撞时间得到碰撞预警信息。例如，预设时间阈值为5秒，当计算得到前方的目标车辆与当前车辆的碰撞时间小于5秒时，可以认为目标车辆若与当前车辆发生碰撞，车辆的驾驶者可能无法做出及时的处理导致危险发生，需要发送碰撞预警信息。可以利用声音、震动、光、文字等不同的表现形式发送碰撞预警信息。本公开不限定碰撞预警信息的具体内容和表现形式。
在本实施例中，根据目标对象与所述车辆之间的距离、目标对象的移动信息和车辆的移动信息，得到碰撞时间；根据碰撞时间和时间阈值，确定碰撞预警信息；发送碰撞预警信息。根据目标对象与车辆的实际距离及移动信息得到的碰撞预警信息，可以用于车辆智能驾驶中的安全驾驶领域，提高安全性。
在一种可能的实现方式中，所述发送所述碰撞预警信息，包括：
在已发送的碰撞预警信息中不存在所述目标对象的碰撞预警信息的发送记录的情况下，发送所述碰撞预警信息；和/或，
在已发送的碰撞预警信息中存在所述目标对象的碰撞预警信息的发送记录的情况下，不发送所述碰撞预警信息。
在一种可能的实现方式中，当车辆产生针对一个目标对象的碰撞预警信息后，可以在已发送的碰撞预警信息的发送记录中，查找是否存在该目标对象的碰撞预警信息，若存在，则不发送，可以提升用户体验。
在一种可能的实现方式中，所述发送所述碰撞预警信息，包括：
获取所述车辆的驾驶状态信息，所述驾驶状态信息包括刹车信息和/或转向信息；
在根据所述驾驶状态信息确定所述车辆未进行相应的刹车和/或转向处置的情况下，根据所述总线信息确定是否发送所述碰撞预警信息。
在一种可能的实现方式中，当车辆按照当前移动信息移动可能发生碰撞时，车辆的额驾驶员可能进行刹车减速和/或转向等操作。可以根据车辆的总线信息，获取车辆的刹车信息和转向信息。当根据总线信息获取到刹车信息和/或转向信息时，可以不发送或停止发送碰撞预警信息。
在本实施例中，获取车辆的总线信息，总线信息包括刹车信息和/或转向信息；根据总线信息确定是否发送碰撞预警信息。根据总线信息可以确定不发送或停止发送碰撞预警信息，使得碰撞预警信息的发送更加人性化，提高用户体验。
在一种可能的实现方式中，所述发送所述碰撞预警信息，包括：
获取所述车辆的驾驶状态信息，所述驾驶状态信息包括刹车信息和/或转向信息；
在根据所述驾驶状态信息确定所述车辆未进行相应的刹车和/或转向处置的情况下，发送所述碰撞预警信息。
在一种可能的实现方式中，可以自车辆的CAN(Controller Area Network,控制器局域网络)总线获取驾驶状态信息。可以根据驾驶状态信息确定车辆是否进行了刹车和/或转向灯相应的处置，根据驾驶状态信息判断车辆的驾驶员或智能驾驶系统已经进行了相关的处置，可以不发送碰撞预警信息，提高用户体验。
在一种可能的实现方式中，所述目标对象为车辆，所述方法还包括：
在所述道路图像中检测所述车辆的车牌和/或车标；
根据所述车牌和/或车标的检测结果确定所述目标对象的参考距离；
根据所述参考距离调整所述目标对象与所述车辆之间的距离。
在一种可能的实现方式中，道路中，车辆间的相互遮挡导致前车车辆的检测框可能非全车检测框，或两车距离很近导致前车的车尾处于车载摄像头盲区导致在道路图像中不可见，或其他类似情形下，车辆的检测框不能准确的框出前车车辆的位置，因为根据检测框计算得到的目标车辆与当前车辆之间的距离误差较大。此时可以利用神经网络识别车辆的车牌和/或车标的检测框，并利用车牌和/或车标的检测框修正目标车辆与当前车辆之间的距离。
可以利用标识了车辆的车牌和/或车标的样本图像，训练车辆标识神经网络。可以将道路图像输入训练好的车辆标识神经网络，得到车辆的车牌和/或车标。如图2所示，图2中前车车尾处的车牌用矩形框框出。车标可以为车尾处或车头处的车辆类型的标识，图2中未示出车标的检测框。车标通常设置在靠近车牌的位置，如设置在邻近车牌的上方位置。
可以根据车牌和/或车标的检测结果确定出的目标对象的参考距离，与根据目标对象车尾或整体确定出的目标对象与车辆之间的距离，可能存在差异。参考距离可以大于或小于根据目标对象车尾或整体确定出的距离。
在一种可能的实现方式中，所述根据所述参考距离调整所述目标对象与所述车辆之间的距离，包括：
在所述参考距离和所述目标对象与所述车辆之间的距离之间的差值大于差值阈值的情况下，将所述目标对象与所述车辆之间的距离调整为所述参考距离，或
计算所述目标对象与所述车辆之间的距离和所述参考距离之间的差值，根据所述差值确定所述目标对象与所述车辆之间的距离。
在一种可能的实现方式中，车辆的车牌和/或车标可以用于确定目标对象与所述车辆之间的参考距离。可以根据需求预设差值阈值，在所述参考距离和所述目标对象与所述车辆之间的距离之间的差值大于差值阈值的情况下，可以将目标对象与所述车辆之间的距离调整为参考距离。当参考距离和计算得到目标对象与车辆之间的距离差别较大时，也可以计算两个距离之间的平均值，将计算得到的平均值确定为目标对象与所述车辆之间调整后的距离。
在本实施例中，在道路图像中检测目标对象的识别信息，识别信息包括车牌和/或车标；根据识别信息确定目标对象的参考距离；根据参考距离调整目标对象与所述车辆之间的距离。根据目标对象的标识信息调整目标对象与车辆之间调整后的距离，可以使得调整后的距离更加准确。
在一种可能的实现方式中，所述根据所述参考距离调整所述目标对象与所述车辆之间的距离，包括：
将所述目标对象与所述车辆之间的距离调整为所述参考距离，或
计算所述目标对象与所述车辆之间的距离和所述参考距离之间的差值，根据所述差值确定所述目标对象与所述车辆之间的距离。
