WO2020238699A1 - 信号指示灯的状态检测方法及装置、驾驶控制方法及装置 - Google Patents

信号指示灯的状态检测方法及装置、驾驶控制方法及装置 Download PDF

Info

Publication number
WO2020238699A1
WO2020238699A1 PCT/CN2020/091064 CN2020091064W WO2020238699A1 WO 2020238699 A1 WO2020238699 A1 WO 2020238699A1 CN 2020091064 W CN2020091064 W CN 2020091064W WO 2020238699 A1 WO2020238699 A1 WO 2020238699A1
Authority
WO
WIPO (PCT)
Prior art keywords
cluster
signal indicator
feature value
color
value
Prior art date
Application number
PCT/CN2020/091064
Other languages
English (en)
French (fr)
Inventor
苏思畅
Original Assignee
深圳市商汤科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市商汤科技有限公司 filed Critical 深圳市商汤科技有限公司
Priority to KR1020217011238A priority Critical patent/KR20210058931A/ko
Priority to SG11202102249UA priority patent/SG11202102249UA/en
Priority to JP2021513233A priority patent/JP2021536069A/ja
Publication of WO2020238699A1 publication Critical patent/WO2020238699A1/zh
Priority to US17/159,352 priority patent/US20210150232A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/14—Adaptive cruise control
    • B60W30/143—Speed control
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2431—Multiple classes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects

Definitions

  • the present disclosure relates to the field of computer vision, and in particular to a method and device for detecting the state of a signal indicator, and a driving control method and device.
  • Autonomous driving vehicles need to detect the location and status of the traffic lights in real time under various environmental interference road conditions to make a good path. planning.
  • Self-driving vehicles can use cameras as sensors to collect images of road scenes to detect traffic lights in real time.
  • the embodiment of the present disclosure provides a solution for detecting the status of a signal indicator.
  • a method for detecting the status of a signal indicator which includes:
  • the target area includes at least one signal indicator light with different display states
  • the display state of the signal indicator is determined based on the obtained multiple clusters.
  • the determining the display state of the signal indicator based on the obtained multiple clusters includes:
  • the reference feature value preset in the image acquisition device of the target image and the first feature value corresponding to the cluster center of each cluster determine whether there is a cluster center matching the reference feature value
  • the method further includes:
  • the reference feature value is determined according to the color value of the pixel point in the preset color area in the reference image.
  • the determining the reference feature value according to the color value of the pixel point in the preset color area in the reference image includes:
  • the reference characteristic value includes a reference characteristic value of a red state, a reference characteristic value of a yellow state, and a reference characteristic value of a green state.
  • the method further includes:
  • the display color of the signal indicator in the target area is determined based on the reference feature value matched by the cluster center of the cluster with the largest area.
  • the method further includes:
  • the determining the first feature value of the pixel in the target area includes:
  • the performing clustering processing on the pixels in the target area based on the first feature value to obtain multiple clusters for the pixels includes:
  • the pixel points in the target area are clustered to obtain a preset number of clusters.
  • a driving control method which includes:
  • a control instruction for controlling the smart driving device is generated and output to control the smart driving device.
  • control instruction includes at least one of the following: a speed maintaining control instruction, a speed adjustment control instruction, a direction maintaining control instruction, a direction adjustment control instruction, an early warning prompt control instruction, and a driving mode switching control instruction.
  • a signal indicator light state detection device which includes:
  • the detection module is used to detect the target area in the target image and determine the first characteristic value of the pixel points in the target area, and the target area includes at least one signal indicator with different display states;
  • a clustering module configured to perform clustering processing on pixels in the target area based on the first feature value to obtain multiple clusters for the pixels
  • the determining module is used to determine the display state of the signal indicator based on the obtained multiple clusters.
  • the determining module is configured to determine whether there is a reference feature value preset in the image acquisition device that acquires the target image and the first feature value corresponding to the cluster center of each cluster. The class center matching the reference feature value;
  • the determining module is further configured to determine whether there is a cluster center matching the reference feature value based on the reference feature value and the first feature value corresponding to the cluster center of each cluster. Afterwards, in response to the absence of a cluster center matching the reference characteristic value, it is determined that the signal indicator is in the second state.
  • the device further includes a setting module, which is used to capture a color calibration plate with the image acquisition device to obtain a reference image;
  • the reference feature value is determined according to the color value of the pixel point in the preset color area in the reference image.
  • the setting module is used to:
  • the color value of the pixel in the preset color area is determined as the reference feature value; or, the color value of the pixel in the preset color area is normalized to obtain the reference feature value.
  • the reference characteristic value includes a reference characteristic value of a red state, a reference characteristic value of a yellow state, and a reference characteristic value of a green state.
  • the determining module is further configured to, in the case of determining that the signal indicator is in the first state, based on the pixel points in the cluster corresponding to the cluster center matching the reference feature value, Determine the first area formed by the cluster in the target area;
  • the display color of the signal indicator in the target area is determined based on the reference feature value matched by the cluster center of the cluster with the largest area.
  • the determining module is further configured to perform a calculation on the pixel points in the cluster corresponding to the cluster center matching the reference characteristic value when the signal indicator is determined to be in the first state. Cluster processing to obtain multiple new clusters;
  • the detection module is used to:
  • the clustering module is configured to use a K-means clustering algorithm to cluster pixels in the target area to obtain a preset number of clusters.
  • a driving control device which includes:
  • Image collection equipment which is installed on the intelligent driving equipment and used to collect road images
  • the signal indicator status detection module which is used to execute the signal indicator status detection method of any one of the first aspect of the present disclosure using the road image as a target image to obtain the signal indicator in the road image
  • the control module is used for generating and outputting control instructions for controlling the intelligent driving device according to the display state of the signal indicator in the road image, so as to control the intelligent driving device.
  • control instruction includes at least one of the following: a speed maintaining control instruction, a speed adjustment control instruction, a direction maintaining control instruction, a direction adjustment control instruction, an early warning prompt control instruction, and a driving mode switching control instruction.
  • an electronic device which is characterized by comprising:
  • a memory for storing processor executable instructions
  • the processor is configured to execute any one of the methods in the first aspect or execute any one of the methods in the second aspect.
  • a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the method of any one of the first aspects is implemented, or Perform any of the methods described in the second aspect.
  • a computer program including computer-readable code, when the computer-readable code is executed in an electronic device, a processor in the electronic device executes for realizing the first aspect The method described in any one of the above, or execute the method described in any one of the second aspect.
  • the embodiment of the present disclosure can detect the target area where the signal indicator light is located in the image, and can perform clustering processing on the feature values of the pixel points of the target area where the signal indicator light is located, to obtain multiple clusters, and then according to the multiple clusters
  • the matching situation with the reference characteristic value obtains the display status of the signal indicator.
  • the embodiments of the present disclosure can reduce the probability of using a neural network when detecting the display state on the premise of realizing the accurate detection of the display status of the signal indicator. On the one hand, it reduces the network training procedure, and on the other hand, it can also shorten the signal indicator The detection time of the display status.
  • the display state of traffic lights can also be determined through the embodiments of the present disclosure, thereby improving the safety of automatic driving.
  • Fig. 1 shows a flow chart of a method for detecting the state of a signal indicator according to an embodiment of the present disclosure
  • step S30 shows a flowchart of step S30 in a method for detecting the state of a signal indicator according to an embodiment of the present disclosure
  • Fig. 3 shows a flow chart of obtaining a reference characteristic value in a method for detecting the state of a signal indicator according to an embodiment of the present disclosure
  • step S34 shows a flowchart of step S34 in a method for detecting the state of a signal indicator according to an embodiment of the present disclosure
  • step S34 shows another flowchart of step S34 in a method for detecting the state of a signal indicator according to an embodiment of the present disclosure
  • Fig. 6 shows a schematic structural diagram of a signal indicator light according to an embodiment of the present disclosure
  • Fig. 7 shows a flow chart of a driving control method according to an embodiment of the present disclosure
  • Fig. 8 shows a block diagram of a device for detecting the status of a signal indicator according to an embodiment of the present disclosure
  • Fig. 9 shows a block diagram of a driving control device according to an embodiment of the present disclosure.
  • FIG. 10 shows a block diagram of an electronic device according to an embodiment of the present disclosure
  • Fig. 11 shows another block diagram of an electronic device according to an embodiment of the present disclosure.
  • the embodiment of the present disclosure provides a method for detecting the status of a signal indicator, which can detect the display status of the signal indicator in a target image.
  • the signal indicator status detection method of the embodiment of the present disclosure can be applied to any image acquisition and image processing equipment, such as video cameras, cameras, mobile phones, computers, PADs, smart watches, smart bracelets, or servers. It can also be applied to robots, intelligent driving equipment, blind guide equipment, etc.
  • image collection or image processing can be performed, the method of the embodiments of the present disclosure can be implemented, which is not specifically limited in the present disclosure.
  • the present disclosure can be applied to scenarios such as indicator status recognition and detection. For example, in automatic driving, path planning and navigation can be realized by detecting the status of traffic lights.
  • the present disclosure does not limit specific application scenarios.
  • Fig. 1 shows a flow chart of a method for detecting the state of a signal indicator according to an embodiment of the present disclosure.
  • the state detection method of the signal indicator light may include:
  • S10 Detect a target area in the target image, and determine a first feature value of a pixel point in the target area, the target area includes at least one signal indicator light with different display states;
  • the method for detecting the state of the signal indicator in the embodiment of the present disclosure can realize the detection of the display state of the signal indicator (hereinafter referred to as the target object) in the target image, wherein the target image can be acquired first.
  • the target image is an image collected by an image acquisition device.
  • an image acquisition device such as a driving recorder can be set in an automatic driving or driving assistance device such as a vehicle or an aircraft, and the image acquisition device can be used to collect The driving record image, which may be the target image of the embodiment of the disclosure.
  • the target image may be obtained by sampling from the received video image, or may be the target image received from other devices, which is not specifically limited in the present disclosure.
  • step S10 may be used to detect the target area where the target object is located in the target image, where the target object may include a signal indicator, and the signal indicator may include straight, straight, and
  • the signal indicator lights for turning may also include signal indicators for guiding stop, driving, and waiting, or may include signal indicators for indicating the working status of various instruments and equipment, which are not illustrated in this disclosure.
  • FIG. 6 shows a schematic diagram of the structure of a signal indicator according to an embodiment of the present disclosure, which is only an example to illustrate the type of each signal indicator, such as a longitudinally arranged traffic light, a horizontally arranged traffic light, or a direction indicator. Among them, FIG. 6
  • the target object shown in may include three indicator lights.
  • the number of indicator lights may be one or more, which is not specifically limited.
  • the signal indicator lights may have different display states. For example, it may be lit or not, or it may have a different lit color when lit, such as at least one of red, yellow, and green, or may also include other lit colors or other display states in other embodiments .
  • the target object is a signal indicator as an example for description. In other embodiments, as long as the target object has different colors or different brightness and other different display states, it can also be used as the embodiment of the present disclosure. target.
  • the detection of the target object and the target area in which it is located can be performed by an image recognition algorithm (a non-neural network detection method), or the target can also be performed by a neural network trained to recognize the target object.
  • the touch operation input by the user can be received through the input component (ie Frame selection operation), based on the area selected by the touch operation to determine the target area where the target object is located.
  • the target area where the target object is located may also be determined in other ways, which is not specifically limited in the present disclosure.
  • the first feature value corresponding to multiple pixels in the target area can be obtained, and the first feature value can represent the pixel value of the pixel, which can specifically be a pixel
  • the corresponding feature value of at least one color channel may be an RGB image (color image)
  • the first characteristic value of the acquired pixel may be the color value of the pixel in the target area
  • the color value is a color in a different color mode
  • the color value corresponding to the color value in the color mode is a model that expresses a color as a digital form, or a way to record the color of an image.
  • RGB mode CMYK mode
  • HSB mode Lab color Mode
  • bitmap mode grayscale mode
  • indexed color mode duotone mode
  • multi-channel mode etc. Therefore, in the RGB mode, the color value may include R value, G value, and B value.
  • the RGB mode is also the most commonly used color mode at present. The following examples only take the RGB mode as an example.
  • the status detection method for signal indicators using other color modes is similar to the status detection method for signal indicators using RGB mode. This will not be repeated here.
  • the other form of image can be converted into an RGB image by means of spatial conversion, for example, the image in the form of YUV can be converted into an image in the form of RGB to obtain the first feature of the pixel. value.
  • the embodiment of the present disclosure does not specifically limit the manner of image conversion.
  • the first feature values of multiple pixels in the target area may also be normalized color values, that is, the embodiment of the present disclosure may obtain multiple pixels in the target area of the target image.
  • the normalization processing method may include dividing the R value, G value, and B value with a standard value to obtain the normalization processing result of the R value, G value, and B value.
  • the standard value can be determined according to requirements, and generally can be determined according to the gray levels of multiple pixels of the target image.
  • the maximum pixel value of the target image can be determined as the standard value.
  • the RGB of a pixel in the target area can be expressed as (255, 0, 0), and the standard value is 255, then the normalized result can be (1,0, 0).
  • S20 Perform clustering processing on the pixels in the target area based on the first feature value to obtain multiple clusters for the pixels;
  • the multiple pixel points can be clustered according to the obtained first feature values to obtain clusters of different color states.
  • the first feature values of multiple pixels can be mapped to the three-dimensional space corresponding to the color values.
  • the color value as RGB as an example
  • the first feature values of multiple pixels can be mapped In the RGB three-dimensional space, the RGB value can be regarded as a coordinate point in the RGB three-dimensional space. For example, for a pixel with a first feature value of (1,0,0), the point can be located on the R axis and on the R axis. The above coordinate value is 1.
  • the position of each pixel in the RGB space can be obtained, and then the multiple pixel points can be clustered according to the positions of the multiple first feature values in the RGB space.
  • a K-means clustering algorithm may be used to perform clustering processing of multiple pixels.
  • the K-means clustering algorithm can first randomly select K (K is an integer greater than 1) objects (first eigenvalues) from the first eigenvalues of multiple pixels in the target area as the initial cluster centers. The number of is the same as the preset number of groups. Then calculate the distance between each object and multiple initial cluster centers, and assign each object to the cluster center closest to it. The cluster centers and the objects assigned to them represent a cluster (cluster group). Once all objects are assigned, the cluster center of each cluster will be recalculated based on the existing objects in the cluster. This process will be repeated until a certain termination condition is met.
  • the termination condition can be that no (or minimum number) of objects are reassigned to different clusters, and no (or minimum number) of cluster centers change again.
  • the clustering of multiple pixels can be completed, and multiple clusters of the set number of clusters can be obtained.
  • the cluster center (cluster center) of the cluster can be determined while obtaining multiple clusters.
  • pixels with a similar first feature value distance can be assigned to a cluster (cluster), and this process can achieve clustering of pixels of the same color.
  • the embodiment of the present disclosure may perform clustering processing for pixels of the same color through step S20, and different clusters obtained through the clustering processing may be expressed as clusters of pixels of different colors. Therefore, the display state of the target object in the target area can be determined according to the color represented by the cluster.
  • the target object may be a signal indicator
  • the display state of the target object in the corresponding embodiment of the present disclosure may include a first state and a second state.
  • the first state is a state where the presence signal indicator is lit, and the second state is non-existent.
  • the lighted state of the signal indicator, and in the first state can further determine the color of the lighted indicator.
  • Fig. 2 shows a flowchart of step S30 in a method for detecting the status of a signal indicator according to an embodiment of the present disclosure, wherein the determining the display status of the target object based on the obtained multiple clusters may include :
  • each reference feature value can have a color value of a corresponding color, such as an RGB value, and the reference feature value can be mapped to a color.
  • the set reference characteristic value may include: the reference characteristic value of the red state, the reference characteristic value of the yellow state, and the reference characteristic value of the green state.
  • the reference feature value can be expressed as a coordinate point in the RGB space, and the coordinate value is the corresponding RGB value.
  • the cluster centers of multiple clusters By comparing the cluster centers of multiple clusters with the reference feature value, it can be determined whether the cluster centers match the reference feature value, that is, whether the color of the corresponding cluster matches the color corresponding to the reference feature value.
  • the class center matches the reference feature value, that is, the color of the class group corresponding to the class center matches the distance threshold.
  • the color corresponding to the reference feature value is matched, that is, the target area may have a highlighted state of the color, such as the state of an indicator light.
  • the target object does not have the lighted state of the color corresponding to the reference feature value, that is, no color corresponding to the reference feature value is highlighted, that is, there is no signal indicator light.
  • the target object in the target area is the first A state, that is, there is a state in which the color corresponding to the reference feature value is highlighted, and at this time, there may be a state in which the indicator light is on.
  • the distance between the first feature value of the cluster center of all clusters and any reference feature value is greater than or equal to the distance threshold, it can be determined that there is no match with the reference feature value.
  • the target object in the target area is in the second state, that is, there is no highlighting state of the color corresponding to the reference feature value, and at this time, it is a state where there is no signal indicator light.
  • S34 Determine the display state of the target object according to the first state or the second state.
  • the display state of the target object is that there is no highlight display of the color corresponding to any reference feature value, that is, there is no lighted state of the signal indicator.
  • the display state of the target object is that there is a highlight display of a color corresponding to the reference characteristic value, for example, there is a state where an indicator light is on.
  • the first state and the second state of the signal indicator can be determined.
  • the second state it can be determined that none of the signal indicators in the target area is lit, and the location can be detected at this time.
  • the signal indicator is a fault indicator (because under normal conditions, one of the signal indicators is on).
  • the failure information can also be reported when it is determined that the signal indicator of the target image is in the second state.
  • the target image, the location information corresponding to the target image, and the second state of the target image are transmitted to the preset storage address (such as the communication address of the transportation department), and the fault information is reported, so as to facilitate the personnel of the relevant department to check the signal indicator Carry out maintenance to improve traffic safety.
  • the preset storage address such as the communication address of the transportation department
  • the reference feature values corresponding to multiple colors in the embodiments of the present disclosure can be determined by the set RGB value.
  • the RGB value of the red color in the standard state can be determined as the reference feature value of red
  • the RGB value of the yellow color in the standard state can be determined as the reference feature value of yellow
  • the RGB value of the green color in the standard state can be determined as the reference feature value of green Eigenvalues.
  • the color calibration board can also be photographed by an image acquisition device, and then reference feature values of multiple colors corresponding to the image acquisition device can be obtained.
  • Fig. 3 shows a flow chart of obtaining a reference characteristic value in a method for detecting the state of a signal indicator according to an embodiment of the present disclosure.
  • the step of obtaining the reference characteristic value includes:
  • the color calibration plate may be color samples with different colors, and a reference image for the color calibration plate can be obtained by capturing the color calibration plate by the image acquisition device that collects the target image.
