CN112699773B - Traffic light identification method and device and electronic equipment - Google Patents
Traffic light identification method and device and electronic equipment Download PDFInfo
- Publication number
- CN112699773B CN112699773B CN202011577703.2A CN202011577703A CN112699773B CN 112699773 B CN112699773 B CN 112699773B CN 202011577703 A CN202011577703 A CN 202011577703A CN 112699773 B CN112699773 B CN 112699773B
- Authority
- CN
- China
- Prior art keywords
- traffic light
- traffic
- lights
- light group
- traffic lights
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000008569 process Effects 0.000 claims abstract description 20
- 238000012163 sequencing technique Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000013136 deep learning model Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012913 prioritisation Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 235000014510 cooky Nutrition 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a traffic light identification method, a traffic light identification device and electronic equipment, and relates to the technical field of artificial intelligence such as automatic driving and intelligent traffic. The specific implementation scheme is as follows: acquiring a target image acquired in the running process of a vehicle, wherein the target image comprises image data of M traffic lights; identifying attribute information of the M traffic lights based on the image data of the M traffic lights; clustering the M traffic lights according to the distance information among the M traffic lights to obtain N traffic light groups, wherein the distance information is determined based on the image data of the M traffic lights, and N is a positive integer less than or equal to M; and determining a first traffic light group from the N traffic light groups based on the attribute information of the M traffic lights, wherein the first traffic light group is a traffic light group corresponding to a vehicle driving route. According to the technology provided by the application, the problem of relatively low recognition efficiency in the traffic light recognition technology is solved, and the recognition efficiency of the traffic light is improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to the technical field of automatic driving and intelligent traffic, and particularly relates to a traffic light identification method, a traffic light identification device and electronic equipment.
Background
With the progress of society and the development of economy, traffic light recognition technology is widely used. The recognition of the traffic light information can strengthen the perception of the driver side to the road, and strengthen the judgment capability and early warning consciousness of the driver side to the road condition in front on the driving route.
Currently, the traffic light identification process is usually to combine with auxiliary information such as a global positioning system or a map to identify traffic light information.
Disclosure of Invention
The disclosure provides a traffic light identification method, a traffic light identification device and electronic equipment.
According to a first aspect of the present disclosure, there is provided a traffic light identification method, comprising:
acquiring a target image acquired in the running process of a vehicle, wherein the target image comprises image data of M traffic lights, and M is a positive integer;
identifying attribute information of the M traffic lights based on the image data of the M traffic lights;
clustering the M traffic lights according to the distance information among the M traffic lights to obtain N traffic light groups, wherein the distance information is determined based on the image data of the M traffic lights, and N is a positive integer less than or equal to M;
and determining a first traffic light group from the N traffic light groups based on the attribute information of the M traffic lights, wherein the first traffic light group is a traffic light group corresponding to a vehicle driving route.
According to a second aspect of the present disclosure, there is provided a traffic light identification device comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a target image acquired in the running process of a vehicle, the target image comprises image data of M traffic lights, and M is a positive integer;
the identification module is used for identifying attribute information of the M traffic lights based on the image data of the M traffic lights;
the clustering module is used for clustering the M traffic lights according to the distance information among the M traffic lights to obtain N traffic light groups, the distance information is determined based on the image data of the M traffic lights, and N is a positive integer less than or equal to M;
and the determining module is used for determining a first traffic light group from the N traffic light groups based on the attribute information of the M traffic lights, wherein the first traffic light group is a traffic light group corresponding to a vehicle driving route.
According to a third aspect of the present disclosure, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any one of the methods of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform any of the methods of the first aspect.
According to a fifth aspect of the present disclosure, there is provided a computer program product, which, when run on an electronic device, is capable of performing any of the methods of the first aspect.
The technology solves the problem of low recognition efficiency in the traffic light recognition technology, and improves the recognition efficiency of the traffic light.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are included to provide a better understanding of the present application and are not to be construed as limiting the application. Wherein:
fig. 1 is a flow chart of a traffic light identification method according to a first embodiment of the present application;
FIG. 2 is a schematic diagram of detection and correction of an image to be identified;
FIG. 3 is a flowchart of a specific example of a traffic light identification method according to an embodiment of the present application;
Fig. 4 is a schematic structural view of a traffic light recognition device according to a second embodiment of the present application;
fig. 5 illustrates a schematic block diagram of an example electronic device 500 that may be used to implement embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present application will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present application are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
First embodiment
As shown in fig. 1, the present application provides a traffic light identification method, comprising the following steps:
step S101: and acquiring a target image acquired in the running process of the vehicle, wherein the target image comprises image data of M traffic lights, and M is a positive integer.
