Signal sensing method and device, control equipment, driving equipment and storage medium
By collecting and analyzing the braking signal images of target vehicles on the window glass of adjacent front vehicles, the problem of difficulty in sensing the driving status of adjacent front vehicles in a timely manner is solved, and the effect of improving the safety of autonomous driving is achieved.
Patent Information
- Application Number
- CN202311028260.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-15
- Publication Date
- 2025-02-21
AI Technical Summary
In autonomous driving vehicles, when the distance between the bicycle and the adjacent vehicle in front is too close, it is difficult for the bicycle to sense the driving status of the adjacent vehicle in front in time, resulting in safety risks such as rear-end collisions.
The braking signal image of the target vehicle is collected by the window glass of the adjacent front vehicle that is traveling in the same direction as the bicycle, and the image is semantically analyzed to obtain the status information of the brake signal to determine the driving status of the target vehicle.
It effectively reduces safety risks such as rear-end collisions caused by untimely response of bicycles, and improves the safety and practicality of autonomous driving.
Smart Images
Figure CN119489841A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of autonomous driving technology, and in particular to a signal sensing method, apparatus, control device, driving device and storage medium. Background Art
[0002] At present, the field of autonomous driving often adopts a type of autonomous driving solution supported by high-precision map data. In this type of solution, high-precision map is regarded as a beyond-line-of-sight sensor, which can model known information in the real world and store and express it semantically through a relational database. However, since high-precision maps usually have a long acquisition cycle, high cost of use, and complex technical processing, this solution has the disadvantages of high production cost, long data production cycle, and untimely data update frequency from acquisition to application of high-precision maps, which greatly restricts the implementation of autonomous driving technology. Therefore, the field of autonomous driving also often adopts another type of low-cost, perception-intensive solution to support the implementation of autonomous driving functions.
[0003] For example, in a scenario using a low-cost, intensive-sensing solution, when an autonomous driving vehicle is driving in a lane, it often needs sensors such as cameras to sense the driving status of the adjacent vehicle in front to make decisions about its own driving. However, in some cases, when the distance between the vehicle and the adjacent vehicle in front is too close, the vehicle may not react in time and find it difficult to effectively sense the driving status of the adjacent vehicle in front, which may easily lead to situations including but not limited to rear-end collisions, affecting the autonomous driving safety of the vehicle. Summary of the invention
[0004] In view of this, embodiments of the present application provide a signal sensing method, apparatus, control device, driving device and storage medium to at least partially solve the above-mentioned problems.
[0005] According to a first aspect of an embodiment of the present application, a signal perception method is provided, comprising: collecting a brake signal image of a target vehicle traveling in front of an adjacent front vehicle traveling in the same direction as a self-vehicle through a window glass of the adjacent front vehicle traveling in the same direction as the self-vehicle; performing semantic analysis on the brake signal image to obtain status information of the brake signal corresponding to the brake signal image; and determining the driving status of the target vehicle based on the status information.
[0006] In some optional embodiments, the method of collecting a brake signal image of a target vehicle traveling in front of an adjacent front vehicle traveling in the same direction as the own vehicle through the window glass of the adjacent front vehicle traveling in the same direction as the own vehicle includes: collecting a brake signal image of the target vehicle traveling in front of the adjacent front vehicle projected on the front window glass and / or rear window glass through the front window glass and / or rear window glass of the adjacent front vehicle traveling in the same direction as the own vehicle.
[0007] In some optional embodiments, the performing semantic analysis on the brake signal image to obtain status information of the brake signal corresponding to the brake signal image includes: performing target detection on the brake lights of the target vehicle based on the brake signal image, and obtaining the status information of the brake lights in the brake signal image based on the result of the target detection.
[0008] In some optional embodiments, the target detection of the brake lights of the target vehicle based on the brake signal image includes: based on the brake signal image, detecting the brake lights that meet predetermined conditions from the brake signal image, wherein the predetermined conditions include at least one of the following: the distance from the ground is within a predetermined distance range, the shape is a long strip and the angle with the ground is within a predetermined angle range, the color when lit is a predetermined color, and the target vehicle is lit when in a braking state and is off when the target vehicle is in a non-braking state.
[0009] In some optional embodiments, the brake signal image includes: a first brake signal image frame collected at a current moment, and at least one second brake signal image frame collected within a preset time period before the current moment; the semantic analysis of the brake signal image includes: determining that the state of the brake light has changed based on a first state detection result of the brake light of the first brake signal image frame, and a second state detection result of the brake light of the at least one second brake signal image frame, and then performing semantic analysis on the first brake signal image frame and the at least one second brake signal image frame.
[0010] In some optional embodiments, determining that the state of the brake light has changed based on a first state detection result of the brake light in the first brake signal image frame and a second state detection result of the brake light in the at least one second brake signal image frame includes: grayscale processing the first brake signal image frame and the at least one second brake signal image frame to obtain their respective corresponding grayscale images; if the difference between the grayscale value of the brake light in the grayscale image corresponding to the first brake signal image frame and the grayscale value of the brake light in the grayscale image corresponding to the at least one second brake signal image frame meets a predetermined condition, determining that the state of the brake light has changed.
