Car navigation methods, computer devices and storage media in parking lot environments
By installing forward and rearward cameras on the car to collect video streams and driving operation information, and generating reverse driving operation information, the problem of navigation difficulties in parking lots is solved, and safe navigation and autonomous driving are realized in environments with poor signal.
Patent Information
- Application Number
- CN202311149300.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-06
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-09-06
AI Technical Summary
Existing navigation technologies are difficult to apply effectively in parking lot environments, causing drivers to get lost, wasting time and affecting traffic safety.
By installing forward and rearward cameras on the car, video streams and driving operation information during the entry and exit processes are collected, and reverse driving operation information is generated for navigation and autonomous driving commands.
In parking lot environments with poor signal, safe navigation and autonomous driving were achieved, reducing the likelihood of getting lost and improving parking lot traffic efficiency.
Smart Images

Figure CN117168461B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of automotive technology, and in particular to a car navigation method, computer device, and storage medium in a parking lot environment. Background Technology
[0002] Automobiles have expanded people's travel range, making it more likely that they can reach places they had never been before, thus creating a demand for guiding drivers to their destinations. Navigation technology can provide real-time positioning and navigation for terminals, greatly facilitating people's travel. Current navigation technologies are mainly based on satellite positioning or indoor positioning technologies. However, a large number of parking lots are located indoors or even underground, where satellite positioning signals are difficult to receive, making it impossible to use satellite-based navigation technologies for cars inside parking lots. Indoor positioning technologies typically require the installation of wireless communication devices such as Bluetooth devices in indoor environments, which is a significant cost for parking lots. Therefore, not all parking lots are equipped with such devices, making indoor positioning technology impractical and thus preventing the use of indoor positioning-based navigation technologies. Because current navigation technologies are generally difficult to apply in parking lot environments, drivers entering, finding parking spaces, and exiting parking lots must rely on observing signs and markings, as well as their memory and spatial reasoning to determine their location and plan their entry and exit routes. This places high demands on drivers' skills and the completeness of parking lot facilities. Because it is not easy to meet such high requirements at the same time in reality, drivers often get lost in parking lots, which wastes their time and affects traffic safety in the parking lot. Summary of the Invention
[0003] To address the technical problems that current navigation technologies are difficult to apply in parking lot environments, leading to traffic chaos due to the lack of navigation support in parking lots, the present invention aims to provide a car navigation method, computer device, and storage medium for parking lot environments.
[0004] On one hand, embodiments of the present invention include a car navigation method in a parking lot environment, the car navigation method in a parking lot environment including the following steps: Acquire the rearward video stream of the vehicle entering the parking lot and the time sequence of the driving operation entering the parking lot; the rearward video stream of the vehicle entering the parking lot is a video stream acquired from the rearward perspective of the vehicle during the entry process, and the time sequence of the driving operation entering the parking lot is a time sequence formed by the driving operation information recorded during the entry process. During the departure process from the parking lot, a forward-looking image is acquired; the forward-looking image is an image acquired from the forward-facing perspective of the vehicle. A first target video frame is determined from the incoming backward video stream; the first target video frame is a frame in the incoming backward video stream, and the first target video frame is matched with the most recently acquired outgoing forward image; Based on the time position of the first target video frame in the incoming video stream, first driving operation information with the corresponding time position is obtained from the time sequence of the incoming driving operation. Based on the first driving operation information, corresponding reverse driving operation information is generated.
[0005] Furthermore, the car navigation method in the parking lot environment also includes: Based on the reverse driving operation information, navigation information and / or autonomous driving instructions are generated.
[0006] Furthermore, the car navigation method in the parking lot environment also includes: Starting from the position of the first target video frame, the incoming video stream is played back to obtain the playback video stream; The playback video stream is played synchronously with the generation process of the reverse driving operation information.
[0007] Furthermore, the acquisition of the post-entry video stream and the time sequence of the entry driving operation includes: By receiving data transmitted from external devices, the approach video stream and the approach driving operation time sequence are obtained.
[0008] Furthermore, the acquisition of the post-entry video stream and the time sequence of the entry driving operation includes: During the entry process into the parking lot, the video stream is captured by this vehicle after the entry process; During the acquisition of the approach video stream, the driving operation information is simultaneously recorded in the vehicle to obtain the time sequence of the approach driving operation.
[0009] Furthermore, the car navigation method in the parking lot environment also includes: The incoming video stream and the time sequence of the incoming driving operation, collected by this vehicle, are shared with external devices.
