Vehicle perception confidence coefficient determination method and device, equipment and storage medium

Abstract

The invention discloses a vehicle perception confidence coefficient determination method and device, equipment and a storage medium. The method comprises the following steps: determining an initial confidence coefficient of at least one target object in a target image according to the target image of a current frame obtained by a target vehicle through front-end sensing; determining candidate confidence of the target object according to the initial confidence and a historical confidence set of the target object; obtaining distance measurement data, speed measurement data and a current state of a target object; and under the condition that the distance measurement data, the speed measurement data and the current state meet the confidence degree adjustment condition, the candidate confidence degree is adjusted to obtain the target confidence degree of the target object. According to the technical scheme, the confidence is updated by introducing the historical confidence set, and the candidate confidence is adjusted according to the speed measurement data, the distance measurement data and the current state adaptability of the target object, so that the reliability of the target confidence can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of visual perception technology, in particular to the field of autonomous driving technology, and specifically to a method, device, equipment and storage medium for determining confidence in vehicle perception. Background Art

[0002] The stability of functions such as adaptive cruise control and autonomous emergency braking in autonomous driving is very important. After the target distance and speed measurement information obtained from the front-end perception is integrated and screened, the regulation and control can plan and control the vehicle functions according to the target state. In this process, the target distance and speed measurement information provided by the front-end perception is very important.

[0003] For example, in normal weather, lighting, and clear target scenes, the distance and speed measurement of the target output by the front-end perception is relatively stable, and the regulation and control can stably complete functions such as adaptive cruise control and autonomous emergency braking. However, if the scene is restricted, such as overexposure at the entrance and exit of the tunnel, rainy and foggy weather, night halos, occlusions and other extreme scenes, the stability of the target by the front-end perception has certain limitations, which will directly affect the screening misjudgment of the back-end fusion and the false triggering of the function. Summary of the invention

[0004] The present application provides a method, device, equipment and storage medium for determining confidence of vehicle perception to improve the reliability of target confidence.

[0005] According to one aspect of the present application, a method for determining confidence in vehicle perception is provided, the method comprising:

[0006] Determine, according to a target image of a current frame acquired by the target vehicle through front-end perception, an initial confidence of at least one target object in the target image;

[0007] Determining a candidate confidence level of the target object based on the initial confidence level and a historical confidence level set of the target object;

[0008] Acquire the distance measurement data, speed measurement data and current state of the target object; and when the distance measurement data, the speed measurement data and the current state satisfy the confidence adjustment condition, adjust the candidate confidence to obtain the target confidence of the target object.

[0009] According to another aspect of the present application, a vehicle perception confidence determination device is provided, the device comprising:

[0010] A first confidence determination module, used to determine an initial confidence of at least one target object in a target image according to a target image of a current frame acquired by the target vehicle through front-end perception;

[0011] a second confidence determination module, configured to determine a candidate confidence of the target object based on the initial confidence and a historical confidence set of the target object;

[0012] The confidence adjustment module is used to obtain the distance measurement data, speed measurement data and current state of the target object; and when the distance measurement data, the speed measurement data and the current state meet the confidence adjustment condition, adjust the candidate confidence to obtain the target confidence of the target object.

[0013] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0014] one or more processors;

[0015] A memory for storing one or more programs;

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement any one of the vehicle perception confidence determination methods provided in the embodiments of the present application.

[0017] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, any one of the vehicle perception confidence determination methods provided in the embodiments of the present application is implemented.

[0018] The present application determines the initial confidence of at least one target object in the target image according to the target image of the current frame acquired by the target vehicle through front-end perception; determines the candidate confidence of the target object according to the initial confidence and the historical confidence set of the target object; obtains the distance measurement data, speed measurement data and current state of the target object; and adjusts the candidate confidence when the distance measurement data, speed measurement data and current state meet the confidence adjustment conditions to obtain the target confidence of the target object. The above technical solution can improve the reliability of the target confidence by introducing the historical confidence set to update the confidence and adaptively adjusting the candidate confidence according to the speed measurement data, distance measurement data and current state of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of a method for determining confidence in vehicle perception provided according to Embodiment 1 of the present application;

[0020] Figure 2 is a flow chart of a method for determining confidence in vehicle perception provided according to Embodiment 2 of the present application;

[0021] Figure 3 It is a structural schematic diagram of a vehicle perception confidence determination device provided according to Embodiment 3 of the present application;

[0022] Figure 4 It is a structural schematic diagram of an electronic device that implements the vehicle perception confidence determination method of an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution 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, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] In addition, it should be noted that in the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of relevant data such as target images and initial confidence levels are in compliance with the relevant laws and regulations and do not violate public order and good morals.

