Method, apparatus, device, storage medium and program product for identifying a signal light

Abstract

According to embodiments of the present disclosure, a method, an apparatus, a device, a storage medium and a program product for identifying a signal light are provided. The method comprises: adjusting luminance information of an input image associated with the signal light to obtain a first intermediate image; processing the first intermediate image by using a detection unit to determine a target region of the signal light; adjusting color information of a second intermediate image associated with the target region to obtain a third intermediate image; processing the third intermediate image by using a classification unit to generate classification information of the signal light. In this way, embodiments of the present disclosure can accurately classify the signal light, so that the identification of the signal light is more accurate. Furthermore, by using such more accurate classification information of the signal light, embodiments of the present disclosure can improve the safety and reliability of the vehicle.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods, apparatus, devices, computer-readable storage media, and computer program products for identifying traffic lights. Background Technology

[0002] Autonomous driving is a technology that uses computers to replace or assist human drivers in perceiving the vehicle's surroundings, planning its trajectory, and controlling it to reach its destination. In autonomous driving, signal light (e.g., traffic light) perception is one of the key aspects of safe vehicle operation. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for identifying traffic lights is provided. The method includes: adjusting brightness information of an input image associated with a traffic light to obtain a first intermediate image; processing the first intermediate image using a detection unit to determine a target region of the traffic light; adjusting color information of a second intermediate image associated with the target region to obtain a third intermediate image; and processing the third intermediate image using a classification unit to generate classification information for the traffic light.

[0004] In a second aspect of this disclosure, an apparatus for identifying traffic lights is provided. The apparatus includes: a first adjustment module configured to adjust brightness information of an input image associated with a traffic light to obtain a first intermediate image; a first processing module configured to process the first intermediate image using a detection unit to determine a target area of ​​the traffic light; a second adjustment module configured to adjust color information of a second intermediate image associated with the target area to obtain a third intermediate image; and a second processing module configured to process the third intermediate image using a classification unit to generate classification information for the traffic light.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product includes computer-executable instructions that, when executed by a processor, implement the method of the first aspect.

[0008] It should be understood that the content described in this summary section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0011] Figure 2 A schematic structural block diagram of an identification traffic light according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A schematic diagram of an example process of detection processing according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A schematic diagram illustrating an example process of classification processing according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A schematic diagram illustrating an example process for identifying traffic lights according to some embodiments of the present disclosure is shown;

[0015] Figure 6 A schematic structural block diagram of an example device for identifying traffic lights according to certain embodiments of the present disclosure is shown; and

[0016] Figure 7 A block diagram of an apparatus capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0019] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0020] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0021] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0022] As briefly mentioned earlier, traffic lights, as an important component of the traffic environment, play a significant role in instructing vehicles to continue driving, stop, or make other decisions. Accurate and timely recognition of traffic lights is crucial for ensuring the safe operation of autonomous vehicles in the traffic environment.

[0023] However, due to the complex and ever-changing environment, the information about traffic lights contained in the images collected by the vehicle is inaccurate, resulting in low accuracy in traffic light recognition, which poses a significant safety hazard to autonomous driving.

[0024] Based on this, embodiments of the present disclosure propose a scheme for identifying traffic lights. According to various embodiments of the present disclosure, the brightness information of an input image associated with a traffic light can be adjusted to obtain a first intermediate image. Further, a detection unit can be used to process the first intermediate image to determine the target area of ​​the traffic light; further, the color information of a second intermediate image associated with the target area can be adjusted to obtain a third intermediate image. Additionally, a classification unit can be used to process the third intermediate image to generate classification information for the traffic light.

[0025] In this way, embodiments of the present disclosure can adjust the brightness of the input image, ensuring accurate traffic light recognition even in environments with strong light, backlight, or low light. Furthermore, embodiments of the present disclosure determine the target area of ​​the traffic light from the first intermediate image, thereby removing information in the image that interferes with traffic light recognition and further improving the accuracy of traffic light recognition. Even further, embodiments of the present disclosure can adjust the color information of the second intermediate image associated with the target area, avoiding color recognition anomalies caused by factors such as the color temperature of the sensor in the second intermediate image, thereby improving the accuracy of the traffic light classification information generated based on such a second intermediate image.