[0010] Furthermore, the car navigation method in the parking lot environment also includes: Search for departure marker information in the incoming video stream; When the departure marker information is not found in the video stream following the entry, a departure forward image and a departure backward image are acquired during the departure process from the parking lot; the departure forward image is an image acquired from the front view of the car, and the departure backward image is an image acquired from the rear view of the car. A second target video frame and a third target video frame are determined from the incoming backward video stream; both the second target video frame and the third target video frame are frames in the incoming backward video stream, the second target video frame is matched with the most recently acquired outgoing forward image, and the third target video frame is matched with the most recently acquired outgoing backward image; Based on the time position of the second target video frame in the post-entry video stream, second driving operation information with the corresponding time position is obtained from the entry driving operation time sequence; Based on the time position of the third target video frame in the incoming video stream, third driving operation information with the corresponding time position is obtained from the time sequence of the incoming driving operation. Based on the second driving operation information and the third driving operation information, fourth driving operation information is generated; the fourth driving operation information is compatible with either the second driving operation information or the third driving operation information. Based on the fourth driving operation information, navigation information and / or autonomous driving instructions are generated.
[0011] Furthermore, the car navigation method in the parking lot environment also includes: Acquire the forward-facing video stream; the forward-facing video stream is the video stream captured from the forward-facing perspective of the car during the entry process into the parking lot. During the process of finding the car in the parking lot, images are collected from the mobile device. A fifth target video frame is determined from the incoming backward video stream or the incoming forward video stream; the fifth target video frame is a frame in the incoming backward video stream or the incoming forward video stream, and the fifth target video frame is matched with the most recently acquired mobile terminal image; Based on the time position of the fifth target video frame in the post-entry video stream or the pre-entry video stream, obtain the fifth driving operation information with the corresponding time position from the entry driving operation time sequence; The target location is determined based on the fifth driving operation information; Navigate to your vehicle based on the target location.
[0012] On the other hand, embodiments of the present invention also include a computer device, including a memory and a processor, the memory for storing at least one program, and the processor for loading at least one program to execute a car navigation method in a parking lot environment according to the embodiments.
[0013] On the other hand, embodiments of the present invention also include a storage medium storing a processor-executable program, which, when executed by a processor, is used to perform a car navigation method in a parking lot environment according to the embodiments.
[0014] The beneficial effects of this invention are as follows: the car navigation method in the parking lot environment described in the embodiments does not rely on satellite navigation technology or indoor navigation technology based on wireless communication, and therefore can be applied in environments such as underground parking lots with poor signal; the reverse driving operation information generated by analyzing the images captured during the entry and exit processes can effectively guide the driver or the car's autonomous driving system to perform the correct driving operations, thereby safely driving the car back the way it came to leave; moreover, the generated reverse driving operation information is easy to integrate with car navigation technology and autonomous driving technology, thereby providing data support for technologies such as voice navigation or autonomous driving. Attached Figure Description
[0015] Figure 1 This is a schematic diagram of a car system in which a car navigation method can be applied in a parking lot environment, as shown in the embodiment. Figure 2 This is a schematic diagram showing the installation positions of the front-facing camera and the rear-facing camera in the embodiment; Figure 3 This is a schematic diagram illustrating the steps of the car navigation method in a parking lot environment in the embodiment; Figure 4 This is a schematic diagram illustrating the principle of comparing and matching the departing image with the incoming video stream in the embodiment. Figure 5 This is a schematic diagram illustrating the car leaving the site via the same route in the embodiment; Figure 6 This is a schematic diagram illustrating the principle of generating a playback video stream in the embodiment; Figure 7 This is a schematic diagram illustrating a scenario where a car leaves the site via a non-return route. Detailed Implementation
[0016] In this embodiment, the car navigation method in a parking lot environment can be applied to... Figure 1 The vehicle system shown. (Refer to...) Figure 1 The system includes a control module, a storage module, a front-facing camera, a rear-facing camera, a short-range communication module, and a long-range communication module.
[0017] In this embodiment, components such as an Electronic Control Unit (ECU) can be used as the control module. The control module can be connected to other modules such as the front-facing camera and the rear-facing camera via a communication controller (EVCC).
[0018] Reference Figure 2 The front-facing camera can be mounted at the front of the vehicle, with a forward-facing view, meaning its field of view is in front of the vehicle. The rear-facing camera can be mounted at the rear of the vehicle, with a rear-facing view, meaning its field of view is behind the vehicle. Both front-facing and rear-facing cameras can record at any time, whether the car is parked, moving forward, reversing, or turning. They can either record continuously to obtain a video stream composed of multiple frames, or record periodically or non-periodically at longer intervals to capture a single image.