[0011] In some optional embodiments, the method further includes: determining, based on the state information, that the target vehicle enters a braking state; and determining a corresponding driving strategy for the vehicle based on the determined braking state.
[0012] In some optional embodiments, determining a corresponding driving strategy for the vehicle based on the determined braking state includes: determining a corresponding driving strategy for the vehicle based on the determined braking state and driving information of the vehicle, the adjacent preceding vehicle and the target vehicle.
[0013] In some optional embodiments, the corresponding driving strategy is determined for the self-vehicle based on the determined braking state and the driving information of the self-vehicle, the adjacent front vehicle and the target vehicle, including: based on the determined braking state and the driving information of the self-vehicle, the adjacent front vehicle and the target vehicle, determining whether the self-vehicle and the adjacent front vehicle will collide within a predetermined time, and if so, controlling the self-vehicle to decelerate for braking.
[0014] In some optional embodiments, the driving information of the self-vehicle, the adjacent preceding vehicle and the target vehicle includes: at least one of the driving speed of the self-vehicle, the driving speed of the adjacent preceding vehicle, the driving speed of the target vehicle, and the distance between the self-vehicle and the adjacent preceding vehicle.
[0015] According to the second aspect of an embodiment of the present application, a signal sensing device is provided, comprising: an acquisition module, for acquiring a brake signal image of a target vehicle traveling in front of an adjacent front vehicle traveling in the same direction as the vehicle, through the window glass of the adjacent front vehicle traveling in the same direction as the vehicle; an analysis module, for performing semantic analysis on the brake signal image to obtain status information of the brake signal corresponding to the brake signal image; and a determination module, for determining the driving status of the target vehicle based on the status information.
[0016] According to a third aspect of an embodiment of the present application, a control device is provided, characterized in that it includes: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store a computer program; and the processor is used to execute the method described in the first aspect above by running the computer program stored in the memory.
[0017] According to a fourth aspect of an embodiment of the present application, a driving device is provided, comprising: the control device provided in the aforementioned third aspect.
[0018] According to a fifth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect is implemented.
[0019] According to a sixth aspect of an embodiment of the present application, a computer program product is provided, including a computer program, wherein the computer program implements the method described in the first aspect when executed by a processor.
[0020] The signal sensing scheme provided in the embodiment of the present application can collect the braking signal image of the target vehicle traveling in front of the adjacent preceding vehicle through the window glass of the adjacent preceding vehicle traveling in the same direction as the own vehicle, and then perform semantic analysis on the braking signal image to obtain the state information of the braking signal corresponding to the braking signal image, and then determine the driving state of the target vehicle based on the state information. Therefore, the signal sensing scheme in the present application can conveniently determine the driving state of the target vehicle in front of the adjacent preceding vehicle of the own vehicle, so as to facilitate the subsequent driving decision of the own vehicle based on the driving state of the target vehicle. This effectively reduces the risk of situations including but not limited to rear-end collisions caused by the untimely reaction of the own vehicle and the difficulty in effectively sensing the driving state of the adjacent preceding vehicle when the distance between the own vehicle and the adjacent preceding vehicle is too close, thereby improving the safety and practicality of autonomous driving and also improving the autonomous driving experience of the own vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0022] Figure 1 A flowchart of the steps of an exemplary signal sensing method in the present application is shown.
[0023] Figure 2 A schematic diagram of the self-vehicle, the adjacent preceding vehicle and the target vehicle in the present application is shown.
[0024] Figure 3 A structural block diagram of an exemplary signal sensing device in the present application is shown.
[0025] Figure 4 A structural block diagram of an exemplary control device in the present application is shown.
[0026] Figure 5 A structural block diagram of an exemplary driving device in the present application is shown. DETAILED DESCRIPTION
[0027] In order to make those skilled in the art better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field should belong to the scope of protection of the embodiments of the present application. It should be understood that the various steps recorded in the method implementation mode of the present disclosure can be performed in different orders and / or performed in parallel. In addition, the method implementation mode may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0028] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. It should be noted that the modifications of "one" and "multiple" mentioned in this application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0029] The specific implementation of the embodiment of the present application is further explained below in conjunction with the accompanying drawings of the embodiment of the present application.
[0030] According to a first aspect of the present application, a signal sensing method is provided. Figure 1 FIG. 1 is a flowchart showing an exemplary signal sensing method in the present application. Figure 1 As shown, the signal sensing method includes steps S102, S104 and S106, specifically:
[0031] Step S102: collecting a brake signal image of a target vehicle traveling in front of the adjacent preceding vehicle through the window glass of the adjacent preceding vehicle traveling in the same direction as the own vehicle.