  • S42 Determine the reference feature value according to the color value of the pixel in the preset color area in the reference image.
  • the reference image can include multiple color regions
  • the color values (such as RGB values) of the pixels in the multiple color regions can be obtained.
  • the embodiment of the present disclosure can use the average value of the color values of the pixels in the corresponding region as the
  • the reference feature value corresponding to the color area is the reference feature value of the color.
  • the average value of the color value of the corresponding color region can also be normalized to obtain the reference feature value of the color.
  • the normalization processing method is the same as the above description, for example, the average value of the color value is divided by the gray level or other standard values to obtain the normalized reference feature value. The specific process is not repeated here.
  • the reference feature value of multiple colors for the image acquisition device can be obtained, so that the subsequent process performs subsequent logical processing based on the reference feature value, that is, the matching process between the class center and the reference feature value, which reduces the The influence of the parameters on the color of pixels.
  • it can also be adapted to be used in various types of image acquisition equipment, reducing the color deviation between the images collected by the image acquisition equipment.
  • the color of the indicator light when it is determined that the target object is in the first state, the color of the indicator light can be further determined.
  • FIG. 4 shows a flowchart of step S34 in a method for detecting the state of a signal indicator according to an embodiment of the present disclosure, wherein the display of the target object is determined according to the first state or the second state Status, including:
  • S3401 In a case where it is determined that the target object is in the first state, based on the pixel points in the cluster corresponding to the cluster center matching the reference feature value, determine the first state formed by the cluster in the target area.
  • the first area of the area formed in the target area by the pixel points in the cluster corresponding to the cluster center matching the reference feature value can be obtained.
  • the pixel points corresponding to the cluster center matching the reference feature value can be remapped to the target area, and the first area formed by the cluster of pixels in the target area can be determined.
  • the first area may be determined according to an integral manner, or the first area may also be obtained in other manners, which is not specifically limited in the present disclosure.
  • S3402 Determine the display color of the target object in the target area based on the reference feature value matched by the cluster center of the first cluster with the largest area.
  • the embodiment of the present disclosure can set the cluster with the largest first area and the first area greater than the area threshold.
  • the color of the reference feature value corresponding to the group is determined as the display color of the target object in the target area. In this way, the color of the signal indicator light in the target area can be easily and conveniently determined.
  • the embodiment of the present disclosure may set a corresponding area threshold according to requirements, which is not specifically limited in the present disclosure.
  • further clustering processing may be performed on multiple pixels remapped into the target area to obtain multiple new clusters, and further determine the display color of the target object. That is, the color of the lit indicator. In this way, the detection accuracy of the display color can be improved.
  • FIG. 5 shows another flowchart of step S34 in a method for detecting the state of a signal indicator according to an embodiment of the present disclosure, wherein the determination of the target object's status according to the first state or the second state
  • the display status can also include:
  • the embodiment of the present disclosure can remap the pixels in the corresponding cluster group of the determined cluster center that matches the reference feature to the target area, and can perform re-focusing on all the remapped pixels. Class processing.
  • the clustering process can also be performed based on the first feature value of the remapped pixel point, for example, K-means clustering process can also be performed, wherein the number of cluster groups set in the clustering process in step S20 and this step
  • the number of clusters set in the clustering process can be the same or different, and generally can be set to a value greater than or equal to 3.
  • multiple new clusters may be obtained, and the new clusters may include at least one remapped to the target area. Pixels, through this step, the re-clustering of the pixel points in the cluster matching the reference feature value obtained in step S20 can be realized to form a new cluster. Based on this, the cluster centers of multiple new clusters can also be obtained. This disclosure does not specifically limit the process.
  • S3412 Determine the reference feature value matched by the cluster center of the new cluster, and determine the second area formed by the pixels in the new cluster in the target area;
  • S3413 Determine the display color of the target object in the target area based on the reference feature value matched by the cluster center of the new cluster with the second largest area.
  • the reference feature value matched by the cluster centers of the multiple new clusters can be re-determined.
  • the color corresponding to the reference feature value with the closest distance to the cluster center is determined as the color corresponding to the new cluster.
  • the second area formed by the corresponding new cluster can also be determined based on the pixels in the new cluster, for example, the area enclosed by the pixels in the new cluster can be determined, and The second area of the region is further determined, that is, the second area of the corresponding new cluster.
  • the new cluster with the largest second area can be selected from it. Furthermore, the color corresponding to the reference feature value matched by the cluster center of the new cluster with the second largest area and greater than the area threshold may be determined as the display color of the target object.
  • the color of the reference feature value corresponding to the new cluster with the second largest area can be obtained, and the display color can be determined as the display color of the target object.
  • the embodiments of the present disclosure provide a technical solution for improving the display status of the accurate detection signal indicator, in which the target area in the image (signal indicator) is detected, and the target area Clustering is performed on the feature values of the pixel points in the target area to obtain multiple clusters, so as to obtain the display state of the target object according to the matching between the multiple clusters and the reference feature values.
  • clustering processing similar pixels with the same display state can be determined as a cluster, and the display state of the target object can be accurately determined through further analysis of the cluster (cluster), which can improve the background of the signal indicator Robustness of interference.
  • the embodiments of the present disclosure also provide an intelligent driving control method, which can be applied to intelligent driving equipment, such as intelligent driving vehicles (including automatic driving and advanced assisted driving systems), aircraft, and robots. And in equipment such as blind guide equipment.
  • intelligent driving equipment such as intelligent driving vehicles (including automatic driving and advanced assisted driving systems), aircraft, and robots.
  • equipment such as blind guide equipment.
  • the present disclosure does not specifically limit the type of intelligent driving equipment, as long as the device can perform driving control in combination with the display state of the signal indicator light, it can be used as the main body of the application of the embodiments of the present disclosure.
  • Fig. 7 shows a flowchart of a driving control method according to an embodiment of the present disclosure, wherein the driving control method may include:
  • S100 Collect road images through the image collection device on the smart driving device
  • An image acquisition device may be provided in the intelligent driving device, and the image acquisition device can acquire real-time road images in front of the intelligent driving device in the form of a process, so that road images including signal indicators can be acquired.
  • S200 Use the road image as the target image to execute the method for detecting the state of the signal indicator light as described in the foregoing embodiment to obtain the display state of the signal indicator light in the road image;
  • the above-mentioned signal indicator state detection method can be used to detect the display state of the signal indicator included in the road image.
  • the specific process will not be repeated, and the detection process of the foregoing embodiment can be referred to.
  • S200 Generate and output a control instruction for controlling the intelligent driving device according to the display state of the signal indicator in the road image, so as to control the intelligent driving device.
  • the control of the driving parameters of the smart driving device can be executed according to the display state, that is, a control instruction for controlling the smart driving device is generated.
  • the control command includes at least one of the following: a speed maintaining control command for maintaining the formal speed, a speed adjustment control command for adjusting the traveling speed, a direction maintaining control command for maintaining the traveling direction, and a direction adjustment control for adjusting the traveling direction Commands, warning prompt control commands for executing early warnings (such as red light warning, turning warning, etc.), and driving mode switching control commands.
  • the color of the reference feature value for performing the clustering process can include a red reference feature value, a green reference feature value, and a yellow reference feature value.
  • the red light in the signal indicator light when it is determined that the red light in the signal indicator light is on, it can correspondingly slow down or stop .
  • the green light in the signal indicator light when it is determined that the green light in the signal indicator light is on, it indicates that it is possible to go straight through, or, in other embodiments, at least one of the driving direction, the selection of the lane, and the driving speed can be determined according to the lighted color of the turn indicator. .
  • the control of the driving parameters of the intelligent driving device can be performed based on the recognized display state of the signal lamp. Since the obtained signal lamp display state is more accurate, the intelligent driving device can be accurately controlled.
  • the writing order of the steps does not mean a strict execution order but constitutes any limitation on the implementation process.
  • the specific execution order of each step should be based on its function and possibility.
  • the inner logic is determined.
  • the present disclosure also provides a signal indicator state detection device, a driving control device, electronic equipment, computer-readable storage medium, and a program, all of which can be used to implement any of the signal indicator state detection methods provided in the present disclosure or Driving control methods, corresponding technical solutions and descriptions, and refer to the corresponding records in the method section, will not be repeated.
  • Fig. 8 shows a block diagram of a device for detecting the status of a signal indicator according to an embodiment of the present disclosure.
  • the device for detecting the status of a signal indicator includes:
  • the detection module 10 is configured to detect a target area in a target image and determine the first characteristic value of a pixel in the target area, and the target area includes at least one signal indicator with different display states;
  • the clustering module 20 is configured to perform clustering processing on the pixels in the target area based on the first feature value to obtain multiple clusters for the pixels;
  • the determining module 30 is configured to determine the display state of the signal indicator based on the obtained multiple clusters.
  • the determining module is further configured to determine whether there is a reference feature value preset in the image acquisition device that acquires the target image and the first feature value corresponding to the cluster center of the cluster. The class center matching the reference feature value;
  • the determining module is configured to determine whether there is a cluster center that matches the reference feature value based on the reference feature value and the first feature value corresponding to the cluster center of the cluster. Thereafter, in response to the absence of a cluster center matching the reference characteristic value, it is determined that the signal indicator is in the second state.
  • the device further includes a setting module, which is configured to use the image acquisition device to shoot a color calibration plate to obtain a reference image;
  • the reference feature value is determined according to the color value of the pixel point in the preset color area in the reference image.
  • the setting module is used to:
  • the color value of the pixel in the preset color area is determined as the reference feature value; or, the color value of the pixel in the preset color area is normalized to obtain the reference feature value.
  • the reference characteristic value includes a reference characteristic value of a red state, a reference characteristic value of a yellow state, and a reference characteristic value of a green state.
  • the determining module is further configured to, in the case of determining that the signal indicator is in the first state, based on the pixels in the cluster corresponding to the cluster center matching the reference feature value, Determine the first area formed by the cluster in the target area;
  • the display color of the signal indicator in the target area is determined based on the reference feature value matched by the cluster center of the cluster with the largest area.
  • the determining module is further configured to perform a calculation on the pixel points in the cluster corresponding to the cluster center matching the reference characteristic value when the signal indicator is determined to be in the first state. Cluster processing to obtain multiple new clusters;
  • the detection module is used to:
  • the clustering module is configured to use a K-means clustering algorithm to cluster pixels in the target area to obtain a preset number of clusters.
  • Fig. 9 shows a block diagram of a driving control device according to an embodiment of the present disclosure.
  • the driving control device includes:
  • the image acquisition device 100 is installed on the intelligent driving device and used to collect road images
  • the signal indicator status detection module 200 which is used to execute the signal indicator status detection method of any one of the first aspect using the road image as a target image to obtain the display of the signal indicator in the road image status;
  • the control module 300 is configured to generate and output control instructions for controlling the smart driving device according to the display state of the signal indicator in the road image, so as to control the smart driving device.
  • control instruction includes at least one of the following: a speed maintaining control instruction, a speed adjustment control instruction, a direction maintaining control instruction, a direction adjustment control instruction, an early warning prompt control instruction, and a driving mode switching control instruction.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the embodiment of the present disclosure also proposes a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium.
  • An embodiment of the present disclosure also provides an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured as the above method.
  • the embodiment of the present disclosure also proposes a computer program, including computer readable code, when the computer readable code is executed in an electronic device, the processor in the electronic device executes to implement the above method.
  • the electronic device can be provided as a terminal, server or other form of device.
  • Fig. 10 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
  • the electronic device 800 may be a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and other terminals.
  • the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, and a sensor component 814 , And communication component 816.
  • the processing component 802 generally controls the overall operations of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • the processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the foregoing method.
  • the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components.
  • the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.
  • the memory 804 is configured to store various types of data to support operations in the electronic device 800. Examples of these data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc.
  • the memory 804 can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic Disk or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EPROM erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Magnetic Disk Magnetic Disk or Optical Disk.
  • the power supply component 806 provides power for various components of the electronic device 800.
  • the power supply component 806 may include a power management system, one or more power supplies, and other components associated with the generation, management, and distribution of power for the electronic device 800.
  • the multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 810 is configured to output and/or input audio signals.
  • the audio component 810 includes a microphone (MIC).
  • the microphone is configured to receive external audio signals.
  • the received audio signal may be further stored in the memory 804 or transmitted via the communication component 816.
  • the audio component 810 further includes a speaker for outputting audio signals.
  • the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module.
  • the peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include but are not limited to: home button, volume button, start button, and lock button.
  • the sensor component 814 includes one or more sensors for providing the electronic device 800 with various aspects of state evaluation.
  • the sensor component 814 can detect the on/off status of the electronic device 800 and the relative positioning of the components.
  • the component is the display and the keypad of the electronic device 800.
  • the sensor component 814 can also detect the electronic device 800 or the electronic device 800.
  • the position of the component changes, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800.
  • the sensor component 814 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact.
  • the sensor component 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.
  • the communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices.
  • the electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G, or 3G, or a combination thereof.
  • the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 816 further includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the electronic device 800 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field A programmable gate array (FPGA), controller, microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.
  • ASIC application specific integrated circuits
  • DSP digital signal processors
  • DSPD digital signal processing devices
  • PLD programmable logic devices
  • FPGA field A programmable gate array
  • controller microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.
  • a non-volatile computer-readable storage medium or a volatile computer-readable storage medium is also provided, such as the memory 804 including computer program instructions, which can be processed by the electronic device 800.
  • the device 820 executes to complete the above method.
  • Fig. 11 shows another block diagram of an electronic device according to an embodiment of the present disclosure.
  • the electronic device 1900 may be provided as a server. 11, the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932, for storing instructions that can be executed by the processing component 1922, such as application programs.
  • the application program stored in the memory 1932 may include one or more modules each corresponding to a set of instructions.
  • the processing component 1922 is configured to execute instructions to perform the above-described method.
  • the electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input output (I/O) interface 1958 .
  • the electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.
  • a non-volatile computer-readable storage medium or a volatile computer-readable storage medium is also provided, such as the memory 1932 including computer program instructions, which can be processed by the electronic device 1900.
  • the component 1922 executes to complete the above method.
  • the present disclosure may be a system, method, and/or computer program product.
  • the computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for enabling a processor to implement various aspects of the present disclosure.
  • the computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, such as a printer with instructions stored thereon
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • flash memory flash memory
  • SRAM static random access memory
  • CD-ROM compact disk read-only memory
  • DVD digital versatile disk
  • memory stick floppy disk
  • mechanical encoding device such as a printer with instructions stored thereon
  • the computer-readable storage medium used here is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, light pulses through optical fiber cables), or through wires Transmission of electrical signals.
  • the computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing/processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • the network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing/processing device .
  • the computer program instructions used to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, or in one or more programming languages.
  • Source code or object code written in any combination, the programming language includes object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages.
  • Computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, executed as a stand-alone software package, partly on the user's computer and partly executed on a remote computer, or entirely on the remote computer or server carried out.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to access the Internet connection).
  • LAN local area network
  • WAN wide area network
  • an electronic circuit such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by using the status information of the computer-readable program instructions.
  • the computer-readable program instructions are executed to realize various aspects of the present disclosure.
  • These computer-readable program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine such that when these instructions are executed by the processor of the computer or other programmable data processing device , A device that implements the functions/actions specified in one or more blocks in the flowchart and/or block diagram is produced. It is also possible to store these computer-readable program instructions in a computer-readable storage medium. These instructions make computers, programmable data processing apparatuses, and/or other devices work in a specific manner, so that the computer-readable medium storing instructions includes An article of manufacture, which includes instructions for implementing various aspects of the functions/actions specified in one or more blocks in the flowchart and/or block diagram.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of an instruction, and the module, program segment, or part of an instruction contains one or more functions for implementing the specified logical function.
  • Executable instructions may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Probability & Statistics with Applications (AREA)
  • Human Computer Interaction (AREA)
  • Image Analysis (AREA)
  • Traffic Control Systems (AREA)

