TW202020734A - Vehicle, vehicle positioning system, and vehicle positioning method - Google Patents

Abstract

The present disclosure provides a vehicle, a vehicle positioning system and a vehicle positioning method. The vehicle positioning system includes a two-dimensional (2D) image sensor,a three-dimensional (3D) sensor and a processor. The 2D image sensor obtains a 2D image data. The 3D sensor obtains a 3D point cloud data. The processor couples to the 2D image sensor and the 3D sensor and configures at least for: fusing the 2D image data and the 3D point cloud data for generating a 3D image data; identifying at least one static object from the 2D image data; obtaining the 3D point cloud data of the static object based on each of the at least one static object in the 3D image data; calculating a vehicle relative coordinate of the vehicle according to the 3D point cloud data of the static object.

Description

Carrier, carrier positioning system and carrier positioning method

The present disclosure relates to a vehicle, a vehicle positioning system, and a vehicle positioning method.

Autonomous driving technology is expected to improve driving safety and convenience to reduce driving burden. In terms of autonomous driving, environmental awareness is a necessary function, which can avoid collisions, and precise positioning is also very important, especially in urban environments, a variety of complex objects make the car drive on urban roads, which is easy to cause positioning error. Based on the types of sensors used, vehicle positioning methods are generally divided into active sensing and passive sensing. The passive sensor is, for example, a camera or a global positioning system (GPS), and the like, and the active sensor is, for example, a LiDAR sensor. However, the camera can identify the objects in the image frame through the image object detection module, but it cannot be correctly positioned in the three-dimensional space, so the position of the carrier cannot be correctly positioned, resulting in positioning errors. In a general GPS positioning method, if a vehicle is in an area such as a tunnel or indoor parking lot, the sensor may not receive a signal due to a shielding problem, and cannot accurately locate the position of the vehicle. The LiDAR sensor can detect objects and locate them in three-dimensional space, but cannot recognize what kind of objects are detected.

Traditional self-driving vehicles need to use pre-built map information. This map information needs to include a variety of road information, such as road boundaries, traffic lights, speed limit signs, etc., so that the self-driving algorithm can make the self-driving car correct according to the specified route and traffic rules Driving. The basic method of creating map data is to load LiDAR and GPS on the vehicle, and after detouring on the road, offline overlay/integration of Point cloud information (ie, LiDAR point cloud map) and GPS coordinates Information (ie, GPS coordinate map). However, the positioning accuracy of the self-driving car needs to be within 10 cm of the error. When the self-driving car is driving, the real-time large amount of point cloud information obtained by the LiDAR sensor is compared with the built-in light point cloud map to obtain Positioning information; however, a large amount of point cloud information contains redundant information, such as dynamically moving vehicles, pedestrians, or vehicles parked on the roadside, which can easily cause comparison errors and increase the amount of calculation.

Therefore, in the existing positioning technology, how to overcome the positioning error of the detection of the image object of the camera and the calculation amount of the large amount of point cloud information of the LiDAR sensor has become a problem to be solved.

In view of this, the present disclosure provides a vehicle, a vehicle positioning system, and a vehicle positioning method, which can be used to solve the above technical problems.

The present disclosure provides a vehicle positioning system, which is configured on a vehicle. The vehicle positioning system includes a two-dimensional image sensor, a three-dimensional sensor and a processor. A two-dimensional image sensor for obtaining a two-dimensional image data; a three-dimensional sensor for obtaining a three-dimensional point cloud data; and a processor coupled to the two-dimensional image sensor and the three-dimensional sensor, and At least configured to be suitable for: an alignment module for fusing the two-dimensional image data and the three-dimensional point cloud data to generate a three-dimensional image data; a static object recognition module recognizes at least one static object from the two-dimensional image data To obtain a 3D point cloud data of the static object from the 3D image data according to each static object of the at least one static object; and a positioning module to calculate the load based on the 3D point cloud data of the static object The relative coordinates of a vehicle.