[0026] Therefore, the embodiments of this disclosure can accurately classify traffic lights, making traffic light identification more accurate. Furthermore, by utilizing such more accurate traffic light classification information, the embodiments of this disclosure can improve vehicle safety and reliability.

[0027] Example Environment

[0028] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. As shown, environment 100 may include vehicle 110. Vehicle 110 may be an autonomous vehicle, that is, a vehicle with autonomous driving capability (or driverless capability), also known as a driverless car, autonomous driving vehicle, etc.

[0029] In some scenarios, vehicle 110 can be assigned to provide travel services to users. For example, users can obtain travel services provided by vehicle 110 through a travel application. In some scenarios, vehicle 110 may also be called a driverless taxi or robotaxi. During the process of vehicle 110 providing travel services to users, vehicle 110 may be equipped with a safety operator. The safety operator can, for example, take over vehicle 110 in case of an emergency. Alternatively, vehicle 110 may also be in an unmanned state.

[0030] During the operation of vehicle 110, vehicle 110 can collect information from the environment. For example, sensors deployed in vehicle 110 can generate a perceived image 121 indicating the surrounding environment based on the information collected. In some scenarios, vehicle 110 can also be equipped with one or more display devices inside the vehicle to provide human-machine interaction functions.

[0031] In some scenarios, electronic device 130 can process the perceived image 121 to obtain classification information 141 of the traffic lights in the traffic light panel. Such classification information 141 includes, but is not limited to, the identification signals in the traffic lights (e.g., straight, left turn, right turn, etc.), the corresponding colors of the traffic lights, the numbers in the traffic lights, etc. Such electronic device 130 may include a terminal and / or a server.

[0032] Such a terminal can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 130 may also support any type of user-facing interface (such as "wearable" circuitry).

[0033] Such servers can be standalone physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Servers can include, for example, computing systems / servers such as mainframes, edge computing nodes, and computing devices in cloud environments, etc.

[0034] The electronic device 130 can be installed in the vehicle 110, or deployed in any electronic unit of the vehicle 110 (such as sensors, control units, etc.), or it can exist independently of the vehicle 110.

[0035] When the electronic device 130 and the vehicle 110 exist independently, a communication connection can be established between the vehicle 110 and the electronic device 130. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth connections, mobile network connections, Universal Serial Bus connections, and Wi-Fi connections; the embodiments of this disclosure are not limited in this respect. Based on this, the vehicle 110 and the electronic device 130 can achieve signaling interaction through their communication connection.

[0036] It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0037] The following will be referenced Figure 2 This document describes an example process for identifying traffic lights according to some embodiments of the present disclosure. Figure 2 A schematic structural block diagram of an identification traffic light according to some embodiments of the present disclosure is shown. Figure 2 The structure 200 shown can be implemented at the electronic device 130. See below for reference. Figure 1 Describe structure 200.

[0038] like Figure 2 As shown, the following example illustrates how electronic device 130 obtains classification information 141 of a traffic light from a perceived image 121. Electronic device 130 processes the perceived image 121 using at least the detection unit 210 to obtain a target region 130. Further, electronic device 130 processes an image (a second intermediate image) associated with the target region 130 using at least the classification unit to obtain classification information 141 of the traffic light.

[0039] In some embodiments, the area occupied by the traffic lights may be relatively small in the perceived image 121. Therefore, the electronic device 130 can determine the portion of the perceived image 121 containing the traffic lights as the input image.

[0040] Specifically, the electronic device 130 obtains the input image by cropping (or using other suitable image processing methods) the area where the traffic lights are projected in the map data from the perceived image. The input image may include the traffic lights and environmental information within a preset range around the traffic lights.

[0041] As examples, map data includes, but is not limited to, high-definition maps. Perceived images can be images perceived by the vehicle's sensors, such as images captured by cameras. The area projected by a traffic light can indicate the location information of the traffic light, including but not limited to the three-dimensional location information of the traffic light, the location information of the traffic light's projection, etc.

[0042] As examples, the input image may indicate environmental information including traffic lights. The input image can be obtained from the perceived image 121 described above, or it can be obtained through other suitable means.

