Intelligent car searching method and related products

Abstract

The embodiment of the invention discloses an intelligent vehicle searching method and related products, and the method comprises the steps: obtaining a desensitization side view from a vehicle through a vehicle-mounted monitoring module of a target vehicle, and determining the number of a parking space region where the target vehicle is located, and the number of a parking space, thereby guaranteeing that a vehicle searching clue is real, reliable, legal and compliant, and improving the vehicle searching efficiency. And dependence on external facilities such as parking lot monitoring and the like or transformation cost can be reduced. Besides, the map position information determined according to the attitude information of the target vehicle and / or the environmental characteristic data of the parking area can make up the positioning defect caused by the fact that the parking space area number or the parking space number cannot be recognized sometimes (for example, a side vehicle is shielded or a parking lot has no number), increases vehicle searching clues, and facilitates the user to quickly and accurately search the target vehicle.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of vehicle management technology, and in particular to a smart vehicle search method and related products. Background Art

[0002] In daily life, users who have a poor sense of direction or are unfamiliar with parking spaces often have difficulty finding their vehicles quickly when they use them again after parking.

[0003] While some parking lots offer surveillance systems to help users find their vehicles, the sheer number of vehicles parked at any one time, or the complex structure of parking lots, makes the cost of implementing a surveillance system prohibitive. This prevents widespread adoption of parking lot surveillance systems, resulting in overall low vehicle search efficiency. Therefore, an effective solution is necessary. Summary of the Invention

[0004] The embodiments of the present application provide a smart vehicle search method and related products for widely improving the efficiency of users in finding target vehicles in parking areas.

[0005] A first aspect of an embodiment of the present application provides a smart car search method, including:

[0006] Obtaining a side view of at least one direction around the target vehicle through the on-board monitoring module of the target vehicle, and performing information desensitization processing on the side view to obtain a desensitized side view in the corresponding direction;

[0007] Identify the parking area number and parking space number of the target vehicle based on the desensitized side view;

[0008] Determining the position information of the target vehicle in the map based on the posture information of the target vehicle and / or the environmental characteristic data of the parking area;

[0009] The parking zone number, the parking space number and the location information are sent to a user terminal so that the user can search for the target vehicle.

[0010] Optionally, determining the position information of the target vehicle in the map based on the posture information of the target vehicle and / or environmental feature data of the parking area includes:

[0011] Collecting the target vehicle's posture information before and after parking and / or environmental feature data in the parking area through the target vehicle's onboard sensors;

[0012] A positioning signal of the target vehicle from a satellite navigation system is received, and position information of the target vehicle in a geographical map is comprehensively determined based on the posture information and / or the environmental feature data and the positioning signal.

[0013] Optionally, determining the position information of the target vehicle in the map based on the posture information of the target vehicle and / or environmental feature data of the parking area includes:

[0014] Collecting environmental feature data of the target vehicle in the parking area as data to be indexed through the onboard sensor of the target vehicle;

[0015] Matching the data to be indexed with data in a pre-built environment map to determine location information of data in the environment map that is most similar to the data to be indexed;

[0016] The environmental map data includes environmental feature data collected in multiple areas before the target vehicle reaches the parking area, and the multiple areas include indoor and / or outdoor passages.

[0017] Optionally, before identifying the parking zone number and parking space number of the target vehicle based on the desensitized side view, the method further includes:

[0018] Performing a perspective conversion on the desensitized side view of the target vehicle in at least one direction to obtain a desensitized bird's-eye view of the target vehicle;

[0019] The identifying the parking zone number and parking space number of the target vehicle based on the desensitized side view includes:

[0020] The parking area number where the target vehicle is located is identified through the desensitized side view, and the parking space number where the target vehicle is located is identified through the desensitized bird's-eye view.

[0021] Optionally, the information desensitization processing includes:

[0022] Sensitive information in each frame of the side view is blurred, where the sensitive information includes face and / or license plate information.

[0023] Optionally, the method further includes:

[0024] The desensitized bird's-eye view of the target vehicle and the side view or the desensitized side view in at least one direction are sent to the user terminal so that the user can search for the target vehicle by himself.

[0025] Optionally, the method further includes:

[0026] When it is detected that the speed, gear position and seat belt signal of the target vehicle meet the preset conditions, or when a vehicle search instruction sent by the user terminal is received, the step of obtaining a side view of the target vehicle in at least one direction around the target vehicle is executed through the on-board monitoring module of the target vehicle.