[0026] Embodiment 1

[0027] Figure 1 This is a flow chart of a method for determining the confidence of vehicle perception provided in accordance with the first embodiment of the present application. This embodiment can be applied to the case where the confidence of object information acquired by the vehicle through the front end during the autonomous driving process is determined. It can be performed by a vehicle perception confidence determination device. The vehicle perception confidence determination device can be implemented in the form of hardware and / or software. The vehicle perception confidence determination device can be configured in a computer device, such as a server. Figure 1 As shown, the method includes:

[0028] S110. Determine an initial confidence level of at least one target object in the target image according to a target image of a current frame acquired by the target vehicle through front-end perception.

[0029] Among them, the target vehicle refers to the vehicle that is currently in autonomous driving and needs to determine the confidence of the front-end perception. The front end refers to the front sensor system of the target vehicle, including radar, camera, and lidar, etc. These sensors are used to collect distance and speed information about the target object. The target image refers to the image of the current frame obtained from the front-end perception system (such as a camera), which is used to detect and analyze the target object. The target object refers to the object of interest or recognition in the image, such as other vehicles, pedestrians, or obstacles, which require further processing and analysis. The initial confidence refers to the confidence or reliability assessment of the existence and correct identification of the target object when it is first detected. It is an indicator to measure the accuracy of target recognition.

[0030] Optionally, based on a visual perception obstacle detection model, an initial confidence level of at least one target object in the target image is determined according to a target image of a current frame acquired by the target vehicle through front-end perception.

[0031] Among them, visual perception obstacle detection models are computer vision models used to identify and classify obstacles from images. These models use machine learning algorithms to analyze images acquired by front-end cameras to detect and locate target objects, such as other vehicles, pedestrians, or obstacles. Initial confidence refers to the model's confidence or reliability assessment of the recognition results.

[0032] S120 : Determine a candidate confidence level of the target object according to the initial confidence level and the historical confidence level set of the target object.

[0033] The historical confidence set refers to the set of records of the confidence of the target object detection results in a period of time in history that is continuous with the current frame, specifically the set of historical confidences corresponding to the N frames before the current frame; N is a positive integer greater than 1. The candidate confidence is to update or predict the confidence of the target object based on the initial confidence and the historical confidence set.

[0034] Optionally, the historical confidence set of the target object is averaged to obtain the historical average confidence of the target object; the historical average confidence and the initial confidence are weighted averaged to obtain the candidate confidence of the target object.

[0035] Among them, the historical average confidence refers to the average of the confidence records of the target object in the past period of time, reflecting the overall recognition reliability of the target object in historical data.

[0036] For example, taking the number of historical frames as 10 frames, the candidate confidence can be calculated by the following formula:

[0037]

[0038] conf fusion =0.5*confhis +0.5*conf model ;

[0039] Among them, conf his Refers to the historical average confidence. conf frame It refers to the historical confidence corresponding to the historical frame within a period of time continuous with the current frame. model Refers to the initial confidence. conf fusion refers to the candidate confidence.

[0040] Furthermore, after determining the candidate confidences, the number of historical existence frames in the historical confidence set of the target object can also be determined; based on the correspondence between the number of existence frames and the confidence update coefficient, the first candidate confidence update coefficient is determined according to the number of historical existence frames; the candidate confidence is updated using the first candidate confidence update coefficient to obtain the candidate confidence after the first update.

[0041] Among them, the historical existence frame number refers to the number of valid detection frames of the target object in its historical confidence set, that is, the number of frames that have been successfully detected and have recorded confidence, which reflects the detection stability and continuity of the target object. The first candidate confidence update coefficient refers to the coefficient calculated based on the correspondence between the historical existence frame number and the confidence update coefficient. This coefficient is used to adjust the candidate confidence to more accurately reflect the performance of the target object in the historical record. The candidate confidence after the first update refers to the value obtained by adjusting the candidate confidence by applying the first candidate confidence update coefficient. This updated confidence integrates the influence of the historical existence frame number and provides a more reliable assessment of the state of the target object.

