A vehicle surround view system

Abstract

The application discloses a kind of vehicle surround view systems.The vehicle surround view system includes: image acquisition unit, image processing unit, driving driving unit, timing calibration unit and vehicle communication unit, each camera unit of the image acquisition unit includes two height positions same, and in transverse interval, two cameras of same specification;The timing calibration unit determines the control delay duration T, wherein T=t2-t1;In the formula, t1 is the time when the image frame starts to be uploaded by the vehicle communication unit, or the time when the image acquisition unit collects image frame;T2 is the time when the control instruction corresponding to the image frame from remote control device is sent to the vehicle execution unit by the driving driving unit.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicle technology, in particular to a vehicle surround view system. BACKGROUND

[0002] The vehicle panoramic surround view system refers to erecting multiple wide-angle cameras around the vehicle which can cover all the field of view of the vehicle periphery, processing the multiple video images collected at the same time into a 360-degree overhead view of the vehicle periphery, and finally displaying on the screen of the center console to let the driver clearly check whether there are obstacles in the vehicle periphery and understand the relative position and distance of the obstacles, so as to help the driver to park or start the vehicle.

[0003] However, the vehicle panoramic surround view system of the prior art is only used for parking or starting the vehicle, and cannot be used for remote control of the vehicle, which wastes the resources of the vehicle panoramic surround view system. SUMMARY

[0004] The present application provides a vehicle surround view system, which comprises:

[0005] an image acquisition unit, an image processing unit, a driving unit, a timing calibration unit and a vehicle communication unit,

[0006] The image acquisition unit comprises front camera units, rear camera units arranged at the front and rear ends of the vehicle, and left camera units and right camera units arranged at the left and right sides of the vehicle; wherein the front camera units, the rear camera units, the left camera units and the right camera units each comprise two cameras of the same specification which are of the same height and spaced apart in the transverse direction, and can be used to form a depth map to determine the relative distance and relative position of the environmental target relative to the vehicle;

[0007] The image processing unit is used to process and splice the images collected by the image acquisition unit to form a surround view image; when splicing the images, only one image signal is selected from the front camera units, the rear camera units, the left camera units and the right camera units for splicing;

[0008] The vehicle communication unit is used to communicate with the remote control device to upload the images collected by the image acquisition unit and / or the surround view images processed by the image processing unit, and to receive the control instructions from the remote control device;

[0009] The driving unit is used to drive the vehicle execution unit to realize remote control of the vehicle;

[0010] The timing calibration unit determines the control delay time T, wherein,

[0011] T=t2-t1;

[0012] Wherein, t1 is the time when the image frame starts to be uploaded through the vehicle communication unit, or the time when the image frame is collected by the image collection unit;

[0013] t2 is the time when the control instruction corresponding to the image frame from the remote control device is sent to the vehicle execution unit through the driving unit.

[0014] Specifically, the vehicle surround view system is remotely controlled in the following method:

[0015] Step S1. Let T = T0, wherein T0 is a preset time threshold;

[0016] Step S2. Collect the current image frame and the timestamp ts1 of the current image frame, and transmit the current image frame, the timestamp ts1 of the current image frame, and the control delay time T to the remote control device;

[0017] Step S3. The remote control device generates a control instruction OCC based on the current image frame and the control delay time T, and transmits the control instruction OCC and the timestamp ts1 of the current image frame to the vehicle communication unit;

[0018] Step S4. Transmit the control instruction OCC and the timestamp ts1 of the current image frame to the driving unit to drive the vehicle execution unit, and record the transmission time ts3; update T = ts3-ts1, and go to step S2.

[0019] Specifically, when the collision safety is judged, the length L is added to the vehicle in the driving direction of the vehicle, L = V*T, and the collision safety is judged based on the virtual total length L0+L after the length is added,

[0020] Wherein, V is the current running speed of the vehicle, T is the control delay time determined by the time sequence calibration unit, L0 is the length of the vehicle, L0 = L01+L02+L03,

[0021] L01 is the front suspension length of the vehicle; L02 is the wheelbase of the vehicle; L03 is the rear suspension length of the vehicle.

[0022] Specifically, on the overhead panoramic surround view image display screen of the remote control device, for the image displayed by the vehicle, the length L is added to the vehicle in the driving direction of the vehicle,

[0023] L = V*T,

[0024] Wherein, V is the current running speed of the vehicle, and T is the control delay time determined by the time sequence calibration unit.