Abstract

本公开涉及一种信号指示灯的状态检测方法及装置、驾驶控制方法及装置，所述信号指示灯的状态检测方法包括：检测目标图像中的目标区域，并确定所述目标区域内像素点的第一特征值，所述目标区域中包括至少一个具有不同显示状态的信号指示灯；基于所述第一特征值对所述目标区域内的像素点进行聚类处理，得到针对像素点的多个类组；基于得到的所述多个类组确定所述信号指示灯的显示状态。

Description

信号指示灯的状态检测方法及装置、驾驶控制方法及装置
本公开要求在2019年5月28日提交中国专利局、申请号为201910450394.3、申请名称为“信号指示灯的状态检测方法及装置、驾驶控制方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及计算机视觉领域，特别涉及一种信号指示灯的状态检测方法及装置、驾驶控制方法及装置。
背景技术
在自动驾驶或辅助驾驶过程中，需要对路口的交通灯进行交通灯状态的检测，自动驾驶车辆需要在各种环境干扰的路况下实时地检测交通灯的位置及其状态才能很好地进行路径规划。自动驾驶车辆可以使用摄像头作为传感器对道路场景进行图像采集，以实时地对交通灯进行检测。
发明内容
本公开实施例提供了一种信号指示灯的状态检测方案。
根据本公开的一方面，提供了一种信号指示灯的状态检测方法，其包括：
检测目标图像中的目标区域，并确定所述目标区域内像素点的第一特征值，所述目标区域中包括至少一个具有不同显示状态的信号指示灯；
基于所述第一特征值对所述目标区域内的像素点进行聚类处理，得到针对像素点的多个类组；
基于得到的所述多个类组确定所述信号指示灯的显示状态。
在一些可能的实施方式中，所述基于得到的所述多个类组确定所述信号指示灯的显示状态，包括：
根据所述目标图像的图像采集设备中预设的参考特征值和每个类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心；
响应于存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第一状态。
在一些可能的实施方式中，所述方法还包括：
在根据所述参考特征值和每个类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心之后，响应于不存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第二状态。
在一些可能的实施方式中，采用以下步骤设定所述参考特征值：
利用所述图像采集设备拍摄色彩标定板，得到参考图像；
根据所述参考图像中预设颜色区域内的像素点的色值，确定所述参考特征值。
在一些可能的实施方式中，所述根据所述参考图像中预设颜色区域内的像素点的色值，确定所述参考特征值，包括：
将预设颜色区域内的像素点的色值确定为所述参考特征值；或者
对所述预设颜色区域内的像素点的色值执行归一化处理，得到所述参考特征值。
在一些可能的实施方式中，所述参考特征值包括红色状态的参考特征值、黄色状态的参考特征值以及绿色状态的参考特征值。
在一些可能的实施方式中，所述方法还包括：
在确定所述信号指示灯为第一状态的情况下，基于与所述参考特征值匹配的类中心对应的类组内的像素点，确定类组在所述目标区域中所形成的第一面积；
将第一面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
基于第一面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述信号指示灯的显示颜色。
在一些可能的实施方式中，所述方法还包括：
在确定所述信号指示灯为第一状态的情况下，对与所述参考特征值匹配的类中心对应的类组内的像素点进行聚类处理，得到多个新的类组；
确定所述新的类组的类中心所匹配的参考特征值，并确定所述新的类组中的像素点在所述目标区域中所形成的第二面积；
将第二面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
基于第二面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述信号指示灯的显示颜色。
在一些可能的实施方式中，所述确定所述目标区域内像素点的第一特征值，包括：
将所述目标区域内像素点的色值确定为所述第一特征值；或者
对所述目标区域内像素点的色值执行归一化处理，得到所述第一特征值。
在一些可能的实施方式中，所述基于所述第一特征值对所述目标区域内的像素点进行聚类处理，得到针对像素点的多个类组，包括：
通过K-均值聚类算法，对所述目标区域内的像素点进行聚类，得到预设数目个类组。
根据本公开的第二方面，提供了一种驾驶控制方法，其包括：
通过智能驾驶设备上的图像采集设备采集道路图像；
将所述道路图像作为目标图像执行本公开的第一方面中的任一信号指示灯的状态检测方法，得到所述道路图像中的信号指示灯的显示状态；
根据所述道路图像中的信号指示灯的显示状态，生成控制所述智能行驶设备的控制指令并输出，以控制所述智能驾驶设备。
在一些可能的实施方式中，所述控制指令包括以下至少之一：速度保持控制指令、速度调整控制指令、方向保持控制指令、方向调整控制指令、预警提示控制指令、驾驶模式切换控制指令。
根据本公开的第三方面，提供了一种信号指示灯的状态检测装置，其包括：
检测模块，其用于检测目标图像中的目标区域，并确定所述目标区域内像素点的第一特征值，所述目标区域中包括至少一个具有不同显示状态的信号指示灯；
聚类模块，其用于基于所述第一特征值对所述目标区域内的像素点进行聚类处理，得到针对像素点的多个类组；
确定模块，其用于基于得到的所述多个类组确定所述信号指示灯的显示状态。
在一些可能的实施方式中，所述确定模块，用于根据获取所述目标图像的图像采集设备中预设的参考特征值和每个类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心；
响应于存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第一状态。
在一些可能的实施方式中，所述确定模块还用于在根据所述参考特征值和每个类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心之后，响应于不存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第二状态。
在一些可能的实施方式中，所述装置还包括设定模块，其用于利用所述图像采集设备拍摄色彩标定板，得到参考图像；
根据所述参考图像中预设颜色区域内的像素点的色值，确定所述参考特征值。
在一些可能的实施方式中，所述设定模块，用于：
利用所述图像采集设备拍摄色彩标定板，得到参考图像；
将预设颜色区域内的像素点的色值确定为所述参考特征值；或者，对所述预设颜色区域内的像素点的色值执行归一化处理，得到所述参考特征值。
在一些可能的实施方式中，所述参考特征值包括红色状态的参考特征值、黄色状态的参考特征值以及绿色状态的参考特征值。
在一些可能的实施方式中，所述确定模块还用于在确定所述信号指示灯为第一状态 的情况下，基于与所述参考特征值匹配的类中心对应的类组内的像素点，确定类组在所述目标区域中所形成的第一面积；
将第一面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
基于第一面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述信号指示灯的显示颜色。
在一些可能的实施方式中，所述确定模块还用于在确定所述信号指示灯为第一状态的情况下，对与所述参考特征值匹配的类中心对应的类组内的像素点进行聚类处理，得到多个新的类组；
确定所述新的类组的类中心所匹配的参考特征值，并确定所述新的类组中的像素点在所述目标区域中所形成的第二面积；
将第二面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
基于第二面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述信号指示灯的显示颜色。
在一些可能的实施方式中，所述检测模块，用于：
检测目标图像中的目标区域；
将所述目标区域内像素点的色值确定为所述第一特征值；或者，对所述目标区域内像素点的色值执行归一化处理，得到所述第一特征值。
在一些可能的实施方式中，所述聚类模块，用于通过K-均值聚类算法，对所述目标区域内的像素点进行聚类，得到预设数目个类组。
根据本公开的第四方面，提供了一种驾驶控制装置，其包括：
图像采集设备，其安装在智能驾驶设备上，并用于采集道路图像；
信号指示灯状态检测模块，其用于将所述道路图像作为目标图像执行本公开的第一方面中任一项所述的信号指示灯的状态检测方法，得到所述道路图像中的信号指示灯的显示状态；
控制模块，其用于根据所述道路图像中的信号指示灯的显示状态，生成控制所述智能行驶设备的控制指令并输出，以控制所述智能驾驶设备。
在一些可能的实施方式中，所述控制指令包括以下至少之一：速度保持控制指令、速度调整控制指令、方向保持控制指令、方向调整控制指令、预警提示控制指令、驾驶模式切换控制指令。
根据本公开的第五方面，提供了一种电子设备，其特征在于，包括：
处理器；
用于存储处理器可执行指令的存储器；
其中，所述处理器被配置为：执行第一方面中任意一项所述的方法，或者执行第二方面中任意一项所述的方法。
根据本公开的第六方面，提供了一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现第一方面中任意一项所述的方法，或者执行第二方面中任意一项所述的方法。
根据本公开的第七方面，提供了一种计算机程序，包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现第一方面中任意一项所述的方法，或者执行第二方面中任意一项所述的方法。
本公开实施例可以检测图像中的信号指示灯所在的目标区域，可以对信号指示灯所在的目标区域的像素点的特征值进行聚类处理，得到多个类组，从而根据该多个类组与参考特征值的匹配情况，得到信号指示灯的显示状态。本公开实施例可以在实现信号指示灯的显示状态的精确检测的前提下，减少检测显示状态时使用神经网络的几率，一方面减少了网络训练的程序，另一方面还可以缩短信号指示灯的显示状态的检测时间。在 自动驾驶领域，也可以通过本公开实施例确定交通灯的显示状态，进而提高自动驾驶的安全性。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。
根据下面参考附图对示例性实施例的详细说明，本公开的其它特征及方面将变得清楚。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。
图1示出根据本公开实施例的一种信号指示灯的状态检测方法的流程图；
图2示出根据本公开实施例的一种信号指示灯的状态检测方法中步骤S30的流程图；
图3示出根据本公开实施例的一种信号指示灯的状态检测方法中获取参考特征值的流程图；
图4示出根据本公开实施例的一种信号指示灯的状态检测方法中步骤S34的流程图；
图5示出根据本公开实施例的一种信号指示灯的状态检测方法中步骤S34的另一流程图；
图6示出根据本公开实施例的信号指示灯的结构示意图；
图7示出根据本公开实施例提供的一种驾驶控制方法的流程图；
图8示出根据本公开实施例的一种信号指示灯的状态检测装置的框图；
图9示出根据本公开实施例的一种驾驶控制装置的框图；
图10示出根据本公开实施例的一种电子设备的框图；
图11示出根据本公开实施例的一种电子设备的另一框图。
具体实施方式
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
另外，为了更好地说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。
本公开实施例提供了一种信号指示灯的状态检测方法，该方法可以检测目标图像中的信号指示灯的显示状态。其中，本公开实施例的信号指示灯的状态检测方法可以应用在任意的图像采集和图像处理设备中，例如可以应用在摄像机、照相机、手机、计算机、PAD、智能手表、智能手环，或者服务器中，或者还可以应用在机器人、智能驾驶设备、导盲设备等，只要能够执行图像采集或者图像处理，即可以实现本公开实施例的方法，本公开的对此不作具体限定。本公开可以应用于指示灯状态识别、检测等场景，例如，在自动驾驶中，可以通过检测交通灯的状态实现路径规划、导航等。本公开不对具体的 应用场景进行限制。
图1示出根据本公开实施例的一种信号指示灯的状态检测方法的流程图。其中，所述信号指示灯的状态检测方法可以包括：
S10：检测目标图像中的目标区域，并确定所述目标区域内像素点的第一特征值，所述目标区域包括至少一个具有不同显示状态的信号指示灯；
如上所述，本公开实施例的信号指示灯的状态检测方法可以实现目标图像中的信号指示灯(下述称为目标对象)的显示状态的检测，其中首先可以获取该目标图像。在一些可能的实施方式中，目标图像为通过图像采集设备采集的图像，例如可以在车辆、飞行器等自动驾驶或者辅助驾驶的设备中设置行车记录仪等图像采集设备，通过该图像采集设备可以采集行驶记录图像，该行驶记录图像可以为本公开实施例的目标图像。或者，也可以为从接收的视频图像中采样获得目标图像，也可以为从其他设备接收的目标图像，本公开对此不作具体限定。
