Position determination method, device, vehicle and storage medium

Abstract

The present invention relates to a position determination method, comprising: obtaining an object point cloud of a target object and first position information corresponding to the target object; wherein the first position information represents position information corresponding to the position of a center point of the target object; clustering points in the object point cloud to obtain at least one target point cloud set; matching a point cloud density value of the target point cloud set with a preset density value; determining a first position correction value based on second position information of the cluster center of the target point cloud set, the point cloud density value, and the first position information; and correcting the first position information based on the first position correction value to obtain first corrected position information of the target object. Through this method, the first position information can be corrected based on the second position information of the cluster center of the target point cloud set, the point cloud density value, and the first position information, thereby helping to improve the accuracy of position measurement of target objects in an environment.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a position determination method, device, vehicle and storage medium. Background Art

[0002] With the development of the automotive industry, intelligent driving has become a hot research topic in the vehicle sector. Autonomous driving based on autonomous driving systems has become a key industry focus within intelligent driving. Autonomous driving systems, also known as unmanned driving systems, utilize onboard computer systems to achieve unmanned driving. Essentially, they simulate human driver behavior from a machine's perspective.

[0003] In related technologies, point cloud information of the vehicle's surrounding environment can be obtained through some sensors such as lidar. The vehicle can first obtain point cloud information of each object in the vehicle's surrounding environment, and then directly determine the position of these objects based on the position information contained in the point cloud information. After that, path planning and vehicle control can be performed for the autonomous driving vehicle based on the position information of these objects and the current position information of the vehicle.

[0004] However, the surrounding environment information obtained by the sensor in the above manner may sometimes jump, which may easily cause the position information of the target object determined based on the environmental information to fluctuate. Therefore, the accuracy of the position measurement of the target object in the environment by the relevant technology is poor. Summary of the Invention

[0005] One of the purposes of the present invention is to provide a position determination method to solve the problem of poor accuracy in position measurement of target objects in an environment in related technologies; a second purpose is to provide a position determination device; a third purpose is to provide a vehicle; and a fourth purpose is to provide a readable storage medium.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] A method for determining a position, the method comprising:

[0008] Acquire an object point cloud of a target object and first position information corresponding to the target object; wherein the first position information represents position information corresponding to a center point position of the target object;

[0009] Clustering the points in the object point cloud to obtain at least one target point cloud set; the point cloud density value of the target point cloud set matches a preset density value;

[0010] determining a first position correction value based on the second position information of the cluster center of the target point cloud set, the point cloud density value, and the first position information;

[0011] The first position information is corrected based on the first position correction value to obtain first corrected position information of the target object.

[0012] Optionally, obtaining an object point cloud of the target object includes:

[0013] Acquire environmental images and point cloud images of the vehicle's surroundings;

[0014] determining the target object from the environment image;

[0015] determining first position information of the target object based on the environment image;

[0016] Based on the first position information, an object point cloud corresponding to the target object is determined from the point cloud image.

[0017] Optionally, determining the object point cloud corresponding to the target object based on the first position information and the point cloud image includes:

[0018] Determining a measurement data interval corresponding to each sensor based on measurement characteristics of each sensor corresponding to the point cloud image; the measurement characteristics include at least one of a measurement object, a measurement data type, a measurement data range, a measurement method, and a measurement delay;

[0019] deleting points corresponding to measurement data outside the measurement data interval from the point cloud image to obtain a second point cloud image;

[0020] An object point cloud corresponding to the target object is determined from the second point cloud image based on the first position information.

[0021] Optionally, determining the target object from the environment image includes:

[0022] fusing the environmental images obtained by the sensors based on the measurement characteristics of the sensors to obtain a fused environmental image;

[0023] The target object is determined from the fused environment image.

[0024] Optionally, determining the first position correction value based on the second position information of the cluster center of the target point cloud set, the point cloud density value, and the first position information includes:

[0025] Obtaining a point cloud density value of the target point cloud set;

[0026] Determine the target point cloud set corresponding to the maximum point cloud density value as the optimal point cloud set;

[0027] The first position correction value is determined based on the second position information corresponding to the optimal point cloud cluster, the point cloud density value of the optimal point cloud cluster, and the first position information.

[0028] Optionally, determining the first position correction value based on the second position information corresponding to the optimal point cloud cluster, the maximum point cloud density value, and the first position information includes:

[0029] determining distance information between a position indicated by the second position information corresponding to the optimal point cluster and a position indicated by the first position information;

[0030] determining a position offset coefficient of a cluster center of the optimal point cloud based on a point cloud density value of the optimal point cloud and a point cloud density value of a position indicated by the first position information;

[0031] Based on the distance information and the position offset coefficient, the first position correction value is determined; the first position correction value includes a position correction direction and a position correction amplitude, the position correction direction represents the direction from the position indicated by the first position information to the position indicated by the second position information corresponding to the optimal point cluster, and the position correction amplitude represents the offset distance in the position correction direction.