[0025] Specifically, based on the control delay time T, the target vehicle speed Vp is adjusted,

[0026] Vp = Vp if T < T0

[0027] Vp = Vp*T / T0 if T0 < T < Tmax

[0028] Vp = 0 if T > Tmax

[0029] wherein T0, Tmax are preset time length thresholds, Tmax < 10*T0.

[0030] Specifically, in the driving scene, the speed limit on the structured road is 25km / h; the speed limit on the unstructured road is 15km / h; the speed limit in the turning scene is 10km / h, the speed limit in the reversing scene is 5km / h, and the speed limit in the parking scene is 5km / h.

[0031] Specifically, the distance between the target and the vehicle is determined based on the image obtained by the camera unit, and the conversion of the top-down surround view is performed based on the determined distance,

[0032] wherein the distance between the target and the vehicle is determined in the following manner:

[0033] Step S1. Form a depth map sequence based on the image frame sequences obtained by the two cameras of the same camera unit at the same time,

[0034] Step S2. Determine the common target features in the previous image frame and the current image frame obtained by the first camera, and the new target features in the current image frame;

[0035] Step S3. Based on the current image frame, the relative distance between the common target features and the new target features in the current image frame and the vehicle is determined using the depth information of the previous depth map.

[0036] Specifically, in the parking scene, the remote control parking is performed in the following manner:

[0037] The remote control vehicle drives forward to pass the target parking space;

[0038] Based on the image detected by the image sensor, the parameters of the target parking space, the parameters of the driving lane and the obstacle, and the target parking position B close to the rear end of the target parking space are determined;

[0039] The arc cutting arc method is used to perform the reverse parking, wherein the first arc DC and the second arc CB have the same central angle β; the turning radius of the first arc DC is R1, and the turning radius of the second arc CB is R2.

[0040] The end point B of the second arc, the start point D and the end point C of the first arc are set as position nodes, and the target speed Vp at the position nodes is zero.

[0041] Specifically, the position of the starting point D of the first circular arc, i.e. the position of the parking starting point, is determined in the following manner:

[0042] First, the target parking position B is determined, specifically, the vehicle position is determined with the position of the center of the rear axle of the vehicle, at the target parking position B, the distance between the rear end of the vehicle and the rearward parking space is d, the left side of the vehicle body is flush with the outer boundary line of the target parking space;

[0043] Secondly, the coordinate system is established in the following manner: taking the position of the center of the rear axle of the vehicle at the target parking position B as the coordinate origin, the coordinate system is established, wherein the front direction of the vehicle is the X direction, the left direction of the vehicle is the Y direction, and the position of the starting point D of the first circular arc is represented as X D , Y D ;

[0044] X D =(R1+R2)sinβ

[0045] Y D =(R1+R2)(1-cosβ)

[0046] Wherein, R1=R2=L02*cotθ

[0047] L02 is the wheelbase of the vehicle; θ is the maximum steering angle of the vehicle;

[0048] β is valued in the following range based on:

[0049] arcsin(a / 2(L02*cotθ))<β<arccos(1-b / 2(L02*cotθ))

[0050] a is the length of the target parking space, i.e. the size of the target parking space in the X direction,

[0051] b is the width of the target parking space, i.e. the size of the target parking space in the Y direction.

[0052] The present application also provides a vehicle, which comprises the vehicle surround view system as described above, and the vehicle is an electric truck running in a mine area.

[0053] The present application also provides a method for operating a vehicle surround view system. For example, a method for operating a vehicle surround view system, the vehicle surround view system comprising: an image acquisition unit, an image processing unit, a driving unit, a timing calibration unit and a vehicle communication unit,

[0054] The image acquisition unit comprises a front camera unit arranged at the front end of the vehicle, a rear camera unit arranged at the rear end of the vehicle, and a left camera unit and a right camera unit arranged at the left side and the right side of the vehicle; wherein the front camera unit, the rear camera unit, the left camera unit and the right camera unit each comprise two cameras of the same specification and the same height position and spaced apart in the transverse direction, which can be used to form a depth map to determine the relative distance and the relative direction of the environmental target relative to the vehicle;

[0055] The image processing unit is configured to process and splice the images acquired by the image acquisition unit to form a surround view image; when splicing the images, only one image signal is selected from the front camera unit, the rear camera unit, the left camera unit and the right camera unit for splicing;