[0032] In the present application, the self-driving vehicle may be a driving device with an automatic driving function. That is, the driving device may include an automatic driving mode, and when the driving device enters the automatic driving mode, automatic driving may be achieved. The driving device may be a fully automatic driving device, or a semi-automatic driving device that includes both a manual driving mode and an automatic driving mode. Or in some other embodiments, the driving device may also be a non-automatic driving device that does not have an automatic driving function, and the driving state of the target vehicle determined by the signal sensing method of the present application may also provide a reference for the user of the self-driving vehicle to manually drive.
[0033] The adjacent preceding vehicle and the target vehicle may also be autonomous driving devices or non-autonomous driving devices, and there is no restriction here.
[0034] Optionally, the self-vehicle in the embodiment of the present application can be a vehicle with automatic driving function (including vehicles with manned functions (such as cars, buses, large buses, minibuses, etc.), vehicles with cargo functions (such as ordinary trucks, vans, trailers, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, trucks with special structures), special vehicles (such as logistics distribution vehicles, automatic guided transport vehicles AGV, patrol cars, cranes, cranes, excavators, bulldozers, forklifts, rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor washing vehicles, sprinkler trucks, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.), vehicles with entertainment functions (such as entertainment vehicles, amusement park automatic driving devices, balance cars, etc.), rescue vehicles (such as fire trucks, ambulances, power repair vehicles, engineering rescue vehicles, etc.)) and robots (such as sweeping robots, food delivery robots, etc.), etc.
[0035] The vehicle may be provided with one or more sensors for sensing the environment and the vehicle itself (e.g., driving status). For example, the sensors may include image acquisition devices (e.g., cameras), point cloud acquisition devices (e.g., laser radars), etc. The sensors may also include millimeter wave radars, ultrasonic radars, inertial measurement units, wheel speed meters, etc., which are not limited here. The data collected by these sensors can be used by the vehicle to achieve perception, positioning, planning, control, and other purposes.
[0036] In the present application, the self-vehicle, the adjacent preceding vehicle and the target vehicle may be traveling in the same lane and in the same direction, wherein the target vehicle may be determined as the first vehicle in front of the adjacent preceding vehicle.
[0037] Based on this, in step S102, an image acquisition device such as a camera can be used to collect a brake signal image of a target vehicle traveling in front of the adjacent front vehicle traveling in the same direction as the vehicle through the window glass of the adjacent front vehicle, which can usually be a brake light signal image. Taking the image acquisition device as a camera as an example, the setting position of the camera is not limited in this application, as long as the brake signal image of the target vehicle can be effectively collected. For example, the camera can be set on the vehicle, and the camera can be a front-view camera of the vehicle.
[0038] In some optional embodiments, step S102 includes: collecting the braking signal image of the target vehicle traveling in front of the adjacent preceding vehicle projected on the front window glass and / or rear window glass through the front window glass and / or rear window glass of the adjacent preceding vehicle traveling in the same direction as the self-vehicle. For example, when the target vehicle takes a braking action, the corresponding braking signal in the target vehicle will be activated, such as the brake light will light up, so the activated braking signal will be transmitted or refracted on the front window glass and / or rear window glass of the vehicle following behind based on the principle of light, because the front window glass and rear window glass of the vehicle will form a perspective, so that the self-vehicle can adopt the braking signal image of the target vehicle through the window glass of the adjacent preceding vehicle.
[0039] The brake signal image of the target vehicle traveling in front of the adjacent vehicle traveling in the same direction as the own vehicle and projected on the front window glass and / or rear window glass is collected, which is more convenient for subsequent data processing such as semantic analysis, so as to obtain a more accurate driving status of the target vehicle.
[0040] In the present application, the brake signal image of the target vehicle can indicate the state of the brake signal of the target vehicle. For example, the brake signal image can include the brake lights of the target vehicle. Generally speaking, the brake lights of the target vehicle will light up when the target vehicle brakes, and will be off when the target vehicle does not brake. Therefore, it can indicate the state of the brake signal of the target vehicle. In the present application, preferably, the brake lights of the target vehicle can be the high-mounted brake lights of the target vehicle. Compared with other types of brake lights, high-mounted brake lights are easier to be perceived and collected by the following vehicles.
[0041] The relationship between the vehicle, the adjacent preceding vehicle and the target vehicle in this application is as follows: Figure 2 See Figure 2 For understanding, the ego vehicle Car1, the adjacent front vehicle Car2, and the target vehicle Car3 are traveling in the same direction and are adjacent to each other. The ego vehicle Car1 is provided with a forward-looking camera, and the ego vehicle Car1 can collect the braking signal image of the target vehicle Car3 through the front windshield and the rear windshield of the adjacent front vehicle Car2. Figure 2FIG. 1 schematically shows the vertical shooting range of the front camera of the ego vehicle Car1, and also schematically shows the schematic diagram of the reflected light signal of the high-mounted brake light of the target vehicle Car3 being photographed and collected by the front camera of the ego vehicle Car1 through the front windshield and rear windshield of the adjacent front vehicle Car2. However, it should be understood that in practice, the range of the front camera of the ego vehicle Car1 is often larger than that of the front camera of the ego vehicle Car2. Figure 2 The examples in the description are more complex and are only used to facilitate understanding and are not intended to limit the present application in any way.