在一种可能的实现方式中，根据参考距离调整目标对象与车辆之间的距离，包括将目标对象与所述车辆之间的距离直接调整为参考距离，或者计算两者的差值，若参考距离大于目标对象与车辆之间的距离，可以将目标对象与车辆之间的距离加上差值，若参考距离小于目标对象与车辆之间的距离，可以将目标对象与车辆之间的距离减去差值。
可以理解，本公开提及的上述各个方法实施例，在不违背原理逻辑的情况下，均可以彼此相互结合形成结合后的实施例，限于篇幅，本公开不再赘述。
此外，本公开还提供了车辆智能驾驶控制装置、电子设备、计算机可读存储介质、程序，上述均可用来实现本公开提供的任一种车辆智能驾驶控制方法，相应技术方案和描述和参见方法部分的相应记载，不再赘述。
本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
图8示出根据本公开实施例的车辆智能驾驶控制装置的框图，如图8所示，所述车辆智能驾驶控制装置包括：
视频流获取模块10，用于经车辆的车载摄像头采集所述车辆所在场景的道路图像的视频流；
可行驶区域确定模块20，用于在所述道路图像中检测目标对象，得到所述目标对象的检测框；在所述道路图像中确定所述车辆的可行驶区域；
检测框调整模块30，用于根据所述可行驶区域调整所述目标对象的检测框；
控制模块40，用于根据调整后的检测框对所述车辆进行智能驾驶控制。
在一种可能的实现方式中，所述可行驶区域确定模块，包括：
图像分割子模块，用于对所述道路图像进行图像分割，得到所述道路图像中所述目标对象所在的分割区域；
第一车道线检测子模块，用于对所述道路图像进行车道线检测；
第一可行驶区域确定子模块，用于根据所述车道线的检测结果和所述分割区域确定所述道路图像中所述车辆的可行驶区域。
在一种可能的实现方式中，所述可行驶区域确定模块，包括：
整体投影区域确定子模块，用于确定所述目标对象在所述道路图像中的整体投影区域；
第二车道线检测子模块，用于对所述道路图像进行车道线检测；
第二可行驶区域确定子模块，用于根据所述车道线的检测结果和所述整体投影区域确定所述道路图像中所述车辆的可行驶区域。
在一种可能的实现方式中，所述目标对象为车辆，所述目标对象的检测框为车辆头部或尾部的检测框。
在一种可能的实现方式中，所述检测框调整模块，包括：
参考边缘确定子模块，用于将与所述检测框的底边对应的所述可行驶区域的边缘确定为参考边缘；
检测框调整子模块，用于根据所述参考边缘调整所述目标对象的检测框在所述道路图像中的位置。
在一种可能的实现方式中，所述检测框调整子模块，用于：
在图像坐标系中，确定所述参考边缘包括的像素点在所述目标对象高度方向的第一坐标值；
计算各所述第一坐标值的平均值得到第一位置平均值；
根据所述第一位置平均值，在所述目标对象高度方向调整所述目标对象的检测框在所述道路图像中的位置。
在一种可能的实现方式中，所述检测框调整子模块，还用于：
在图像坐标系中，确定所述参考边缘包括的像素点在所述目标对象宽度方向的第二坐标值；
计算各所述第二坐标值的平均值得到第二位置平均值；
根据所述第二位置平均值，在所述目标对象宽度方向调整所述目标对象的检测框在所述道路图像中的位置。
在一种可能的实现方式中，所述控制模块，包括：
检测宽高比确定子模块，用于根据调整后的检测框确定所述目标对象的检测宽高比；
高度调整值确定子模块，用于在所述检测宽高比与所述目标对象的预定宽高比之间的差值大于差值阈值的情况下，确定高度调整值；
第一控制子模块，用于根据所述高度调整值和所述检测框对所述车辆进行智能驾驶控制。
在一种可能的实现方式中，所述控制模块，包括：
实际位置确定子模块，用于根据调整后的检测框，利用所述车载摄像头的多个单应矩阵确定所述目标对象在道路上的实际位置，各单应矩阵的标定距离范围不同；
第二控制子模块，用于根据所述目标对象在道路上的实际位置对所述车辆进行智能驾驶控制。
在一种可能的实现方式中，所述装置还包括：
危险区域确定模块，用于确定所述车辆的危险区域；
危险等级确定模块，用于根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的危险等级；
第一提示信息发送模块，用于在所述危险等级满足危险阈值的情况下，发送危险等级提示信息。
在一种可能的实现方式中，所述危险等级确定模块，包括：
第一危险等级确定子模块，用于根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的第一危险等级；
相邻位置确定子模块，用于在所述目标对象的第一危险等级为最高危险等级的情况下，在所述视频流中所述道路图像的相邻图像中，确定所述目标对象的相邻位置；
第二危险等级确定子模块，用于根据所述相邻位置和所述目标对象的实际位置，确定所述目标对象的危险等级。
在一种可能的实现方式中，所述装置还包括：
碰撞时间获取模块，用于根据所述目标对象与所述车辆之间的距离、所述目标对象的移动信息和所述车辆的移动信息，得到碰撞时间；
碰撞预警信息确定模块，用于根据所述碰撞时间和时间阈值，确定碰撞预警信息；
第二提示信息发送模块，用于发送所述碰撞预警信息。
在一种可能的实现方式中，所述第二提示信息发送模块，包括：
第二提示信息发送子模块，用于在已发送的碰撞预警信息中不存在所述目标对象的碰撞预警信息的发送记录的情况下，发送所述碰撞预警信息；和/或，
在已发送的碰撞预警信息中存在所述目标对象的碰撞预警信息的发送记录的情况下，不发送所述碰撞预警信息。
在一种可能的实现方式中，所述第二提示信息发送模块，包括：
驾驶状态信息获取子模块，用于获取所述车辆的驾驶状态信息，所述驾驶状态信息包括刹车信息和/或转向信息；