[0019] The front-facing and rear-facing cameras send the captured video streams or images to the control module for processing, or store them in the storage module.
[0020] Reference Figure 1 The short-range communication module can be a communication module based on protocols such as Bluetooth or Wi-Fi. Through the short-range communication module, the control module can communicate with terminals such as mobile phones carried by the driver or other passengers in the vehicle, or with communication equipment in the parking lot or communication equipment installed in other vehicles. The long-range communication module can be a communication module based on communication standards such as 4G or 5G. Through the long-range communication module, the control module can connect to the cloud server.
[0021] In this embodiment, the car navigation method in a parking lot environment can be executed by the control module. When the control module executes certain steps in the car navigation method in a parking lot environment, and needs to acquire certain data, or send out processed data or control commands, the control module can call... Figure 1 The various modules within.
[0022] In this embodiment, refer to Figure 3 The car navigation method in a parking lot environment includes the following steps: S1. Obtain the back-end video stream and the time sequence of the entry driving operation; S2. During the departure process from the parking lot, acquire images of the departure direction; S3. Determine the first target video frame from the incoming backward video stream; the first target video frame is a frame in the incoming backward video stream, and the first target video frame is matched with the latest acquired outgoing forward image; S4. Based on the time position of the first target video frame in the video stream after the entry, obtain the first driving operation information with the corresponding time position from the entry driving operation time sequence; S5. Generate corresponding reverse driving operation information based on the first driving operation information.
[0023] Steps S1-S5 can be executed by the control module. Specifically, the latitude and longitude coordinates of the entrance to a specific parking lot (e.g., a parking lot with a large area, many floors, unclear guidance information, and a history of multiple people getting lost) can be stored in the storage module. The control module calls the satellite navigation module to detect the real-time coordinate information of the car and reads the latitude and longitude coordinates of the specific parking lot from the storage module. It compares the latitude and longitude coordinates of the car with the real-time coordinate information of the car. When the real-time coordinate information of the car is consistent with or close to the latitude and longitude coordinates of a specific parking lot, it indicates that the car is about to enter that specific parking lot, thus generating the need to execute steps S1-S5, triggering the control module to start executing steps S1-S5.
[0024] In step S1, the rearward video stream to be acquired by the control module is the video stream captured by the rearward camera when the vehicle or other vehicles enter the parking lot. In other words, the content of the rearward video stream is the scenery seen from the rearward perspective when the vehicle or other vehicles enter the parking lot.
[0025] In this embodiment, the form of the incoming backward video stream is as follows: Figure 4 As shown, it can be decomposed into multiple video frames, such as frame1, frame2, frame3, etc. Frame1 is captured by the rear camera at 8:00:00, frame2 at 8:00:01, frame3 at 8:00:02, and so on. Specifically, the numbers frame1, frame2, etc., can simply indicate the sequential relationship between video frames and do not necessarily require the next frame of frame1 to be frame2. However, for simplicity in this embodiment, frame1, frame2, frame3, etc., can be understood as a video stream composed of one video frame captured per second.
[0026] In step S1, the time sequence of the approach driving operation to be acquired by the control module is shown in Table 1.
[0027] Table 1
[0028] Referring to Table 1, the entry driving operation time series records driving operation information such as throttle opening and steering wheel position at each of the following times: 8:00:00, 8:00:01, 8:00:02, etc. For example, the throttle opening at time 8:00:00 is 20% and the steering wheel position is -1°, indicating that at time 8:00:00, the road condition for the car whose entry driving operation time series was collected is a straight line, and therefore the car is driving straight with a 20% throttle opening and a -1° steering wheel position.
[0029] In Table 1, a positive throttle opening indicates that the brake pedal is not pressed and the throttle pedal is pressed to a corresponding degree; a zero throttle opening indicates that neither the throttle pedal nor the brake pedal is pressed; and a negative throttle opening indicates that the throttle pedal is not pressed and the brake pedal is pressed to a corresponding absolute value.
[0030] In Table 1, a positive steering wheel angle indicates that the steering wheel is turned to the right, which is a right turn when the car is moving; a negative steering wheel angle indicates that the steering wheel is turned to the left, which is a left turn when the car is moving.
[0031] In Table 1, after a car enters the parking lot, the control module can call the wheel speed sensors to record the number of wheel rotations, thereby calculating the distance the car has traveled since entering the parking lot. The result is expressed as a relative position. The relative position is represented in the form of the distance traveled, indicating the car's position within the parking lot with the parking lot entrance as the zero point.