In this embodiment, the traffic light recognition method relates to the technical field of artificial intelligence such as automatic driving and intelligent traffic, and can be widely applied to various scenes such as green light prompt during parking waiting, deceleration parking early warning and overspeed red light running early warning when green light is gradually changed into red light.
In actual use, the traffic light identification method of the embodiment of the application can be executed by the traffic light identification device of the embodiment of the application. The traffic light identification device of the embodiment of the application can be configured in the electronic equipment to execute the traffic light identification method of the embodiment of the application. The electronic device may be a vehicle-mounted device.
The traffic light recognition device may include a camera, the target image may be an image to be recognized collected by the camera in the traffic light recognition device during the running process of the vehicle, and the target image may also be an image obtained by processing the image to be recognized collected by the camera in the traffic light recognition device during the running process of the vehicle, which is not particularly limited herein.
The target image may include image data of M traffic lights, which may be data in the form of block areas, that is, image data of block areas having a certain shape and generally consistent colors may be determined to be one traffic light due to color and shape attributes of the traffic lights.
The target image may be obtained in various ways, for example, an image to be identified including image data of the traffic light acquired by a camera in the traffic light identification device may be used as the target image. For another example, the image to be identified may be obtained, and the area including the traffic light in the image to be identified may be intercepted, so as to obtain the target image.
Step S102: and identifying attribute information of the M traffic lights based on the image data of the M traffic lights.
In this step, the attribute information of the traffic light may include three types, color attribute information, shape attribute information, and orientation attribute information, respectively, the color attribute information may include no lighting (the traffic light may be in a bad or unopened state), red, green, and yellow, the shape attribute information may include a cookie, a time number, straight, left turn, right turn, turning around, pedestrians, and non-motor vehicles, and the orientation attribute information may include a front, a side, and a back.
The attribute information of the M traffic lights may be identified using a deep learning model such as a neural network based on the image data of the M traffic lights. Specifically, the target image may be input to a neural network, and the neural network may determine the type of color, shape and orientation of the traffic lights based on the image data of the M traffic lights marked in the target image by using geometric features of the traffic lights (such as a shape of a traffic light generally in a shape of a pie, an arrow, or a pattern indicating pedestrians and motor vehicles, etc.), so as to identify attribute information of the M traffic lights.
Step S103: and clustering the M traffic lights according to the distance information among the M traffic lights to obtain N traffic light groups, wherein the distance information is determined based on the image data of the M traffic lights, and N is a positive integer less than or equal to M.
In this step, since the image data of the traffic light is a block area, that is, the image data of the M traffic lights can be divided into M block areas, the distance information between the M traffic lights can be determined by determining the distance information between the M block areas in the target image. The distance information between the two block areas can represent the distance information between the corresponding two traffic lights, and the larger the distance represented by the distance information between the two block areas is, the larger the distance between the corresponding two traffic lights is.
The M traffic lights can be clustered according to the distance information among the M traffic lights, and the principle of clustering can be to cluster the traffic lights with relatively close distances together and classify the traffic lights with relatively far distances.
When clustering is carried out, a distance threshold value can be set, two traffic lights with the distance represented by the distance information being close to the distance threshold value are clustered together to form a traffic light group, and two traffic lights with the distance represented by the distance information being far from the distance threshold value are separated, so that N traffic light groups can be finally generated. Each traffic light group includes at least one traffic light, as shown in fig. 2, and the target image includes three traffic lights, namely, traffic light 201, traffic light 202 and traffic light 203, where the traffic lights 201 and 202 can be clustered together to generate one traffic light group 204, and the traffic lights 203 are clustered separately into one group to generate another traffic light group because they are far from both traffic light 201 and traffic light 202.
Step S104: and determining a first traffic light group from the N traffic light groups based on the attribute information of the M traffic lights, wherein the first traffic light group is a traffic light group corresponding to a vehicle driving route.
In this step, the first traffic light group may be a traffic light group corresponding to a vehicle driving route, that is, a traffic light group that a driver should pay attention to on the vehicle driving route, that is, the first traffic light group includes traffic lights indicating how the driver drives on the vehicle driving route. For example, the traffic light group that the driver usually needs to pay attention to on the vehicle driving route is a traffic light group whose orientation attribute information is positive, that is, the orientation attribute information of the first traffic light group is positive.