The present disclosure provides a vehicle positioning method suitable for a vehicle positioning system configured on a vehicle. The method includes: obtaining a two-dimensional image data; obtaining a three-dimensional point cloud data; fusing the two-dimensional image data and the three-dimensional point cloud data to generate a three-dimensional image data; identifying at least one static object from the two-dimensional image data Obtaining a 3D point cloud data of the static object from the 3D image data according to each static object of the at least one static object; and calculating a vehicle of the vehicle based on the 3D point cloud data of the static object Relative coordinates.

The present disclosure provides a vehicle equipped with a vehicle positioning system. The vehicle includes a two-dimensional image sensor, a three-dimensional sensor and a processor. The processor is coupled to the two-dimensional image sensor and the three-dimensional sensor, and is at least configured to be suitable for: an alignment module for fusing the two-dimensional image data and the three-dimensional point cloud data to generate a three-dimensional image Data; a static object recognition module that recognizes at least one static object from the two-dimensional image data to obtain a three-dimensional point cloud data of the static object from the three-dimensional image data according to each static object of the at least one static object And a positioning module, based on the three-dimensional point cloud data of the static object, calculating a relative coordinate of the vehicle.

Based on the above, the vehicle, the vehicle positioning system and the vehicle positioning method proposed in the present disclosure can allow the vehicle to combine two heterogeneous sensors, a two-dimensional image sensor and a three-dimensional sensor, to obtain three-dimensional image data and recognize two After the static objects in the dimensional image data, the three-dimensional point cloud data of each static object is obtained from the three-dimensional image data, and the relative coordinates of the vehicle and the static object can be calculated to achieve the vehicle positioning.

In order to make the above-mentioned features and advantages of the present disclosure more comprehensible, the embodiments are specifically described below in conjunction with the accompanying drawings for detailed description as follows.

FIG. 1 is a schematic diagram of a vehicle positioning system according to an embodiment of the disclosure. In the embodiment shown in FIG. 1, the vehicle positioning system 100 is configured to be executed on the vehicle, but the invention is not limited thereto. The vehicle positioning system 100, methods, etc. disclosed herein can be implemented in alternative environments to detect objects in traffic, fields of view, etc. For example, one or more of the functions described in this article can be implemented by: electronic devices, mobile devices, game consoles, automotive system consoles (eg, ADAS), wearable devices (eg, personal wearable cameras ), head-mounted displays, etc. Additional embodiments include, but are not limited to robots or robotic devices, unmanned aerial vehicles (UAV), and remotely controlled aircraft. In the embodiment of FIG. 1, the vehicle of the vehicle positioning system 100 may be a motor vehicle (eg, car, truck, locomotive, bus, or train), ship (eg, boat or boat), aircraft (eg, airplane or straight) Helicopter), spacecraft (eg, space shuttle), bicycle or another vehicle. As an illustrative embodiment, the vehicle may be a wheeled vehicle, a tracked vehicle, a rail vehicle, an aerial vehicle, or a skid vehicle. In some situations, the vehicle may be operated by one or more drivers. For example, the vehicle may include an advanced driving assistance system (ADAS) that is configured to provide the driver of the vehicle as assistance. In other cases, the vehicle may be a computer-controlled vehicle. In addition, although the vehicle positioning system 100 in the embodiment of FIG. 1 is implemented at the vehicle, in other embodiments, the vehicle positioning system 100 disclosed herein may be in the "cloud" or outside the vehicle carried out. For example, a vehicle or other electronic device may provide position data and/or image data to another device to perform vehicle positioning.

The vehicle positioning system 100 includes one or more two-dimensional image sensors 102, one or more three-dimensional sensors 104, a processor 106, and a storage circuit 108. In the following embodiments, the carrier positioning system 100 of FIG. 1 is configured on the carrier, but the disclosure is not limited thereto, and the storage circuit 108 may not be limited to be included in the carrier positioning system 100.