[0032] In this embodiment, steps S1-S5 can be applied to... Figure 5 In the parking lot environment shown, this vehicle (equipped with...) Figure 1 The car in the system shown enters from the entrance and stops at a certain parking space. It needs to return to the exit near the entrance to leave. Steps S1-S5 can be executed during the departure process.
[0033] Before executing steps S1-S5, during the vehicle's entry process, the control module can utilize the rear-facing camera and sensors installed on the accelerator pedal, brake pedal, steering wheel, etc. While capturing the entry rear-facing video stream via the rear-facing camera, the system simultaneously detects and obtains the entry driving operation time sequence. For example, at 8:00:00, the control module uses the rear-facing camera to capture video frame 1, and simultaneously uses various sensors to detect driving operation information such as accelerator opening and steering wheel position, marking this as the driving operation information corresponding to 8:00:00; at 8:00:01, the control module uses the rear-facing camera to capture video frame 2, and simultaneously uses various sensors to detect driving operation information such as accelerator opening and steering wheel position, marking this as the driving operation information corresponding to 8:00:01… Video frames 1, 2… captured at multiple times form the entry rear-facing video stream, and the driving operation information collected at multiple times, as shown in Table 1, forms the entry driving operation time sequence.
[0034] After obtaining the entry rear video stream and driving operation time sequence, the control module can store the entry rear video stream and driving operation time sequence in the storage module, or send them to other cars about to enter the same parking lot via the short-range communication module, so that other cars can also obtain the entry rear video stream and driving operation time sequence and thus execute steps S2-S5; the vehicle's control module can also upload the entry rear video stream and driving operation time sequence to the cloud server for sharing via the remote communication module, so that other cars entering the same parking lot can request the cloud server to obtain the entry rear video stream and driving operation time sequence and thus execute steps S2-S5.
[0035] In step S1, if other vehicles obtain the approach rearward video stream and driving operation time sequence before this vehicle, this vehicle can also receive the approach rearward video stream and driving operation time sequence directly from other vehicles or from the cloud server without collecting them through the rearward camera and various sensors. This achieves the sharing of the approach rearward video stream and driving operation time sequence, reducing the repeated data collection and processing processes.
[0036] In step S2, when the vehicle drives out of its parking space and needs to leave the parking lot, the control module calls the forward-facing camera to take a picture. The image captured by the forward-facing camera at this time is the departure image. The forward-facing camera sends the departure image to the control module in real time.
[0037] In step S3, the control module can compare and match each departing forward image received from the forward-facing camera with each video frame in the incoming backward-facing video stream. (Refer to...) Figure 4 For the newly received departure forward image, the control module can execute comparison algorithms such as autoencoder (AE), pairwise similarity, or hash locally or by calling a cloud server. It processes each video frame (frame1, frame2, etc.) in the arrival backward video stream, calculating the similarity between the departure forward image and each frame, and identifies the video frame with the highest similarity as the first target video frame. Alternatively, the control module can run trained artificial intelligence models such as Siamese Network or Triplet Network locally or by calling a cloud server. Through convolutional layers, it extracts features (such as signs, markings, vehicle colors, and license plate numbers) from each video frame (frame1, frame2, etc.) in the departure forward image and performs depth comparison, identifying the video frame in frame1, frame2, etc., that is closest to the departure forward image as the first target video frame.
[0038] In step S3, if the scene content in the first target video frame is the same as or very similar to the scene content in the departure forward image, it can be determined that the first target video frame and the departure forward image were captured by the rear camera and the front camera respectively, targeting the same scene in the parking lot.
[0039] In this embodiment, refer to Figure 4 For the newly captured departure forward image, video frames such as frame1 and frame2 are not the first target video frames. That is, the scene content in video frames such as frame1 and frame2 is different from the scene content in the departure forward image, and they are not captured from the same scene in the parking lot. Video frame 7 is the first target video frame. That is, the scene content in video frame 7 is the same as the scene content in the departure forward image, and it is captured from the same scene in the parking lot from the same perspective.
[0040] In step S4, refer to Figure 4 After determining that video frame 7 is the first target video frame, its time position in the incoming video stream can be determined by its marked shooting time of 8:00:06. Then, from the driving operation time sequence shown in Table 1, the driving operation information (throttle opening -10%, steering wheel angle 60°) collected at the same time of 8:00:06 is obtained as the first driving operation information.