[0043] The following will be referenced Figure 3 This document describes an example process for detection processing according to some embodiments of the present disclosure. Figure 3 A schematic diagram of an example process of detection processing according to some embodiments of the present disclosure is shown. Figure 3 The process 300 shown can be implemented at the electronic device 130. The following reference... Figures 1 to 2 To describe process 400.

[0044] As some examples, electronic device 130 can determine input image 311 from perceived image 121.

[0045] In some scenarios, due to factors such as strong light, weak light, and backlighting, the input image 311 may suffer from insufficient lighting, overexposure, or other problems, making it unusable for accurately identifying the classification information of traffic lights. Therefore, the electronic device 130 can adjust the brightness information of the input image 311 to obtain a first intermediate image.

[0046] As examples, brightness information can indicate the brightness or darkness of each pixel in the input image 311. Based on adjustments to the brightness information of the input image 311, the electronic device 130 can acquire a first intermediate image that makes the traffic light more easily identifiable.

[0047] In some embodiments, the electronic device 130 may utilize a neural network model to adjust the brightness information of the input image 311 associated with the traffic light. Specifically, the electronic device 130 may utilize a first model 320 to process first feature information of the input image to generate brightness adjustment parameters. Further, the electronic device 130 may adjust the brightness information of the input image based on the brightness adjustment parameters.

[0048] As examples, the first model 320 may be nested within the detection unit 210, or it may be deployed independently of the detection unit 210 in the electronic device 130. Alternatively, the first model 320 may be deployed in other devices and supported for invocation by the electronic device 130 via an interface. The first model 320 may include at least one convolutional layer and at least one fully connected layer to perform feature extraction and adaptive brightness adjustment on the input image 311.

[0049] Convolutional layers can be used to extract local features (e.g., brightness distribution, contrast, color information, etc.) from the input image 311. The electronic device 130 can progressively aggregate detailed information from the input image through at least one convolutional layer, thereby providing data support for subsequent brightness adjustments.

[0050] Fully connected layers can be used to further process the features extracted by the convolutional layers and map these features to specific brightness adjustment parameters. Using these parameters, the first model 320 can generate a suitable brightness adjustment strategy based on the actual illumination conditions of the input image 311.

[0051] As examples, brightness adjustment parameters include, for instance, the gamma parameter 330. The gamma parameter 330 adjusts the tonal levels of overly dark / overly bright areas of the input image 311 while preserving the details of the input image 311. This brightness adjustment parameter is adaptively calculated by the convolutional and fully connected layers. To ensure fast convergence and avoid extreme values, the gamma parameter 330 can be set within a reasonable range.

[0052] Therefore, the electronic device 130 can use the gamma parameter 330 to apply a gamma transform to the input image 311 to obtain a first intermediate image 341 with more reasonable brightness. For example, the details in the dark areas of the first intermediate image 341 can be clearer, making it easier for the subsequent detection unit 210 to locate the outline of the signal light panel to determine the target area of ​​the signal light.

[0053] Furthermore, the electronic device 130 uses the detection unit 210 to process the first intermediate image 341 to determine the target area of ​​the traffic light.

[0054] As examples, the target area for the traffic light can be the image area occupied by the traffic light in the first intermediate image 341. Based on such a target area, embodiments of this disclosure can avoid interference from information affecting the accuracy of traffic light recognition.

[0055] As some examples, please refer to Figure 3 The detection unit 210 may include at least a backbone network 350, a neck network 360, a head network 370, and a loss network 380.

[0056] The electronic device 130 can further extract higher-level features using the backbone network 350 and pass the features extracted by the backbone network 350 to the neck network 360. The electronic device 130 can use the neck network 360 to combine features of different scales to enhance the robustness of detection. Furthermore, the electronic device 130 uses the head network 370 to locate the target region of the traffic light. Additionally, the electronic device 130 can calculate a loss function through the loss network 380 to adjust parameters, thereby optimizing the localization result of the target region of the traffic light.

[0057] In some embodiments, the electronic device 130 can collaboratively train the first model 320 and the detection unit 210 through an end-to-end training method to synchronously optimize the first model 320 and the detection unit 210. For example, the electronic device 130 can combine the first model 320 and the detection unit 210 into a detection model to train such a detection model.