[0042] Step S104: performing semantic analysis on the brake signal image to obtain state information of the brake signal corresponding to the brake signal image.
[0043] In the present application, after the brake signal image of the target vehicle is collected through the window glass of the adjacent front vehicle, the brake signal image can be semantically analyzed to obtain the state information of the brake signal corresponding to the brake state image, so as to facilitate the subsequent determination of the driving state of the target vehicle. Among them, the state information of the brake signal can indicate whether the brake signal is currently in a lit state or an extinguished state.
[0044] In some optional embodiments, step S104 includes: performing target detection on the brake lights of the target vehicle based on the brake signal image, and obtaining state information of the brake lights in the brake signal image according to the result of the target detection.
[0045] Under normal circumstances, the braking of a vehicle can be reflected by the brake lights. Based on this, in this application, the state information of the brake lights in the brake signal image is accurately determined by performing target detection on the brake lights, and the state information of the brake signal corresponding to the brake state image is accurately obtained. In this way, it not only conforms to the actual vehicle braking situation, but also can efficiently determine the state of the brake signal.
[0046] Since the brake signal image is collected based on the window glass of the adjacent front vehicle, further optionally, in order to improve the accuracy of target detection of the brake lights of the target vehicle, the brake signal image can be pre-processed, including but not limited to denoising, to reduce the interference of other noises in the brake signal image other than the brake lights on the target detection. Optionally, the brake signal image can also be enhanced in detail to enhance the details of the brake lights in the brake signal image, so as to better improve the accuracy of target detection of the brake lights of the target vehicle.
[0047] In some optional embodiments, for the brake lights of the target vehicle including the high-mounted brake lights of the target vehicle, the aforementioned "based on the brake signal image, performing target detection on the brake lights of the target vehicle" may include: based on the brake signal image, detecting the brake lights that meet predetermined conditions from the brake signal image, wherein the predetermined conditions include at least one of the following: the distance from the ground is within a predetermined distance range, the shape is a long strip and the angle with the ground is within a predetermined angle range, the color when lit is a predetermined color, and the target vehicle is lit when the target vehicle is in a braking state and is off when the target vehicle is in a non-braking state.
[0048] Based on this, the present application performs target detection on the brake lights of the target vehicle based on the brake signal image in this way, and can accurately detect the brake lights that meet the predetermined conditions in the brake signal image, so as to obtain the status information of the brake lights that meet the predetermined conditions in the brake signal image according to the target detection result.
[0049] Among them, the predetermined distance range, the predetermined angle range, and the predetermined color can all be set as needed. For example, in some optional embodiments, when the brake light of the target vehicle is a high-mounted brake light of the target vehicle, the predetermined distance range can be set to 1 meter to 2 meters, the predetermined angle range can be set to 0° to 10°, and the predetermined color is red. It should be understood that this example is only an optional embodiment and is not intended to be a limitation of the present application.
[0050] In some optional embodiments, the brake signal image includes: a first brake signal image frame collected at the current moment, and at least one second brake signal image frame collected within a preset time period before the current moment; then the "performing semantic analysis on the brake signal image" in step S104 includes: determining that the state of the brake light has changed based on a first state detection result of the brake light of the first brake signal image frame, and a second state detection result of the brake light of at least one second brake signal image frame, then performing semantic analysis on the first brake signal image frame and the at least one second brake signal image frame.
[0051] Based on this, in the present application, after determining that the state of the brake lights of the target vehicle has changed based on the first state detection result of the brake lights of the first brake signal image frame and the second state detection result of the brake lights of at least one second brake signal image frame, semantic analysis is performed on the first brake signal image frame and at least one second brake signal image frame, which can facilitate obtaining the state information of the brake signal corresponding to the brake signal image and save computing resources.
[0052] In the present application, the length of the preset time period can be set as needed, and can generally be shorter to meet the real-time requirements. In the present application, the brake signal image can include at least one second brake signal image frame. When multiple second brake signal image frames are included, in some optional embodiments, it can be two second brake signal image frames. Generally speaking, multiple second brake signal image frames (e.g., two frames) are easier to ensure the accuracy of determining the state of the brake light than one second brake signal image frame.
[0053] Optionally, at least one second brake signal image frame and the first brake signal image frame collected at the current moment may be multiple brake signal image frames collected continuously. Taking two second brake signal image frames as an example, the state of the brake light may be detected using three continuously collected brake signal image frames as input sources, and whether the state of the brake light has changed is determined based on the state detection results of the brake light of the three continuously collected brake signal image frames. By determining whether the state of the brake light has changed based on the state detection results of the brake light of the three continuously collected brake signal image frames, accuracy can be better ensured.