[0027] When the method described in the first aspect of this application is specifically implemented, the content described in the second aspect of this application can be used to achieve it.

[0028] A second aspect of an embodiment of the present application provides an electronic device, including: a processor and a memory;

[0029] The processor is configured to communicate with the memory and execute instructions in the memory to implement the method described in the first aspect of the embodiment of the present application or any specific implementation of the first aspect.

[0030] A third aspect of an embodiment of the present application provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, they implement the method described in the first aspect of the embodiment of the present application or any specific implementation of the first aspect.

[0031] A fourth aspect of an embodiment of the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed by a processor, they implement the method described in the first aspect of the embodiment of the present application or any specific implementation of the first aspect.

[0032] It can be seen from the above technical solutions that the embodiments of the present application have at least the following advantages:

[0033] The embodiments of the present application use the vehicle itself to obtain a desensitized side view using the target vehicle's onboard monitoring module, thereby determining the parking zone number and parking space number of the target vehicle. This ensures that the vehicle search clues are authentic, reliable, legal, and compliant, and helps reduce reliance on or modification costs for external facilities such as parking lot monitoring. In addition, the map location information determined based on the target vehicle's posture information and / or environmental characteristic data of the parking area can compensate for positioning defects caused by the inability to identify the parking zone number or parking space number in certain situations (such as when the parking lot is blocked by a nearby vehicle or there are no parking spaces), thereby increasing vehicle search clues and facilitating users to quickly and accurately search for the target vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0035] It should be noted that although the steps in the process diagrams (if any) involved in each embodiment are drawn sequentially as indicated by the arrows, unless otherwise explicitly stated herein, there is no strict order restriction on the execution of these steps, and these steps may be executed in other orders. Moreover, at least a portion of the steps in the flow diagrams involved in each embodiment may include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but may be executed at different times. The order of execution of these steps or stages is not necessarily sequential, but may be executed in rotation or alternation with other steps or at least a portion of steps or stages in other steps.

[0036] Figure 1 A schematic diagram of a flow chart of the method according to an embodiment of the present application;

[0037] Figure 2 Schematic diagram of the information desensitization process in the embodiment method of the present application;

[0038] Figure 3 This is a schematic diagram of the system architecture corresponding to the method of the embodiment of the present application;

[0039] Figure 4 This is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0041] The terms "first," "second," "third," "fourth," and the like (if any) in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that shown or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, product, or apparatus.

[0042] In the following description, references to "one specific embodiment" or "one specific example" and similar expressions describe a subset of all possible embodiments, but it is understood that "one specific embodiment" or "one specific example" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. In the following description, the term "multiple" refers to at least two. In some specific examples, the numerical value mentioned in this application reaches a threshold value (if any), which may include the case where the former is greater than the latter; if references to "any" or "at least one" and similar expressions are made, it may specifically refer to any one of the listed examples or any combination of these examples.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0044] The method of this application will be described in detail below.

[0045] See also Figure 1 In a first aspect, the present application provides a specific embodiment of a smart car search method, which includes the following steps:

[0046] Step S11: obtaining a side view of at least one direction around the target vehicle through the onboard monitoring module of the target vehicle, and performing information desensitization processing on the side view to obtain a desensitized side view in the corresponding direction;

[0047] The above-mentioned vehicle-mounted monitoring module may specifically refer to a camera installed at least in the front of the vehicle, the trunk, the left rearview mirror, and the right rearview mirror. Preferably, fisheye cameras (which can output spherical images) can be installed in these four places respectively to obtain more comprehensive view information in the four directions around the vehicle, thereby ensuring the richness of clues for finding the vehicle.

[0048] The reason for desensitizing the side view is that the side view may contain sensitive information involving privacy, such as faces and license plates. Therefore, in order to meet the requirements of laws, regulations or ethical morals, the obtained side view needs to be desensitized.

[0049] Step S12: Identify the parking zone number and parking space number of the target vehicle based on the desensitized side view;

[0050] As described above, the side view can reflect the visual information around the vehicle, such as the parking area number and / or parking space number displayed on the wall, signboard or ground, which are effective clues for finding the vehicle. Therefore, based on the desensitized side view, an attempt can be made to identify the parking area number and parking space number of the target vehicle.

[0051] Step S13: determining the location information of the target vehicle in the map based on the posture information of the target vehicle and / or the environmental characteristic data of the parking area;

[0052] In practical applications, map location information plays an important role in path planning or positioning. Therefore, we can try to obtain the location information of the target vehicle in the map, such as the geographical latitude and longitude in a macro sense or the indoor floor in a micro sense.