[0032] Optionally, the correcting the first position information based on the first position correction value to obtain first corrected position information of the target object includes:

[0033] Obtaining a driving speed value of the vehicle, and obtaining a measurement delay of each sensor from the measurement characteristics of each sensor;

[0034] determining a travel distance of the vehicle within the measurement delay based on the speed value and the measurement delay, and obtaining the second position correction value;

[0035] The first position information is corrected based on the first position correction value and the second position correction value to obtain the first corrected position information.

[0036] A position determination device, comprising:

[0037] A first acquisition module is configured to acquire first position information of a target object and an object point cloud corresponding to the target object; wherein the first position information represents position information corresponding to a center point position of the target object;

[0038] A clustering module, configured to cluster the points in the object point cloud to obtain at least one target point cloud set; the point cloud density value of the target point cloud set matches a preset density value;

[0039] a determination module, configured to determine a first position correction value based on second position information of a cluster center of the target point cloud set, the point cloud density value, and the first position information;

[0040] The correction module is configured to correct the first position information based on the first position correction value to obtain first corrected position information of the target object.

[0041] Optionally, the first acquisition module includes:

[0042] The first acquisition submodule is used to acquire an environmental image and a point cloud image of the vehicle's surrounding environment;

[0043] A first determining submodule, configured to determine the target object from the environment image;

[0044] a second determining submodule, configured to determine first position information of the target object based on the environment image;

[0045] A third determining submodule is configured to determine, based on the first position information, an object point cloud corresponding to the target object from the point cloud image.

[0046] Optionally, the third determining submodule includes:

[0047] a first determining unit, configured to determine a measurement data interval corresponding to each sensor based on measurement characteristics of each sensor corresponding to the point cloud image; the measurement characteristics including at least one of a measurement object, a measurement data type, a measurement data range, a measurement method, and a measurement delay;

[0048] a deleting unit, configured to delete points corresponding to measurement data outside the measurement data interval from the point cloud image to obtain a second point cloud image;

[0049] A second determining unit is configured to determine an object point cloud corresponding to the target object from the second point cloud image based on the first position information.

[0050] Optionally, the first determining submodule includes:

[0051] a fusion unit, configured to fuse the environment images obtained by the respective sensors based on measurement characteristics of the respective sensors to obtain a fused environment image;

[0052] The third determining unit is configured to determine the target object from the fused environment image.

[0053] Optionally, the determining module includes:

[0054] A second acquisition submodule is used to obtain the point cloud density value of the target point cloud set;

[0055] A fourth determination submodule is used to determine the target point cloud set corresponding to the maximum point cloud density value as the optimal point cloud set;

[0056] A fifth determining submodule is configured to determine the first position correction value based on the second position information corresponding to the optimal point cloud cluster, the point cloud density value of the optimal point cloud cluster, and the first position information.

[0057] Optionally, the fifth determining submodule includes:

[0058] a fourth determining unit, configured to determine distance information between a position indicated by the second position information corresponding to the optimal point cluster and a position indicated by the first position information;

[0059] a fifth determining unit, configured to determine a position offset coefficient of a cluster center of the optimal point cloud based on a point cloud density value of the optimal point cloud and a point cloud density value of a position indicated by the first position information;

[0060] A sixth determination unit is used to determine the first position correction value based on the distance information and the position offset coefficient; the first position correction value includes a position correction direction and a position correction size, the position correction direction represents the direction from the position indicated by the first position information to the position indicated by the second position information corresponding to the optimal point cloud, and the position correction size represents the offset distance in the position correction direction.

[0061] Optionally, the correction module includes:

[0062] a third acquisition submodule, configured to acquire a driving speed value of the vehicle and acquire a measurement delay of each sensor from the measurement characteristics of each sensor;

[0063] a sixth determining submodule, configured to determine a travel distance of the vehicle within the measurement delay based on the speed value and the measurement delay, and obtain the second position correction value;

[0064] The correction submodule is configured to correct the first position information based on the first position correction value and the second position correction value to obtain the first corrected position information.

[0065] A vehicle comprises the position determination device as described above, and is used to execute any of the position determination methods as described above.

[0066] A storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute any of the above-mentioned position determination methods.