[0041] In step S5, corresponding reverse driving operation information is generated based on the first driving operation information. Specifically, the data representing direction in the first driving operation information can be inverted to obtain the reverse driving operation information. For example, the first driving operation information obtained in step S4 is throttle opening -10% and steering wheel angle 60°, where the signs of throttle opening and steering wheel angle represent their directions. Inverting these values yields throttle opening 10% and steering wheel angle -60°, which serves as the reverse driving operation information.
[0042] For the reverse driving operation information (throttle opening 10%, steering wheel angle -60°) obtained in step S5, the control module can generate navigation information in manual driving mode and generate autonomous driving commands in automatic driving mode. For example, in manual driving mode, the control module can generate voice information and send it to the speaker to play the voice message "Please turn left 60°"; in automatic driving mode, the control module generates control commands to control the engine to output 10% of the power and control the steering mechanism to turn 60° to the left.
[0043] In this embodiment, the principle of executing steps S1-S5 is as follows: the rearward video stream upon entry records the image content that can be detected from the rearward perspective during the process of the car entering the parking lot; the driving operation time sequence upon entry records the driving operations (especially steering-related operations) during the process of the car entering the parking lot; when leaving the parking lot and needing to return via the same route, the car's forward perspective is the same as the rearward perspective during the entry process; therefore, by detecting the first target video frame that matches the forward image during the exit in the rearward video stream upon entry, it can be confirmed that the car has reached the location of the first target video frame; and the first driving operation information indicates the driving operation performed by the car at the location corresponding to the first target video frame during the entry process; therefore, by obtaining the reverse driving operation information, it is possible to guide the driver or the car's autonomous driving system to return via the same route to exit.
[0044] The car navigation method in this embodiment does not rely on satellite navigation technology or wireless communication-based indoor navigation technology, so it can be applied in environments with poor signal, such as underground parking lots. By analyzing the images captured during the entry and exit processes, the generated reverse driving operation information can effectively guide the driver or the car's autonomous driving system to perform the correct driving operations, thereby safely driving the car back along the original route to achieve departure.
[0045] In this embodiment, after determining the location of the first target video frame, video playback can also be performed. (Refer to...) Figure 6After executing steps S1-S5 and determining frame7 as the first target video frame, the control module can use frame7 as the first frame, frame6 as the second frame, and so on, with frame2 as the second-to-last frame and frame1 as the last frame, thereby generating a playback video stream. The control module can then send the playback video stream to terminals such as the central control display screen for playback.
[0046] The playback effect of the replay video stream is equivalent to reversing the video stream after entering the venue. When leaving the venue by returning along the original route, the replay video stream can show the exit route from a forward perspective, thereby guiding the driver to leave the venue.
[0047] In this embodiment, when executing the car navigation method in a parking lot environment, the following steps may also be performed: S6. Search for departure marker information in the incoming video stream; S7. When no departure marker information is found in the video stream after entry, acquire the departure forward image and departure backward image during the departure process of the parking lot; S8. Determine the second and third target video frames from the incoming video stream; S9. Based on the time position of the second target video frame in the video stream after the entry, obtain the second driving operation information with the corresponding time position from the entry driving operation time sequence; S10. Based on the time position of the third target video frame in the video stream after the approach, obtain the third driving operation information with the corresponding time position from the approach driving operation time sequence; S11. Generate fourth driving operation information based on the second and third driving operation information; S12. Generate navigation information and / or automatic driving instructions based on the fourth driving operation information.
[0048] The control module can execute image detection algorithms locally or by calling a cloud server. For example, when capturing an approaching rear video stream using the vehicle's rear camera, the search process in step S6 is executed for each video frame obtained.
[0049] In step S6, the departure marker information may be a marker such as an indicator board marked with the Chinese word "出口" or the English word "exit" that indicates a departure marker. Since the backward video stream after entering the venue shows the scene of the route that the car has already passed when entering the venue, if the video frames in the backward video stream after entering the venue contain departure marker information, it indicates that the parking lot exit is located near the route that the car has already passed, the car may leave the venue by returning along the original route, and steps S1 to S5 may be executed; on the contrary, if none of the video frames in the backward video stream after entering the venue contain departure marker information, it indicates that there is no parking lot exit near the route that the car has already passed, the car cannot leave the venue by returning along the original route, and the scenario is as shown in Figure 7 .
[0050] In the scenario shown in Figure 7 , step S7 is executed, and during the departure process, the control module invokes the forward camera to capture a departure forward image, and invokes the backward camera to capture a departure backward image.
[0051] The principle of step S8 is the same as that of step S3. Each time the control module receives one departure forward image and one departure backward image, it may compare and match the departure forward image with each video frame in the backward video stream after entering the venue, and compare and match the departure backward image with each video frame in the backward video stream after entering the venue.