[0056] The vehicle-mounted communication unit is configured to communicate with the remote control device to upload the images acquired by the image acquisition unit and / or the surround view image processed by the image processing unit, and to receive the control instructions from the remote control device;

[0057] The driving unit is configured to drive the vehicle-mounted execution unit to realize remote control of the vehicle;

[0058] The timing calibration unit determines the control delay time T in the following manner:

[0059] T = t2 - t1;

[0060] In the formula, t1 is the time when the image frame starts to be uploaded by the vehicle-mounted communication unit, or the time when the image frame is acquired by the image acquisition unit;

[0061] t2 is the time when the control instruction corresponding to the image frame and coming from the remote control device is sent to the vehicle execution unit by the driving unit. BRIEF DESCRIPTION OF DRAWINGS

[0062] Figure 1 is a schematic block diagram of a vehicle surround view system according to an embodiment of the present application.

[0063] Figure 2 is a schematic side view of a truck using the vehicle surround view system according to an embodiment of the present application.

[0064] Figure 3 is a schematic top view of the truck shown in Figure 2 .

[0065] Figure 4 is a schematic diagram illustrating the operation mode of the vehicle surround view system according to an embodiment of the present application in a forward direction scenario.

[0066] Figure 5is a driving route map for remote control parking by a vehicle surround view system according to an embodiment of the present application.

[0067] Figure 6 is a flow chart for remote control by a vehicle surround view system according to an embodiment of the present application.

[0068] Figure 7 is a schematic diagram illustrating the relationship between the turning radius at the midpoint of the rear axle and the wheelbase of the vehicle when the vehicle is turning. DETAILED DESCRIPTION

[0069] In the drawings, the same or similar elements or elements having the same or similar functions are denoted by the same or similar reference signs. The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0070] The vehicle surround view system according to the embodiments of the present application can be used to provide the driver with a spliced surround view image in the scenarios of starting, reversing, turning, etc., to avoid or reduce the dead angle of observation and improve the safety performance.

[0071] Moreover, the vehicle surround view system according to the embodiments of the present application can also be used for automatic driving. The vehicle surround view system acquires image information (environment information) around the vehicle based on the on-board visual sensor, and transmits the image information to a remote platform through a communication network. With the powerful computing capability of the remote platform (such as a cloud computing platform), the image information is deeply processed, the environment information is extracted by using a neural network, etc., the driving route is planned, and the vehicle driving control instruction is formed.

[0072] For example, the position information of the road setting such as lane lines and road curbs; the position and speed information of dynamic targets such as other vehicles (motor vehicles or non-motor vehicles); the position, size, etc. of static obstacles such as traffic cones; the state information of traffic lights; the information indicated by traffic signs; and the like. In addition, the GPS positioning can be based on the corresponding information in the prior map, so as to more accurately determine the driving environment information.

[0073] Further, the vehicle surround view system according to the embodiments of the present application can also be used for remote control in specific scenarios, such as remote control by the driver or the operator of the remote control platform through the communication network. The specific scenarios are, for example, that the vehicle driver cannot directly control the vehicle due to some reasons; or mine driving operation in a closed or semi-closed environment; or parking operation, etc.

[0074] The vehicle surround view system according to embodiments of the present application can be applied to any suitable vehicle, for example, can be applied to a car, a truck, etc. In one embodiment, the vehicle surround view system is applied to an electric vehicle, for example, the vehicle is an electric truck. The vehicle surround view system is particularly suitable for an electric vehicle running at a low speed. In addition, the vehicle surround view system is suitable for a vehicle running in a closed area, for example, the vehicle is an electric truck running in a mine area.

[0075] Embodiments of the present application also provide a method for operating a vehicle surround view system. The method for operating a vehicle surround view system is described below in detail in combination with the vehicle surround view system.

[0076] Figure 1 is a schematic block diagram of a vehicle surround view system according to an embodiment of the present application. Figure 1 The vehicle surround view system shown includes a plurality of vision sensors (image acquisition units), an image processing unit, a driving unit, a timing calibration unit (not shown) and a vehicle communication unit.

[0077] The remote control device and the communication network can also be part of the vehicle surround view system according to the present application.