[0054] In some optional embodiments, the "determining that the state of the brake light has changed based on a first state detection result of the brake light in the first brake signal image frame and a second state detection result of the brake light in at least one second brake signal image frame" includes: performing grayscale processing on the first brake signal image frame and at least one second brake signal image frame to obtain their corresponding grayscale images; if the difference between the grayscale value of the brake light in the grayscale image corresponding to the first brake signal image frame and the grayscale value of the brake light in the grayscale image corresponding to at least one second brake signal image frame meets a predetermined condition, then determining that the state of the brake light has changed.
[0055] In the present application, if the difference between the grayscale value of the brake light in the grayscale image corresponding to the first brake signal image frame and the grayscale value of the brake light in the grayscale image corresponding to at least one second brake signal image frame meets a predetermined condition, it can be considered that the intensity of the light emitted by the brake light of the target vehicle has changed significantly, and the change can be caused by the light turning on and off, for example, from the off state to the lit state. Therefore, in this way, the present application can accurately determine whether the state of the brake light of the target vehicle has changed.
[0056] Correspondingly, if the difference between the grayscale value of the brake light in the grayscale image corresponding to the first brake signal image frame and the grayscale value of the brake light in the grayscale image corresponding to at least one frame of the second brake signal image frame does not meet the predetermined condition, it is determined that the state of the brake light has not changed.
[0057] The predetermined conditions in the present application can be set as needed. For example, in some optional embodiments, the predetermined conditions may include: the difference between the grayscale value of the brake light in the grayscale image corresponding to the first brake signal image frame and the grayscale value of the brake light in at least one second brake signal image frame is greater than a predetermined value. When the difference is greater than the predetermined value, it is considered that the brake light of the target vehicle has changed from on to off. Of course, the predetermined conditions may also be other conditions, which are not limited here.
[0058] Step S106: Determine the driving state of the target vehicle according to the state information.
[0059] Based on this, in the present application, through the above steps S102 to S106, since it is possible to collect the brake signal image of the target vehicle traveling in front of the adjacent front vehicle traveling in the same direction as the own vehicle through the window glass of the adjacent front vehicle, and then perform semantic analysis on the brake signal image to obtain the state information of the brake signal corresponding to the brake signal image, and then determine the driving state of the target vehicle based on the state information, therefore, the signal perception scheme in the present application can conveniently determine the driving state of the target vehicle in front of the adjacent front vehicle of the own vehicle, which can facilitate the subsequent decision-making of the own vehicle's driving according to the driving state of the target vehicle, thereby effectively reducing the risk of situations including but not limited to rear-end collisions caused by the self-vehicle's untimely response and difficulty in effectively perceiving the driving state of the adjacent front vehicle when the distance between the self-vehicle and the adjacent front vehicle is too close, thereby improving the safety and practicality of autonomous driving, and also improving the autonomous driving experience of the self-vehicle.
[0060] In some optional embodiments, the signal sensing method of the present application further includes: determining, based on the state information, that the target vehicle enters a braking state; and determining a corresponding driving strategy for the vehicle based on the determined braking state.
[0061] Based on this, in the present application, after determining that the target vehicle enters a braking state, a driving strategy can be determined for the ego vehicle according to the determined braking state to implement the ego vehicle's driving decision, thereby improving the ego vehicle's driving experience, and further effectively reducing the risk of situations including but not limited to rear-end collisions caused by the ego vehicle not reacting in time and having difficulty in effectively perceiving the driving state of the adjacent vehicle in front when the distance between the ego vehicle and the adjacent vehicle in front is too close, thereby improving the safety and practicality of autonomous driving, and also improving the ego vehicle's autonomous driving experience.
[0062] In the present application, when determining a corresponding driving strategy for the self-vehicle according to the determined braking state, the corresponding driving strategy can be directly determined for the self-vehicle according to the determined braking state. For example, in one possible implementation, after determining that the target vehicle enters the braking state, the self-vehicle can be directly controlled to decelerate for braking; and in another possible implementation, after determining that the target vehicle enters the braking state, the self-vehicle can be controlled to change lanes; and so on, or other driving strategies can also be used, which are not limited in the present application.
[0063] However, it is not limited thereto, when determining a corresponding driving strategy for the vehicle according to the determined braking state, the corresponding driving strategy for the vehicle can also be determined according to the determined braking state and in combination with other perception information. For example, in some optional implementations, the aforementioned "determining a corresponding driving strategy for the vehicle according to the determined braking state" includes: determining a corresponding driving strategy for the vehicle according to the determined braking state and driving information of the vehicle, the adjacent preceding vehicle, and the target vehicle.
[0064] Based on this, the present application can more reasonably determine the corresponding driving strategy for the own vehicle in this way, thereby improving the driving experience of the own vehicle, and further effectively reducing the risk of situations including but not limited to rear-end collisions caused by the own vehicle not reacting in time and difficulty in effectively perceiving the driving status of the adjacent vehicle in front when the distance between the own vehicle and the adjacent vehicle in front is too close, thereby improving the safety and practicality of autonomous driving, and also improving the autonomous driving experience of the own vehicle.