在一些可能的实施方式中，在获得目标图像之后，可以通过步骤S10检测目标图像中目标对象所在的目标区域，其中目标对象可以包括信号指示灯，该信号指示灯可以包括引导行驶方向的直行、转弯的信号指示灯，或者也可以包括引导停止、行驶、等待的信号指示灯，也可以包括指示各种仪器设备的工作状态的信号指示灯，本公开对此不作一一举例说明。图6示出根据本公开实施例的信号指示灯的结构示意图，其中只是示例性举例说明各信号指示灯的类型，例如纵向排列的红绿灯，横向排列的红绿灯，或者方向指示灯，其中，图6中示出的目标对象可以包括三个指示灯，本公开实施例对于指示灯的数量可以为1个也可以为多个，对此不作具体限定，另外，信号指示灯可以具有不同的显示状态，如亮起或者不亮，或者也可以为亮起时具有不同的亮起颜色，如红色、黄色、绿色中的至少一种，或者在其他实施例中也可以包括其他亮起颜色或者其他显示状态。本公开实施例中，以目标对象为信号指示灯为例进行说明，在其他实施例中，只要目标对象具有不同的颜色或者不同的亮度等不同显示状态的情况，也可以作为本公开实施例的目标对象。
在一些可能的实施方式中，可以通过图像识别算法(非神经网络检测的方法)执行目标对象及其所在的目标区域的检测，或者也可以通过经过训练用于识别目标对象的神经网络来执行目标对象及其目标区域的检测，其中神经网络可以为卷积神经网络，或者，也可以通过接收的框选操作确定目标对象所在的目标区域，例如可以通过输入组件接收用户输入的触控操作(即框选操作)，基于所述触控操作所框选出的区域确定目标对象所在的目标区域。上述仅为示例性举例说明，在其他实施例中也可以通过其他方式确定目标对象所在的目标区域，本公开对此不做具体限定。
在确定了目标对象在目标图像中所在的目标区域时，可以获取该目标区域中多个像素点对应的第一特征值，该第一特征值可以表示像素点的像素值，具体可以为像素点所对应的至少一个颜色通道的特征值。如本公开实施例中的目标图像可以为RGB图像(彩色图像)，则获取的像素点的第一特征值可以为目标区域内像素点的色值，色值是一种颜色在不同的颜色模式中所对应的颜色值，颜色模式是将一种颜色表现为数字形式的模型，或者说是一种记录图像颜色的方式，目前常用的颜色模式包括：RGB模式、CMYK模式、HSB模式、Lab颜色模式、位图模式、灰度模式、索引颜色模式、双色调模式和多通道模式，等等。因此，在RGB模式中，该色值可以包括R值、G值和B值。RGB模式也是目前最常用的颜色模式，以下示例中仅以RGB模式为例进行说明，对于采用其他颜色模式的信号指示灯的状态检测方法与采用RGB模式的信号指示灯的状态检测方法类似，在此不再赘述。另外，在目标图像为其他形式的图像时，可以通过空间转换的方式，将其他形式的图像转换成RGB图像，例如将YUV形式的图像转换成RGB形式的图像，进而获得像素点的第一特征值。其中本公开实施例对图像转换的方式不做具体限定。
在一些可能的实施方式中，目标区域内多个像素点的第一特征值也可以为经过归一化处理后的色值，即本公开实施例可以在获取目标图像的目标区域内多个像素点的色值(R值、G值和B值)之后，可以对获得的R值、G值和B值执行归一化处理，从而可以减少噪声，减少第一特征值由于噪声的引入所带来的差异，从而提高聚类精度以及显示状态的显示精度。其中，归一化处理的方式可以包括分别将R值、G值和B值与一标准值做除法运算，得到R值、G值和B值的归一化处理结果。其中，标准值可以根据需求确定，一般可以按照目标图像多个像素点的灰度确定，如可以将目标图像的最大像素值确定为该标准值。例如目标区域内一像素点的RGB可以表示为(255,0,0)，标准值为255，则归一化的结果可以为(1,0,0)。
S20：基于所述第一特征值对所述目标区域内的像素点进行聚类处理，得到针对像素点的多个类组；
本公开实施例中，在获得了目标区域内多个像素点的第一特征值的情况下，可以根据获得的第一特征值对多个像素点进行聚类，得到不同颜色状态的类组。
在一些可能的实施方式中，可以将多个像素点的第一特征值映射到色值所对应的三维空间，以色值为RGB为例，即可以将多个像素点的第一特征值映射到RGB三维空间中，可以将RGB值视作RGB三维空间上的坐标点，例如对于第一特征值为(1,0,0)的像素点，该点可以位于R轴上，并且在R轴上的坐标值为1。以此类推，可以得到每个像素点在RGB空间中的位置，进而根据多个第一特征值在RGB空间中的位置对多个像素点进行聚类处理。
在一些可能的实施方式中，可以采用K均值聚类算法执行多个像素点的聚类处理。K均值聚类算法可以先从目标区域内多个像素点的第一特征值中随机选取K(K为大于1的整数)个对象(第一特征值)作为初始的聚类中心，聚类中心的个数与预先设定的类组数相同。然后计算每个对象与多个初始的聚类中心之间的距离，把每个对象分配给距离它最近的聚类中心。聚类中心以及分配给它们的对象就代表一个聚类(类组)。一旦全部对象都被分配了，每个聚类的聚类中心会根据聚类中现有的对象被重新计算。这个过程将不断重复直到满足某个终止条件。终止条件可以是没有(或最小数目的)对象被重新分配给不同的聚类，没有(或最小数目)聚类中心再发生变化。通过上述方式，即可以完成多个像素点的聚类，得到设定的类组数的多个类组。其中，通过K均值聚类处理后，在得到了多个类组的同时还可以确定类组的类中心(聚类中心)。
本公开实施例中，通过上述聚类处理可以将第一特征值距离相近的像素点分配到一个类组(聚类)中，该过程可以实现相同颜色的像素点的聚类处理。
S30：基于得到的所述多个类组确定所述信号指示灯的显示状态。
如上所述，本公开实施例通过步骤S20可以执行针对相同颜色的像素点的聚类处理，通过聚类处理得到的不同类组可以表示成不同颜色的像素点的聚类。因此，可以根据聚类代表的颜色确定目标区域中目标对象的显示状态。其中，目标对象可以为信号指示灯，对应的本公开实施例中目标对象的显示状态可以包括第一状态和第二状态，第一状态为存在信号指示灯亮起的状态，第二状态为不存在信号指示灯亮起的状态，以及在第一状态下，还可以进一步确定亮起的指示灯的颜色。
图2示出根据本公开实施例的一种信号指示灯的状态检测方法中步骤S30的流程图，其中，所述基于得到的所述多个类组确定所述目标对象的显示状态，可以包括：
S31：根据每个类组的类中心对应的第一特征值与参考特征值，确定是否存在与参考特征值匹配的类中心；
在一些可能的实施方式中，可以设置有多个颜色状态的参考特征值，同样的，每个参考特征值可以具有相应颜色的色值，如RGB值，并可以将该参考特征值映射到色值空间中，从而可以根据该参考特征值对应的色值与类组的类中心之间的距离确定类中心是 否与参考特征值匹配。其中，对于目标对象为信号指示灯的情况，设置的参考特征值可以包括：红色状态的参考特征值、黄色状态的参考特征值以及绿色状态的参考特征值。参考特征值可以表示成RGB空间中的一个坐标点，坐标值为相应的RGB值。
通过将聚类处理得到的多个类组的类中心与参考特征值进行比较，可以确定类中心是否与参考特征值匹配，即相应类组的颜色是否与参考特征值对应的颜色匹配。
在一些可能的实施方式中，在一类中心与一参考特征值之间的距离小于距离阈值时，可以确定该类中心与该参考特征值匹配，即该类中心对应的类组的颜色与该参考特征值对应的颜色匹配，也就是说，目标区域可能存在该颜色的高亮显示状态，如指示灯亮起的状态。如果对于全部的类组的类中心，都不存在与类中心匹配的参考特征值，即每个类中心与多个参考特征值之间的距离都大于或者等于距离阈值，此时说明目标区域中的目标对象并不存在与参考特征值对应的颜色的亮起状态，即没有与参考特征值对应的颜色被高亮显示，即不存在信号指示灯亮起。
S32：响应于存在与所述参考特征值匹配的类中心，确定所述目标对象为第一状态；
如上述所述，在存在一类中心与参考特征值之间的距离小于距离阈值时，可以确定为存在与所述参考特征值匹配的类中心，此时可以判断为目标区域的目标对象为第一状态，即存在参考特征值对应的颜色的高亮显示的状态，此时为可能存在指示灯亮起的状态。
S33：响应于不存在与所述参考特征值匹配的类中心，确定所述目标对象为第二状态；
如上述所述，在对于全部的类组的类中心的第一特征值，与任意的参考特征值之间的距离都大于或者等于距离阈值时，可以确定为不存在与所述参考特征值匹配的类中心，此时可以判断为目标区域的目标对象为第二状态，即不存在参考特征值对应的颜色的高亮显示状态，此时为不存在信号指示灯亮起的状态。
S34：根据所述第一状态或者所述第二状态，确定所述目标对象的显示状态。
在一些可能的实施方式中，在确定目标对象为第二状态时，目标对象的显示状态即为不存在任意参考特征值对应的颜色的高亮显示，即不存在信号指示灯亮起的状态。
在一些可能的实施方式中，在确定目标对象为第一状态时，目标对象的显示状态即为存在与参考特征值对应的颜色的高亮显示，如存在指示灯亮起的状态。
通过本公开实施例可以确定信号指示灯的第一状态和第二状态，其中在第二状态的情况下，可以确定该目标区域内的信号指示灯均未亮起，此时可以检测出该处的信号指示灯为故障的指示灯(因为在正常情况下，信号指示灯中有一个指示灯是亮的)。另外，为了提醒相关部门该处指示灯的故障情况，还可以在确定目标图像的信号指示灯处于第二状态的情况下，上报该故障信息。例如将目标图像、目标图像对应的位置信息、目标图像的第二状态一起传送给预设的存储地址(例如交通部门的通信地址)，上报该故障信息，从而方便有关部门的人员对信号指示灯进行检修，提高交通安全性。
另外，本公开实施例中的多个颜色对应的参考特征值，如参考RGB值可以通过设定的RGB值确定。其中可以将标准状态下红色颜色的RGB值确定为红色的参考特征值，将标准状态下黄色颜色的RGB值确定为黄色的参考特征值，将标准状态下绿色颜色的RGB值确定为绿色的参考特征值。
在另一些实施方式中，也可以通过图像采集设备拍摄彩标定板，进而得到该图像采集设备对应的多个颜色的参考特征值。图3示出根据本公开实施例的一种信号指示灯的状态检测方法中获取参考特征值的流程图。所述获取所述参考特征值的步骤，包括：
S41：利用获取所述目标图像的图像采集设备拍摄色彩标定板，得到参考图像；
在一些可能的实施方式中，色彩标定板可以为具有不同颜色的彩色样本，通过采集目标图像的图像采集设备拍摄该色彩标定板可以得到针对该色彩标定板的参考图像。
S42：根据所述参考图像中预设颜色区域内的像素点的色值，确定所述参考特征值。
由于参考图像中可以包括多个颜色区域，因此，可以获取多个颜色区域内的像素点的色值(如RGB值)，本公开实施例可以将相应区域内像素点的色值的均值作为该颜色区域对应的参考特征值，即该颜色的参考特征值。
同样的，与第一特征值的获取方式类似，也可以对相应颜色区域的色值的均值做归一化处理，得到该颜色的参考特征值。归一化处理方式与上述说明相同，例如将色值的均值除以灰度级或者其他标准值，得到归一化的参考特征值，具体过程在此不作重复赘述。
通过上述实施例，可以得到针对图像采集设备对多个颜色的参考特征值，使得后续流程基于此参考特征值进行后续的逻辑处理，即类中心与参考特征值的匹配处理，减少由于图像采集设备的参数对颜色的像素的影响。同时还可以适应用于多种类型的图像采集设备，减少图像采集设备采集的图像之间的颜色偏差。
在一些可能的实施方式中，在确定目标对象为第一状态时，还可以进一步确定指示灯亮起的颜色。
图4示出根据本公开实施例的一种信号指示灯的状态检测方法中步骤S34的流程图，其中，所述根据所述第一状态或者所述第二状态，确定所述目标对象的显示状态，包括：
S3401：在确定所述目标对象为第一状态的情况下，基于与所述参考特征值匹配的类中心对应的类组内的像素点，确定该类组在所述目标区域中所形成的第一面积；
在一些可能的实施方式中，在确定目标对象为第一状态的情况下，可以得到与参考特征值匹配的类中心对应的类组内的像素点在目标区域中形成的区域的第一面积。如可以将与参考特征值匹配的类中心对应的像素点重新映射到目标区域中，确定出该类组的像素点在目标区域中构成的第一面积。本公开实施例可以根据积分的方式确定第一面积，或者也可以通过其他方式得到第一面积，本公开对此不作具体限定。
S3402：基于第一面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述目标对象的显示颜色。
由于与参考特征值匹配的类中心可能存在多个，因此可能得到至少一个类组对应的第一面积，此时，本公开实施例可以将第一面积最大且该第一面积大于面积阈值的类组对应的参考特征值的颜色，确定为目标区域中目标对象的显示颜色。通过该方式可以简单方便的确定目标区域中亮起的信号指示灯的颜色。其中，本公开实施例可以根据需求设定相应的面积阈值，本公开对此不作具体限定。
或者，在本公开的另一些实施例中，也可以对重新映射到目标区域内的多个像素点执行进一步的聚类处理，得到新的多个类组，并进一步确定目标对象的显示颜色，即亮起的指示灯的颜色。通过该种方式可以提高显示颜色的检测精度。
图5示出根据本公开实施例的一种信号指示灯的状态检测方法中步骤S34的另一流程图，其中所述根据所述第一状态或者所述第二状态，确定所述目标对象的显示状态，还可以包括：
S3411：在确定所述目标对象为第一状态的情况下，对与所述参考特征值匹配的类中心对应的类组内的像素点执行聚类处理，得到多个新的类组；
如上述实施例所述，本公开实施例可以将确定的与参考特征匹配的类中心的对应的类组内的像素点重新映射到目标区域中，并可以对所有重新映射的像素点重新执行聚类处理。
其中，同样可以基于重新映射的像素点的第一特征值执行聚类处理，如也可以执行K均值聚类处理，其中，步骤S20中聚类处理中设定的聚类的组数和本步骤中聚类处理设定的类组的组数可以相同，也可以不同，一般可以设置成大于或者等于3的数值。
在基于重新映射的像素点的第一特征值执行该重新映射的像素点的聚类处理后，可以得到多个新的类组，该新的类组可以包括至少一个重新映射到目标区域内的像素点， 通过该步骤可以实现步骤S20得到的与参考特征值匹配的类组内的像素点的重新聚类，形成新的类组，基于此同样也可以得到多个新的类组的类中心，本公开对该过程不作具体限定。