[0053] The posture information of a vehicle when parked in different locations is generally different. For example, vehicles parked on different floors (basement or second floor) have different heights, and the inclination angle of a vehicle parked on a slope is greater than that of a vehicle parked on a horizontal surface. The environmental characteristics of indoor and outdoor parking lots are different. For example, the specific values ​​of at least one of the satellite signal strength, light brightness, geomagnetic signal strength, etc. are different. Therefore, based on the posture information of the target vehicle and / or the environmental characteristic data of the parking area, we can try to determine the location information of the target vehicle on the map to further increase the richness of the vehicle search clues and ensure that the target vehicle is found quickly and accurately.

[0054] In practical applications, the order of executing step S13 and step S11 or S12 is not limited, and they may be executed simultaneously, depending on the actual situation.

[0055] Step S14: Send the parking zone number, parking space number and location information to the user terminal so that the user can search for the target vehicle.

[0056] In summary, the embodiments of the present application start from the vehicle itself and use the on-board monitoring module of the target vehicle to obtain a desensitized side view, thereby determining the parking area number and parking space number where the target vehicle is located. This can ensure that the vehicle search clues are authentic, reliable, legal and compliant, and help reduce dependence on or modification costs for external facilities such as parking lot monitoring. In addition, the map location information determined based on the posture information of the target vehicle and / or the environmental characteristic data of the parking area can make up for the positioning defects caused by the inability to identify the parking area number or parking space number in some cases (such as when the parking lot is blocked by a nearby vehicle or there is no parking number), increase the vehicle search clues, and facilitate users to search for the target vehicle quickly and accurately.

[0057] Based on the above examples, the method of the present application will be further described in detail below, and some specific possible implementation examples will be provided. In actual applications, the implementation contents between these examples can be combined or implemented separately as needed according to the corresponding functional principles and application logic. If implemented in combination, the execution order between the combined examples can be determined according to their respective processing logic, which can be determined by the actual scenario.

[0058] In some specific examples, the information desensitization process in step S11 may include: blurring sensitive information in each frame of the side view, where the sensitive information includes face and / or license plate information.

[0059] like Figure 2 As shown, offline desensitization technology can be used for desensitization: after the on-board monitoring module (or camera) captures the side view, the desensitization process can process at least part of the image one by one, such as four single views of the four perspectives of front, back, left and right (referred to as four-way views). The processing method can be to take out the images one by one from the folder where the images are saved, and then use AI technology to anonymize the face and / or license plate of the image (such as mosaic). After the desensitization process, a new image (i.e., desensitized side view) file will be generated and saved in the original file directory.

[0060] Alternatively, online desensitization technology can be used for desensitization: the original video captured by the camera (such as four-way video from four perspectives of front, back, left and right) is desensitized online in real time. The desensitization frequency can be 5Hz. AI technology is used to anonymize the face and license plate of each frame in the video. After desensitization, a new video file is generated and the video is output in real time, so that the required desensitized side views can be extracted frame by frame.

[0061] Typically, a single view (i.e., a side view) of at least a portion of the vehicle's front, rear, left, or right perspectives (e.g., the front, back, left, and right) may display information such as signs or wall placards surrounding the vehicle, thereby indicating the target vehicle's parking zone number and parking space number. Therefore, in some specific examples, the target vehicle's parking zone number and parking space number can also be identified using the aforementioned partial side view. Alternatively, sending a desensitized side view of at least a portion of the perspective to the user can also assist in finding the vehicle.

[0062] However, in some cases, the side view of at least some of the above perspectives (such as 1 to 3 directions) may not be able to well or completely reflect the signage or wall slogans around the vehicle, and the identification result of the parking space number may be missing (for example, the vehicle is actually in parking space 11, but it may be identified as parking space 1). Therefore, it is possible to choose to construct a more global bird's-eye view (BEV) based on this side view. That is, in some specific examples, before step S12, the method of the embodiment of the present application may also include: performing a perspective conversion on the desensitized side view of at least one direction of the target vehicle to obtain a desensitized bird's-eye view of the target vehicle. Therefore, the specific operation process of step S12 may include: identifying the parking area number of the target vehicle through the desensitized side view, and identifying the parking space number of the target vehicle through the desensitized bird's-eye view.