The two-dimensional image sensor 102 is an image capturing device, a camera device, or a camera capable of capturing an image, such as a photosensitive coupled device (Charge Coupled Device; CCD) camera and/or a complementary metal oxide semiconductor (Complementary Metal-Oxide Semiconductor; CMOS) camera. Since the two-dimensional image sensors 102 can be installed at different positions of the vehicle, they can capture images with different angles and different fields of view. For example, a front camera device, a side camera device, and a rear camera device can be provided as needed.

The two-dimensional image sensor 102 obtains a two-dimensional image data. The two-dimensional image sensor 102 can provide the two-dimensional image data to the processor 106. The two-dimensional image sensor 102 can continuously, periodically or occasionally capture images and can load images (eg, two-dimensional image data) into the storage circuit 108.

The 3D sensor 104 is a sensor capable of detecting the distance between the vehicle and an external object, such as a LiDAR sensor (LiDAR sensor). The 3D sensor 104 can obtain information about reflective objects within the scanning range To obtain 3D point cloud data. The three-dimensional sensor 104 continuously, periodically or occasionally captures three-dimensional point cloud data and loads it into the storage circuit 108. The three-dimensional sensor 104 may provide three-dimensional point cloud data to the processor 106, wherein each three-dimensional point cloud data may include distance information about the vehicle and the reflective object, wherein each three-dimensional point cloud data data includes a spatial position ( X, Y, Z) information. The three-dimensional sensor 104, such as a LiDAR sensor, can measure the distance information between the vehicle and the reflective object/object without being affected by light.

The processor 106 is coupled to the two-dimensional image sensor 102 and the three-dimensional sensor 104, and receives two-dimensional image data and three-dimensional point cloud data. In one embodiment, the processor 106 can retrieve two-dimensional image data and three-dimensional point cloud data from the storage circuit 108. To illustrate, the storage circuit 108 or a portion thereof can be configured to store the 2D image data received from the 2D image sensor 102 and the 3D point cloud data received from the 3D sensor 104 to serve as a 2D image sensor 102 and the three-dimensional sensor 104 receive a circular buffer of data.

In one embodiment, the processor 106 may include an alignment module 110, a static object recognition module 112, and a positioning module 114. The alignment module 110, the static object recognition module 112, and the positioning module 114 may be hardware components corresponding to the vehicle, software (eg, instructions) executed by the processor 106, or a combination of the foregoing hardware components and software.

The vehicle positioning system 100 can pre-store a preset map information in the storage circuit 108, the preset map information includes road starting and ending coordinates, lane width, lane number, road heading angle, road curvature and road length and other road information The default map information includes three-dimensional point cloud information obtained through a three-dimensional sensor 104, such as a LiDAR sensor, and GPS absolute coordinate information obtained through GPS. The preset map information can also be corrected by RTK (Real-Time Kinematic, real-time dynamic positioning) of the National Land Surveying and Mapping Center, and then projected on an absolute coordinate system after coordinate conversion.

The storage circuit 108 is, for example, a memory, a hard disk, or any other component that can be used to store data, and can be used to record or store multiple modules, where each module is composed of one or more code segments. The processor 106 is coupled to the storage circuit 108, and can execute each step of the carrier positioning method proposed by the present disclosure by accessing a module in the storage circuit 108, respectively. In different embodiments, the processor 106 may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor, multiple microprocessors, or one or more combined digital signal processors Core microprocessor, controller, microcontroller, application specific integrated circuit (ASIC), field programmable gate array (FPGA), any other kind of integrated circuit, status Machine, processor based on Advanced Reduced Instruction Set Machine (Advanced RISC Machine, ARM) and similar products.