[0058] In some scenarios, even if the electronic device 130 can determine the target area of ​​the traffic light through the above steps, misclassification may still occur during the traffic light classification stage. For example, a red light may be misidentified as an off light, leading to the serious consequence of vehicle 110 running a red light. Therefore, the embodiments of this disclosure further optimize the classification of traffic lights.

[0059] The following is in conjunction with the appendix Figure 4 The process of classifying traffic lights in the embodiments of this disclosure will be further described. Figure 4 A schematic diagram illustrating an example process of classification processing according to some embodiments of the present disclosure is shown. Figure 4 The process 400 shown can be implemented at electronic device 130, as described below. Figures 1 to 2 To describe process 400.

[0060] To avoid deviation from the target area of ​​the traffic light, the electronic device 130 can acquire a second intermediate image 421 associated with the target area 411 of the traffic light from the perceived image 121. The image area corresponding to the second intermediate image 421 includes the target area 411 and a preset range surrounding the target area. For example, the electronic device 130 can acquire the second intermediate image 421 associated with the target area 411 by expanding the target area 411.

[0061] Furthermore, the electronic device 130 adjusts the color information of the second intermediate image 421 associated with the target region 411 to obtain a third intermediate image.

[0062] As examples, color information includes, but is not limited to, pixel values, color channels, etc. The electronic device 130 can input the second intermediate image 421 into the normalization unit 430, thereby normalizing the pixel values ​​of the second intermediate image 421 using the normalization unit 430. This results in a more consistent pixel value distribution and improves the performance stability of traffic light recognition in different scenarios.

[0063] In some embodiments, the electronic device 130 may perform normalization processing on each color channel of the second intermediate image 421 to ensure that the contrast and brightness of each channel are reasonably corrected and to avoid overall color difference. Specifically, the electronic device 130 acquires multiple sets of pixel values ​​corresponding to multiple color channels of the second intermediate image; based on the distribution information of each set of pixel values, it performs normalization processing on each set of pixel values ​​to obtain the third intermediate image.

[0064] Furthermore, the electronic device 130 uses a classification unit to process the third intermediate image to generate classification information for the traffic lights.

[0065] As examples, the classification unit may include, but is not limited to, a feature extraction network 440, a feature aggregation network 450, and a multi-task head network 460. The feature extraction network 440 may include, for example, an 18-layer residual network (ResNet-18 network), and the electronic device 130 may input a third intermediate image into the feature extraction network 440 to extract features from the third intermediate image. The feature aggregation network 450 may include, for example, a feature pyramid network (UFPN), and the electronic device 130 may further aggregate the features from the third intermediate image to improve detection and classification performance. Furthermore, the electronic device 130 may utilize the multi-task head network 460 to simultaneously perform detection and classification tasks. The multi-task head network 460 may detect the color of traffic lights, the category of traffic lights, the color of digital lights, the numerical value of digital lights, etc.

[0066] Therefore, electronic device 130 can generate classification information for traffic lights.

[0067] In some embodiments, the electronic device 130 can collaboratively train the normalization unit 430 and the classification unit 230 through an end-to-end training method to simultaneously optimize the normalization unit 430 and the classification unit 230. For example, the electronic device 130 can combine the normalization unit 430 and the classification unit 230 into a classification model to train such a classification model.

[0068] In some embodiments, such a detection unit (or detection model) can be trained independently of a classification unit (or classification model). Therefore, the embodiments of this disclosure overcome the drawbacks of increased training difficulty and failure caused by cascading multiple filters. While improving the stability of traffic light recognition, the embodiments of this disclosure maintain the same training complexity. Furthermore, by splitting the tasks of traffic light target area detection and traffic light classification, the embodiments of this disclosure reduce the complexity of each task, thereby improving the overall speed and accuracy of the traffic light recognition process.