[0063] In some cases, a bird's-eye view can also be generated using side views in one to three directions (i.e., a single view), but its view range may be limited, such as only displaying a portion of the parking space number "No. 1". However, in comparison, a bird's-eye view generated using side views in the front, rear, left, and right directions of the vehicle contains more comprehensive or complete information, such as being able to display the complete parking space number "No. 11" to avoid misleading users.

[0064] Therefore, it is preferred to select four desensitized side views of the target vehicle (the front, rear, left, and right directions) and perform perspective conversion to obtain a bird's-eye view. This bird's-eye view can be a view with a transparent vehicle chassis, allowing the vehicle's parking space number and other information to be viewed. Accordingly, the following will provide an exemplary and detailed description of how to generate a bird's-eye view based on the four-way views.

[0065] Specifically, the spatial pose and projection relationship of the four-way camera can be clarified through the camera's intrinsic and extrinsic parameters, providing a mathematical foundation for perspective transformation. Intrinsic parameters include the intrinsic parameters of each camera (focal length, pixel size, and principal point coordinates), which describe how the lens projects light. Extrinsic parameters include the position (e.g., mounting height, horizontal distance from the center of the vehicle) and pose (e.g., pitch and yaw) of each camera in the vehicle coordinate system, which define the relative spatial relationship between the camera and the vehicle.

[0066] Afterwards, the four simultaneous views can be converted from a "perspective projection" to a "bird's-eye view." The key is to eliminate the perspective effect of near-sighted objects appearing larger than far-sighted objects through inverse perspective transformation (IPM). Based on the camera's intrinsic and extrinsic parameters, a mapping relationship is established between pixel coordinates in a single view and ground plane coordinates in the BEV image (assuming the ground is flat). For example, the "distant lane line pixels" in the front view image can be mapped to the "ground coordinates far in front of the vehicle" in the BEV through transformation. The four views correspond to the "front, rear, left, and right" ground areas of the vehicle in the BEV, and after transformation, each forms a local BEV subimage.

[0067] Finally, the four sets of local BEV sub-images can be aligned to a unified coordinate system and the overlapped areas can be smoothed out. Coordinate System 1: A BEV world coordinate system is established with the vehicle center as the origin (e.g., x-axis pointing forward, y-axis pointing left, and z-axis perpendicular to the ground). The coordinates of the four local sub-images are unified to this coordinate system using camera extrinsics. Overlapping Area Fusion: The four sub-images may overlap around the vehicle (e.g., the left front and front view corners overlap). Therefore, algorithms such as weighted averaging and edge smoothing can be used to smooth out the overlapped edges, ultimately forming a complete BEV map covering the ground around the vehicle in all directions.

[0068] Through the above operations, the planar information of the four-way single view can be "unfolded" to the same ground perspective, ultimately obtaining a spatially continuous bird's-eye view without perspective distortion. This can intuitively present environmental information such as location indicators and lane markings around the vehicle, making it easier for users to find their vehicle. Of course, in some examples, the four video streams can be converted into a bird's-eye view video stream, and then a bird's-eye view of the target vehicle at a specific moment can be extracted from the bird's-eye view video stream.

[0069] For indoor and outdoor parking areas with good satellite environmental signals (such as strong GPS signals), vehicle positioning can be achieved with the help of external satellite signals. Therefore, as a possible implementation method, the specific operation process of the above-mentioned step S13 may include: collecting the posture information of the target vehicle before and after parking and / or the environmental characteristic data in the parking area through the on-board sensors of the target vehicle; receiving the positioning signal of the target vehicle from the satellite navigation system, and comprehensively determining the position information of the target vehicle in the geographic map based on the posture information and / or environmental characteristic data and the positioning signal.

[0070] (1) The above operations can be summarized as a combined positioning technology based on GNSS+IMU, which is suitable for parking areas with good satellite environment signals.

[0071] Specifically, the aforementioned Global Navigation Satellite System (GNSS) may be at least one of the Global Positioning System (GPS), the BeiDou Navigation Satellite System (BDS), the GLONASS (Global Navigation Satellite System), and the Galileo (Galileo) Satellite Navigation System. GNSS positioning receives satellite signals (such as GPS signals) to calculate the vehicle's absolute position (i.e., positioning signal) in the global geographic coordinate system (WGS-84), including three-dimensional information such as longitude, latitude, and altitude.