其中，f_u 、f_v 分別為水平以及垂直方向之焦距；u₀ 、v₀ 為影像平面的中心點；求得轉化矩陣Ｍ將三維點雲資料(x,y,z )映射到二維影像資料之像素點 (u,v )；Ｒ 與Ｔ 分別為旋轉矩陣以及平移向量。The alignment module 110 combines the two-dimensional image data obtained by the two-dimensional image sensor 102 and the three-dimensional point cloud data obtained by the three-dimensional sensor 104 with an alignment algorithm to fuse the two-dimensional image data and the three-dimensional point cloud data to Get a three-dimensional image data. The three-dimensional image data includes color information (for example, RGB data) and depth data (for example, position (X,Y,Z) data) of each image pixel, so the three-dimensional image data includes RGBXYZ image data. In one embodiment, an alignment algorithm for fusing 2D image data and 3D point cloud data is described. It is assumed that the 3D point cloud data is represented as (x, y, z), and the pixel points of the 2D image data are (u, v), according to the following formula, the pixel points of the three-dimensional point cloud data (x, y, z) mapped to the two-dimensional image data are (u, v), the alignment algorithm formula is as follows:

Where f _u and f _v are the focal lengths in the horizontal and vertical directions; u ₀ and v ₀ are the center points of the image plane; the transformation matrix M is obtained to map the three-dimensional point cloud data ( x,y,z ) to the two-dimensional image Pixels of the data ( u, v ); R and T are rotation matrix and translation vector, respectively.

FIG. 2 is a schematic diagram illustrating alignment processing of two-dimensional image data and three-dimensional point cloud data according to an embodiment of the present disclosure. Please refer to FIGS. 1 and 2 at the same time, which are the two-dimensional image data image (the background image in FIG. 2) obtained by the two-dimensional image sensor 102 and the three-dimensional point cloud data obtained by the three-dimensional sensor 104 (please refer to The point image in Figure 2), through the alignment algorithm, the three-dimensional image data image of the two-dimensional image data and the three-dimensional point cloud data fusion, as shown in Figure 2.

For the two-dimensional image data obtained by the two-dimensional image sensor 102, the static object identification module 112 can determine and identify at least one static object of the two-dimensional image data. For example, the static object identification module 112 may include a deep learning module that specifically detects static objects, identifying the types of static objects, such as road signs, buildings, substations, roads, sidewalks, bridges, trees, Telephone poles, New Jersey guardrails, etc., and the deep learning module or deep neural network of the static object identification module 112 uses image recognition algorithms to identify static objects in the image, which is currently known Object recognition algorithms, such as object contour tracking algorithms, are not described here. Among them, the search window for the static object recognition module 112 to detect the static object may correspond to the model, frame, or bounding box (BB) of the object. FIG. 3 is a schematic diagram illustrating the identification of static objects from two-dimensional image data according to an embodiment of the present disclosure. Please refer to FIG. 3, through the static object identification algorithm, each static object in the two-dimensional image data is identified, and each static object in the two-dimensional image data is marked by a bounding frame, as shown in the bounding frame of FIG. 3, each The bounding box contains information about each static object, for example, information such as the object type, object length, object width, and position in the two-dimensional image data.

After each static object in the two-dimensional image data is obtained, the three-dimensional of each static object can be obtained from the three-dimensional image data according to the information of each static object (for example, category, length, width, and position information). Point cloud data (X, Y, Z data), where each static object corresponds to the size of the object in the 3D image data, therefore, each static object can contain multiple 3D point cloud data (depth information). FIG. 4 is a schematic diagram illustrating that after identifying each static object, the three-dimensional point cloud data of each static object is obtained from the three-dimensional image data according to the embodiment of FIG. 3. Please refer to FIG. 3 and FIG. 4, according to the information of each static object (including traffic signs, street lights and roads) marked in the bounding box of FIG. 3, corresponding to the 3D point cloud data of each static object in the 3D image data.