[0052] In step S8, if it is detected that there is a video frame in the backward video stream after entering the venue that matches the departure forward image, this video frame in the backward video stream after entering the venue is marked as a second target video frame; if it is detected that there is a video frame in the backward video stream after entering the venue that matches the departure backward image, this video frame in the backward video stream after entering the venue is marked as a third target video frame.
[0053] The principles of steps S9 and S10 are the same as that of step S4.
[0054] In step S9, after the second target video frame is determined, its time position in the backward video stream after entering the venue may be determined according to the shooting time marked by the second target video frame, and then the driving operation information with the corresponding time position, that is, collected at the same moment, is acquired from the entry driving operation time sequence shown in Table 1 as the second driving operation information.
[0055] In step S10, after the third target video frame is determined, its time position in the backward video stream after entering the venue may be determined according to the shooting time marked by the third target video frame, and then the driving operation information with the corresponding time position, that is, collected at the same moment, is acquired from the entry driving operation time sequence shown in Table 1 as the third driving operation information.
[0056] In step S11, the generated fourth driving operation information is compatible with the second or third driving operation information. Specifically, the fourth driving operation information can guide the driver or control the automatic driving system to perform driving operations that are the same as or similar to the second or third driving operation information. This similarity can be mainly reflected in operations related to the driving direction. For example, if the second or third driving operation information indicates driving forward or to the left, then the fourth driving operation information can be set to be the same as "driving forward or to the left," that is, driving forward or to the left in the current direction; or the fourth driving operation information can be set to the case where "driving forward or to the left" is also true, that is, driving to the left front in the current direction; or the fourth driving operation information can be set to be similar to "driving forward or to the left," such as driving to the left rear in the current direction.
[0057] In step S12, similar to the principle of generating navigation information and / or automatic driving instructions based on the first driving operation information, the control module can generate navigation information and / or automatic driving instructions based on the fourth driving operation information, thereby navigating the driver or executing automatic driving.
[0058] In this embodiment, the principle of executing steps S6-S12 is as follows: by confirming that there is no departure marker information in the video stream after the car enters the scene, it can be determined that the parking lot where the car is located is... Figure 7 As shown, the car needs to avoid returning along the original route to find an exit. The second driving operation information indicates the matching of the vehicle's forward image and the backward video stream, which is the driving operation information when the vehicle is returning along the original entry route. By setting a fourth driving operation information compatible with the second driving operation information, it is beneficial to correct the vehicle's driving route, so that the vehicle does not continue to drive along the original entry route, thus increasing the likelihood of finding the correct exit route. The third driving operation information indicates the matching of the vehicle's backward image and the backward video stream, which is the vehicle driving in the opposite direction to the original entry route. By setting a fourth driving operation information compatible with the third driving operation information, it is beneficial to maintain the vehicle's current driving route, prevent the vehicle from returning along the original entry route, thus increasing the likelihood of finding the correct exit route.
[0059] In this embodiment, when executing the car navigation method in a parking lot environment, the following steps may also be performed: S13. Obtain the incoming forward video stream; S14. During the process of finding the car in the parking lot, collect images from the mobile device; S15. Determine the fifth target video frame from the incoming video stream or the incoming video stream; S16. Based on the time position of the fifth target video frame in the video stream after entry or the video stream before entry, obtain the fifth driving operation information with the corresponding time position from the entry driving operation time sequence; S17. Determine the target location based on the fifth driving operation information; S18. Navigate to your vehicle based on the target location.
[0060] Steps S13-S18 can be performed when the driver has already parked the vehicle in the parking space and left the car, and needs to return to the parking lot to retrieve the vehicle.
[0061] In step S13, the control module can simultaneously call the front camera to capture the front video stream during the entry process, while calling the rear camera to capture the entry rear video stream.
[0062] In step S14, when searching for their vehicle, the driver can use their mobile phone or other mobile device to... Figure 1 The short-range communication module maintains a connection with the control module. The driver uses a mobile device to take pictures of their direction of travel, obtaining images that are then sent to the control module.
[0063] The principle of step S15 is the same as that of steps S3 and S8. The control module can compare and match each mobile terminal image it receives with each video frame in the incoming backward video stream or the incoming forward video stream to determine the video frame in the incoming backward video stream or the incoming forward video stream that matches the mobile terminal image, i.e., the fifth target video frame.