[0067] Beneficial effects of the present invention:

[0068] The present invention obtains an object point cloud of a target object and first position information corresponding to the target object, wherein the first position information represents the position information corresponding to the center point position of the target object, clusters the points in the object point cloud to obtain at least one target point cloud set, the point cloud density value of the target point cloud set matches the preset density value, determines a first position correction value based on the second position information of the cluster center of the target point cloud set, the point cloud density value and the first position information, corrects the first position information based on the first position correction value to obtain the first corrected position information of the target object, and can, after determining the first position information of the target object, correct the first position information based on the second position information of the cluster center of the target point cloud set corresponding to the target object, the point cloud density value and the first position information to determine corrected position information with higher accuracy, thereby helping to improve the accuracy of position measurement of target objects in an environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A schematic diagram of a flow chart of a location determination method provided by an embodiment of the present invention;

[0070] Figure 2 A schematic diagram of a flow chart of another location determination method provided by an embodiment of the present invention;

[0071] Figure 3 A logic block diagram of a position determination device provided by an embodiment of the present invention;

[0072] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0074] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0075] like Figure 1 As shown, Figure 1A schematic flow chart of a location determination method provided in an embodiment of the present invention may include:

[0076] Step 101: Acquire an object point cloud of a target object and first position information corresponding to the target object; wherein the first position information represents position information corresponding to a center point position of the target object.

[0077] In an embodiment of the present invention, the vehicle can obtain environmental images and point cloud images around the vehicle during the automatic driving process, and then determine the target object in the environmental image, and then obtain the first position information of the target object, and then determine the object point cloud corresponding to the target object from the point cloud image based on the first position information of the target object.

[0078] In an embodiment of the present invention, after a vehicle acquires an image of the surrounding environment, it can perform target recognition on the environment image. Recognizable targets may include lanes, lane lines, vehicle targets, pedestrian targets, road traffic signs, traffic flows, traffic lights, and intersection signs. Target recognition can be performed using some trained target recognition models. After target recognition is completed, the identified targets can be marked with rectangular frames. For targets of the same type, rectangular frames of the same color can be used for marking, and for targets of different types, rectangular frames of different colors can be used for marking. Afterwards, the target object can be determined from the marked targets. In this way, the target object can be determined from the environment image.

[0079] Step 102: clustering the points in the object point cloud to obtain at least one target point cloud set; the point cloud density value of the target point cloud set matches a preset density value.

[0080] In an embodiment of the present invention, after acquiring an object point cloud of a target object, a point cloud set of the target object can be obtained through clustering. Since the point clouds of the target object may differ in their representation of local features, clustering can be used to obtain one or more point cloud sets of the target object. Clustering can be performed based on the point cloud density of the point cloud set, where regions with a point cloud density less than a preset value can be excluded from the point cloud set, while regions with a point cloud density greater than or equal to the preset value can be included in the point cloud set.

[0081] Step 103 : Determine a first position correction value based on the second position information of the cluster center of the target point cloud set, the point cloud density value, and the first position information.

[0082] In an embodiment of the present invention, after obtaining at least one target point cloud set, a first position correction value of the target object can be determined based on the second position information of each cluster center of each target point cloud set, the point cloud density value of the target point cloud set, and the first position information. Specifically, a position offset coefficient can be obtained based on the point cloud density value of the target point cloud set and the point cloud density value of the position indicated by the first position information. The direction of the position correction can be determined based on the second position information and the first position information. The magnitude of the position correction can be determined based on the second position information, the first position information, and the position offset coefficient. Thus, the first position correction value can be determined based on the magnitude and direction of the position correction.

[0083] Step 104 : Correct the first position information based on the first position correction value to obtain first corrected position information of the target object.

[0084] In an embodiment of the present invention, after obtaining the first position correction value, the position indicated by the first position information can be corrected, thereby obtaining the first corrected position information of the target object. Specifically, after obtaining the first position correction value, the magnitude and direction of the correction can be determined, and then the position indicated by the first position information can be offset along the correction direction, with the magnitude of the offset being the same as the magnitude of the correction. In this way, a corrected position can be obtained, thereby obtaining the first corrected position information of the target object.

[0085] The present invention obtains an object point cloud of a target object and first position information corresponding to the target object, wherein the first position information represents the position information corresponding to the center point position of the target object, clusters the points in the object point cloud to obtain at least one target point cloud set, the point cloud density value of the target point cloud set matches the preset density value, determines a first position correction value based on the second position information of the cluster center of the target point cloud set, the point cloud density value and the first position information, corrects the first position information based on the first position correction value to obtain the first corrected position information of the target object, and can, after determining the first position information of the target object, correct the first position information based on the second position information of the cluster center of the target point cloud set corresponding to the target object, the point cloud density value and the first position information to determine corrected position information with higher accuracy, thereby helping to improve the accuracy of position measurement of target objects in an environment.

[0086] like Figure 2 As shown, Figure 2 A flowchart of another location determination method provided by an embodiment of the present invention may include:

[0087] Step 201: Acquire an environmental image and a point cloud image of the vehicle's surroundings.