第三提示信息发送子模块，用于在根据所述驾驶状态信息确定所述车辆未进行相应的刹车和/或转向处置的情况下，发送所述碰撞预警信息。
在一种可能的实现方式中，所述装置还包括距离确定装置，所述距离确定装置用于确定目标对象与所述车辆之间的距离，所述距离确定装置包括：
车牌车标检测子模块，用于在所述道路图像中检测所述车辆的车牌和/或车标；
参考距离确定子模块，用于根据所述车牌和/或车标的检测结果确定所述目标对象的参考距离；
距离确定子模块，用于根据所述参考距离调整所述目标对象与所述车辆之间的距离。
在一种可能的实现方式中，所述距离确定子模块，用于：
在所述参考距离和所述目标对象与所述车辆之间的距离之间的差值大于差值阈值的情况下，将所述目标对象与所述车辆之间的距离调整为所述参考距离，或
计算所述目标对象与所述车辆之间的距离和所述参考距离之间的差值，根据所述差值确定所述目标对象与所述车辆之间的距离。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文方法实施例描述的方法，其具体实现可以参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例还提出一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。计算机可读存储介质可以是非易失性计算机可读存储介质。
本公开实施例还提出一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为上述方法。
电子设备可以被提供为终端、服务器或其它形态的设备。
图9是根据一示例性实施例示出的一种电子设备800的框图。例如，电子设备800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等终端。
参照图9，电子设备800可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制电子设备800的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在电子设备800的操作。这些数据的示例包括用于在电子设备800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为电子设备800的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为电子设备800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述电子设备800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当电子设备800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当电子设备800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为电子设备800提供各个方面的状态评估。例如，传感器组件814可以检测到电子设备800的打开/关闭状态，组件的相对定位，例如所述组件为电子设备800的显示器和小键盘，传感器组件814还可以检测电子设备800或电子设备800一个组件的位置改变，用户与电子设备800接触的存在或不存在，电子设备800方位或加速/减速和电子设备800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于电子设备800和其他设备之间有线或无线方式的通信。电子设备800可以接入基于通信标 准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，电子设备800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器804，上述计算机程序指令可由电子设备800的处理器820执行以完成上述方法。
图10是根据一示例性实施例示出的一种电子设备1900的框图。例如，电子设备1900可以被提供为一服务器。参照图10，电子设备1900包括处理组件1922，其进一步包括一个或多个处理器，以及由存储器1932所代表的存储器资源，用于存储可由处理组件1922的执行的指令，例如应用程序。存储器1932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1922被配置为执行指令，以执行上述方法。
电子设备1900还可以包括一个电源组件1926被配置为执行电子设备1900的电源管理，一个有线或无线网络接口1950被配置为将电子设备1900连接到网络，和一个输入输出(I/O)接口1958。电子设备1900可以操作基于存储在存储器1932的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器1932，上述计算机程序指令可由电子设备1900的处理组件1922执行以完成上述方法。
本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出 一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的技术改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (34)