S3412：确定所述新的类组的类中心所匹配的参考特征值，并确定新的类组中的像素点在所述目标区域中所形成的第二面积；
S3413：基于第二面积最大的新的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述目标对象的显示颜色。
在一些可能的实施方式中，在得到多个新的类组之后，可以重新确定多个新的类组的类中心所匹配的参考特征值，该步骤中，可以将与一新的类组的类中心距离最近的参考特征值对应的颜色，确定为该新的类组对应的颜色。
并且，本公开实施例中，还可以基于新的类组内的像素点确定相应的新的类组所构成的第二面积，如可以确定新的类组内像素点所围成的区域，并进一步确定该区域的第二面积，即为相应的新的类组的第二面积。
在得到新的类组的第二面积之后，可以从中选择出第二面积最大的新的类组。进而可以将第二面积最大且大于面积阈值的新的类组的类中心所匹配的参考特征值对应的颜色，确定为目标对象的显示颜色。
通过上述实施例，可以得到第二面积最大的新的类组所对应的参考特征值的颜色，可以将该显示颜色确定为目标对象的显示颜色。通过对匹配到与参考特征值的类组内的像素点重新聚类，由于该重新聚类的过程是针对步骤S20中匹配到参考特征值的类组内的像素点重新聚类，可以减少其他像素点的影响，提高重新聚类得到的类组的精度，以及提高相应颜色的匹配度。
综上所述，本公开实施例提供了一种提高精确的检测信号指示灯的显示状态的技术方案，其中通过检测图像中的目标对象(信号指示灯)所在的目标区域，并对目标对象所在的目标区域内的像素点的特征值进行聚类处理，得到多个聚类，从而根据该多个类组与参考特征值的匹配情况，得到的目标对象的显示状态。通过上述聚类处理，可以将具有相同显示状态的相似像素点确定为一个聚类，通过进一步的对聚类(类组)进行分析准确的确定出目标对象的显示状态，可以提高信号指示灯背景干扰的鲁棒性。
另外，本公开实施例还提供了一种智能驾驶控制方法，该智能驾驶控制方法可以应用在智能驾驶设备中，例如可以应用在智能驾驶车辆(包括自动驾驶和高级辅助驾驶系统)、飞行器、机器人以及导盲设备等设备中。本公开对于智能驾驶设备的类型不作具体限定，只要能够结合信号指示灯的显示状态执行驾驶控制的设备，即可以作为本公开实施例的应用主体。
图7示出根据本公开实施例提供的一种驾驶控制方法的流程图，其中所述驾驶控制方法可以包括：
S100：通过智能驾驶设备上的图像采集设备采集道路图像；
在智能驾驶设备中可以设置有图像采集设备，该图像采集设备可以实时的采集形式过程中的智能驾驶设备前方的道路图像，从而可以采集到包括信号指示灯的道路图像。
S200：将所述道路图像作为目标图像执行如上述实施例所述的信号指示灯的状态检测方法，得到所述道路图像中的信号指示灯的显示状态；
在得到道路图像之后，可以采用上述信号指示灯的状态检测方法检测道路图像中包括的信号指示灯的显示状态，具体过程不再重复，可以参见上述实施例的检测过程。
S200：根据所述道路图像中的信号指示灯的显示状态，生成控制所述智能行驶设备的控制指令并输出，以控制所述智能驾驶设备。
在得到道路图像中包括的信号指示灯的显示状态之后，可以根据该显示状态执行智能行驶设备的行驶参数的控制，即生成控制智能行驶设备的控制指令。控制指令包括以 下至少之一：用于保持形式速度的速度保持控制指令、用于调整行驶速度的速度调整控制指令、用于保持行驶方向的方向保持控制指令、用于调整行驶方向的方向调整控制指令、用于执行预警(如红灯预警、转弯预警等)的预警提示控制指令、驾驶模式切换控制指令。其中，执行聚类处理的参考特征值的颜色可以包括红色参考特征值、绿色参考特征值以及黄色参考特征值，例如，在确定信号指示灯中的红灯亮起时，可以对应的减速或者停止。在确定信号指示灯中的绿灯亮起时，表示可以直行通过，或者，在其他的实施方式中，还可以根据转向指示灯的亮起颜色确定行驶方向、选择车道以及行驶速度中的至少一种。
通过上述实施例可以基于识别的信号灯的显示状态，执行智能驾驶设备的驾驶参数的控制，由于得到的信号灯的显示状态准确性较高，因此，可以准确控制智能驾驶设备。
本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
可以理解，本公开提及的上述各个方法实施例，在不违背原理逻辑的情况下，均可以彼此相互结合形成结合后的实施例，限于篇幅，本公开不再赘述。在不违背逻辑的情况下，本公开提供的不同实现方式之间可以相互结合。
此外，本公开还提供了信号指示灯的状态检测装置、驾驶控制装置、电子设备、计算机可读存储介质、程序，上述均可用来实现本公开提供的任一种信号指示灯的状态检测方法或者驾驶控制方法，相应技术方案和描述和参见方法部分的相应记载，不再赘述。
图8示出根据本公开实施例的一种信号指示灯的状态检测装置的框图，如图8所示，所述信号指示灯的状态检测装置包括：
检测模块10，其用于检测目标图像中的目标区域，并确定所述目标区域内像素点的第一特征值，所述目标区域中包括至少一个具有不同显示状态的信号指示灯；
聚类模块20，其用于基于所述第一特征值对所述目标区域内的像素点进行聚类处理，得到针对像素点的多个类组；
确定模块30，其用于基于得到的所述多个类组确定所述信号指示灯的显示状态。
在一些可能的实施方式中，所述确定模块还用于根据获取所述目标图像的图像采集设备中预设的参考特征值和所述类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心；
响应于存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第一状态。
在一些可能的实施方式中，所述确定模块，用于在根据所述参考特征值和所述类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心之后，响应于不存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第二状态。
在一些可能的实施方式中，所述装置还包括设定模块，其用于利用所述图像采集设备拍摄色彩标定板，得到参考图像；
根据所述参考图像中预设颜色区域内的像素点的色值，确定所述参考特征值。
在一些可能的实施方式中，所述设定模块，用于：
利用所述图像采集设备拍摄色彩标定板，得到参考图像；
将预设颜色区域内的像素点的色值确定为所述参考特征值；或者，对所述预设颜色区域内的像素点的色值执行归一化处理，得到所述参考特征值。
在一些可能的实施方式中，所述参考特征值包括红色状态的参考特征值、黄色状态的参考特征值以及绿色状态的参考特征值。
在一些可能的实施方式中，所述确定模块还用于在确定所述信号指示灯为第一状态的情况下，基于与所述参考特征值匹配的类中心对应的类组内的像素点，确定所述类组在所述目标区域中所形成的第一面积；
将第一面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
基于第一面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述信号指示灯的显示颜色。
在一些可能的实施方式中，所述确定模块还用于在确定所述信号指示灯为第一状态的情况下，对与所述参考特征值匹配的类中心对应的类组内的像素点进行聚类处理，得到多个新的类组；
确定所述新的类组的类中心所匹配的参考特征值，并确定新的类组中的像素点在所述目标区域中所形成的第二面积；
将第二面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
基于第二面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述信号指示灯的显示颜色。
在一些可能的实施方式中，所述检测模块，用于：
检测目标图像中的目标区域；
将所述目标区域内像素点的色值确定为所述第一特征值；或者，对所述目标区域内像素点的色值执行归一化处理，得到所述第一特征值。
在一些可能的实施方式中，所述聚类模块，用于通过K-均值聚类算法，对所述目标区域内的像素点进行聚类，得到预设数目个类组。
图9示出根据本公开实施例的一种驾驶控制装置的框图；所述驾驶控制装置包括：
图像采集设备100，其安装在智能驾驶设备上，并用于采集道路图像；
信号指示灯状态检测模块200，其用于将所述道路图像作为目标图像执行第一方面中任一项所述的信号指示灯的状态检测方法，得到所述道路图像中的信号指示灯的显示状态；
控制模块300，其用于根据所述道路图像中的信号指示灯的显示状态，生成控制所述智能行驶设备的控制指令并输出，以控制所述智能驾驶设备。
在一些可能的实施方式中，所述控制指令包括以下至少之一：速度保持控制指令、速度调整控制指令、方向保持控制指令、方向调整控制指令、预警提示控制指令、驾驶模式切换控制指令。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文方法实施例描述的方法，其具体实现可以参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例还提出一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。计算机可读存储介质可以是非易失性计算机可读存储介质或易失性计算机可读存储介质。
本公开实施例还提出一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为上述方法。
本公开实施例还提出一种计算机程序，包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现上述方法。
电子设备可以被提供为终端、服务器或其它形态的设备。
图10示出根据本公开实施例的一种电子设备的框图。例如，电子设备800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等终端。
参照图10，电子设备800可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制电子设备800的整体操作，诸如与显示，电话呼叫，数据通信， 相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在电子设备800的操作。这些数据的示例包括用于在电子设备800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为电子设备800的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为电子设备800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述电子设备800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当电子设备800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当电子设备800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为电子设备800提供各个方面的状态评估。例如，传感器组件814可以检测到电子设备800的打开/关闭状态，组件的相对定位，例如所述组件为电子设备800的显示器和小键盘，传感器组件814还可以检测电子设备800或电子设备800一个组件的位置改变，用户与电子设备800接触的存在或不存在，电子设备800方位或加速/减速和电子设备800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于电子设备800和其他设备之间有线或无线方式的通信。电子设备800可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，电子设备800可以被一个或多个应用专用集成电路(ASIC)、数 字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质或易失性计算机可读存储介质，例如包括计算机程序指令的存储器804，上述计算机程序指令可由电子设备800的处理器820执行以完成上述方法。
图11示出根据本公开实施例的一种电子设备的另一框图。例如，电子设备1900可以被提供为一服务器。参照图11，电子设备1900包括处理组件1922，其进一步包括一个或多个处理器，以及由存储器1932所代表的存储器资源，用于存储可由处理组件1922的执行的指令，例如应用程序。存储器1932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1922被配置为执行指令，以执行上述方法。
电子设备1900还可以包括一个电源组件1926被配置为执行电子设备1900的电源管理，一个有线或无线网络接口1950被配置为将电子设备1900连接到网络，和一个输入输出(I/O)接口1958。电子设备1900可以操作基于存储在存储器1932的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质或易失性计算机可读存储介质，例如包括计算机程序指令的存储器1932，上述计算机程序指令可由电子设备1900的处理组件1922执行以完成上述方法。
本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用 计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中技术的技术改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (27)