[0042] Exemplarily, the updated candidate confidence can be determined by the following formula:

[0043]

[0044] Among them, conf tmp1 Refers to the updated candidate confidence. conf fusion Refers to the candidate confidence before the update. 1.3, 1.1, and 0.9 are the first candidate confidence update coefficients. Hits refers to the number of historical frames.

[0045] Furthermore, after obtaining the updated candidate confidence, the candidate confidence can be further updated according to the frame loss situation in the historical confidence set, specifically: if there is frame loss in the process of determining the historical confidence set, the target frame loss number of the target object is determined; based on the correspondence between the number of frame losses and the confidence update coefficient, the second candidate confidence update coefficient is determined according to the target frame loss number; the second candidate confidence update coefficient is used to update the candidate confidence to obtain the candidate confidence after the second update.

[0046] Among them, the target frame loss number refers to the number of frames lost due to some reasons (such as system failure or sensor problem) in the process of the historical confidence set of the target object, which reflects the frequency of the target object not being successfully detected in the historical record. The second candidate confidence update coefficient refers to a coefficient determined according to the corresponding relationship between the target frame loss number and the confidence update coefficient. This coefficient is used to adjust the candidate confidence to take into account the detection discontinuity caused by frame loss. The updated candidate confidence refers to the value obtained by adjusting the candidate confidence after the first update by applying the second candidate confidence update coefficient, which can more accurately reflect the current state of the target object and take into account the impact of frame loss in historical data.

[0047] Exemplarily, the candidate confidence after the second update can be obtained by the following formula:

[0048]

[0049] Among them, conf tmp2 Refers to the candidate confidence after the second update. conf tmp1 Refers to the candidate confidence after the first update. 0.95, 0.9, 0.8 refer to the second candidate confidence update coefficient. drop refers to the target number of dropped frames.

[0050] S130, obtaining distance measurement data, speed measurement data and current state of the target object; and when the distance measurement data, speed measurement data and current state meet the confidence adjustment condition, adjusting the candidate confidence to obtain the target confidence of the target object.

[0051] Among them, ranging data refers to the information about the distance between the target object and the measuring device. These data usually come from sensors or ranging systems, and provide information about the position or distance of the target object in space. Speed ​​data refers to information about the speed of the target object. These data can be obtained through speed sensors, radars, or other measuring tools, and provide information about the rate at which the target object moves. Current state refers to the state information of the target object at a specific point in time. Target confidence refers to the value obtained by adjusting the candidate confidence, which combines information such as ranging data, speed data, and current state, and indicates the final degree of confidence in the state of the target object, and is used for further decision-making or analysis. The confidence adjustment conditions are artificially pre-set through a large number of experiments or empirical values.

[0052] The embodiment of the present application determines the initial confidence of at least one target object in the target image according to the target image of the current frame acquired by the target vehicle through front-end perception; determines the candidate confidence of the target object according to the initial confidence and the historical confidence set of the target object; obtains the distance measurement data, speed measurement data and current state of the target object; and adjusts the candidate confidence when the distance measurement data, speed measurement data and current state meet the confidence adjustment conditions to obtain the target confidence of the target object. The above technical scheme can improve the reliability of the target confidence by introducing the historical confidence set to update the confidence and adaptively adjusting the candidate confidence according to the speed measurement data, distance measurement data and current state of the target object.

[0053] Embodiment 2

[0054] Figure 2 It is a flow chart of a method for determining confidence in vehicle perception provided in accordance with the second embodiment of the present application. Based on the technical solutions of the above embodiments, this embodiment refines "when the distance measurement data, speed measurement data and current state meet the confidence adjustment conditions, the candidate confidence is adjusted to obtain the target confidence of the target object" into "determine the measurement influence coefficient of the target object according to the distance measurement data and speed measurement data of the target object; when the measurement influence coefficient meets the confidence adjustment conditions, the candidate confidence is adjusted to obtain the intermediate confidence of the target object; when the current state of the target vehicle meets the confidence adjustment conditions, the intermediate confidence is adjusted to obtain the target confidence of the target object". It should be noted that for the parts not described in detail in the embodiments of the present application, please refer to the relevant statements of other embodiments. Figure 2 As shown, the method includes:

[0055] S210. Determine an initial confidence level of at least one target object in the target image according to a target image of a current frame acquired by the target vehicle through front-end perception.