[0069] Based on this approach, embodiments of this disclosure can adjust the brightness of the input image, ensuring accurate traffic light recognition even in environments with strong light, backlight, or low light. Furthermore, embodiments of this disclosure determine the target area of ​​the traffic light from the first intermediate image, thereby removing information in the image that interferes with traffic light recognition and further improving the accuracy of traffic light recognition. Even further, embodiments of this disclosure can adjust the color information of the second intermediate image associated with the target area, avoiding color recognition anomalies caused by factors such as the sensor's color temperature in the second intermediate image, thereby improving the accuracy of the traffic light classification information generated based on such a second intermediate image.

[0070] Therefore, the embodiments of this disclosure can accurately classify traffic lights, making traffic light identification more accurate. Furthermore, by utilizing such more accurate traffic light classification information, the embodiments of this disclosure can improve vehicle safety and reliability.

[0071] Example process

[0072] Figure 5 A flowchart of an example process 500 for identifying traffic lights according to some embodiments of the present disclosure is shown. Process 500 can be implemented at electronic device 130. Reference is made below. Figure 1 Describe the process 500.

[0073] like Figure 5 As shown, at box 510, electronic device 130 adjusts the brightness information of the input image associated with the traffic light to obtain a first intermediate image.

[0074] In frame 520, electronic device 130 uses a detection unit to process the first intermediate image to determine the target area of ​​the traffic light.

[0075] In frame 530, electronic device 130 adjusts the color information of a second intermediate image associated with the target area to obtain a third intermediate image.

[0076] In frame 540, electronic device 130 uses a classification unit to process the third intermediate image to generate classification information for the traffic lights.

[0077] In some embodiments, process 500 further includes: obtaining location information of traffic lights from map data; and determining an input image that matches the location information from the perceived image based on the location information.

[0078] In some embodiments, adjusting the brightness information of an input image associated with a traffic light includes: processing first feature information of the input image using a first model to generate brightness adjustment parameters; and adjusting the brightness information of the input image based on the brightness adjustment parameters.

[0079] In some embodiments, adjusting the brightness information of the input image based on the brightness adjustment parameters includes: applying a gamma transform to the input image based on the brightness adjustment parameters to obtain a first intermediate image.

[0080] In some embodiments, process 500 further includes: acquiring a second intermediate image associated with a target region from a perceived image, wherein the image region corresponding to the second intermediate image includes the target region and a preset range surrounding the target region.

[0081] In some embodiments, adjusting the color information of the second intermediate image associated with the target region includes: obtaining multiple sets of pixel values ​​corresponding to the second intermediate image and multiple color channels; and normalizing each set of pixel values ​​based on the distribution information of each set of pixel values ​​to obtain a third intermediate image.

[0082] In some embodiments, the classification information indicates at least one of the following: the color corresponding to the traffic light; the number in the traffic light.

[0083] In some embodiments, the detection unit and the classification unit are trained independently.

[0084] Example devices and equipment

[0085] Figure 6 A schematic structural block diagram of a traffic light identification device 600 according to certain embodiments of the present disclosure is shown. The device 600 may be implemented as or included in an electronic device 130. The various modules / components in the device 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0086] As shown in the figure, the device 600 includes a first adjustment module 610 configured to adjust the brightness information of an input image associated with a traffic light to obtain a first intermediate image; a first processing module 320 configured to process the first intermediate image using a detection unit to determine a target area of ​​the traffic light; a second adjustment module 630 configured to adjust the color information of a second intermediate image associated with the target area to obtain a third intermediate image; and a second processing module 640 configured to process the third intermediate image using a classification unit to generate classification information for the traffic light.

[0087] In some embodiments, the apparatus 600 further includes a determining module configured to: acquire location information of traffic lights from map data; and determine an input image that matches the location information from a perceived image based on the location information.

[0088] In some embodiments, the first adjustment module 610 is further configured to: adjust the brightness information of an input image associated with a traffic light by: processing first feature information of the input image using a first model to generate brightness adjustment parameters; and adjusting the brightness information of the input image based on the brightness adjustment parameters.

[0089] In some embodiments, the first adjustment module 610 is further configured to apply a gamma transform to the input image based on brightness adjustment parameters to obtain a first intermediate image.

[0090] In some embodiments, the apparatus 600 further includes an acquisition module configured to acquire a second intermediate image associated with a target region from a perceived image, wherein the image region corresponding to the second intermediate image includes the target region and a preset range surrounding the target region.