A first traffic light group may be determined from the N traffic light groups based on attribute information of the M traffic lights. And the first traffic light group may be determined from the N traffic light groups based on the attribute information of the M traffic lights in a variety of ways.
For example, based on the fact that the driver usually does not pay attention to traffic lights with side and front facing attribute information on the vehicle driving route, the color attribute information is a traffic light which is not lighted by a lamp, and the shape attribute information is a traffic light of pedestrians and non-vehicles, it is possible to determine that the driver does not pay attention to the traffic light on the vehicle driving route among the M traffic lights based on the attribute information of the M traffic lights, and filter the traffic light group including the traffic light which the driver does not pay attention to on the vehicle driving route from the N traffic light groups.
Then, the first traffic light group may be selected from the remaining traffic light groups according to a preset rule, for example, in the case that the traffic intersection is relatively complex, the traffic light group that the driver needs to pay attention to generally includes a relatively large number of traffic lights, and at this time, the traffic light group with the largest number of traffic lights may be selected according to the number of traffic lights in the traffic light group, that is, the traffic light group with the largest number of traffic lights is selected as the first traffic light group. For another example, the traffic light group that the driver needs to pay attention to is usually located at a position with a relatively high distance from the ground, and at this time, the traffic light group may be selected according to the distance between the traffic light and the ground in the traffic light group, that is, the traffic light group with the highest distance between the traffic light and the ground is selected as the first traffic light group.
For another example, the N traffic light groups may be ranked in priority based on attribute information of the M traffic lights, for example, in a case where a traffic intersection is complex, the N traffic light groups may be ranked in order of a number from more to less, traffic light groups with a relatively large number of traffic lights may be ranked in front, and traffic light groups with a relatively small number of traffic lights may be ranked in rear. For another example, the N traffic light groups may be ordered according to the direction of the traffic light in the traffic light group, where the traffic light group with the front direction of the traffic light is arranged in front, and the traffic light group with the side and back directions of the traffic light is arranged in back. Also for example, the N traffic light groups may be ordered in order of a distance between the traffic light and the ground in the traffic light group from high to low. Alternatively, the comprehensive ordering can be performed from the number, the direction and the distance between the traffic lights and the ground. Thereafter, the traffic light group that is most front ranked may be determined as the first traffic light group.
In this embodiment, by identifying attribute information of M traffic lights in the target image, clustering the M traffic lights according to distance information between the M traffic lights to obtain N traffic light groups, and determining a first traffic light group from the N traffic light groups based on the attribute information of the M traffic light groups, where the first traffic light group is a traffic light group for determining that a driver advances or stops on a vehicle driving route. Therefore, the target traffic light group which needs to be focused by the driver of the vehicle driving route can be identified by adopting a pure vision scheme without assistance information such as a global positioning system, a map and the like, so that the identification efficiency of the traffic light can be improved.
And the method can get rid of the dependence of global positioning system information, map information, road side transmission signals and the like, is effective for each traditional traffic light of urban roads, and has wide popularization. Moreover, due to the characteristics of a pure visual scheme, the method is efficient, quick and low in cost.
Optionally, the step S104 specifically includes:
filtering second traffic light groups from the N traffic light groups based on the attribute information of the M traffic lights to obtain P traffic light groups, wherein the second traffic light groups are traffic light groups irrelevant to a vehicle driving route, and P is a positive integer less than or equal to N;
A first traffic light group is determined from the P traffic light groups.
In this embodiment, in order to improve the processing efficiency, to avoid the influence of some drivers on the final result by the traffic light groups on the vehicle driving route, the second traffic light groups may be filtered from the N traffic light groups based on the attribute information of the M traffic lights, where the second traffic light groups are traffic light groups unrelated to the vehicle driving route, for example, the traffic light groups including traffic lights with shape attribute information of pedestrians and non-vehicles, and the traffic light groups are usually traffic light groups indicating pedestrians and non-vehicles, where the drivers do not need to pay attention, and may filter. For another example, a traffic light set that includes traffic lights with side and back facing attribute information, which generally indicates vehicles on the side and vehicles on the opposite side, may be filtered out without attention from the driver.