[0078] Referring to Figure 2 and Figure 3 , the image acquisition unit 10 includes a plurality of vision sensors. The plurality of vision sensors are arranged around the vehicle, for example, include a front camera unit 11 arranged at the front end of the vehicle, a rear camera unit 14 arranged at the rear end of the vehicle, and a left camera unit 12 and a right camera unit 13 arranged at the left side and the right side of the vehicle. The front camera unit 11, the rear camera unit 14, the left camera unit 12 and the right camera unit 13 each include two cameras of the same specification and same parameters at the same height position and spaced apart in the lateral direction. Here, the height direction refers to the up-down direction of the figure, i.e., the height direction of the vehicle. The lateral direction refers to the left-right direction of the figure, i.e., the front-rear direction of the vehicle for the left and right camera units; and refers to the up-down direction of the figure, i.e., the left-right direction of the vehicle for the front and rear camera units. Figure 2 Figure 3 Figure 3

[0079] In other words, each camera unit includes two cameras of the same specification and same parameters pre-calibrated, so that a depth map can be formed to determine the relative distance and relative position of an environmental target relative to the vehicle (ego vehicle). In this way, compared with a conventional vehicle surround view system, in addition to providing a surround view image, the position of an environmental target relative to the vehicle can also be accurately determined. Thus, assisted driving, autonomous driving, remote control driving can be performed based on the image acquired by the camera unit.

[0080] ​​​The image processing unit is configured to process and stitch the images collected by the image collection unit to form a surround view image. When stitching the images, only one image signal from each of the front, rear, left and right image collection units is selected for stitching.

[0081] It can be understood that a GPS, a radar and other non-vision sensors can also be provided on the vehicle. Information collected by the non-vision sensors and information collected by the vision sensors can be fused to better determine the driving environment information of the vehicle.

[0082] As shown in the figure, the image collection unit further includes a downward-looking image collection unit 15. The downward-looking image collection unit 15 is arranged at the upper portion of the truck head and is configured to acquire bar code information on the ceiling in a tunnel or underground garage scenario. The bar code information is positioning information or warning information corresponding to the position of the bar code information. For example, the bar code information can be associated with the length of the tunnel, driving precautions and other information.

[0083] The vehicle-mounted communication unit is configured to communicate with the remote control device to upload the images collected by the image collection unit and / or the surround view image processed by the image processing unit, and to receive remote control instructions from the remote control device.

[0084] The vehicle-mounted communication unit is a remote communication unit and communicates in a wireless manner. Specifically, the vehicle-mounted communication unit communicates with the remote control device through a communication network. The communication network can be a 4G network, a 5G network or other communication networks.

[0085] The remote control device can take any appropriate form. In one embodiment, the remote control device is a cloud computing platform, for example, including a central cloud and an edge cloud to reduce communication latency. In Figure 1 In one embodiment, the remote control device includes a remote control platform and a remote control terminal. The remote control platform performs corresponding image processing and driving calculation and transmits corresponding information to the remote control terminal. The remote control personnel input operation instructions based on the information. In another embodiment, the remote control platform can automatically generate operation instructions to remotely control the vehicle. Only in some specific or extreme scenarios, the manual remote control mode is switched to introduce the remote control personnel to remotely control the vehicle.

[0086] As shown in the figure, the remote control device further includes a driver terminal. The driver or the owner can remotely control the vehicle through the driver terminal. In one embodiment, the driver or the owner connects to the remote control platform through the driver terminal and remotely controls the vehicle by means of the computing power of the remote control platform. In another embodiment, the driver or the owner directly connects to the vehicle through the driver terminal to perform surround view observation, vehicle start, engine stop and other operations.

[0087] Because network communication and image processing need certain time, there is a delay between the received remote control instruction and the corresponding image. The delay affects the safe driving of the vehicle. For this reason, the vehicle surround view system of the present application is provided with a timing calibration unit. The timing calibration unit is not shown. The timing calibration unit can take any appropriate form, for example, a relatively independent circuit and software, and can also be integrated in the electronic control unit.

[0088] The timing calibration unit determines the control delay duration T, wherein,

[0089] T = t2 - t1.

[0090] In the formula, t1 is the time when the image frame starts to be uploaded by the vehicle-mounted communication unit, or the time when the image frame is collected by the image collection unit. The time when the image frame is collected by the image collection unit refers to the time when a certain image frame is collected. This can be achieved by synchronously generating a time stamp (for example, a digital code representing the time ts1, wherein ts1 represents t1) when the image is collected. The time stamp is packaged together with the image frame and uploaded together with the image frame. The time when the image frame starts to be uploaded by the vehicle-mounted communication unit refers to the time when a certain image frame is uploaded by the vehicle-mounted communication unit.