  1. 一种车辆智能驾驶控制方法，其特征在于，所述方法包括：
    经车辆的车载摄像头采集所述车辆所在场景的道路图像的视频流；
    在所述道路图像中检测目标对象，得到所述目标对象的检测框；在所述道路图像中确定所述车辆的可行驶区域；
    根据所述可行驶区域调整所述目标对象的检测框；
    根据调整后的检测框对所述车辆进行智能驾驶控制。
  2. 根据权利要求1所述的方法，其特征在于，所述在所述道路图像中确定所述车辆的可行驶区域，包括：
    对所述道路图像进行图像分割，得到所述道路图像中所述目标对象所在的分割区域；
    对所述道路图像进行车道线检测；
    根据所述车道线的检测结果和所述分割区域确定所述道路图像中所述车辆的可行驶区域。
  3. 根据权利要求1所述的方法，其特征在于，所述在所述道路图像中确定所述车辆的可行驶区域，包括：
    确定所述目标对象在所述道路图像中的整体投影区域；
    对所述道路图像进行车道线检测；
    根据所述车道线的检测结果和所述整体投影区域确定所述道路图像中所述车辆的可行驶区域。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述目标对象为车辆，所述目标对象的检测框为车辆头部或尾部的检测框。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，所述根据所述可行驶区域调整所述目标对象的检测框，包括：
    将与所述检测框的底边对应的所述可行驶区域的边缘确定为参考边缘；
    根据所述参考边缘调整所述目标对象的检测框在所述道路图像中的位置。
  6. 根据权利要求5所述的方法，其特征在于，所述根据所述参考边缘调整所述目标对象的检测框在所述道路图像中的位置，包括：
    在图像坐标系中，确定所述参考边缘包括的像素点在所述目标对象高度方向的第一坐标值；
    计算各所述第一坐标值的平均值得到第一位置平均值；
    根据所述第一位置平均值，在所述目标对象高度方向调整所述目标对象的检测框在所述道路图像中的位置。
  7. 根据权利要求5或6所述的方法，其特征在于，所述根据所述参考边缘调整所述目标对象的检测框在所述道路图像中的位置，包括：
    在图像坐标系中，确定所述参考边缘包括的像素点在所述目标对象宽度方向的第二坐标值；
    计算各所述第二坐标值的平均值得到第二位置平均值；
    根据所述第二位置平均值，在所述目标对象宽度方向调整所述目标对象的检测框在所述道路图像中的位置。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述根据调整后的检测框对所述车辆进行智能驾驶控制，包括：
    根据调整后的检测框确定所述目标对象的检测宽高比；
    在所述检测宽高比与所述目标对象的预定宽高比之间的差值大于差值阈值的情况下，确定高度调整值；
    根据所述高度调整值和所述检测框对所述车辆进行智能驾驶控制。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，所述根据调整后的检测框对所述车辆进行智能驾驶控制，包括：
    根据调整后的检测框，利用所述车载摄像头的多个单应矩阵确定所述目标对象在道路上的实际位置，各单应矩阵的标定距离范围不同；
    根据所述目标对象在道路上的实际位置对所述车辆进行智能驾驶控制。
  10. 根据权利要求9所述的方法，其特征在于，所述方法还包括：
    确定所述车辆的危险区域；
    根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的危险等级；
    在所述危险等级满足危险阈值的情况下，发送危险等级提示信息。
  11. 根据权利要求10所述的方法，其特征在于，所述根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的危险等级，包括：
    根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的第一危险等级；
    在所述目标对象的第一危险等级为最高危险等级的情况下，在所述视频流中所述道路图像的相邻图像中，确定所述目标对象的相邻位置；
    根据所述相邻位置和所述目标对象的实际位置，确定所述目标对象的危险等级。
  12. 根据权利要求1至11中任一项所述的方法，其特征在于，所述方法还包括：
    根据所述目标对象与所述车辆之间的距离、所述目标对象的移动信息和所述车辆的移动信息，得到碰撞时间；
    根据所述碰撞时间和时间阈值，确定碰撞预警信息；
    发送所述碰撞预警信息。
  13. 根据权利要求12所述的方法，其特征在于，所述发送所述碰撞预警信息，包括：
    在已发送的碰撞预警信息中不存在所述目标对象的碰撞预警信息的发送记录的情况下，发送所述碰撞预警信息；和/或，
    在已发送的碰撞预警信息中存在所述目标对象的碰撞预警信息的发送记录的情况下，不发送所述碰撞预警信息。
  14. 根据权利要求1至13中任一项所述的方法，其特征在于，所述发送所述碰撞预警信息，包括：