[0072] The aforementioned on-board sensors may include inertial measurement units (IMUs). IMU measurements: Using accelerometers and gyroscopes, IMUs measure the three-axis linear acceleration (primarily the gravity component) and angular velocity (close to zero) of a static vehicle. These measurements are then integrated to yield relative position and attitude information (including at least one of roll, pitch, and yaw). This relative position is relative to the local coordinates of the initial point (such as easting and northing in the ENU coordinate system), not the global coordinate system (latitude and longitude). While the relative position of a static vehicle can theoretically be calculated, the error increases rapidly in practice. Its practical value for positioning in static scenarios is minimal or nonexistent. Therefore, the calculation and application of relative position can be ignored in vehicle search scenarios. The roll, pitch, and yaw angles refer to the vehicle's rotation angles around the X-axis (head direction), Y-axis (left direction), and Z-axis (perpendicular to the ground), respectively.

[0073] Because GNSS signals are susceptible to obstruction (e.g., indoor buildings and urban canyons) and have a low update frequency (e.g., 1-10Hz), and IMU measurements are prone to error accumulation (drift), to mitigate these effects, combining the data from both can be used to leverage their strengths and mitigate their weaknesses, resulting in higher positioning accuracy for both indoor and outdoor vehicles. For example, GNSS and IMU data can be fused to construct a joint equation (used to comprehensively calculate the target vehicle's position on a geographic map) to enhance the ability to resist interference from the effects of using either GNSS or IMU alone.

[0074] In some examples, environmental characteristic data may be used in place of the aforementioned posture information in combination with the positioning signal. Alternatively, the environmental characteristic data, the aforementioned posture information, and the positioning signal may be combined to comprehensively determine the target vehicle's location on a geographic map. The specific determination may be based on actual circumstances and is not limited here. The geographic map may be a general-purpose outdoor real-world map such as Amap, Tencent Maps, or Baidu Maps. For a detailed description of environmental characteristic data, please see below.

[0075] For indoor and outdoor parking areas where the satellite environment signal is not strong enough (e.g., a weak GPS signal), it is difficult to accurately locate the vehicle position by relying on external satellite signals. Therefore, the vehicle can be located primarily with the aid of onboard sensors (without relying on external satellite signals). That is, as another possible implementation, the specific operation process of the above-mentioned step S13 may include: collecting environmental feature data of the target vehicle in the parking area as data to be indexed through the onboard sensors of the target vehicle; matching the data to be indexed with data in a pre-constructed environmental map to determine the location information of the data in the environmental map that is most similar to the data to be indexed; wherein the environmental map data includes environmental feature data collected in multiple areas before the target vehicle reaches the parking area, and the multiple areas include indoor and / or outdoor passages. The following will be exemplified using light and geomagnetism as environmental features.

[0076] (2) For indoor and outdoor parking areas with poor satellite signal environment but good lighting, vehicle positioning can be performed based on visual mapping and positioning technology, which is suitable for parking areas with good lighting.

[0077] Specifically, the "map first, localize later" model of visual simultaneous localization and mapping (SLAM) technology can be used to achieve vehicle locating. Taking an indoor parking lot as an example, during the mapping phase, a comprehensive visual scan of the parking lot's light signature data can be performed to construct a global light environment map. This light environment map can include light signature data for the indoor and outdoor areas that the target vehicle passed through before being parked. Alternatively, this map can include pre-collected light signature data for most or even all areas of the parking lot, such as at least one of the following: brightness, light intensity, and light direction at the parking lot's entrances and exits. In some examples, this light signature data can be further bound to the parking lot's physical coordinates (e.g., X- and Y-axis coordinates with the entrance as the origin) to generate a coordinate-labeled visual feature map, helping users find their vehicles more quickly and accurately based on the provided geographic coordinates.

[0078] Positioning: After the target vehicle enters the parking lot and parks, the surrounding light signature data is collected in real time as indexed data. This data is then compared with the existing light signature data in the pre-built light environment map, and the target vehicle's position in the light environment map is determined through feature matching. This location can be the location of the data most similar to the indexed data, such as the XY coordinates (15.2m, 8.7m) with the parking lot entrance as the zero point. These coordinates can be mapped to a specific parking area code and parking space number.

[0079] (3) For indoor and outdoor parking areas with poor satellite signal and light conditions but no geomagnetic interference, a geomagnetic map can be established based on geomagnetic features, and then geomagnetic feature matching technology can be used for vehicle positioning (suitable for parking areas with less geomagnetic interference)

[0080] Using an indoor parking lot as an example, a comprehensive visual scan of the parking lot's geomagnetic signature data can be performed in advance to construct a global geomagnetic environment map. These geomagnetic signatures can specifically include at least one of magnetic field strength and magnetic field direction (the magnetic field in the Northern Hemisphere points diagonally downward toward the ground, while the magnetic field in the Southern Hemisphere points diagonally downward toward the ground). After a target vehicle enters the parking lot and parks, its surrounding geomagnetic signature data can be collected in real time as indexed data. This data is then compared with the existing geomagnetic signature data in the pre-constructed geomagnetic environment map to determine the target vehicle's position within the geomagnetic environment map. For details, please refer to the aforementioned exemplary description of light signatures and will not be repeated here.