[0091] t2 is the time when the control instruction corresponding to the image frame from the remote control device is sent to the vehicle execution unit by the driving unit.

[0092] When the remote control instruction is generated by the remote control device, a time stamp (for example, a digital code representing the time ts1, ts2; or only a digital code representing the time ts1) can be synchronously generated with the control instruction. The time stamp is packaged together with the control instruction and transmitted back to the vehicle together with the control instruction.

[0093] The vehicle-mounted communication unit or the electronic control unit of the vehicle records the sending time ts3 when the control instruction is sent to the driving unit, wherein ts3 is taken as t2.

[0094] t1 and t2 are both generated on the vehicle-mounted unit, and there is no need for time calibration between the vehicle-mounted unit and the system platform, so that the timing calculation deviation caused by the timing deviation between the vehicle-mounted unit and the system platform can be avoided.

[0095] The vehicle-mounted execution unit can also be referred to as the vehicle driving unit. The vehicle-mounted execution unit can include, for example, a power unit (engine or motor), a steering unit, etc., for controlling the longitudinal speed or acceleration and the lateral speed or acceleration. The vehicle-mounted execution unit can also include a turn signal, a horn, etc.

[0096] The determined control delay time T can be transmitted to the remote control device for collision safety judgment and the like.

[0097] In an embodiment of the present application, the control delay time T is determined in the following manner. Alternatively, the vehicle surround view system of the embodiment of the present application is remotely controlled in the following manner.

[0098] In an embodiment of the present application, the control delay time T is determined in the following manner. Alternatively, the vehicle surround view system of the embodiment of the present application is remotely controlled in the following manner.

[0099] Step S1. Let T = T0, wherein T0 is a preset time threshold. T0 can be determined in advance according to the vehicle model and the vehicle driving scene. In an optional embodiment, T0 is 100 milliseconds or 200 milliseconds.

[0099] Step S2. Collect the current image frame and the timestamp ts1 of the current image frame, and package and transmit the current image frame, the timestamp ts1 of the current image frame, and the control delay time T to the remote control device. The image frame is collected by the image sensor. The timestamp ts1 can be obtained by the image sensor when collecting the image, or added by the image processing unit.

[0100] Step S3. The remote control device generates a control instruction OCC based on the current image frame and the control delay time T, and packages and transmits the control instruction OCC and the timestamp ts1 of the current image frame to the vehicle-mounted communication unit.

[0101] Step S4. Transmit the control instruction OCC and the timestamp ts1 of the current image frame to the driving unit to drive the vehicle-mounted execution unit, and record the transmission time ts3. Update T = ts3-ts1, and go to step S2.

[0102] In an embodiment of the present application, when performing collision safety judgment, a length L is added to the vehicle in the driving direction of the vehicle, L = V*T, and the collision safety judgment is performed based on the virtual total length L0+L after the length is added,

[0103] Wherein, V is the current running speed (longitudinal driving speed) of the vehicle, T is the control delay time determined by the time sequence calibration unit, L0 is the length of the vehicle, L0 = L01+L02+L03,

[0104] Referring to Figure 7 L01 is the front suspension length of the vehicle; L02 is the wheelbase of the vehicle; and L03 is the rear suspension length of the vehicle.

[0105] In an optional embodiment of the present application, in the case of control by the remote control personnel, a length L is added to the vehicle in the driving direction of the vehicle on the image displayed on the overhead panoramic surround view image display screen of the remote control device (remote control terminal),

[0106] L = V*T,

[0107] Wherein, V is the current running speed of the vehicle, and T is the operation delay time determined by the time sequence calibration unit.

[0108] In an alternative embodiment of the present application, the vehicle speed is adjusted based on the operation delay time T. Specifically, the target vehicle speed Vp is adjusted based on the operation delay time T according to the following formula,

[0109] Vp = Vp if T≦T0

[0110] Vp = Vp*T / T0 if T0<T≦Tmax

[0111] Vp = 0 if T>Tmax

[0112] Wherein, T0 and Tmax are preset time thresholds, and Tmax≦10*T0.