[0056] S220 : Determine a candidate confidence level of the target object according to the initial confidence level and the historical confidence level set of the target object.

[0057] S230: Acquire distance measurement data, speed measurement data, and current state of the target object, and determine a measurement influence coefficient of the target object according to the distance measurement data and speed measurement data of the target object.

[0058] The measurement influence coefficient refers to the coefficient calculated based on the distance measurement data and speed measurement data of the target object. It indicates the influence of the measurement data on the state assessment of the target object. It is used to adjust or weigh the contribution of different data sources to the final confidence or state estimation to improve the accuracy and reliability of the measurement results.

[0059] Optionally, determining the measurement influence coefficient of the target object based on the ranging data and the speed measurement data of the target object can be performed by respectively calculating the variance of the ranging data and the speed measurement data of the target object to obtain the ranging variance and the speed measurement variance; and determining the measurement influence coefficient of the target object based on the ranging variance, the speed measurement variance and a preset reference value.

[0060] Among them, the distance measurement variance refers to the variance of the distance measurement data of the target object, which indicates the degree of discreteness or range of variation of the distance measurement data in multiple measurements. The larger the variance, the higher the uncertainty or volatility of the distance measurement data. The speed measurement variance refers to the variance of the speed measurement data of the target object, which indicates the degree of discreteness or range of variation of the speed measurement data in multiple measurements. The larger the variance, the higher the uncertainty or volatility of the speed measurement data. The reference value refers to the reference standard used to determine the measurement influence coefficient of the target object. It can be a preset value used to compare with the actual distance measurement variance and speed measurement variance to quantify the impact of these variances on the measurement results of the target object.

[0061] Exemplarily, the measurement influence coefficient can be determined by the following formula:

[0062]

[0063] Where uncertainty refers to the measurement influence coefficient. d 2 Refers to the ranging variance. v 2 It refers to the speed measurement variance.

[0064] S240: When the measured influence coefficient satisfies the confidence adjustment condition, the candidate confidence is adjusted to obtain an intermediate confidence of the target object.

[0065] The intermediate confidence level refers to the confidence level obtained by adjusting the candidate confidence level according to the speed measurement data and the distance measurement data.

[0066] Exemplarily, the intermediate confidence level may be determined by the following formula:

[0067] conf tmp3 =conf tmp2 *0.9,uncertainty∈[0.5,1];

[0068] Among them, conf tmp3 Refers to the intermediate confidence level. conf tmp2 It refers to the candidate confidence after the second update. It should be noted that if the candidate confidence is not updated for the second time, the candidate confidence after the first update is used. Uncertainty refers to the measurement influence coefficient. Uncertainty∈[0.5,1] refers to the confidence adjustment condition.

[0069] S250: When the current state of the target vehicle satisfies the confidence adjustment condition, the intermediate confidence is adjusted to obtain the target confidence of the target object.

[0070] Optionally, when the current state of the target vehicle satisfies the confidence adjustment condition, based on the correspondence between the current state and the confidence adjustment coefficient, the target confidence adjustment coefficient is determined according to the current state; the intermediate confidence is adjusted using the target confidence adjustment coefficient to obtain the target confidence of the target object.

[0071] The confidence adjustment coefficient refers to a coefficient determined according to the current state of the target vehicle when the confidence adjustment conditions are met, and is used to adjust the confidence of the target object. This coefficient is usually determined based on the corresponding relationship between the current state and the confidence adjustment coefficient, reflecting the reliability or accuracy of the actual measurement results. The target confidence adjustment coefficient refers to the confidence adjustment coefficient corresponding to the current state.

[0072] Exemplarily, the intermediate confidence level is adjusted to obtain the target confidence level of the target object, which can be achieved by the following formula:

[0073]

[0074] Among them, conf refers to the target confidence. tmp3 Refers to the intermediate confidence. 0.8 and 0.9 refer to the confidence adjustment coefficients. The occlusion state refers to the situation where part or all of the target object is blocked by other objects, resulting in the inability to fully observe all features of the target object. The truncation state refers to the situation where part of the target object is truncated by the image boundary or field of view, making the target object appear incomplete during detection or observation.