Thereafter, a first traffic light group may be determined from the P traffic light groups. The manner of determining the first traffic light group from the P traffic light groups is similar to the manner of determining the first traffic light group from the N traffic light groups described above, and will not be described in detail herein.
In this embodiment, the second traffic light group is filtered from the N traffic light groups based on the attribute information of the M traffic lights to obtain P traffic light groups, and the first traffic light group is determined from the P traffic light groups, so that the processing efficiency of determining the first traffic light group can be improved.
Optionally, the determining the first traffic light group from the P traffic light groups includes:
for each traffic light group in the P traffic light groups, acquiring L sorting priorities corresponding to L dimensions of the traffic light groups respectively, wherein L is a positive integer;
determining the comprehensive sequencing priority of a target traffic light group based on L sequencing priorities of the target traffic light group, wherein the target traffic light group is any traffic light group in the P traffic light groups;
and determining the traffic light group with the highest comprehensive sequencing priority among the P traffic light groups as the first traffic light group.
In this embodiment, L may be a positive integer, and a case where L is 3 will be described in detail below.
The L dimensions can comprise the number, the orientation and the height of the traffic lights and the ground, the sorting priority of each of the P traffic light groups can be obtained according to each traffic light group in the traffic light groups, the sorting priority of each dimension is respectively corresponding to the traffic light groups, and finally the L sorting priorities of each traffic light group can be obtained. For example, for the traffic light group a, the ranking priority is rank 1 according to the number dimension, the ranking priority is rank 1 according to the direction dimension, and the ranking priority is rank 2 according to the height of the traffic light and the ground.
The comprehensive prioritization of the target traffic light group may be determined based on the L prioritization priorities of the target traffic light group, which may be any one of the P traffic light groups. Specifically, the sorting priority of the target traffic light group may be the sorting priority of the target traffic light group when the L sorting priorities are equal in level, and the comprehensive sorting priority of the target traffic light group may be determined based on the weights of the L sorting priorities and the L sorting priorities when the L sorting priorities are unequal in level.
In addition, the P traffic light groups can be ranked based on the distance between the traffic light and the vehicle in the traffic light group, so that the ranking priority of the dimension can be obtained. The farther a traffic light is from the vehicle in a traffic light group, the lower the ranking priority level in the traffic light group, otherwise the higher the level. That is, the driver typically needs to pay attention to traffic lights that are closer together and then to traffic lights that are farther apart on the vehicle's travel route. And then, the sorting priorities of the 3 dimensions can be combined with the sorting priorities of the dimensions to determine the comprehensive sorting priorities of the traffic light groups.
And then, the traffic light group with the highest comprehensive sorting priority among the P traffic light groups can be determined as the first traffic light group.
In this embodiment, for each of the P traffic light groups, L sorting priorities of the traffic light groups corresponding to L dimensions are obtained; determining a comprehensive sequencing priority of a target traffic light group based on L sequencing priorities of the target traffic light group; and determining the traffic light group with the highest comprehensive sequencing priority among the P traffic light groups as the first traffic light group. In this way, the comprehensive sort priority of the traffic light groups may be evaluated from one or more dimensions to determine the first traffic light group from the P traffic light groups based on the comprehensive sort priority, which may improve the accuracy of the identification of the first traffic light group.
Optionally, the step S101 specifically includes:
acquiring an image to be identified acquired by a camera in the running process of a vehicle, wherein the image to be identified comprises image data of a traffic light;
and intercepting the area including the traffic light in the image to be identified to obtain the target image.
In this embodiment, the target image may be an image obtained by processing an image to be identified acquired by a camera in the traffic light identification device during the running process of the vehicle.
In general, in consideration of the actual situation of a driver during the running of a vehicle, it is necessary to prompt the driver to run in advance based on the recognition result of traffic lights, and thus it is necessary to start the recognition of traffic lights at a distance from a traffic intersection. In such an application scenario, the traffic light is far from the vehicle, and the image data of the traffic light is generally distributed in a certain area in the image to be recognized on the position distribution in the collected image to be recognized, but the area is generally not located at a position higher than the position in the image to be recognized.
Meanwhile, for a driver, the traffic light which should be focused is not positioned at a position with a relatively border in the image to be recognized, and when the traffic light is positioned at the border position, the driver is relatively close to the traffic light, and does not need to carry out driving prompt based on the traffic light, or the traffic light is positioned in other directions of other intersections, and is not a traffic light which needs to be focused on a vehicle driving route.