[0113] The vehicle surround view system of the present application is suitable for operation at low speed. For example, in a driving scenario, the speed limit on a structured road is 25 km / h; the speed limit on an unstructured road is 15 km / h; the speed limit in a turning scenario is 10 km / h; the speed limit in a reversing scenario is 5 km / h; and the speed limit in a parking scenario is 5 km / h.

[0114] In an embodiment of the present application, the distance between the target and the vehicle is determined based on the image obtained by the camera unit, and the conversion of the top view surround view is performed based on the determined distance. Specifically, the distance between the target and the vehicle is determined in the following manner:

[0115] Step S1. Form a depth map sequence based on the image frame sequences obtained by the two cameras of the same camera unit at the same time,

[0116] Step S2. Determine the common target features in the previous image frame and the current image frame obtained by the first camera, and the newly added target features in the current image frame;

[0117] Step S3. Determine the relative distance between the common target features and the newly added target features in the current image frame and the vehicle based on the current image frame using the depth information of the previous depth map.

[0118] Because the depth information of the previous depth map is used in combination with the current image frame to calculate the distance or relative position between the target and the vehicle, time is saved.

[0119] The vehicle surround view system of the embodiment of the present application is suitable for low-speed driving scenarios. Specifically, in a low-speed driving scenario, the speed planning is performed in the following manner.

[0120] The road model is established according to the obstacle information obtained by the panoramic surround view splicing device and the map information, and the current lane is regionally divided, and the current lane region with a length of S1+S2 and a width of W in front of the vehicle is divided into a braking region and a deceleration region; the region with a length of S1 and a width of W in front of the vehicle is the braking region, and the region with a length of S2 and a width of W in front of the braking region is the deceleration region. The distance between the braking region and the deceleration region and the left side of the lane is W1, and the distance between the braking region and the deceleration region and the right side of the lane is W2.

[0121] Wherein, W=W0*K01+L0*K02, W0 is the maximum width of the vehicle; L0 is the length of the truck; K01, K02 are setting coefficients. For example, K01 is a constant greater than 1, which can be 1.1, or can be determined based on the vehicle speed. K02 is a constant in the range of 0.01-0.05, for example.

[0122] S1 is the braking distance of the vehicle from the current driving speed to the stop with the maximum deceleration.

[0123] S2=K1*S1; K1 is a setting coefficient; K1 can be a constant in the range of 0.5-1, for example.

[0124] Secondly, longitudinal speed planning is performed according to the position of the detected obstacle to determine the target longitudinal speed Vp,

[0125] If an obstacle located in the braking region is detected, Vp=0; at this time, the maximum deceleration can be applied.

[0126] If an obstacle located in the deceleration region is detected, Vp=V*(S-L1) / L2, S is the distance between the obstacle and the vehicle; V is the current longitudinal speed; at this time, the maximum deceleration or a smaller deceleration can be applied, which is selected according to the control strategy.

[0127] Finally, if -0.3<(W1-W2) / (W1+W2)<0.3, the target lateral speed Vc is determined,

[0128] Vc=V01*(W1-W2) / (W1+W2), where V01 is a lateral speed preset based on the vehicle performance. At this time, the corresponding turning angle or lateral acceleration can be selected according to the control strategy.

[0129] The vehicle surround view system of the embodiment of the application is suitable for a parking scene. Specifically, in the parking scene, remote control parking is performed in the following manner.

[0130] Referring to Figure 5 and Figure 7, A1, A2, A3, A4 are left rear point, right rear point, right front point and left front point of the vehicle respectively. M is the front axle center point, N is the rear axle center point. MP is perpendicular to the steering wheel angle. P is the intersection of the straight line MP and the extension line of the rear axle. The target parking space is between the forward parking space and the backward parking space. There are vehicles parked in the forward parking space and the backward parking space, or there are no vehicles parked. The length of the target parking space is a, and the width is b.

[0131] In the process of determining and checking the parking driving route, it is assumed that there are vehicles parked in the forward parking space and the backward parking space, and the parked vehicles do not intrude into the current parking space.

[0132] In the route checking process, the vehicle does not interfere with the forward parking space and the backward parking space as the benchmark.

[0133] First, the remote control vehicle drives forward through the target parking space; that is, Figure 5 from the left side to the right side of the target parking space.

[0134] In the process of driving, based on the image detected by the image sensor, the parameters of the target parking space are determined, including but not limited to a, b; the parameters of the driving lane and the obstacle, including but not limited to the driving lane width h, and the target parking position B, which is close to the rear end of the target parking space.