[0091] In some embodiments, the second adjustment module 630 is further configured to: obtain multiple sets of pixel values ​​corresponding to the second intermediate image and multiple color channels; and perform normalization processing on each set of pixel values ​​based on the distribution information of each set of pixel values ​​to obtain a third intermediate image.

[0092] In some embodiments, the classification information indicates at least one of the following: the color corresponding to the traffic light; the number in the traffic light.

[0093] In some embodiments, the detection unit and the classification unit are trained independently.

[0094] Figure 7 A block diagram is shown illustrating a computing device 700 in which one or more embodiments of the present disclosure may be implemented. It should be understood that... Figure 7 The computing device 700 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 7 The computing device 700 shown can be used to implement Figure 1 130 electronic devices.

[0095] like Figure 7 As shown, computing device 700 is in the form of a general-purpose computing device. Components of computing device 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage devices 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processing unit 710 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of computing device 700.

[0096] Computing device 700 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to computing device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 720 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 730 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data (e.g., training data for training) and can be accessed within computing device 700.

[0097] The computing device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 7 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 720 may include computer program product 725 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0098] The communication unit 740 enables communication with other computing devices via a communication medium. Additionally, the components of the computing device 700 can function as a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the computing device 700 can operate in a networked environment using logical connections to one or more other servers, networked personal computers (PCs), or another network node.

[0099] Input device 750 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 760 can be one or more output devices, such as a monitor, speaker, printer, etc. Computing device 700 can also communicate as needed with one or more external devices (not shown) via communication unit 740. These external devices, such as storage devices, display devices, etc., can communicate with one or more devices that enable user interaction with computing device 700, or with any device (e.g., network card, modem, etc.) that enables computing device 700 to communicate with one or more other computing devices. Such communication can be performed via input / output (I / O) interface (not shown).

[0100] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0101] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0102] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0103] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0104] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0105] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for identifying traffic lights, comprising: Adjust the brightness information of the input image associated with the traffic light to obtain a first intermediate image; The first intermediate image is processed using a detection unit to determine the target area of ​​the traffic light; Adjust the color information of the second intermediate image associated with the target region to obtain the third intermediate image; as well as The third intermediate image is processed using a classification unit to generate classification information for the traffic light.

2. The method according to claim 1, further comprising: The location information of the traffic lights is obtained from map data; as well as Based on the location information, the input image matching the location information is determined from the perceived image.

3. The method of claim 1, wherein adjusting the brightness information of the input image associated with the traffic light comprises: The first feature information of the input image is processed using the first model to generate brightness adjustment parameters; as well as The brightness information of the input image is adjusted based on the brightness adjustment parameters.

4. The method according to claim 3, wherein adjusting the brightness information of the input image based on the brightness adjustment parameters includes: Based on the brightness adjustment parameters, a gamma transform is applied to the input image to obtain the first intermediate image.

5. The method according to claim 1, further comprising: A second intermediate image associated with the target region is obtained from the perceived image, wherein the image region corresponding to the second intermediate image includes the target region and a preset range surrounding the target region.

6. The method of claim 1, wherein adjusting the color information of the second intermediate image associated with the target region comprises: Obtain multiple sets of pixel values ​​corresponding to the second intermediate image and multiple color channels; Based on the distribution information of each group of pixel values, the pixel values ​​of each group are normalized to obtain the third intermediate image.

7. The method of claim 1, wherein the classification information indicates at least one of the following: The color corresponding to the signal light; The numbers in the traffic lights.

8. The method according to claim 1, wherein the detection unit and the classification unit are trained independently.

9. A device for identifying traffic lights, the device comprising: The first adjustment module is configured to adjust the brightness information of the input image associated with the traffic light to obtain a first intermediate image; A first processing module is configured to process the first intermediate image using a detection unit to determine the target area of ​​the traffic light; The second adjustment module is configured to adjust the color information of a second intermediate image associated with the target region to obtain a third intermediate image; as well as The second processing module is configured to process the third intermediate image using a classification unit to generate classification information for the traffic light.

10. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 8.

12. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 8.

Images