[0064] In step S16, the control module searches for the fifth driving operation information at the corresponding time in Table 1 (when the fifth target video frame is a video frame in the video stream after the entrance or before the entrance) based on the time position of the fifth target video frame in the video stream after the entrance. In step S17, the corresponding relative position can be found according to Table 1 and used as the target position.
[0065] In step S18, the control module calculates the navigation route by comparing the target position obtained in step S17 with the relative position of the car after it is parked in the parking space. The navigation route is then sent to the mobile terminal via the short-range communication module, and the mobile terminal displays the navigation route.
[0066] In this embodiment, the principle of executing steps S13-S18 is as follows: the fifth target video frame represents the video frame that matches the mobile terminal image in the video stream after the vehicle enters or the video stream before the vehicle enters. The mobile terminal image is the image captured by the driver in real time. Therefore, the content in the fifth target video frame is the location that the car passes through when it enters the parking lot. This location is the current location of the driver. This allows the control module to calculate the navigation route based on the target location. The navigation route points to the relative location of the vehicle, thereby guiding the driver to find the vehicle and reducing the time and effort spent by the driver in finding the car in an unfamiliar parking lot environment.
[0067] A computer program that executes the car navigation method in the parking lot environment of this embodiment can be written into a computer device or storage medium. When the computer program is read out and run, the car navigation method in the parking lot environment of this embodiment is executed, thereby achieving the same technical effect as the car navigation method in the parking lot environment of the embodiment.
[0068] It should be noted that, unless otherwise specified, when a feature is referred to as "fixed" or "connected" to another feature, it can be directly fixed or connected to the other feature, or indirectly fixed or connected to the other feature. Furthermore, the descriptions of "upper," "lower," "left," and "right" used in this disclosure are only relative to the relative positional relationships of the components of this disclosure in the accompanying drawings. The singular forms "a," "an," and "the" used in this disclosure are also intended to include the plural forms, unless the context clearly indicates otherwise. Moreover, unless otherwise defined, all technical and scientific terms used in this embodiment have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this embodiment specification is only for describing particular embodiments and is not intended to limit the invention. The term "and / or" as used in this embodiment includes any combination of one or more of the associated listed items.
[0069] It should be understood that although the terms first, second, third, etc., may be used to describe various elements in this disclosure, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, a first element may also be referred to as a second element without departing from the scope of this disclosure, and similarly, a second element may also be referred to as a first element. The use of any and all instances or exemplary language (“e.g.,” “such as,” etc.) provided in this embodiment is intended only to better illustrate embodiments of the invention and, unless otherwise required, does not impose a limitation on the scope of the invention.
[0070] It should be recognized that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable storage medium. The method can be implemented using standard programming techniques—including a non-transitory computer-readable storage medium configured with a computer program, wherein such a storage medium causes the computer to operate in a specific and predefined manner—according to the methods and drawings described in the specific embodiments. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, for this purpose, the program can run on a programmed application-specific integrated circuit (ASIC).
[0071] Furthermore, the procedures described in this embodiment can be performed in any suitable order unless otherwise indicated by this embodiment or clearly contradicted by the context. The procedures (or variations and / or combinations thereof) described in this embodiment can be executed under the control of one or more computer systems configured with executable instructions, and can be implemented by hardware or a combination thereof as code (e.g., executable instructions, one or more computer programs, or one or more applications) that commonly executes on one or more processors. A computer program includes multiple instructions executable by one or more processors.
[0072] Furthermore, the method can be implemented in any suitable type of computing platform, including but not limited to personal computers, minicomputers, mainframes, workstations, networked or distributed computing environments, standalone or integrated computer platforms, or in communication with charged particle tools or other imaging devices, etc. Aspects of the invention can be implemented as machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. Furthermore, the machine-readable code, or portions thereof, can be transmitted via wired or wireless networks. The invention of this embodiment includes these and other different types of non-transitory computer-readable storage media when such media comprises instructions or programs that implement the steps above in conjunction with a microprocessor or other data processor. When programmed according to the methods and techniques of the invention, the invention also includes the computer itself.
[0073] A computer program can be applied to input data to perform the functions of this embodiment, thereby transforming the input data to generate output data stored in non-volatile memory. The output information can also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects generated on the display.
[0074] The above are merely preferred embodiments of the present invention. The present invention is not limited to the above-described embodiments. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention, as long as they achieve the technical effects of the present invention by the same means, should be included within the scope of protection of the present invention. Within the scope of protection of the present invention, the technical solutions and / or implementation methods can have various modifications and variations.