Then, when the vehicle positioning system 100 on the vehicle obtains the three-dimensional point cloud data of each static object, the positioning module 114 of the vehicle positioning system 100 can use the positioning algorithm according to the three-dimensional point cloud data of the static object For example, the three-point positioning algorithm or the iterative comparison of the current 3D point cloud data and the map point cloud data, through optimization to calculate the minimum of the 3D point cloud data of the vehicle point cloud data and at least one static object Mean squared distances (MSD), the relative coordinates of the vehicle and the static object are calculated to achieve the positioning of the vehicle. In one embodiment, the above-mentioned relative mapping of the vehicle can be mapped to the pre-stored preset map information. Since the default map information includes 3D point cloud information and GPS absolute coordinate information, the relative Coordinates are defined and converted with preset map information, so that the three-dimensional absolute coordinates of the vehicle can be obtained.

In another embodiment, the 3D point cloud data of each static object can be mapped to pre-stored preset map information. Since the preset map information includes 3D point cloud information and GPS absolute coordinate information, , By comparing the 3D point cloud data of the static object with the static 3D object of the preset map information, to obtain the absolute coordinates of the 3D object of the static object, so that the vehicle can be deduced from the position of the preset map information, and then obtained The absolute coordinates of the three-dimensional vehicle.

In an embodiment of the present disclosure, the two-dimensional image data obtained by the two-dimensional image sensor 102 can generally only provide information projected on the image plane in the real world based on the reflection characteristics of the object surface to obtain the outline and boundary of the object , Texture and other features, so the identification algorithm based on two-dimensional information to identify the actual three-dimensional object, the object cannot be positioned in the correct position in the three-dimensional space, and there is a problem that the vehicle position cannot be correctly positioned. The three-dimensional sensor 104 can obtain the three-dimensional point cloud data of the object, but cannot identify what type the object belongs to, resulting in an excessively large amount of calculation of the three-dimensional point cloud data. Therefore, combining the characteristics and advantages of the two heterogeneous sensors, the two-dimensional image sensor 102 and the three-dimensional sensor 104, and real-time positioning of the vehicle can be achieved by detecting the three-dimensional point cloud data of static objects.

The present disclosure recognizes static objects rather than dynamic objects through the static object recognition module 112 because static objects can be more easily detected and recognized than dynamic objects, and changes in shape and color of static objects are usually also more dynamic than dynamic objects Since the static object recognition module 112 requires less training data and lower model complexity, it can achieve a good static object recognition rate. In this way, combining the two-dimensional image data of the two-dimensional image sensor 102 and the three-dimensional point cloud data of the three-dimensional sensor 104, each static object is identified through the static object identification module 112, and a three-dimensional point cloud of each static object is obtained Data, and then calculate the relative coordinates of the vehicle and the static object to achieve the positioning of the vehicle.

FIG. 5 is a schematic flowchart illustrating the operation of the vehicle positioning system according to an embodiment of the present disclosure.

Referring to FIG. 5, in step S501, the two-dimensional image sensor 102 obtains two-dimensional image data, where the two-dimensional image data includes a scene of at least one static object. In step S503, the three-dimensional sensor 104 obtains three-dimensional point cloud data. In step S505, the alignment module 110 fuses the two-dimensional image data and the three-dimensional point cloud data through the alignment algorithm to obtain a three-dimensional image data. In step S507, the static object recognition module 112 recognizes at least one static object from the two-dimensional image data. In step S509, the 3D point cloud data of each static object is obtained from the 3D image data according to each static object. In step S511, the positioning module 114 calculates the relative coordinates of the vehicle based on the three-dimensional point cloud data of the static object. Among them, a positioning algorithm can be used to calculate the three-dimensional image of the vehicle based on the three-dimensional point cloud data of the static object. The relative coordinates of the vehicle.