[0081] It should be noted that the above-mentioned environmental map (micro) mainly considers the microscopic phenomena of local areas compared to the above-mentioned geographical map (macro), and involves more dimensions (such as various environmental characteristics), or in other words, the requirements for accuracy are higher.

[0082] The above mainly describes how to obtain the parking zone number and parking space number (identifiable from the side view or bird's-eye view) of the target vehicle, the location information of the target vehicle on the map, etc. from the perspective of the server. For the user, in some specific examples, the method of the embodiments of the present application may also include: sending a desensitized bird's-eye view of the target vehicle and a side view or desensitized side view in at least one direction to the user, so that the user can search for the target vehicle independently.

[0083] For example, a trained Fv-Det or OCC model can be used to extract parking space numbers from a desensitized bird's-eye view using AI technology. This information can then be stored in the memory of an embedded multimedia card (EMMC). This bird's-eye view can then be sent to the user for parking location search. Similarly, for parking area numbers, a trained Fv-Det or OCC model can be used to extract the area numbers from four desensitized side views using AI technology. This information can then be stored in the EMMC for subsequent transmission to the user for parking location search. These models can be trained using a large number of historical parking images and are not detailed here.

[0084] In some specific examples, the method of the embodiments of the present application may also include (actively or passively turning on the smart vehicle search function): when it is detected that the speed, gear position and seat belt signal of the target vehicle meet the preset conditions, or when a vehicle search instruction sent by the user terminal is received, executing the step of obtaining a side view of the target vehicle in at least one direction around the target vehicle through the on-board monitoring module of the target vehicle (i.e., S11).

[0085] For example, the judgment can be made based on the vehicle speed, gear position, and seat belt signal. If it is detected that the vehicle speed becomes 0 km / h, the gear position changes to P gear, and the seat belt signal status becomes released, that is, when these three conditions are met, the vehicle monitoring system (providing the information acquisition conditions relied on for smart car search) and the smart car search function can be automatically turned on to start executing step S11 and other operations for finding the car.

[0086] On the contrary, if at least one of the speed, gear position, and seat belt status does not meet the above conditions, the smart car search function will not be automatically turned on. At this time, the user can also actively turn on the monitoring system remotely through the mobile phone APP and remotely turn on the smart car search function.

[0087] As described above, in general, the application scenarios of the method of the embodiment of the present application include:

[0088] 1) If the user turns on the smart car search function (actively or passively) before leaving the car, the server sends an image and text information (such as coordinates and parking space number) of the vehicle's location to the user, allowing the user to selectively use at least some of these clues to find the car:

[0089] a. If the parking location has satellite signals, good lighting, or no geomagnetic interference, and the parking infrastructure is in good condition (e.g., clearly displayed text information such as the parking area code and parking number), users can choose from a variety of methods to find their vehicle. For example, users can navigate to the vehicle based on the vehicle's map location information (also known as map positioning); they can also search by parking space number or parking area number index; and they can search for the vehicle using five images (desensitized single views from four perspectives: front, back, left, and right, and one desensitized bird's-eye view).

[0090] b. The vehicle's parked location only requires signal availability, good lighting, or no interference from geomagnetic interference. Users can navigate to the vehicle based on the vehicle's map positioning. Alternatively, users can search for the vehicle using five images (single views from four perspectives: front, back, left, and right, plus a desensitized bird's-eye view).

[0091] c. The parking location of the vehicle only meets the requirements of good parking infrastructure. Users can search by parking space number and parking zone number index. They can also search for vehicles using five images (single views from four perspectives: front, back, left, and right, and a desensitized bird's-eye view).

[0092] d. The parking location lacks signal reception, good lighting, or interference-free geomagnetic fields. The parking infrastructure is also poor (no parking space number or area code). Users can only search for the vehicle using five images (single views from four perspectives: front, back, left, and right, plus a desensitized bird's-eye view).