    获取所述车辆的驾驶状态信息，所述驾驶状态信息包括刹车信息和/或转向信息；
    在根据所述驾驶状态信息确定所述车辆未进行相应的刹车和/或转向处置的情况下，发送所述碰撞预警信息。
  15. 根据权利要求12至14中任一项所述的方法，其特征在于，所述目标对象与所述车辆之间的距离的确定步骤，包括：
    在所述道路图像中检测所述车辆的车牌和/或车标；
    根据所述车牌和/或车标的检测结果确定所述目标对象的参考距离；
    根据所述参考距离调整所述目标对象与所述车辆之间的距离。
  16. 根据权利要求15所述的方法，其特征在于，所述根据所述参考距离调整所述目标对象与所述车辆之间的距离，包括：
    在所述参考距离和所述目标对象与所述车辆之间的距离之间的差值大于差值阈值的情况下，将所述目标对象与所述车辆之间的距离调整为所述参考距离，或
    计算所述目标对象与所述车辆之间的距离和所述参考距离之间的差值，根据所述差值确定所述目标对象与所述车辆之间的距离。
  17. 一种车辆智能驾驶控制装置，其特征在于，所述装置包括：
    视频流获取模块，用于经车辆的车载摄像头采集所述车辆所在场景的道路图像的视频流；
    可行驶区域确定模块，用于在所述道路图像中检测目标对象，得到所述目标对象的检测框；在所述道路图像中确定所述车辆的可行驶区域；
    检测框调整模块，用于根据所述可行驶区域调整所述目标对象的检测框；
    控制模块，用于根据调整后的检测框对所述车辆进行智能驾驶控制。
  18. 根据权利要求17所述的装置，其特征在于，所述可行驶区域确定模块，包括：
    图像分割子模块，用于对所述道路图像进行图像分割，得到所述道路图像中所述目标对象所在的分割区域；
    第一车道线检测子模块，用于对所述道路图像进行车道线检测；
    第一可行驶区域确定子模块，用于根据所述车道线的检测结果和所述分割区域确定所述道路图像中所述车辆的可行驶区域。
  19. 根据权利要求17所述的装置，其特征在于，所述可行驶区域确定模块，包括：
    整体投影区域确定子模块，用于确定所述目标对象在所述道路图像中的整体投影区域；
    第二车道线检测子模块，用于对所述道路图像进行车道线检测；
    第二可行驶区域确定子模块，用于根据所述车道线的检测结果和所述整体投影区域确定所述道路图像中所述车辆的可行驶区域。
  20. 根据权利要求17至19中任一项所述的装置，其特征在于，所述目标对象为车辆，所述目标对象的检测框为车辆头部或尾部的检测框。
  21. 根据权利要求17至20中任一项所述的装置，其特征在于，所述检测框调整模块，包括：
    参考边缘确定子模块，用于将与所述检测框的底边对应的所述可行驶区域的边缘确定为参考边缘；
    检测框调整子模块，用于根据所述参考边缘调整所述目标对象的检测框在所述道路图像中的位置。
  22. 根据权利要求21所述的装置，其特征在于，所述检测框调整子模块，用于：
    在图像坐标系中，确定所述参考边缘包括的像素点在所述目标对象高度方向的第一坐标值；
    计算各所述第一坐标值的平均值得到第一位置平均值；
    根据所述第一位置平均值，在所述目标对象高度方向调整所述目标对象的检测框在所述道路图像中的位置。
  23. 根据权利要求21或22所述的装置，其特征在于，所述检测框调整子模块，还用于：
    在图像坐标系中，确定所述参考边缘包括的像素点在所述目标对象宽度方向的第二坐标值；
    计算各所述第二坐标值的平均值得到第二位置平均值；
    根据所述第二位置平均值，在所述目标对象宽度方向调整所述目标对象的检测框在所述道路图像中的位置。
  24. 根据权利要求17至23中任一项所述的装置，其特征在于，所述控制模块，包括：
    检测宽高比确定子模块，用于根据调整后的检测框确定所述目标对象的检测宽高比；
    高度调整值确定子模块，用于在所述检测宽高比与所述目标对象的预定宽高比之间的差值大于差值阈值的情况下，确定高度调整值；
    第一控制子模块，用于根据所述高度调整值和所述检测框对所述车辆进行智能驾驶控制。
  25. 根据权利要求17至24中任一项所述的装置，其特征在于，所述控制模块，包括：
    实际位置确定子模块，用于根据调整后的检测框，利用所述车载摄像头的多个单应矩阵确定所述目标对象在道路上的实际位置，各单应矩阵的标定距离范围不同；
    第二控制子模块，用于根据所述目标对象在道路上的实际位置对所述车辆进行智能驾驶控制。
  26. 根据权利要求25所述的装置，其特征在于，所述装置还包括：
    危险区域确定模块，用于确定所述车辆的危险区域；
    危险等级确定模块，用于根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的危险等级；
    第一提示信息发送模块，用于在所述危险等级满足危险阈值的情况下，发送危险等级提示信息。
  27. 根据权利要求26所述的装置，其特征在于，所述危险等级确定模块，包括：
    第一危险等级确定子模块，用于根据所述目标对象的实际位置和所述危险区域，确定所述目标对象的第一危险等级；