[0135] The circular arc cutting circular arc method is selected for the reverse parking mode, wherein the first circular arc DC and the second circular arc CB have the same central angle β; the turning radius of the first circular arc DC is R1 (the center is O1), and the turning radius of the second circular arc CB is R2 (the center is O2).

[0136] The end point B of the second circular arc, the start point D and the end point C of the first circular arc are set as position nodes, and the target speed Vp at the position nodes is zero. Thus, the influence of the control delay time T on the safety check can be eliminated. Moreover, it is convenient for steering operation. Therefore, the safety of vehicle driving is improved.

[0137] Specifically, the position of the start point D of the first circular arc, that is, the position of the parking starting point, is determined in the following manner:

[0138] First, the target parking position B (see Figure 5 ) is determined, and specifically, the position of the vehicle is determined based on the center position of the rear axle of the vehicle, and at the target parking position B, the distance between the rear end of the vehicle and the backward parking space is d, and the left side of the vehicle body is flush with the outer boundary line of the target parking space.

[0139] Secondly, the coordinate system is established in the following manner: taking the position of the center of the rear axle of the vehicle at the target parking position B as the coordinate origin, establishing the coordinate system, wherein the forward direction of the vehicle is the X direction, the left direction of the vehicle is the Y direction, and the position of the start point D of the first circular arc is represented as XD , Y D ;

[0140] X D = (R1+R2) sin β

[0141] Y D = (R1+R2) (1-cos β)

[0142] wherein let R1=R2;

[0143] Referring to Figure 7 , a turn is made with the maximum turning angle,

[0144] so that R1=R2=R min =L02*cot θ

[0145] wherein L02 is the wheelbase of the vehicle; θ is the maximum turning angle of the vehicle.

[0146] Let X D be greater than the length a of the target parking space,

[0147] so that β>arcsin(a / 2(L02*cot θ))

[0148] Let Y D be greater than the width a of the target parking space, strictly speaking, should be greater than the width W0 of the vehicle, and W0 is generally equivalent to the width of the target parking space;

[0149] so that β<arccos(1-b / 2(L02*cot θ))

[0150] Therefore, β is based on the following range of values:

[0151] arcsin(a / 2(L02*cot θ))<β<arccos(1-b / 2(L02*cot θ))

[0152] wherein a is the length of the target parking space, i.e. the size of the target parking space in the X direction,

[0153] b is the width of the target parking space, i.e. the size of the target parking space in the Y direction.

[0154] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit it. Those skilled in the art should understand that the technical solutions described in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle surround view system, characterized by, Comprise: Image acquisition unit, image processing unit, driving unit, timing calibration unit and vehicle communication unit, The image acquisition unit comprises front camera unit, rear camera unit arranged at the front and rear of the vehicle, and left camera unit and right camera unit arranged at the left and right sides of the vehicle; wherein the front camera unit, rear camera unit, left camera unit and right camera unit each comprise two cameras of the same specification with the same height and spaced apart in the transverse direction, which can be used to form a depth map to determine the relative distance and direction of the target relative to the vehicle; wherein the distance between the target and the vehicle; Step S1. Based on the image frame sequence acquired by the two cameras of the same camera unit respectively at the same time, a depth map sequence is formed, Step S2. Determine the common target features in the previous image frame and the current image frame acquired by the first camera, and the new target features in the current image frame; Step S3. Based on the current image frame, the relative distance between the common target features and new target features in the current image frame and the vehicle is determined using the depth information of the previous depth map; The image processing unit is used to process and splice the images collected by the image acquisition unit to form a surround view image; when splicing images, only one image signal is selected for splicing for the front camera unit, rear camera unit, left camera unit and right camera unit; The vehicle communication unit is used to communicate with the remote control device to upload the images collected by the image acquisition unit and / or the surround view images processed by the image processing unit; and to receive control instructions from the remote control device; The driving unit is used to drive the vehicle execution unit to realize remote control of the vehicle; The timing calibration unit is used to determine the control delay time T, wherein T=t2-t1; In the formula, t1 is the time when the image frame starts to be uploaded through the vehicle communication unit, or the time when the image frame is collected by the image acquisition unit; t2 is the time when the vehicle execution unit issues a control instruction corresponding to the image frame from the remote control device through the driving unit.