[0093] 2) If the user does not enable the Smart Car Finder function before leaving the vehicle, the car search operations such as step S11 will generally not be enabled, and the corresponding intuitive index information such as the desensitized single view, desensitized bird's-eye view, and map location will not be obtained. In this case, the user can remotely activate the vehicle monitoring system and search for the vehicle using the four-channel video (front, back, left, and right) monitoring. Of course, the user can also actively send a car search command to try to remotely activate the Smart Car Finder function.

[0094] In summary, through the method of the embodiment of the present application, users can obtain vehicle location information on the map, desensitized side views of the vehicle's surroundings, parking space numbers, parking area numbers and other vehicle search clues through a mobile phone APP to help users quickly find the target vehicle in an unfamiliar environment.

[0095] See also Figure 3 As shown in the system block diagram, the vehicle monitoring system corresponding to the method of the embodiment of the present application may include: an intelligent driving domain controller, a communication box Tbox or Pbox, a car cloud, and a mobile phone APP (installed on the user side). Specifically:

[0096] 1. The Intelligent Driving Domain Controller is the main controller for the vehicle monitoring system and the smart car search system. Integrating parking-to-parking technology, the Intelligent Driving Domain Controller can obtain and record a list of frequently used parking spaces. When a vehicle is parked in a recorded frequently used space, the vehicle monitoring system automatically shuts down. When a vehicle is parked outside the recorded frequently used space, the vehicle monitoring system automatically turns on, providing the information necessary for smart car search.

[0097] 2. When the vehicle monitoring system is on, the intelligent driving domain controller uses vehicle speed, gear position, and seatbelt signal to determine if the vehicle is in a safe state. When the vehicle speed reaches 0 km / h, the gear position is shifted to P, and the seatbelt signal status is released, the intelligent vehicle search function will automatically activate.

[0098] 3. When the Smart Car Finder feature is enabled, the Smart Car Finder app instructs the perception module to desensitize the fisheye side views (also known as the four-way view) from the onboard monitoring module in four directions. This desensitization is performed to meet regulatory requirements. The desensitized four-way surround view video stream is then sent to the Around View Monitor (AVM) module for dedistortion, perspective conversion, and stitching to produce a bird's-eye view. The stitched bird's-eye view and the original surround view (the four-way view) are then sent to the Operation Control Center (OCC-model) module for parking zone and space number recognition. This involves unflattening the spherical image captured by the dedistorted fisheye camera into a flat image. Of course, if accuracy is not a priority, the generation and use of the bird's-eye view can be omitted, and the desensitized four-way view can be used directly for parking zone and space number recognition.

[0099] 4. The Smart Car Finder app notifies the Video Processor (VPS) to receive the bird's-eye view video stream generated by the AVM module. It then extracts a frame of data from the video stream, converts it into a .jpg image (i.e., a bird's-eye view image), and saves it to the Double Data Rate SDRAM (DDR) for subsequent transmission to the mobile app for the user to find the car.

[0100] 5. When the parking lot has numbered spaces or zones, the OCC-model module uses the OCC model to identify the zone number from the surround view image (i.e., the four-way view) and the space number from the bird's-eye view image using machine learning. The module then saves the zone and space number information to the embedded multimedia card (EMMC).

[0101] 6. When the Smart Vehicle Search function is enabled, the ALAM module can access a combination of positioning sensors (such as INS sensors) from the monitoring module to obtain the vehicle's location information on the map. If the vehicle is located in an indoor parking lot, the Adaptive Load Control Module (ALCM) will also use indoor positioning technologies (such as geomagnetic matching positioning, SLAM, satellite positioning, etc.) to perform multi-data fusion to obtain the vehicle's accurate position on the environmental map, further increasing the practicality and reliability of the vehicle search clues. In addition, the vehicle's location information can be saved to the EMMC for subsequent transmission to the mobile app for users to find the vehicle.

[0102] 7. Finally, the Smart Car Search app can notify the Gateway module to read the desensitized bird's-eye view from the DDR address and the parking zone number, parking space number, and vehicle location information on the map from the EMMC.

[0103] 8. After reading the information, the Smart Car Search App will continue to notify the Gateway module to send the read information to the Car Cloud via Tbox / Pbox, and the Car Cloud will synchronize it to the mobile app.

[0104] It can be seen that the vehicle monitoring system of the embodiment of the present application is intended to help users find the target vehicle quickly and accurately in the parking lot. For the specific operation process, please refer to the description in the above method, which will not be repeated here.

[0105] See also Figure 4 The electronic device of the embodiment of the present application may include one or more processors (such as central processing units (CPU)) and a memory, in which one or more applications or data are stored.