[0088] In embodiments of the present invention, the environmental image may be an environmental image within a certain range around the vehicle, which may be obtained by a camera mounted on the vehicle. The point cloud image may be a point cloud image within the same range as the environmental image, which may be obtained by a device such as a laser radar or radar sensor mounted on the vehicle. The vehicle may be equipped with an autonomous driving function, which may acquire the environmental image and point cloud image of the vehicle's surroundings in real time during the autonomous driving process using sensors such as the vehicle's cameras and laser radar.

[0089] Step 202: Determine the target object from the environment image.

[0090] In an embodiment of the present invention, the environmental image may include all information about the environment surrounding the vehicle, and therefore, also includes various objects existing in the environment surrounding the vehicle. In an embodiment of the present invention, after the vehicle acquires the environmental image of the surroundings, it may perform target recognition on the environmental image. Among them, identifiable targets may include lanes, lane lines, vehicle targets, pedestrian targets, road traffic signs, traffic flows, traffic lights, and intersection signs, etc. Target recognition may be performed using some trained target recognition models. After completing target recognition, the identified targets may be marked with rectangular frames. For targets of the same type, rectangular frames of the same color may be used for marking, and for targets of different types, rectangular frames of different colors may be used for marking. Afterwards, the target object may be determined from the marked targets. In this way, the target object may be determined from the environmental image.

[0091] Specifically, step 202 may include the following sub-steps:

[0092] Sub-step 2021 : Based on the measurement characteristics of the various sensors, the environmental images obtained by the various sensors are fused to obtain a fused environmental image.

[0093] In embodiments of the present invention, a vehicle may be equipped with multiple or more environmental information capture devices. Therefore, after various environmental information capture devices acquire images of the vehicle's surroundings, these images may be fused to produce a fused image. During the fusion process, image fusion may be performed based on the same objects in the environmental images.

[0094] Sub-step 2022: determining the target object from the fused environment image.

[0095] In an embodiment of the present invention, after acquiring a fused environment image, a target object can be identified from the fused environment image by a target recognition method. Since the fused image includes information obtained by each sensor, the target in the fused image will be clearer and easier to identify.

[0096] In an embodiment of the present invention, by fusing the environmental images obtained by each sensor based on the measurement characteristics of each sensor to obtain a fused environmental image, and determining the target object from the fused environmental image, the problem of target position fluctuations obtained based on a single sensor can be avoided, so that the determined position of the target object has higher reliability.

[0097] Step 203: Determine first position information of the target object based on the environment image.

[0098] In an embodiment of the present invention, after identifying a target object, relative position information of the target object in the environment image can be determined, thereby obtaining first position information of the target object. The first position information can be relative position information between the target object and the vehicle. When determining the first position information of the target object, the target object's reference point can be the target object's center point, where the center point can be the center of the diagonal line of the rectangular frame marking the target object during the target recognition process.

[0099] Step 204 : Determine an object point cloud corresponding to the target object from the point cloud image based on the first position information.

[0100] In an embodiment of the present invention, after obtaining the first position information of the target object, a local point cloud image of the corresponding position can be found in the point cloud image according to the first position information, so that the object point cloud corresponding to the target object can be determined from the point cloud image.

[0101] Specifically, step 204 may include the following sub-steps:

[0102] Sub-step 2041: determining a measurement data interval corresponding to each sensor based on measurement characteristics of each sensor corresponding to the point cloud image; the measurement characteristics include at least one of a measurement object, a measurement data type, a measurement data range, a measurement method, and a measurement delay.

[0103] In embodiments of the present invention, a measurement data interval represents a sensor's reasonable measurement range. For example, if a camera captures a car, the resulting image of the vehicle may be an image of the vehicle viewed from a corresponding angle. If the resulting image does not conform to the view angle, the image captured by the sensor may be considered to be outside the reasonable measurement range. Based on this sensor's measurement characteristics, the measurement data interval corresponding to each sensor can be determined.

[0104] Sub-step 2042: deleting points corresponding to measurement data outside the measurement data interval from the point cloud image to obtain a second point cloud image.

[0105] In embodiments of the present invention, errors inevitably occur when sensors perform electronic measurements. These errors can cause the sensor's measurement data to fall outside the measurement data range. Therefore, the sensor's measurement data can be preprocessed to remove any data outside the measurement data range caused by sensor errors. After removing this unexpected data, a second point cloud image can be obtained. In this case, all points in the second point cloud image are within the sensor's measurement data range, resulting in a higher level of reliability.