  1. 一种信号指示灯的状态检测方法，其特征在于，包括：
    检测目标图像中的目标区域，并确定所述目标区域内像素点的第一特征值，所述目标区域中包括至少一个具有不同显示状态的信号指示灯；
    基于所述第一特征值对所述目标区域内的像素点进行聚类处理，得到针对像素点的多个类组；
    基于得到的所述多个类组确定所述信号指示灯的显示状态。
  2. 根据权利要求1所述的方法，其特征在于，所述基于得到的所述多个类组确定所述信号指示灯的显示状态，包括：
    根据所述目标图像的图像采集设备中预设的参考特征值和所述类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心；
    响应于存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第一状态。
  3. 根据权利要求2所述的方法，其特征在于，所述方法还包括：
    在根据所述参考特征值和所述类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心之后，响应于不存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第二状态。
  4. 根据权利要求2或3所述的方法，其特征在于，采用以下步骤设定所述参考特征值：
    利用所述图像采集设备拍摄色彩标定板，得到参考图像；
    根据所述参考图像中预设颜色区域内的像素点的色值，确定所述参考特征值。
  5. 根据权利要求4所述的方法，其特征在于，所述根据所述参考图像中预设颜色区域内的像素点的色值，确定所述参考特征值，包括：
    将所述预设颜色区域内的像素点的色值确定为所述参考特征值；或者
    对所述预设颜色区域内的像素点的色值执行归一化处理，得到所述参考特征值。
  6. 根据权利要求2-5中任一项所述的方法，其特征在于，所述参考特征值包括红色状态的参考特征值、黄色状态的参考特征值以及绿色状态的参考特征值。
  7. 根据权利要求2-6中任一项所述的方法，其特征在于，所述方法还包括：
    在确定所述信号指示灯为第一状态的情况下，基于与所述参考特征值匹配的类中心对应的类组内的像素点，确定所述类组在所述目标区域中所形成的第一面积；
    将第一面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
    基于所述第一面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述信号指示灯的显示颜色。
  8. 根据权利要求2-6中任一项所述的方法，其特征在于，所述方法还包括：
    在确定所述信号指示灯为第一状态的情况下，对与所述参考特征值匹配的类中心对应的类组内的像素点进行聚类处理，得到多个新的类组；
    确定所述新的类组的类中心所匹配的参考特征值，并确定所述新的类组中的像素点在所述目标区域中所形成的第二面积；
    将第二面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
    基于所述第二面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述信号指示灯的显示颜色。
  9. 根据权利要求1-8中任意一项所述的方法，其特征在于，所述确定所述目标区域内像素点的第一特征值，包括：
    将所述目标区域内像素点的色值确定为所述第一特征值；或者
    对所述目标区域内像素点的色值执行归一化处理，得到所述第一特征值。
  10. 根据权利要求1-9中任意一项所述的方法，其特征在于，所述基于所述第一特征值对所述目标区域内的像素点进行聚类处理，得到针对像素点的多个类组，包括：
    通过K-均值聚类算法，对所述目标区域内的像素点进行聚类，得到预设数目个类组。
  11. 一种驾驶控制方法，其特征在于，包括：
    通过智能驾驶设备上的图像采集设备采集道路图像；
    将所述道路图像作为目标图像执行如权利要求1-10中任一项所述的信号指示灯的状态检测方法，得到所述道路图像中的信号指示灯的显示状态；
    根据所述道路图像中的信号指示灯的显示状态，生成控制所述智能行驶设备的控制指令并输出，以控制所述智能驾驶设备。
  12. 根据权利要求11所述的方法，其特征在于，所述控制指令包括以下至少之一：速度保持控制指令、速度调整控制指令、方向保持控制指令、方向调整控制指令、预警提示控制指令、驾驶模式切换控制指令。
  13. 一种信号指示灯的状态检测装置，其特征在于，包括：
    检测模块，其用于检测目标图像中的目标区域，并确定所述目标区域内像素点的第一特征值，所述目标区域中包括至少一个具有不同显示状态的信号指示灯；
    聚类模块，其用于基于所述第一特征值对所述目标区域内的像素点进行聚类处理，得到针对像素点的多个类组；
    确定模块，其用于基于得到的所述多个类组确定所述信号指示灯的显示状态。
  14. 根据权利要求13所述的装置，其特征在于，所述确定模块，用于根据获取所述目标图像的图像采集设备中预设的参考特征值和所述类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心；
    响应于存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第一状态。
  15. 根据权利要求14所述的装置，其特征在于，所述确定模块，还用于在根据所述参考特征值和所述类组的类中心对应的第一特征值，确定是否存在与所述参考特征值匹配的类中心之后，响应于不存在与所述参考特征值匹配的类中心，确定所述信号指示灯为第二状态。
  16. 根据权利要求14或15所述的装置，其特征在于，所述装置还包括设定模块，其用于利用所述图像采集设备拍摄色彩标定板，得到参考图像；
    根据所述参考图像中预设颜色区域内的像素点的色值，确定所述参考特征值。
  17. 根据权利要求16所述的装置，其特征在于，所述设定模块，用于：
    利用所述图像采集设备拍摄色彩标定板，得到参考图像；
    将所述预设颜色区域内的像素点的色值确定为所述参考特征值；或者，对所述预设颜色区域内的像素点的色值执行归一化处理，得到所述参考特征值。
  18. 根据权利要求14-17中任意一项所述的装置，其特征在于，所述参考特征值包括红色状态的参考特征值、黄色状态的参考特征值以及绿色状态的参考特征值。
  19. 根据权利要求14-18中任意一项所述的装置，其特征在于，所述确定模块还用于在确定所述信号指示灯为第一状态的情况下，基于与所述参考特征值匹配的类中心对应的类组内的像素点，确定所述类组在所述目标区域中所形成的第一面积；
    将第一面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
    基于所述第一面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内的所述信号指示灯的显示颜色。
  20. 根据权利要求14-18中任意一项所述的装置，其特征在于，所述确定模块还用于在确定所述信号指示灯为第一状态的情况下，对与所述参考特征值匹配的类中心对应的类组内的像素点进行聚类处理，得到多个新的类组；
    确定所述新的类组的类中心所匹配的参考特征值，并确定所述新的类组中的像素点在所述目标区域中所形成的第二面积；
    将第二面积最大的类组包含的像素点确定为所述信号指示灯包含的像素点；
    基于所述第二面积最大的类组的类中心所匹配的参考特征值，确定所述目标区域内 的所述信号指示灯的显示颜色。
  21. 根据权利要求14-20中任意一项所述的装置，其特征在于，所述检测模块，用于：
    检测目标图像中的目标区域；
    将所述目标区域内像素点的色值确定为所述第一特征值；或者，对所述目标区域内像素点的色值执行归一化处理，得到所述第一特征值。
  22. 根据权利要求14-21中任意一项所述的装置，其特征在于，所述聚类模块，用于通过K-均值聚类算法，对所述目标区域内的像素点进行聚类，得到预设数目个类组。
  23. 一种驾驶控制装置，其特征在于，包括：
    图像采集设备，其安装在智能驾驶设备上，并用于采集道路图像；
    信号指示灯状态检测模块，其用于将所述道路图像作为目标图像执行如权利要求1-10中任一项所述的信号指示灯的状态检测方法，得到所述道路图像中的信号指示灯的显示状态；
    控制模块，其用于根据所述道路图像中的信号指示灯的显示状态，生成控制所述智能行驶设备的控制指令并输出，以控制所述智能驾驶设备。
  24. 根据权利要求23所述的装置，其特征在于，所述控制指令包括以下至少之一：速度保持控制指令、速度调整控制指令、方向保持控制指令、方向调整控制指令、预警提示控制指令、驾驶模式切换控制指令。
  25. 一种电子设备，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为：执行权利要求1至10中任意一项所述的方法，或者执行权利要求11或12所述的方法。
  26. 一种计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现权利要求1至10中任意一项所述的方法，或者实现权利要求11或12所述的方法。
  27. 一种计算机程序，包括计算机可读代码，其特征在于，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现权利要求1至10中任意一项所述的方法，或者实现权利要求11或12所述的方法。
PCT/CN2020/091064 2019-05-28 2020-05-19 信号指示灯的状态检测方法及装置、驾驶控制方法及装置 WO2020238699A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020217011238A KR20210058931A (ko) 2019-05-28 2020-05-19 신호 표시등의 상태 검출 방법 및 장치, 운전 제어 방법 및 장치
SG11202102249UA SG11202102249UA (en) 2019-05-28 2020-05-19 State detection method and device for signal indicator, driving control method and device
JP2021513233A JP2021536069A (ja) 2019-05-28 2020-05-19 信号表示灯の状態検出方法及び装置、運転制御方法及び装置
US17/159,352 US20210150232A1 (en) 2019-05-28 2021-01-27 Method and device for detecting a state of signal indicator light, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910450394.3 2019-05-28
CN201910450394.3A CN112016344A (zh) 2019-05-28 2019-05-28 信号指示灯的状态检测方法及装置、驾驶控制方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/159,352 Continuation US20210150232A1 (en) 2019-05-28 2021-01-27 Method and device for detecting a state of signal indicator light, and storage medium