[0075] The embodiment of the present application determines the initial confidence of at least one target object in the target image according to the target image of the current frame acquired by the target vehicle through front-end perception; determines the candidate confidence of the target object according to the initial confidence and the historical confidence set of the target object; obtains the distance measurement data, speed measurement data and current state of the target object; and determines the measurement influence coefficient of the target object according to the distance measurement data and speed measurement data of the target object; when the measurement influence coefficient meets the confidence adjustment condition, adjusts the candidate confidence to obtain the intermediate confidence of the target object; when the current state of the target vehicle meets the confidence adjustment condition, adjusts the intermediate confidence to obtain the target confidence of the target object. The above technical scheme can improve the reliability of the target confidence by introducing the historical confidence set to update the confidence, and adaptively adjusts the candidate confidence according to the speed measurement data, distance measurement data and current state of the target object.

[0076] Embodiment 3

[0077] Figure 3 It is a structural diagram of a vehicle perception confidence determination device provided in accordance with Example 3 of the present application, which can be applicable to situations where confidence is determined for object information acquired by the vehicle through the front end during autonomous driving. The vehicle perception confidence determination device can be implemented in the form of hardware and / or software, and the vehicle perception confidence determination device can be configured in a computer device, such as a server.

[0078] like Figure 3 As shown, the device comprises:

[0079] A first confidence determination module 310, configured to determine an initial confidence of at least one target object in a target image according to a target image of a current frame acquired by the target vehicle through front-end perception;

[0080] A second confidence determination module 320, for determining a candidate confidence of the target object based on the initial confidence and the historical confidence set of the target object;

[0081] The confidence adjustment module 330 is used to obtain the distance measurement data, speed measurement data and current state of the target object; and when the distance measurement data, speed measurement data and current state meet the confidence adjustment conditions, adjust the candidate confidence to obtain the target confidence of the target object.

[0082] The embodiment of the present application determines the initial confidence of at least one target object in the target image according to the target image of the current frame acquired by the target vehicle through front-end perception; determines the candidate confidence of the target object according to the initial confidence and the historical confidence set of the target object; obtains the distance measurement data, speed measurement data and current state of the target object; and adjusts the candidate confidence when the distance measurement data, speed measurement data and current state meet the confidence adjustment conditions to obtain the target confidence of the target object. The above technical scheme can improve the reliability of the target confidence by introducing the historical confidence set to update the confidence and adaptively adjusting the candidate confidence according to the speed measurement data, distance measurement data and current state of the target object.

[0083] Optionally, the confidence adjustment module 330 includes:

[0084] A coefficient determination unit, used to determine a measurement influence coefficient of the target object according to the distance measurement data and the speed measurement data of the target object;

[0085] A first confidence adjustment unit, configured to adjust the candidate confidences to obtain an intermediate confidence of the target object when the measured influence coefficient satisfies the confidence adjustment condition;

[0086] The second confidence adjustment unit is used to adjust the intermediate confidence to obtain the target confidence of the target object when the current state of the target vehicle meets the confidence adjustment condition.

[0087] Optionally, the second confidence adjustment unit is specifically configured to:

[0088] In the case where the current state of the target vehicle satisfies the confidence adjustment condition, based on the corresponding relationship between the current state and the confidence adjustment coefficient, the target confidence adjustment coefficient is determined according to the current state;

[0089] The target confidence adjustment coefficient is used to adjust the intermediate confidence to obtain the target confidence of the target object.

[0090] Optional, coefficient determination unit, specifically used for:

[0091] Calculate the variance of the distance measurement data and the speed measurement data of the target object respectively to obtain the distance measurement variance and the speed measurement variance;

[0092] The measurement influence coefficient of the target object is determined based on the distance measurement variance, speed measurement variance and a preset reference value.

[0093] Optionally, the second confidence determination module 320 is specifically configured to:

[0094] The historical confidence set of the target object is averaged to obtain the historical average confidence of the target object;

[0095] The historical average confidence and the initial confidence are weighted and averaged to obtain the candidate confidence of the target object.

[0096] Optionally, the device further includes: a confidence updating module, configured to:

[0097] Determine the number of historical existence frames in the historical confidence set of the target object;

[0098] Based on the correspondence between the number of existing frames and the confidence update coefficient, a candidate confidence update coefficient is determined according to the number of historical existing frames;

[0099] The candidate confidence is updated using the candidate confidence update coefficient to obtain an updated candidate confidence.