    相邻位置确定子模块，用于在所述目标对象的第一危险等级为最高危险等级的情况下，在所述视频流中所述道路图像的相邻图像中，确定所述目标对象的相邻位置；
    第二危险等级确定子模块，用于根据所述相邻位置和所述目标对象的实际位置，确定所述目标对象的危险等级。
  28. 根据权利要求17至27中任一项所述的装置，其特征在于，所述装置还包括：
    碰撞时间获取模块，用于根据所述目标对象与所述车辆之间的距离、所述目标对象的移动信息和所述车辆的移动信息，得到碰撞时间；
    碰撞预警信息确定模块，用于根据所述碰撞时间和时间阈值，确定碰撞预警信息；
    第二提示信息发送模块，用于发送所述碰撞预警信息。
  29. 根据权利要求28所述的装置，其特征在于，所述第二提示信息发送模块，包括：
    第二提示信息发送子模块，用于在已发送的碰撞预警信息中不存在所述目标对象的碰撞预警信息的发送记录的情况下，发送所述碰撞预警信息；和/或，
    在已发送的碰撞预警信息中存在所述目标对象的碰撞预警信息的发送记录的情况下，不发送所述碰撞预警信息。
  30. 根据权利要求17至29中任一项所述的装置，其特征在于，所述第二提示信息发送模块，包括：
    驾驶状态信息获取子模块，用于获取所述车辆的驾驶状态信息，所述驾驶状态信息包括刹车信息和/或转向信息；
    第三提示信息发送子模块，用于在根据所述驾驶状态信息确定所述车辆未进行相应的刹车和/或转向处置的情况下，发送所述碰撞预警信息。
  31. 根据权利要求28至30中任一项所述的装置，其特征在于，所述装置还包括距离确定装置，所述距离确定装置用于确定目标对象与所述车辆之间的距离，所述距离确定装置包括：
    车牌车标检测子模块，用于在所述道路图像中检测所述车辆的车牌和/或车标；
    参考距离确定子模块，用于根据所述车牌和/或车标的检测结果确定所述目标对象的参考距离；
    距离确定子模块，用于根据所述参考距离调整所述目标对象与所述车辆之间的距离。
  32. 根据权利要求31所述的装置，其特征在于，所述距离确定子模块，用于：
    在所述参考距离和所述目标对象与所述车辆之间的距离之间的差值大于差值阈值的情况下，将所述目标对象与所述车辆之间的距离调整为所述参考距离，或
    计算所述目标对象与所述车辆之间的距离和所述参考距离之间的差值，根据所述差值确定所述目标对象与所述车辆之间的距离。
  33. 一种电子设备，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为：执行权利要求1至16中任意一项所述的方法。
  34. 一种计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现权利要求1至16中任意一项所述的方法。
PCT/CN2019/076441 2019-02-28 2019-02-28 车辆智能驾驶控制方法及装置、电子设备和存储介质 WO2020172842A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
SG11202108455PA SG11202108455PA (en) 2019-02-28 2019-02-28 Vehicle intelligent driving control method and apparatus, electronic device and storage medium
KR1020217026297A KR20210115026A (ko) 2019-02-28 2019-02-28 차량 인텔리전트 운전 제어 방법 및 장치, 전자 기기 및 기억 매체
JP2021545946A JP2022520544A (ja) 2019-02-28 2019-02-28 車両インテリジェント運転制御方法及び装置、電子機器並びに記憶媒体
PCT/CN2019/076441 WO2020172842A1 (zh) 2019-02-28 2019-02-28 车辆智能驾驶控制方法及装置、电子设备和存储介质
US17/398,686 US20210365696A1 (en) 2019-02-28 2021-08-10 Vehicle Intelligent Driving Control Method and Device and Storage Medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/076441 WO2020172842A1 (zh) 2019-02-28 2019-02-28 车辆智能驾驶控制方法及装置、电子设备和存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/398,686 Continuation US20210365696A1 (en) 2019-02-28 2021-08-10 Vehicle Intelligent Driving Control Method and Device and Storage Medium