Publications (1)

Publication Number Publication Date
WO2020238699A1 true WO2020238699A1 (zh) 2020-12-03

Family

ID=73501363

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/091064 WO2020238699A1 (zh) 2019-05-28 2020-05-19 信号指示灯的状态检测方法及装置、驾驶控制方法及装置

Country Status (6)

Country Link
US (1) US20210150232A1 (zh)
JP (1) JP2021536069A (zh)
KR (1) KR20210058931A (zh)
CN (1) CN112016344A (zh)
SG (1) SG11202102249UA (zh)
WO (1) WO2020238699A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114148252A (zh) * 2021-12-27 2022-03-08 一汽解放汽车有限公司 应用于车辆中的指示灯控制方法、装置、设备及介质
CN117350485A (zh) * 2023-09-27 2024-01-05 广东电网有限责任公司 基于数据挖掘模型的电力市场管控方法和系统

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112699773B (zh) * 2020-12-28 2023-09-01 阿波罗智联(北京)科技有限公司 交通灯识别方法、装置及电子设备
US20220318954A1 (en) * 2021-03-31 2022-10-06 Advanced Micro Devices, Inc. Real time machine learning-based privacy filter for removing reflective features from images and video
CN113657175A (zh) * 2021-07-21 2021-11-16 山东爱普电气设备有限公司 配电柜开关状态智能识别方法、系统、存储介质及设备
CN113747636B (zh) * 2021-08-24 2022-04-19 安顺市成威科技有限公司 一种基于无线传感器技术的智慧路灯智能调控方法及云调控系统
CN114066823A (zh) * 2021-10-27 2022-02-18 随锐科技集团股份有限公司 检测色块的方法及其相关产品
CN114359844B (zh) * 2022-03-21 2022-06-21 广州银狐科技股份有限公司 一种基于色彩识别的aed设备状态监测方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102785645A (zh) * 2012-04-20 2012-11-21 中兴通讯股份有限公司 一种判断交通灯的方法及终端
CN103093245A (zh) * 2013-01-21 2013-05-08 信帧电子技术（北京）有限公司 视频图像中识别信号灯的方法
US20160318490A1 (en) * 2015-04-28 2016-11-03 Mobileye Vision Technologies Ltd. Systems and methods for causing a vehicle response based on traffic light detection
CN108108761A (zh) * 2017-12-21 2018-06-01 西北工业大学 一种基于深度特征学习的快速交通信号灯检测方法
CN109389838A (zh) * 2018-11-26 2019-02-26 爱驰汽车有限公司 无人驾驶路口路径规划方法、系统、设备及存储介质
US20190130199A1 (en) * 2018-12-27 2019-05-02 Intel Corporation Infrastructure element state model and prediction

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1220182A3 (en) * 2000-12-25 2005-08-17 Matsushita Electric Industrial Co., Ltd. Image detection apparatus, program, and recording medium
CN100498870C (zh) * 2006-06-26 2009-06-10 上海宝信软件股份有限公司 基于视频图像处理的交通信号灯状态判定方法
JP2013242686A (ja) * 2012-05-21 2013-12-05 Nissan Motor Co Ltd 信号機検出装置及び信号機検出方法
CN104019901B (zh) * 2014-06-16 2016-02-17 哈尔滨工业大学 一种基于动态聚类方法的汽车仪表指示灯颜色检测方法
JP6679857B2 (ja) * 2015-04-02 2020-04-15 株式会社リコー 認識装置、認識方法及びプログラム
CN107527511B (zh) * 2016-06-22 2020-10-09 杭州海康威视数字技术股份有限公司 一种智能车辆行车提醒方法及装置
JP6819996B2 (ja) * 2016-10-14 2021-01-27 国立大学法人金沢大学 交通信号認識方法および交通信号認識装置
JP6825299B2 (ja) * 2016-10-24 2021-02-03 株式会社リコー 情報処理装置、情報処理方法およびプログラム
CN108961357B (zh) * 2017-05-17 2023-07-21 浙江宇视科技有限公司 一种交通信号灯过爆图像强化方法及装置
CN109684900B (zh) * 2017-10-18 2021-03-02 百度在线网络技术（北京）有限公司 用于输出颜色信息的方法和装置
CN108681994B (zh) * 2018-05-11 2023-01-10 京东方科技集团股份有限公司 一种图像处理方法、装置、电子设备及可读存储介质
CN109116846B (zh) * 2018-08-29 2022-04-05 五邑大学 一种自动驾驶方法、装置、计算机设备和存储介质
CN109784317B (zh) * 2019-02-28 2021-02-23 东软睿驰汽车技术（沈阳）有限公司 一种交通信号灯的识别方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102785645A (zh) * 2012-04-20 2012-11-21 中兴通讯股份有限公司 一种判断交通灯的方法及终端
CN103093245A (zh) * 2013-01-21 2013-05-08 信帧电子技术（北京）有限公司 视频图像中识别信号灯的方法
US20160318490A1 (en) * 2015-04-28 2016-11-03 Mobileye Vision Technologies Ltd. Systems and methods for causing a vehicle response based on traffic light detection
CN108108761A (zh) * 2017-12-21 2018-06-01 西北工业大学 一种基于深度特征学习的快速交通信号灯检测方法
CN109389838A (zh) * 2018-11-26 2019-02-26 爱驰汽车有限公司 无人驾驶路口路径规划方法、系统、设备及存储介质
US20190130199A1 (en) * 2018-12-27 2019-05-02 Intel Corporation Infrastructure element state model and prediction

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114148252A (zh) * 2021-12-27 2022-03-08 一汽解放汽车有限公司 应用于车辆中的指示灯控制方法、装置、设备及介质
CN114148252B (zh) * 2021-12-27 2023-12-29 一汽解放汽车有限公司 应用于车辆中的指示灯控制方法、装置、设备及介质
CN117350485A (zh) * 2023-09-27 2024-01-05 广东电网有限责任公司 基于数据挖掘模型的电力市场管控方法和系统

Also Published As

Publication number Publication date
JP2021536069A (ja) 2021-12-23
SG11202102249UA (en) 2021-04-29
KR20210058931A (ko) 2021-05-24
CN112016344A (zh) 2020-12-01
US20210150232A1 (en) 2021-05-20

Similar Documents

Publication Publication Date Title
WO2020238699A1 (zh) 信号指示灯的状态检测方法及装置、驾驶控制方法及装置
TWI728621B (zh) 圖像處理方法及其裝置、電子設備、電腦可讀儲存媒體和電腦程式
US20200326179A1 (en) Distance Measurement Method, Intelligent Control Method, Electronic Device, and Storage Medium
WO2021155632A1 (zh) 图像处理方法及装置、电子设备和存储介质
US10007841B2 (en) Human face recognition method, apparatus and terminal
CN106651955B (zh) 图片中目标物的定位方法及装置
CN108629354B (zh) 目标检测方法及装置
WO2020259291A1 (zh) 指示灯的指示信息识别方法及装置、电子设备和存储介质
TW202105246A (zh) 人臉識別方法、電子設備和儲存介質
CN110009090B (zh) 神经网络训练与图像处理方法及装置
US11288531B2 (en) Image processing method and apparatus, electronic device, and storage medium
US9733713B2 (en) Laser beam based gesture control interface for mobile devices
WO2020019760A1 (zh) 活体检测方法、装置及系统、电子设备和存储介质
CN107784279B (zh) 目标跟踪方法及装置
CN105335684B (zh) 人脸检测方法及装置
JP7419495B2 (ja) 投影方法および投影システム
US11455836B2 (en) Dynamic motion detection method and apparatus, and storage medium
US20210152750A1 (en) Information processing apparatus and method for controlling the same
WO2021057244A1 (zh) 光强调节方法及装置、电子设备和存储介质
US11450021B2 (en) Image processing method and apparatus, electronic device, and storage medium
US11574415B2 (en) Method and apparatus for determining an icon position
AU2020323956B2 (en) Image processing method and apparatus, electronic device, and storage medium
CN112819714A (zh) 目标对象曝光方法、装置、存储介质及设备
EP3825894A1 (en) Method, device and terminal for performing word segmentation on text information, and storage medium
US9684828B2 (en) Electronic device and eye region detection method in electronic device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20814736

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021513233

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20217011238

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20814736

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25.08.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20814736

Country of ref document: EP

Kind code of ref document: A1