6 is a schematic diagram illustrating that the carrier 600 can directly or indirectly communicate with the carrier positioning system according to an embodiment of the present disclosure. The processor 606 and the storage 608 of the vehicle positioning system of FIG. 6 may be disposed on the vehicle 600 or at another location/location at the far end of the vehicle 600. Assuming that the processor 606 and the storage 608 of the vehicle positioning system are located at the remote end, the vehicle 600 has the ability to communicate with the remote processor 606 and the storage 608. In this embodiment, the vehicle 600 is a car, but this disclosure is not limited to this.

One or more two-dimensional image sensors 602 and one or more three-dimensional sensors 604 are disposed on the carrier 600. In this embodiment, the vehicle positioning system can perform the functions and operations as described above in FIGS. 1 to 4, and align the 2D image data obtained by the 2D image sensor 602 of the vehicle 600 with the 3D sensor 604 to capture The obtained 3D point cloud data has obtained 3D image data, and the 3D point cloud data of each static object is obtained from the 3D image data according to each static object of the 2D image data, and then the load is calculated through the 3D point cloud data of the static object The relative coordinates of the carrier of the vehicle can achieve the positioning of the vehicle.

In summary, the carrier, carrier positioning system and carrier positioning method proposed in the present disclosure can enable the carrier to combine two heterogeneous sensors, a two-dimensional image sensor and a three-dimensional sensor, to obtain three-dimensional image data, and After identifying the static objects of the two-dimensional image data, the three-dimensional point cloud data of each static object is obtained from the three-dimensional image data, and the relative coordinates of the vehicle and the static object can be calculated, and then mapped to The preset map information obtains the relative coordinates of the vehicle to achieve vehicle positioning. In this way, the vehicle can shorten the image recognition time of the static object through the deep learning model that specifically detects the static object, and only requires the 3D point cloud data of the static object, so the calculation amount of the 3D point cloud data is further reduced, and the load is reached. Precise positioning.

Although this disclosure has been disclosed as above with examples, it is not intended to limit this disclosure. Anyone who has ordinary knowledge in the technical field should make some changes and retouching without departing from the spirit and scope of this disclosure. The scope of protection disclosed in this disclosure shall be subject to the scope defined in the appended patent application.

100: Vehicle positioning system 102: 2D image sensor 104: 3D sensor 106: processor 108: storage circuit 110: Align module 112: Static object recognition module 114: Positioning module 600: Vehicle 602: Two-dimensional image sensor 604: 3D sensor 606: processor 608: storage S501, S503, S505, S507, S509, S511: Steps of vehicle positioning system operation

FIG. 1 is a schematic diagram of a vehicle positioning system according to an embodiment of the disclosure. FIG. 2 is a schematic diagram illustrating alignment processing of two-dimensional image data and three-dimensional point cloud data according to an embodiment of the present disclosure. FIG. 3 is a schematic diagram illustrating the identification of static objects from two-dimensional image data according to an embodiment of the present disclosure. FIG. 4 is a schematic diagram illustrating that after identifying each static object, the three-dimensional point cloud data of each static object is obtained from the three-dimensional image data according to the embodiment of FIG. 3. FIG. 5 is a schematic flowchart illustrating the operation of the vehicle positioning system according to an embodiment of the present disclosure. 6 is a schematic diagram illustrating that a vehicle can directly or indirectly communicate with a vehicle positioning system according to an embodiment of the present disclosure.

100: Vehicle positioning system

102: 2D image sensor

104: 3D sensor

106: processor

108: storage circuit

110: Align module

112: Static object recognition module

114: Positioning module

Claims (16)