[0106] In an embodiment of the present invention, there may also be another method for preprocessing measurement data. Depending on the measurement characteristics of the sensor, there may sometimes be omissions in the information captured about the target object. In this case, the measurement data that the sensor failed to capture correctly can be corrected. The process of data correction can be to first detect the local point cloud density of the point cloud. If the local point cloud density of a certain position is significantly lower than the point cloud density of other surrounding positions, the point cloud at that position is corrected. The position of the corrected point can be random, and the final result of the correction is to make the point cloud density value at that position equal to the point cloud density value of the surrounding positions. The determination of the local position can start from any position in the point cloud, and then calibrate a position change value, an initial angle value, and a change angle value. In this way, other positions related to the initial position can be determined. Then, starting from other points according to this method, new local positions can be determined. And so on, the entire object point cloud can be covered. After data preprocessing, the measurement data will be more consistent with the corresponding measured features of the target object.

[0107] Sub-step 2043: determining the object point cloud corresponding to the target object from the second point cloud image based on the first position information.

[0108] In an embodiment of the present invention, the second point cloud image includes point clouds of multiple objects, so based on the first position information, the position of the target object can be determined, and the second point cloud image also includes the position information of the target object, so the corresponding position in the second point cloud image can be determined, and thus the object point cloud corresponding to the target object can be determined.

[0109] In an embodiment of the present invention, the measurement data interval corresponding to each sensor is determined based on the measurement characteristics of each sensor corresponding to the point cloud image, where the measurement characteristics include at least one of the measurement object, measurement data type, measurement data range, measurement method, and measurement delay. Points corresponding to the measurement data outside the measurement data interval are deleted from the point cloud image to obtain a second point cloud image. Based on the first position information, the object point cloud corresponding to the target object is determined from the second point cloud image. The object point cloud of the target object that best conforms to the actual situation can be obtained, thereby making the determined target position more accurate.

[0110] In an embodiment of the present invention, by acquiring an environmental image and a point cloud image of the vehicle's surroundings, determining a target object from the environmental image, determining the first position information of the target object based on the environmental image, and determining the object point cloud corresponding to the target object from the point cloud image based on the first position information, the first position information of the target object and the object point cloud corresponding to the target object can be made highly reliable, thereby improving the accuracy of subsequent position corrections.

[0111] Step 205 : clustering the points in the object point cloud to obtain at least one target point cloud set; the point cloud density value of the target point cloud set matches a preset density value.

[0112] In an embodiment of the present invention, after acquiring an object point cloud of a target object, a clustering algorithm can be applied to the object point cloud to obtain at least one target point cloud set. A preset density value can be calibrated, and when the density of the clustered point cloud is less than the preset density value, the clustering algorithm can be stopped at that location. Thus, when clustering stops at all locations in a region, the region is clustered into a target point cloud set.

[0113] Step 206: Obtain the point cloud density value of the target point cloud set.

[0114] In an embodiment of the present invention, after obtaining a target point cloud set, a point cloud density value of the target point cloud set can be obtained. This point cloud density value can be the average point cloud density value of the point cloud set. Specifically, an algorithm can first obtain all points in the target point cloud set and the spatial volume occupied by the target point cloud set, then calculate the number of points contained in a unit space, and use the number of points contained in the unit space as the point cloud density value of the target point cloud set.

[0115] Step 207 : Determine the target point cloud set corresponding to the maximum point cloud density value as the optimal point cloud set.

[0116] In an embodiment of the present invention, after obtaining the point cloud density values ​​of each target point cloud set, the maximum point cloud density value can be determined, and then the target point cloud set corresponding to the maximum point cloud density value can be determined as the optimal point cloud set. In other words, the point cloud density value of the optimal point cloud set is the maximum value among the point cloud density values ​​of each target point cloud set.

[0117] Step 208 : Determine the first position correction value based on the second position information corresponding to the optimal point cloud cluster, the point cloud density value of the optimal point cloud cluster, and the first position information.

[0118] In this embodiment of the present invention, since the optimal point cloud is one of the target point clouds, the location information of the cluster center of the optimal point cloud can be included in the second location information. Thus, the second location information corresponding to the optimal point cloud can be obtained. The first location correction value can then be determined based on the second location information corresponding to the optimal point cloud, the point cloud density value of the optimal point cloud, and the first location information.

[0119] Specifically, step 208 may include the following sub-steps:

[0120] Sub-step 2081: Determine the distance information between the position indicated by the second position information corresponding to the optimal point cluster and the position indicated by the first position information.

[0121] In an embodiment of the present invention, the distance between the cluster center of the optimal point cluster and the location indicated by the first location information can first be determined. Specifically, based on the location information of the cluster center of the optimal point cluster and the first location information, the distance between the cluster center of the optimal point cluster and the location indicated by the first location information can be obtained. Furthermore, the direction from the location indicated by the first location information to the cluster center of the optimal point cluster can be obtained.