2. The vehicle surround view system of claim 1, wherein, The vehicle surround view system is remotely controlled in the following method: Step S1. Let T=T0, where T0 is a preset time threshold; Step S2. Collect the current image frame and the timestamp ts1 of the current image frame, and transmit the current image frame, the timestamp ts1 of the current image frame, and the control delay time T to the remote control device; Step S3. The remote control device generates a control instruction OCC based on the current image frame and the control delay time T, and transmits the control instruction OCC and the timestamp ts1 of the current image frame to the vehicle communication unit; Step S4. Transmit the control instruction OCC and the timestamp ts1 of the current image frame to the driving unit to drive the vehicle execution unit, and record the transmission time ts3; Update T=ts3-ts1, and go to step S2.

3. The vehicle surround view system of claim 1, wherein, When judging the collision safety, the length L of the vehicle is increased in the driving direction of the vehicle, L=V*T, and the collision safety is judged based on the virtual total length L0+L after the length is increased, Wherein, V is the current running speed of the vehicle, T is the operation delay time determined by the timing calibration unit, L0 is the length of the vehicle, L0=L01+L02+L03, L01 is the front suspension length of the vehicle; L02 is the wheelbase of the vehicle; L03 is the rear suspension length of the vehicle.

4. The vehicle surround view system of claim 1, wherein, On the overhead panoramic surround view image display screen of the remote control device, for the image displayed by the vehicle, in the driving direction of the vehicle, the length L is added to the vehicle, L=V*T, Wherein, V is the current running speed of the vehicle, T is the operation delay time determined by the timing calibration unit.

5. The vehicle surround view system of claim 3, wherein, Based on the operation delay time T, the target vehicle speed Vp is adjusted, Vp=Vp if T≦T0 Vp=Vp*T / T0 if T0<T≦Tmax Vp=0 if T>Tmax Wherein, T0, Tmax are preset time thresholds, Tmax≦10*T0.

6. The vehicle surround view system of claim 1, wherein, In the driving scene, the speed limit on the structured road is 25km / h; the speed limit on the unstructured road is 15km / h; the speed limit in the turning scene is 10km / h, the speed limit in the reversing scene is 5km / h, and the speed limit in the parking scene is 5km / h.

7. The vehicle surround view system of any one of claims 1-6, wherein, In the parking scene, the remote control parking is carried out in the following manner: The remote control vehicle drives forward to pass the target parking space; Based on the image detected by the image sensor, the parameters of the target parking space, the parameters of the driving lane and the obstacles, and the target parking position B close to the rear end of the target parking space are determined; The circular arc cutting circular arc method is used to carry out the reversing parking mode, wherein the first circular arc DC and the second circular arc CB have the same central angle β; the turning radius of the first circular arc DC is R1, and the turning radius of the second circular arc CB is R2; The end point B of the second circular arc, the start point D and the end point C of the first circular arc are set as position nodes, and the target vehicle speed Vp at the position nodes is zero.

8. The vehicle surround view system of claim 7, wherein, The position of the start point D of the first circular arc, i.e. the position of the parking starting point, is determined in the following manner: Firstly, the target parking position B is determined, specifically, the vehicle position is determined by the center position of the rear axle of the vehicle, and at the target parking position B, the distance between the rear end of the vehicle and the rearward parking space is d, and the left side of the vehicle body is flush with the outer boundary line of the target parking space; Secondly, the coordinate system is established in the following manner: taking the position of the center of the rear axle of the vehicle at the target parking position B as the coordinate origin, the coordinate system is established, wherein the front direction of the vehicle is the X direction, and the left direction of the vehicle is the Y direction, and the position of the start point D of the first circular arc is represented as XD, YD; XD=(R1+R2)sinβ YD=(R1+R2)(1-cosβ) Wherein, R1=R2=L02*cotθ L02 is the wheelbase of the vehicle; θ is the maximum steering angle of the vehicle; β is valued based on the following value range: arcsin(a / 2(L02*cotθ))<β<arccos(1-b / 2(L02*cotθ)) a is the length of the target parking space, i.e. the size of the target parking space in the X direction, b is the width of the target parking space, i.e. the size of the target parking space in the Y direction.

9. A vehicle characterized by comprising: The vehicle surround view system as claimed in any one of claims 1-8, the vehicle being an electric truck operating in a mine.

Images