[0106] The memory may be volatile or persistent. The program stored in the memory may include one or more modules, each of which may include a series of instruction operations on the electronic device. Furthermore, the processor may be configured to communicate with the memory and execute the series of instruction operations in the memory on the electronic device.

[0107] The electronic device may also include one or more power supplies, one or more wired or wireless network interfaces, one or more input and output interfaces, and / or one or more operating systems, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.

[0108] The processor can execute the operations performed by the aforementioned first aspect or any specific method embodiment of the first aspect, and the details will not be repeated here.

[0109] The present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on a computer, the computer executes the method described in the first aspect or any specific implementation of the first aspect.

[0110] The present application provides a computer program product comprising instructions or a computer program. When the computer program product is run on a computer, the computer is enabled to execute the method described in the first aspect or any specific implementation of the first aspect.

[0111] It is understood that in the various embodiments of the present application, the sequence numbers of the steps do not imply a specific order of execution. The order of execution of the steps should be determined by their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The operations added or refined in the example schemes of the above-mentioned methods, systems or devices (if any) are not necessarily required to be performed during the specific implementation. If two or more operations are added, these operations can be implemented in combination or separately, depending on the actual scenario.

[0112] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system (if any) and device can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system or device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection of some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0115] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0116] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product (or computer program product) is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, a business server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk, and other media that can store program code.

Claims

1. A smart car-finding method, characterized in that: include: Obtaining a side view of at least one direction around the target vehicle through the on-board monitoring module of the target vehicle, and performing information desensitization processing on the side view to obtain a desensitized side view in the corresponding direction; Identify the parking area number and parking space number of the target vehicle based on the desensitized side view; Determining the position information of the target vehicle in the map based on the posture information of the target vehicle and / or the environmental characteristic data of the parking area; The parking zone number, the parking space number and the location information are sent to a user terminal so that the user can search for the target vehicle.

2. The intelligent car-finding method according to claim 1, characterized in that: The determining the position information of the target vehicle in the map based on the posture information of the target vehicle and / or the environmental characteristic data of the parking area includes: Collecting the target vehicle's posture information before and after parking and / or environmental feature data in the parking area through the target vehicle's onboard sensors; A positioning signal of the target vehicle from a satellite navigation system is received, and position information of the target vehicle in a geographical map is comprehensively determined based on the posture information and / or the environmental feature data and the positioning signal.

3. The intelligent car-finding method according to claim 1, characterized in that: The determining the position information of the target vehicle in the map based on the posture information of the target vehicle and / or the environmental characteristic data of the parking area includes: Collecting environmental feature data of the target vehicle in the parking area as data to be indexed through the onboard sensor of the target vehicle; Matching the data to be indexed with data in a pre-built environment map to determine location information of data in the environment map that is most similar to the data to be indexed; The environmental map data includes environmental feature data collected in multiple areas before the target vehicle reaches the parking area, and the multiple areas include indoor and / or outdoor passages.

4. The intelligent car-finding method according to claim 1, characterized in that: Before identifying the parking zone number and parking space number of the target vehicle based on the desensitized side view, the method further includes: Performing a perspective conversion on the desensitized side view of the target vehicle in at least one direction to obtain a desensitized bird's-eye view of the target vehicle; The identifying the parking zone number and parking space number of the target vehicle based on the desensitized side view includes: The parking area number where the target vehicle is located is identified through the desensitized side view, and the parking space number where the target vehicle is located is identified through the desensitized bird's-eye view.

5. The intelligent car-finding method according to claim 1, characterized in that: The information desensitization processing includes: Sensitive information in each frame of the side view is blurred, where the sensitive information includes face and / or license plate information.

6. The intelligent car-finding method according to claim 1, characterized in that: The method further comprises: The desensitized bird's-eye view of the target vehicle and the side view or the desensitized side view in at least one direction are sent to the user terminal so that the user can search for the target vehicle by himself.

7. The intelligent car-finding method according to claim 1, characterized in that: The method further comprises: When it is detected that the speed, gear position and seat belt signal of the target vehicle meet the preset conditions, or when a vehicle search instruction sent by the user terminal is received, the step of obtaining a side view of the target vehicle in at least one direction around the target vehicle is executed through the on-board monitoring module of the target vehicle.

8. An electronic device, characterized in that: include: processor and memory; The processor is configured to communicate with the memory and execute instructions in the memory to implement the method according to any one of claims 1 to 7.

9. A readable storage medium, characterized in that The readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The computer program product comprises computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images