[0122] Sub-step 2082: determining a position offset coefficient of the cluster center of the optimal point cloud based on the point cloud density value of the optimal point cloud and the point cloud density value of the position indicated by the first position information.

[0123] In an embodiment of the present invention, the point cloud density value of the optimal point cluster and the local point cloud density value around the position indicated by the first position information can first be obtained. Then, the local point cloud density value around the position indicated by the first position information can be used as a reference to calculate the difference between the point cloud density value of the optimal point cluster and the local point cloud density value around the position indicated by the first position information. Thus, the ratio of this difference to the local point cloud density value can be determined as the position offset coefficient of the cluster center of the optimal point cluster. In an embodiment of the present invention, there can also be other methods for determining the position offset coefficient. For example, the ratio can be subjected to a normal transformation and the transformed value can be used as the position offset coefficient, etc., which is not limited in the embodiment of the present invention.

[0124] Sub-step 2083, determining the first position correction value based on the distance information and the position offset coefficient; the first position correction value includes a position correction direction and a position correction amplitude, the position correction direction represents the direction from the position indicated by the first position information to the position indicated by the second position information corresponding to the optimal point cluster, and the position correction amplitude represents the offset distance in the position correction direction.

[0125] In an embodiment of the present invention, the distance information includes a distance value and a direction of the distance. The direction of the distance may be a direction from the location indicated by the first location information toward the center of the cluster where the optimal point is located. This direction may be determined as the direction of the position correction. Based on the position offset coefficient and the distance value, the magnitude of the position correction, i.e., the offset distance in the position correction direction, may be determined.

[0126] In an embodiment of the present invention, by determining the distance information between the position indicated by the second position information corresponding to the optimal point cloud cluster and the position indicated by the first position information, the position offset coefficient of the cluster center of the optimal point cloud cluster is determined based on the point cloud density value of the optimal point cloud cluster and the point cloud density value of the position indicated by the first position information, and based on the distance information and the position offset coefficient, the first position correction value is determined. The first position correction value includes a position correction direction and a position correction amplitude. The position correction direction represents the direction from the position indicated by the first position information to the position indicated by the second position information corresponding to the optimal point cloud cluster, and the position correction amplitude represents the offset distance in the position correction direction. The position information of the target object can be corrected from two dimensions, so that the corrected position information of the target object is more accurate and has higher reliability.

[0127] In an embodiment of the present invention, by obtaining the point cloud density value of the target point cloud set, the target point cloud set corresponding to the maximum point cloud density value is determined to be the optimal point cloud set, and the first position correction value is determined based on the second position information corresponding to the optimal point cloud set, the point cloud density value of the optimal point cloud set and the first position information. The first position correction value can be determined after determining the optimal second position information, so that the first position correction value has higher reliability.

[0128] Step 209 : Acquire the driving speed value of the vehicle, and acquire the measurement delay of each sensor from the measurement characteristics of each sensor.

[0129] In an embodiment of the present invention, since there is a certain time delay from the sensor sensing environmental information to outputting environmental information data, the position of the vehicle has already shifted when the object point cloud of the target object is obtained. Therefore, in order to correct this part of the position offset, the vehicle's driving speed value and the measurement delay of each sensor can be obtained.

[0130] Step 210: Determine the travel distance of the vehicle within the measurement delay based on the speed value and the measurement delay, and obtain the second position correction value.

[0131] In an embodiment of the present invention, after obtaining the vehicle's speed and the measurement delays of each sensor, the speed value can be multiplied by the measurement delays of each sensor. Sensors that capture point cloud images, such as lidar, provide a high reference value for position offsets, so the measurement delays of the sensors corresponding to the point cloud images can be selected for calculation. The result of this multiplication is the vehicle's travel distance within the measurement delays, which can be used as the second position correction value.

[0132] Step 211: Correct the first position information based on the first position correction value and the second position correction value to obtain the first corrected position information.

[0133] In an embodiment of the present invention, after obtaining the first position correction value and the second position correction value, the first position information can be directly corrected to obtain the first corrected position information. The correction can be performed according to the correction methods corresponding to the two position correction values. For example, if the first position correction value can determine the offset direction and offset distance, the corresponding numerical information in the first position information should be increased or decreased accordingly. If the second position correction value can determine the offset distance of the vehicle, the corresponding numerical information can be directly increased or decreased in the first position information.

[0134] In an embodiment of the present invention, by obtaining the vehicle's driving speed value, obtaining the measurement delay of each sensor from the measurement characteristics of each sensor, determining the vehicle's driving distance within the measurement delay based on the speed value and the measurement delay, and obtaining a second position correction value, the first position information is corrected based on the first position correction value and the second position correction value to obtain first corrected position information. The first position information can be corrected from two dimensions, thereby further improving the accuracy of the position determined based on the sensor.