[0065] Optionally, the driving information of the vehicle, the adjacent preceding vehicle and the target vehicle in the present application may include: at least one of the driving speed of the vehicle, the driving speed of the adjacent preceding vehicle, the driving speed of the target vehicle, and the distance between the vehicle and the adjacent preceding vehicle. In the present application, such driving information is processed to more reasonably determine a corresponding driving strategy for the vehicle, thereby improving the driving experience of the vehicle.
[0066] It can be understood that the driving speed of the vehicle can be obtained through a sensor for measuring the vehicle speed installed on the vehicle. In addition, the driving speed of the adjacent preceding vehicle, the driving speed of the target vehicle, and the distance between the vehicle and the adjacent preceding vehicle can also be calculated through information collected by the vehicle through various sensors.
[0067] In some optional embodiments, "determining a corresponding driving strategy for the vehicle based on the determined braking state and the driving information of the vehicle, the adjacent preceding vehicle and the target vehicle" includes: determining whether the vehicle and the adjacent preceding vehicle will collide within a predetermined time based on the determined braking state and the driving information of the vehicle, the adjacent preceding vehicle and the target vehicle, and if so, controlling the vehicle to decelerate for braking.
[0068] Based on this, in this application, according to the determined braking state, as well as the driving information of the own vehicle, the adjacent front vehicle and the target vehicle, it is analyzed and determined that the own vehicle and the adjacent front vehicle will collide within a predetermined time, and then the own vehicle is controlled to slow down for braking, which can effectively ensure the driving safety of the own vehicle, improve the safety and practicality of autonomous driving, and also improve the autonomous driving experience of the own vehicle.
[0069] It should be noted that if, based on the determined braking state and the driving information of the own vehicle, the adjacent front vehicle and the target vehicle, it is determined that the own vehicle and the adjacent front vehicle will not collide within the predetermined time, the own vehicle can continue to be controlled to drive normally, or the own vehicle can be controlled to slow down for braking. This is not restricted in the present application.
[0070] To sum up, the signal sensing scheme in the present application can conveniently determine the driving status of the target vehicle in front of the adjacent preceding vehicle of the own vehicle, thereby being conducive to making subsequent driving decisions of the own vehicle according to the driving status of the target vehicle. This effectively reduces the risk of situations including but not limited to rear-end collisions caused by the fact that the distance between the own vehicle and the adjacent preceding vehicle is too close and the own vehicle fails to react in time and is unable to effectively perceive the driving status of the adjacent preceding vehicle. This improves the safety and practicality of autonomous driving and also improves the autonomous driving experience of the own vehicle.
[0071] It can be understood that the above description of the signal sensing method of the present application is merely an exemplary description of the present application and does not constitute any limitation to the present application.
[0072] According to a second aspect of an embodiment of the present application, a signal sensing device is provided. Figure 3 FIG. 1 is a block diagram showing an exemplary signal sensing device 100 of the present application. The signal sensing device 100 of the present embodiment includes:
[0073] The acquisition module 102 is used to acquire a braking signal image of a target vehicle traveling in front of the adjacent preceding vehicle through a window glass of the adjacent preceding vehicle traveling in the same direction as the vehicle;
[0074] An analysis module 104, configured to perform semantic analysis on the brake signal image to obtain state information of the brake signal corresponding to the brake signal image;
[0075] The determination module 106 is used to determine the driving state of the target vehicle according to the state information.
[0076] The signal sensing scheme provided in the embodiment of the present application has the following advantages: the acquisition module 102 can collect the braking signal image of the target vehicle traveling in front of the adjacent preceding vehicle traveling in the same direction as the own vehicle through the window glass of the adjacent preceding vehicle, the analysis module 104 can perform semantic analysis on the braking signal image to obtain the state information of the braking signal corresponding to the braking signal image, and the determination module 106 can determine the driving state of the target vehicle based on the state information. Therefore, the signal sensing scheme in the present application can conveniently determine the driving state of the target vehicle in front of the adjacent preceding vehicle of the own vehicle, so as to facilitate the subsequent decision-making of the own vehicle's driving based on the driving state of the target vehicle. This effectively reduces the risk of situations including but not limited to rear-end collisions caused by the untimely reaction of the own vehicle and the difficulty in effectively sensing the driving state of the adjacent preceding vehicle when the distance between the own vehicle and the adjacent preceding vehicle is too close, thereby improving the safety and practicality of autonomous driving and also improving the autonomous driving experience of the own vehicle.
[0077] In some optional embodiments, the acquisition module 102 is specifically used to: collect the brake signal image projected on the front window glass and / or rear window glass of the adjacent front vehicle traveling in the same direction as the own vehicle, by a target vehicle traveling in front of the adjacent front vehicle.