[0100] The vehicle perception confidence determination device provided in the embodiments of the present application can execute the vehicle perception confidence determination method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing each vehicle perception confidence determination method.

[0101] Embodiment 4

[0102] Figure 4 4 is a schematic diagram of the structure of an electronic device 410 that implements the confidence determination method of vehicle perception of an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0103] like Figure 4 As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In RAM413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, ROM412 and RAM413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0104] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0105] The processor 411 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as a confidence determination method for vehicle perception.

[0106] In some embodiments, the vehicle-perceived confidence determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the vehicle-perceived confidence determination method described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured as a vehicle-perceived confidence determination method in any other appropriate manner (e.g., by means of firmware).

[0107] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] Computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable vehicle-perceived confidence determination device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0109] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0110] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0111] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0112] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0113] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0114] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for determining confidence in vehicle perception, characterized in that: include: Determine, according to a target image of a current frame acquired by the target vehicle through front-end perception, an initial confidence of at least one target object in the target image; Determining a candidate confidence level of the target object based on the initial confidence level and a historical confidence level set of the target object; Obtaining distance measurement data, speed measurement data and current state of the target object; And when the distance measurement data, the speed measurement data and the current state satisfy the confidence adjustment condition, the candidate confidence is adjusted to obtain the target confidence of the target object.

2. The method according to claim 1, characterized in that When the distance measurement data, the speed measurement data, and the current state satisfy a confidence adjustment condition, adjusting the candidate confidence to obtain a target confidence of the target object includes: Determining a measurement influence coefficient of the target object according to the distance measurement data and the speed measurement data of the target object; When the measurement influence coefficient satisfies the confidence adjustment condition, adjusting the candidate confidence to obtain the intermediate confidence of the target object; When the current state of the target vehicle satisfies the confidence adjustment condition, the intermediate confidence is adjusted to obtain the target confidence of the target object.

3. The method according to claim 2, characterized in that When the current state of the target vehicle satisfies the confidence adjustment condition, adjusting the intermediate confidence to obtain the target confidence of the target object includes: In the case where the current state of the target vehicle satisfies the confidence adjustment condition, based on the corresponding relationship between the current state and the confidence adjustment coefficient, determining the target confidence adjustment coefficient according to the current state; The target confidence adjustment coefficient is used to adjust the intermediate confidence to obtain the target confidence of the target object.

4. The method according to claim 2, wherein determining the measurement influence coefficient of the target object according to the distance measurement data and the speed measurement data of the target object comprises: Calculating variances of the distance measurement data and the speed measurement data of the target object respectively to obtain distance measurement variance and speed measurement variance; A measurement influence coefficient of the target object is determined according to the distance measurement variance, the speed measurement variance and a preset reference value.

5. The method according to claim 1, characterized in that The step of determining a candidate confidence level of the target object according to the initial confidence level and a historical confidence level set of the target object comprises: averaging the historical confidence sets of the target object to obtain the historical average confidence of the target object; The historical average confidence and the initial confidence are weighted and averaged to obtain a candidate confidence of the target object.

6. The method according to claim 5, characterized in that After weighted averaging the historical average confidence and the initial confidence to obtain the candidate confidence of the target object, the method further includes: Determining the number of historical existence frames in the historical confidence set; Based on the correspondence between the number of existing frames and the confidence update coefficient, a candidate confidence update coefficient is determined according to the number of historical existing frames; The candidate confidence is updated using the candidate confidence update coefficient to obtain an updated candidate confidence.

7. A device for determining confidence in vehicle perception, characterized in that: include: A first confidence determination module, used to determine an initial confidence of at least one target object in a target image according to a target image of a current frame acquired by the target vehicle through front-end perception; a second confidence determination module, configured to determine a candidate confidence of the target object based on the initial confidence and a historical confidence set of the target object; A confidence adjustment module, used to obtain distance measurement data, speed measurement data and current state of the target object; And when the distance measurement data, the speed measurement data and the current state satisfy the confidence adjustment condition, the candidate confidence is adjusted to obtain the target confidence of the target object.

8. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle perception confidence determination method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining the confidence of vehicle perception as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the vehicle-perceived confidence determination method according to any one of claims 1 to 6.

Images