[0135] like Figure 3 As shown, Figure 3 This is a logical block diagram of a position determination device provided in an embodiment of the present invention. The device 300 may include:

[0136] A first acquisition module 301 is configured to acquire first position information of a target object and an object point cloud corresponding to the target object; wherein the first position information represents position information corresponding to a center point of the target object;

[0137] A clustering module 302 is configured to cluster the points in the object point cloud to obtain at least one target point cloud set; the point cloud density value of the target point cloud set matches a preset density value;

[0138] A determination module 303 is configured to determine a first position correction value based on the second position information of the cluster center of the target point cloud set, the point cloud density value, and the first position information;

[0139] The correction module 304 is configured to correct the first position information based on the first position correction value to obtain first corrected position information of the target object.

[0140] Optionally, the first acquisition module 301 includes:

[0141] The first acquisition submodule is used to acquire an environmental image and a point cloud image of the vehicle's surrounding environment;

[0142] A first determining submodule, configured to determine the target object from the environment image;

[0143] a second determining submodule, configured to determine first position information of the target object based on the environment image;

[0144] A third determining submodule is configured to determine, based on the first position information, an object point cloud corresponding to the target object from the point cloud image.

[0145] Optionally, the third determining submodule includes:

[0146] a first determining unit, configured to determine a measurement data interval corresponding to each sensor based on measurement characteristics of each sensor corresponding to the point cloud image; the measurement characteristics including at least one of a measurement object, a measurement data type, a measurement data range, a measurement method, and a measurement delay;

[0147] a deleting unit, configured to delete points corresponding to measurement data outside the measurement data interval from the point cloud image to obtain a second point cloud image;

[0148] A second determining unit is configured to determine an object point cloud corresponding to the target object from the second point cloud image based on the first position information.

[0149] Optionally, the first determining submodule includes:

[0150] a fusion unit, configured to fuse the environment images obtained by the respective sensors based on measurement characteristics of the respective sensors to obtain a fused environment image;

[0151] The third determining unit is configured to determine the target object from the fused environment image.

[0152] Optionally, the determining module 303 includes:

[0153] A second acquisition submodule is used to obtain the point cloud density value of the target point cloud set;

[0154] A fourth determination submodule is used to determine the target point cloud set corresponding to the maximum point cloud density value as the optimal point cloud set;

[0155] A fifth determining submodule is configured to determine the first position correction value based on the second position information corresponding to the optimal point cloud cluster, the point cloud density value of the optimal point cloud cluster, and the first position information.

[0156] Optionally, the fifth determining submodule includes:

[0157] a fourth determining unit, configured to determine distance information between a position indicated by the second position information corresponding to the optimal point cluster and a position indicated by the first position information;

[0158] a fifth determining unit, configured to determine a position offset coefficient of a cluster center of the optimal point cloud based on a point cloud density value of the optimal point cloud and a point cloud density value of a position indicated by the first position information;

[0159] A sixth determination unit is used to determine the first position correction value based on the distance information and the position offset coefficient; the first position correction value includes a position correction direction and a position correction size, the position correction direction represents the direction from the position indicated by the first position information to the position indicated by the second position information corresponding to the optimal point cloud, and the position correction size represents the offset distance in the position correction direction.

[0160] Optionally, the correction module 304 includes:

[0161] a third acquisition submodule, configured to acquire a driving speed value of the vehicle and acquire a measurement delay of each sensor from the measurement characteristics of each sensor;

[0162] a sixth determining submodule, configured to determine a travel distance of the vehicle within the measurement delay based on the speed value and the measurement delay, and obtain the second position correction value;

[0163] The correction submodule is configured to correct the first position information based on the first position correction value and the second position correction value to obtain the first corrected position information.

[0164] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0165] The advantages of the position determination device and the position determination method described in the above embodiment over the prior art are the same and will not be described in detail here.

[0166] An embodiment of the present invention provides an electronic device, see Figure 4The electronic device 40 includes: a processor 401, a memory 402, and a computer program 4021 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the program, the location determination method of the aforementioned embodiment is implemented.

[0167] An embodiment of the present invention provides a readable storage medium. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the aforementioned position determination method.

[0168] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. According to the above description, it is obvious that the structure required for constructing this type of system. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0169] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0170] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Accordingly, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the present invention.

[0171] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition may be divided into multiple submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed herein may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0172] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the sorting device according to the present invention. The present invention may also be implemented as an apparatus or device program for performing a portion or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0173] It should be noted that the above embodiments illustrate rather than limit the invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0174] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0175] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0176] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0177] It should be noted that the various data-related processes in the embodiments of the present invention are all carried out in compliance with the corresponding data protection laws and policies of the country where they are located, and with the authorization given by the corresponding device owner.