Publications (1)

Publication Number Publication Date
WO2020172842A1 true WO2020172842A1 (zh) 2020-09-03

Family

ID=72238812

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/076441 WO2020172842A1 (zh) 2019-02-28 2019-02-28 车辆智能驾驶控制方法及装置、电子设备和存储介质

Country Status (5)

Country Link
US (1) US20210365696A1 (zh)
JP (1) JP2022520544A (zh)
KR (1) KR20210115026A (zh)
SG (1) SG11202108455PA (zh)
WO (1) WO2020172842A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220198200A1 (en) * 2020-12-22 2022-06-23 Continental Automotive Systems, Inc. Road lane condition detection with lane assist for a vehicle using infrared detecting device
WO2023103459A1 (zh) * 2021-12-07 2023-06-15 中兴通讯股份有限公司 车辆控制方法、决策服务器及存储介质

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20220013203A (ko) * 2020-07-24 2022-02-04 현대모비스 주식회사 차량의 차선 유지 보조 시스템 및 이를 이용한 차선 유지 방법
CN114360201A (zh) * 2021-12-17 2022-04-15 中建八局发展建设有限公司 基于ai技术的建筑临边危险区域越界识别方法和系统
US20230196791A1 (en) * 2021-12-21 2023-06-22 Gm Cruise Holdings Llc Road paint feature detection
CN114322799B (zh) * 2022-03-14 2022-05-24 北京主线科技有限公司 一种车辆行驶方法、装置、电子设备和存储介质
CN114582132B (zh) * 2022-05-05 2022-08-09 四川九通智路科技有限公司 一种基于机器视觉的车辆碰撞检测预警系统及方法
CN114998863B (zh) * 2022-05-24 2023-12-12 北京百度网讯科技有限公司 目标道路识别方法、装置、电子设备以及存储介质
CN115019556B (zh) * 2022-05-31 2023-09-08 重庆长安汽车股份有限公司 车辆碰撞预警方法、系统、电子设备及可读存储介质
CN115526055B (zh) * 2022-09-30 2024-02-13 北京瑞莱智慧科技有限公司 模型鲁棒性检测方法、相关装置及存储介质
CN116385475B (zh) * 2023-06-06 2023-08-18 四川腾盾科技有限公司 一种针对大型固定翼无人机自主着陆的跑道识别分割方法
CN117274939B (zh) * 2023-10-08 2024-05-28 北京路凯智行科技有限公司 安全区域检测方法和安全区域检测装置
CN117253380B (zh) * 2023-11-13 2024-03-26 国网天津市电力公司培训中心 一种基于数据融合技术的智慧校园安全管理系统和方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130054086A1 (en) * 2011-08-31 2013-02-28 Autorad Tech Co., Ltd Adjusting Method and System of Intelligent Vehicle Imaging Device
KR20140148171A (ko) * 2013-06-21 2014-12-31 가천대학교 산학협력단 지능형 차량의 차선 검출방법
CN104392212A (zh) * 2014-11-14 2015-03-04 北京工业大学 一种基于视觉的道路信息检测及前方车辆识别方法
CN105620489A (zh) * 2015-12-23 2016-06-01 深圳佑驾创新科技有限公司 驾驶辅助系统及车辆实时预警提醒方法
CN105912998A (zh) * 2016-04-05 2016-08-31 辽宁工业大学 一种基于视觉的车辆防碰撞预警方法
CN106056100A (zh) * 2016-06-28 2016-10-26 重庆邮电大学 一种基于车道检测与目标跟踪的车辆辅助定位方法