Claims
1. A car navigation method in a parking lot environment, characterized in that, The car navigation method in the parking lot environment includes: Acquire the rearward video stream of the vehicle entering the parking lot and the time sequence of the driving operation entering the parking lot; the rearward video stream of the vehicle entering the parking lot is a video stream acquired from the rearward perspective of the vehicle during the entry process, and the time sequence of the driving operation entering the parking lot is a time sequence formed by the driving operation information recorded during the entry process. During the departure process from the parking lot, a forward-looking image is acquired; the forward-looking image is an image acquired from the forward-facing perspective of the vehicle. A first target video frame is determined from the incoming backward video stream; the first target video frame is a frame in the incoming backward video stream, and the first target video frame is matched with the most recently acquired outgoing forward image; Based on the time position of the first target video frame in the incoming video stream, first driving operation information with the corresponding time position is obtained from the time sequence of the incoming driving operation. Based on the first driving operation information, generate corresponding reverse driving operation information; Search for departure marker information in the incoming video stream; When the departure marker information is not found in the video stream following the entry, a departure forward image and a departure backward image are acquired during the departure process from the parking lot; the departure forward image is an image acquired from the front view of the car, and the departure backward image is an image acquired from the rear view of the car. A second target video frame and a third target video frame are determined from the incoming backward video stream; both the second target video frame and the third target video frame are frames in the incoming backward video stream, the second target video frame is matched with the most recently acquired outgoing forward image, and the third target video frame is matched with the most recently acquired outgoing backward image; Based on the time position of the second target video frame in the post-entry video stream, second driving operation information with the corresponding time position is obtained from the entry driving operation time sequence; Based on the time position of the third target video frame in the incoming video stream, third driving operation information with the corresponding time position is obtained from the time sequence of the incoming driving operation. Based on the second driving operation information and the third driving operation information, a fourth driving operation information is generated; the fourth driving operation information is used to guide the driver or control the automatic driving system to perform driving operations that are the same as or similar to the second driving operation information or the third driving operation information. Based on the fourth driving operation information, navigation information and / or autonomous driving instructions are generated.
2. The car navigation method in a parking lot environment according to claim 1, characterized in that, The car navigation method in the parking lot environment also includes: Based on the reverse driving operation information, navigation information and / or autonomous driving instructions are generated.
3. The car navigation method in a parking lot environment according to claim 2, characterized in that, The car navigation method in the parking lot environment also includes: Starting from the position of the first target video frame, the incoming video stream is played back to obtain the playback video stream; The playback video stream is played synchronously with the generation process of the reverse driving operation information.
4. The car navigation method in a parking lot environment according to claim 1, characterized in that, The acquisition of the post-entry video stream and the time sequence of the entry driving operation includes: By receiving data transmitted from external devices, the approach video stream and the approach driving operation time sequence are obtained.
5. The car navigation method in a parking lot environment according to claim 1, characterized in that, The acquisition of the post-entry video stream and the time sequence of the entry driving operation includes: During the entry process into the parking lot, the video stream is captured by this vehicle after the entry process; During the acquisition of the approach video stream, the driving operation information is simultaneously recorded in the vehicle to obtain the time sequence of the approach driving operation.
6. The car navigation method in a parking lot environment according to claim 5, characterized in that, The car navigation method in the parking lot environment also includes: The incoming video stream and the time sequence of the incoming driving operation, collected by this vehicle, are shared with external devices.
7. The car navigation method in a parking lot environment according to any one of claims 1-6, characterized in that, The car navigation method in the parking lot environment also includes: Acquire the forward-facing video stream; the forward-facing video stream is the video stream captured from the forward-facing perspective of the car during the process of entering the parking lot. During the process of finding the car in the parking lot, images are collected from the mobile device. A fifth target video frame is determined from the incoming backward video stream or the incoming forward video stream; the fifth target video frame is a frame in the incoming backward video stream or the incoming forward video stream, and the fifth target video frame is matched with the most recently acquired mobile terminal image; Based on the time position of the fifth target video frame in the post-entry video stream or the pre-entry video stream, obtain the fifth driving operation information with the corresponding time position from the entry driving operation time sequence; The target location is determined based on the fifth driving operation information; Navigate to your vehicle based on the target location.
8. A computer device, characterized in that, It includes a memory and a processor, the memory being used to store at least one program, and the processor being used to load at least one program to execute the car navigation method in a parking environment as described in any one of claims 1-7.
9. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to perform the car navigation method in a parking lot environment as described in any one of claims 1-7.
Citation Information
Patent Citations
Driving assistance method and system
CN110901638A
Automobile light control system and automobile
CN116234115A