[0178] The above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or modification made by those skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A method for determining a position, characterized in that: The method comprises: Acquire an object point cloud of a target object and first position information corresponding to the target object; wherein the first position information represents position information corresponding to a center point position of the target object; Clustering the points in the object point cloud to obtain at least one target point cloud set; the point cloud density value of the target point cloud set matches a preset density value; determining a first position correction value based on second position information of the cluster center of the target point cloud set, the point cloud density value, and the first position information; Correcting the first position information based on the first position correction value to obtain first corrected position information of the target object; The step of correcting the first position information based on the first position correction value to obtain first corrected position information of the target object includes: According to the first position correction value, the magnitude and direction of the correction are determined to offset the position indicated by the first position information along the correction direction to obtain the first corrected position information of the target object, wherein the magnitude of the offset is the same as the magnitude of the correction.

2. The method according to claim 1, characterized in that The obtaining of the object point cloud of the target object includes: Acquire environmental images and point cloud images of the vehicle's surroundings; determining the target object from the environment image; determining first position information of the target object based on the environment image; Based on the first position information, an object point cloud corresponding to the target object is determined from the point cloud image.

3. The method according to claim 2, characterized in that The determining, from the point cloud image, an object point cloud corresponding to the target object based on the first position information includes: Determining a measurement data interval corresponding to each sensor based on measurement characteristics of each sensor corresponding to the point cloud image; the measurement characteristics include at least one of a measurement object, a measurement data type, a measurement data range, a measurement method, and a measurement delay; deleting points corresponding to measurement data outside the measurement data interval from the point cloud image to obtain a second point cloud image; An object point cloud corresponding to the target object is determined from the second point cloud image based on the first position information.

4. The method according to claim 3, characterized in that The determining the target object from the environment image includes: fusing the environmental images obtained by the sensors based on the measurement characteristics of the sensors to obtain a fused environmental image; The target object is determined from the fused environment image.

5. The method according to claim 1, wherein The determining of a first position correction value based on the second position information of the cluster center of the target point cloud set, the point cloud density value, and the first position information includes: Obtaining a point cloud density value of the target point cloud set; Determine the target point cloud set corresponding to the maximum point cloud density value as the optimal point cloud set; The first position correction value is determined based on the second position information corresponding to the optimal point cloud cluster, the point cloud density value of the optimal point cloud cluster, and the first position information.

6. The method according to claim 5, characterized in that Determining the first position correction value based on the second position information corresponding to the optimal point cloud cluster, the point cloud density value of the optimal point cloud cluster, and the first position information includes: determining distance information between a position indicated by the second position information corresponding to the optimal point cluster and a position indicated by the first position information; determining a position offset coefficient of a cluster center of the optimal point cloud based on a point cloud density value of the optimal point cloud and a point cloud density value of a position indicated by the first position information; Based on the distance information and the position offset coefficient, the first position correction value is determined; the first position correction value includes a position correction direction and a position correction amplitude, the position correction direction represents the direction from the position indicated by the first position information to the position indicated by the second position information corresponding to the optimal point cluster, and the position correction amplitude represents the offset distance in the position correction direction.

7. The method according to claim 3, characterized in that Correcting the first position information based on the first position correction value to obtain first corrected position information of the target object includes: Obtaining a driving speed value of the vehicle, and obtaining a measurement delay of each sensor from the measurement characteristics of each sensor; determining a travel distance of the vehicle within the measurement delay based on the travel speed value and the measurement delay, and obtaining the second position correction value; The first position information is corrected based on the first position correction value and the second position correction value to obtain the first corrected position information.

8. A position determination device, characterized in that: The device comprises: A first acquisition module is configured to acquire first position information of a target object and an object point cloud corresponding to the target object; wherein the first position information represents position information corresponding to a center point position of the target object; A clustering module, configured to cluster the points in the object point cloud to obtain at least one target point cloud set; the point cloud density value of the target point cloud set matches a preset density value; a determination module, configured to determine a first position correction value based on second position information of a cluster center of the target point cloud set, the point cloud density value, and the first position information; A correction module is used to correct the first position information based on the first position correction value to obtain the first corrected position information of the target object; according to the first position correction value, determine the size and direction of the correction to offset the position indicated by the first position information along the correction direction to obtain the first corrected position information of the target object, wherein the size of the offset is the same as the size of the correction.

9. A vehicle, characterized in that: The device comprises the apparatus according to claim 8, configured to execute the position determination method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device executes the position determination method according to any one of claims 1 to 7.

Images