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3064759B2 (ja) * 1993-09-28 2000-07-12 株式会社日立製作所 車両の周囲を監視する装置、車両の運転支援システムおよび運転支援装置
JP3430641B2 (ja) * 1994-06-10 2003-07-28 日産自動車株式会社 車間距離検出装置
JPH1096626A (ja) * 1996-09-20 1998-04-14 Oki Electric Ind Co Ltd 車間距離検知装置
JP2001134769A (ja) * 1999-11-04 2001-05-18 Honda Motor Co Ltd 対象物認識装置
JP2004038624A (ja) * 2002-07-04 2004-02-05 Nissan Motor Co Ltd 車両認識方法、車両認識装置及び車両認識用プログラム
JP4196841B2 (ja) * 2004-01-30 2008-12-17 株式会社豊田自動織機 映像位置関係補正装置、該映像位置関係補正装置を備えた操舵支援装置、及び映像位置関係補正方法
JP4502733B2 (ja) * 2004-07-15 2010-07-14 ダイハツ工業株式会社 障害物測定方法及び障害物測定装置
JP5752729B2 (ja) * 2013-02-28 2015-07-22 富士フイルム株式会社 車間距離算出装置およびその動作制御方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130054086A1 (en) * 2011-08-31 2013-02-28 Autorad Tech Co., Ltd Adjusting Method and System of Intelligent Vehicle Imaging Device
KR20140148171A (ko) * 2013-06-21 2014-12-31 가천대학교 산학협력단 지능형 차량의 차선 검출방법
CN104392212A (zh) * 2014-11-14 2015-03-04 北京工业大学 一种基于视觉的道路信息检测及前方车辆识别方法
CN105620489A (zh) * 2015-12-23 2016-06-01 深圳佑驾创新科技有限公司 驾驶辅助系统及车辆实时预警提醒方法
CN105912998A (zh) * 2016-04-05 2016-08-31 辽宁工业大学 一种基于视觉的车辆防碰撞预警方法
CN106056100A (zh) * 2016-06-28 2016-10-26 重庆邮电大学 一种基于车道检测与目标跟踪的车辆辅助定位方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220198200A1 (en) * 2020-12-22 2022-06-23 Continental Automotive Systems, Inc. Road lane condition detection with lane assist for a vehicle using infrared detecting device
WO2023103459A1 (zh) * 2021-12-07 2023-06-15 中兴通讯股份有限公司 车辆控制方法、决策服务器及存储介质

Also Published As

Publication number Publication date
JP2022520544A (ja) 2022-03-31
KR20210115026A (ko) 2021-09-24
SG11202108455PA (en) 2021-09-29
US20210365696A1 (en) 2021-11-25

Similar Documents

Publication Publication Date Title
WO2020172842A1 (zh) 车辆智能驾驶控制方法及装置、电子设备和存储介质
US11468581B2 (en) Distance measurement method, intelligent control method, electronic device, and storage medium
US11308809B2 (en) Collision control method and apparatus, and storage medium
US20200317190A1 (en) Collision Control Method, Electronic Device and Storage Medium
US10733462B2 (en) Travel assistance device and computer program
RU2656933C2 (ru) Способ и устройство для предупреждения о встречном транспортном средстве
KR102240197B1 (ko) 사발형 이미징 시스템에서의 물체 추적
JP2019008460A (ja) 物体検出装置、物体検出方法およびプログラム
KR102580476B1 (ko) 차량의 차량 주변환경 내 가림 영역 산출 방법 및 장치
KR101986734B1 (ko) 차량 운전 보조 장치 및 이의 안전 운전 유도 방법
JP2015139128A (ja) 車両用周辺監視装置
CN111157014A (zh) 路况展示方法、装置及车载终端、存储介质
JP2019109707A (ja) 表示制御装置、表示制御方法および車両
US20230343108A1 (en) Systems and methods for detecting projection attacks on object identification systems
KR101658089B1 (ko) 차선 유지 제어를 위한 차선 중심 추정 방법 및 그 장치
KR101374653B1 (ko) 차량의 움직임을 검출하는 장치 및 방법
JP2018073275A (ja) 画像認識装置
JP2018074286A (ja) 運転支援装置
KR101947473B1 (ko) 후방 차량을 고려한 안전 운전 지원 장치 및 방법
US20220172490A1 (en) Image processing apparatus, vehicle control apparatus, method, and program
JP6185327B2 (ja) 車両後側方警報装置、車両後側方警報方法および他車両距離検出装置
JP6179249B2 (ja) 車両検出装置
US10867397B2 (en) Vehicle with a driving assistance system with a low power mode
US20240221389A1 (en) System and method for deep learning based lane curvature detection from 2d images
JP5609597B2 (ja) 接触可能性検知装置、接触可能性検知方法、及びプログラム

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: 19916890

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021545946

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20217026297

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 19.10.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19916890

Country of ref document: EP

Kind code of ref document: A1