[0078] In some optional embodiments, the analysis module 104 is specifically used to: perform target detection on the brake lights of the target vehicle based on the brake signal image, and obtain status information of the brake lights in the brake signal image according to a result of the target detection.
[0079] In some optional embodiments, the analysis module 104 is specifically used to: based on the brake signal image, detect brake lights that meet predetermined conditions from the brake signal image, wherein the predetermined conditions include at least one of the following: the distance from the ground is within a predetermined distance range, the shape is a long strip and the angle with the ground is within a predetermined angle range, the color when lit is a predetermined color, and the target vehicle is lit when the target vehicle is in a braking state and is off when the target vehicle is in a non-braking state.
[0080] In some optional embodiments, the brake signal image includes: a first brake signal image frame collected at a current moment, and at least one second brake signal image frame collected within a preset time period before the current moment; the analysis module 104 is specifically used to: determine that the state of the brake light has changed based on a first state detection result of the brake light of the first brake signal image frame, and a second state detection result of the brake light of the at least one second brake signal image frame, and then perform semantic analysis on the first brake signal image frame and the at least one second brake signal image frame.
[0081] In some optional embodiments, the analysis module 104 is specifically used to: perform grayscale processing on the first brake signal image frame and the at least one second brake signal image frame to obtain their respective corresponding grayscale images; if the difference between the grayscale value of the brake light in the grayscale image corresponding to the first brake signal image frame and the grayscale value of the brake light in the grayscale image corresponding to the at least one second brake signal image frame meets a predetermined condition, it is determined that the state of the brake light has changed.
[0082] In some optional embodiments, the signal sensing device 100 is further used to: determine, based on the state information, that the target vehicle enters a braking state; and determine a corresponding driving strategy for the vehicle based on the determined braking state.
[0083] In some optional embodiments, the signal sensing device 100 is further specifically used to determine a corresponding driving strategy for the vehicle according to the determined braking state and driving information of the vehicle, the adjacent preceding vehicle and the target vehicle.
[0084] In some optional embodiments, the signal sensing device 100 is further specifically used to: determine whether the self-vehicle and the adjacent front vehicle will collide within a predetermined time based on the determined braking state and the driving information of the self-vehicle, the adjacent front vehicle and the target vehicle; if so, control the self-vehicle to decelerate for braking.
[0085] In some optional embodiments, the driving information of the self-vehicle, the adjacent preceding vehicle and the target vehicle includes: at least one of the driving speed of the self-vehicle, the driving speed of the adjacent preceding vehicle, the driving speed of the target vehicle, and the distance between the self-vehicle and the adjacent preceding vehicle.
[0086] The signal sensing device 100 of the embodiment of the present application and the signal sensing method provided in the first aspect are based on the same inventive concept, and are used to implement the corresponding signal sensing methods in the aforementioned multiple method embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be described in detail here. In addition, the functional implementation of each module in the signal sensing device 100 of this embodiment can refer to the description of the corresponding parts in the aforementioned method embodiments, which will not be described in detail here.
[0087] According to the third aspect of an embodiment of the present application, a control device is provided, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store a computer program; and the processor is used to execute the signal sensing method described in the first aspect above by running the computer program stored in the memory.
[0088] Figure 4 The embodiment of the present application does not limit the specific implementation of the control device 400. As an example, refer to Figure 4 The control device 400 provided in the embodiment of the present application includes: a processor 402, a communication interface 404, a memory 406, and a communication bus 408. Among them:
[0089] The processor 402 , the communication interface 404 , and the memory 406 communicate with each other via a communication bus 408 .
[0090] The communication interface 404 is used to communicate with other electronic devices or servers.
[0091] The processor 402 is used to execute the computer program 410, and specifically can execute the relevant steps in any of the aforementioned signal sensing method embodiments.
[0092] Specifically, the computer program 410 may include program codes including computer operation instructions.
[0093] The processor 402 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.
[0094] The memory 406 is used to store the computer program 410. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.
[0095] The computer program 410 may be specifically configured to enable the processor 402 to execute the signal sensing method in any of the aforementioned embodiments.
[0096] The specific implementation of each step in the computer program 410 can refer to the corresponding description of the corresponding steps and units in any of the above-mentioned signal sensing method embodiments, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above-mentioned method embodiments, which will not be repeated here.
[0097] The control device 400 in the embodiment of the present application has been described in detail in the aforementioned signal sensing method embodiment, so its related contents and beneficial effects can be understood with reference to the aforementioned method embodiment and will not be described again here.
[0098] According to a fourth aspect of the embodiment of the present application, a driving device 500 is provided, referring to Figure 5 As shown in the block diagram, the driving device 500 includes the control device 400 provided by the third aspect.
[0099] According to a fifth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the signal sensing method as described in the first aspect is implemented.
[0100] According to a sixth aspect of an embodiment of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the signal sensing method as described in the first aspect is implemented.