A vehicle positioning system is configured on a vehicle. The vehicle positioning system includes: A two-dimensional image sensor, used to obtain a two-dimensional image data; A three-dimensional sensor for obtaining a three-dimensional point cloud data; and A processor, coupled to the two-dimensional image sensor and the three-dimensional sensor, is at least configured to be suitable for: An alignment module for fusing the two-dimensional image data and the three-dimensional point cloud data to generate a three-dimensional image data; A static object identification module, identifying at least one static object from the two-dimensional image data to obtain a three-dimensional point cloud data of the static object from the three-dimensional image data according to each static object of the at least one static object; and A positioning module calculates a relative coordinate of a vehicle based on the three-dimensional point cloud data of the static object. The vehicle positioning system as described in item 1 of the patent application scope, wherein the relative coordinates of the vehicle are mapped to a preset map information pre-stored in a storage circuit to obtain a three-dimensional vehicle absolute coordinate. The vehicle positioning system as described in item 1 of the patent application scope, wherein the three-dimensional point cloud data of the static object is mapped to preset map information pre-stored in a storage circuit to obtain a static object Absolute coordinates of three-dimensional objects. The vehicle positioning system according to item 3 of the patent application scope, wherein the positioning module calculates the absolute coordinates of the three-dimensional vehicle of the vehicle based on the absolute coordinates of the three-dimensional object of the static object. The vehicle positioning system as described in item 1 of the patent application, wherein the two-dimensional image sensor is a photosensitive coupling device camera or a complementary metal oxide semiconductor camera. The vehicle positioning system as described in item 1 of the patent application scope, wherein the three-dimensional sensor is a light sensor. A vehicle positioning method is applicable to a vehicle positioning system configured on one of the vehicles. The method includes: Obtain a two-dimensional image data; Get a 3D point cloud data; Fuse the two-dimensional image data and the three-dimensional point cloud data to generate a three-dimensional image data; Identify at least one static object from the two-dimensional image data; Obtaining a three-dimensional point cloud data of the static object from the three-dimensional image data according to the static object; and Based on the three-dimensional point cloud data of the static object, a relative coordinate of the vehicle is calculated. The method for positioning a vehicle as described in item 7 of the patent application scope further includes mapping the relative coordinates of the vehicle to a preset map information stored in advance to obtain a three-dimensional absolute coordinate of the vehicle. The vehicle positioning method described in item 7 of the patent application scope further includes mapping the three-dimensional point cloud data of the static object to a pre-stored preset map information to obtain a three-dimensional absolute coordinate of the static object . The method for positioning a vehicle as described in item 9 of the scope of the patent application further includes calculating the absolute coordinates of the three-dimensional vehicle based on the absolute coordinates of the three-dimensional object of the static object. A carrier equipped with a carrier positioning system includes: A two-dimensional image sensor, used to obtain a two-dimensional image data; A three-dimensional sensor for obtaining a three-dimensional point cloud data; and A processor, coupled to the two-dimensional image sensor and the three-dimensional sensor, is at least configured to be suitable for: An alignment module for fusing the two-dimensional image data and the three-dimensional point cloud data to generate a three-dimensional image data; A static object identification module, identifying at least one static object from the two-dimensional image data to obtain a three-dimensional point cloud data of the static object from the three-dimensional image data according to each static object of the at least one static object; and A positioning module calculates a relative coordinate of a vehicle based on the three-dimensional point cloud data of the static object. The vehicle according to item 11 of the patent application scope, wherein the relative coordinates of the vehicle are mapped to a preset map information pre-stored in a storage circuit to obtain a three-dimensional absolute coordinate of the vehicle. The vehicle according to item 11 of the patent application scope, wherein the three-dimensional point cloud data of the static object is mapped to a predetermined map information pre-stored in a storage circuit to obtain a three-dimensional object of the static object Absolute coordinates. The vehicle according to item 13 of the patent application scope, wherein the positioning module calculates a three-dimensional absolute coordinate of the vehicle based on the absolute coordinate of the three-dimensional object of the static object. The carrier as described in item 11 of the patent application scope, wherein the two-dimensional image sensor is a photosensitive coupling device camera or a complementary metal oxide semiconductor camera. The vehicle as described in item 11 of the patent application scope, wherein the three-dimensional sensor is a light sensor.

Images