[0101] The driving device 500 / computer storage medium / computer program product embodiment in the embodiment of the present application has been described in detail in the aforementioned signal sensing method embodiment, so its related content and beneficial effects can be understood with reference to the above-mentioned method embodiment and will not be repeated here.
[0102] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.
[0103] The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as a computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a special-purpose processor or programmable or special-purpose hardware (such as an ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a special-purpose computer for executing the method shown here.
[0104] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.
[0105] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.
Claims
1. A signal sensing method, characterized in that: include: Through the window glass of the adjacent preceding vehicle traveling in the same direction as the own vehicle, a braking signal image of a target vehicle traveling in front of the adjacent preceding vehicle is collected; performing semantic analysis on the brake signal image to obtain state information of the brake signal corresponding to the brake signal image; The driving state of the target vehicle is determined according to the state information.
2. The method according to claim 1, characterized in that The step of collecting a brake signal image of a target vehicle traveling in front of the adjacent preceding vehicle through a window glass of the adjacent preceding vehicle traveling in the same direction as the vehicle includes: Through the front window glass and / or rear window glass of the adjacent preceding vehicle traveling in the same direction as the own vehicle, the brake signal image projected on the front window glass and / or rear window glass by the target vehicle traveling in front of the adjacent preceding vehicle is collected.
3. The method according to claim 1, characterized in that The performing semantic analysis on the brake signal image to obtain state information of the brake signal corresponding to the brake signal image includes: Based on the brake signal image, target detection is performed on the brake lights of the target vehicle, and according to the result of the target detection, state information of the brake lights in the brake signal image is obtained.
4. The method according to claim 3, characterized in that The performing target detection on the brake light of the target vehicle based on the brake signal image includes: Based on the brake signal image, a brake light that meets predetermined conditions is detected from the brake signal image, wherein the predetermined conditions include at least one of the following: a distance from the ground is within a predetermined distance range, a shape is a long strip and an angle with the ground is within a predetermined angle range, a color when lit is a predetermined color, and the light is on when the target vehicle is in a braking state and is off when the target vehicle is in a non-braking state.
5. The method according to any one of claims 1 to 4, characterized in that The brake signal image includes: a first brake signal image frame collected at the current moment, and at least one second brake signal image frame collected within a preset time period before the current moment; The performing semantic analysis on the brake signal image includes: Based on a first state detection result of the brake light of the first brake signal image frame and a second state detection result of the brake light of the at least one second brake signal image frame, it is determined that the state of the brake light has changed, and then a semantic analysis is performed on the first brake signal image frame and the at least one second brake signal image frame.
6. The method according to claim 5, characterized in that The step of determining that the state of the brake light has changed according to a first state detection result of the brake light of the first brake signal image frame and a second state detection result of the brake light of the at least one second brake signal image frame comprises: Performing grayscale processing on the first brake signal image frame and the at least one second brake signal image frame to obtain respective corresponding grayscale images; If the difference between the grayscale value of the brake light in the grayscale image corresponding to the first brake signal image frame and the grayscale value of the brake light in the grayscale image corresponding to the at least one second brake signal image frame meets a predetermined condition, it is determined that the state of the brake light has changed.
7. The method according to any one of claims 1 to 4, characterized in that The method further comprises: According to the state information, determining that the target vehicle enters a braking state; According to the determined braking state, a corresponding driving strategy is determined for the vehicle.
8. The method according to claim 7, characterized in that Determining a corresponding driving strategy for the vehicle according to the determined braking state includes: A corresponding driving strategy is determined for the vehicle according to the determined braking state and the driving information of the vehicle, the adjacent preceding vehicle and the target vehicle.
9. The method according to claim 8, characterized in that Determining a corresponding driving strategy for the vehicle based on the determined braking state and driving information of the vehicle, the adjacent preceding vehicle, and the target vehicle includes: According to the determined braking state, and the driving information of the own vehicle, the adjacent front vehicle and the target vehicle, it is determined whether the own vehicle and the adjacent front vehicle will collide within a predetermined time. If so, the own vehicle is controlled to decelerate for braking.
10. The method according to claim 7, characterized in that The driving information of the self-vehicle, the adjacent preceding vehicle and the target vehicle includes: At least one of the traveling speed of the own vehicle, the traveling speed of the adjacent preceding vehicle, the traveling speed of the target vehicle, and the distance between the own vehicle and the adjacent preceding vehicle.
11. A signal sensing device, characterized in that: include: The acquisition module is used to acquire the braking signal image of the target vehicle traveling in front of the adjacent preceding vehicle through the window glass of the adjacent preceding vehicle traveling in the same direction as the vehicle; an analysis module, configured to perform semantic analysis on the brake signal image to obtain state information of the brake signal corresponding to the brake signal image; A determination module is used to determine the driving state of the target vehicle according to the state information.
12. A control device, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is configured to execute the method according to any one of claims 1 to 10 by running the computer program stored in the memory.
13. A driving device, characterized in that: include: A control device as claimed in claim 12.
14. A computer storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.