Based on the position distribution characteristics of the traffic lights which need to be focused by the driver in the image to be recognized, the image to be recognized collected by the camera is not used as the input of the traffic light recognition, but the area including the traffic lights in the image to be recognized is intercepted, and the target image is obtained to be used as the input of the traffic light recognition. The traffic light to be focused on by the driver is usually located in the middle area of the image to be recognized, so that the middle area in the image to be recognized can be intercepted to obtain a target image, as shown in fig. 2, the area including the traffic light in the image to be recognized is the area 205, and the image obtained by intercepting the area 205 is the target image.
In this embodiment, based on the position distribution characteristics of the traffic light to be focused by the driver in the image to be recognized, the area including the traffic light in the image to be recognized, which is collected by the camera during the driving process of the vehicle, is intercepted, and the target image is obtained. Because the image data is reduced, when the traffic lights are identified based on the target image, the deep learning model can be extremely compressed, so that the traffic lights are identified very efficiently and quickly.
Optionally, before the step S102, the method further includes:
detecting the image data of the traffic lights in the target image to obtain the image data of Q traffic lights in the target image, wherein Q is a positive integer less than or equal to M;
and correcting the image data of the Q traffic lights in the target image based on cluster characteristics of the traffic lights on the vehicle driving route to obtain the image data of the M traffic lights in the target image.
In this embodiment, since the image is a purely visual scheme, it is necessary to detect the image data of the M traffic lights in the target image after the target image is acquired and before the attribute information of the M traffic lights is identified based on the image data of the M traffic lights.
Specifically, a deep learning model, such as a neural network, may be used to detect the image data of the traffic lights in the target image, so as to obtain the image data of Q traffic lights in the target image, where Q is a positive integer less than or equal to M.
In the detection phase, it may not be necessary to completely detect the image data of the M traffic lights in the target image, and thus, this phase may be used as a coarse positioning phase of the image data of the traffic lights in the target image.
And in the fine positioning stage, the image data of the Q traffic lights in the target image can be corrected based on the cluster characteristics of the traffic lights on the vehicle driving route, so that the image data of the M traffic lights in the target image can be obtained.
Taking fig. 2 as an example, in the detection stage, only the image data of the traffic light 201 and the traffic light 203 can be detected through the deep learning model, and based on the cluster clustering feature of the traffic lights on the vehicle driving route, for example, on the traffic intersection of two lanes, two traffic lights are usually arranged on the traffic light device for prompting the vehicle to drive, at this time, the image data of the traffic light 202 can be corrected in the correction stage, and finally the image data of the traffic light 201, the traffic light 202 and the traffic light 203 can be obtained.
In the correction stage, the image data of the Q traffic lights in the target image may also be corrected based on a deep learning model, such as a neural network, based on the cluster characteristics of the traffic lights on the vehicle driving route and the image data of the Q traffic lights detected in the detection stage, so as to finally obtain the image data of the M traffic lights in the target image.
In this embodiment, image data of Q traffic lights in the target image is obtained by detecting image data of traffic lights in the target image in a detection stage, where Q is a positive integer less than or equal to M; and correcting the image data of the Q traffic lights in the target image based on the cluster characteristics of the traffic lights on the vehicle driving route through a correction stage to obtain the image data of the M traffic lights in the target image. Therefore, the image data of the M traffic lights in the target image are detected in two stages, the detection accuracy and the sufficiency of the image data of the traffic lights in the target image can be improved, and the image data of the traffic lights in the target image can be corrected by utilizing the cluster characteristics of the traffic lights on the vehicle driving route, so that the detection efficiency can be improved.
Optionally, after the step S104, the method further includes:
tracking the traffic light states of the traffic lights in the first traffic light group in the target image to obtain a state conversion result of the traffic lights in the first traffic light group;
and carrying out driving prompt based on the state conversion result of the traffic lights in the first traffic light group.
In this embodiment, after the first traffic light group is determined, based on the efficient principle, the first traffic light group may be continuously tracked by using a pure vision scheme, so as to determine a state conversion result of the traffic lights in the first traffic light group, and prompt the driver to travel.
The method can track traffic lights in each frame of target image acquired in the vehicle driving process by adopting a deep learning model such as a neural network, identify the traffic light state of the traffic lights in each frame of target image, and determine the state conversion result of the traffic lights in the first traffic light group based on the state information of the traffic lights in the first traffic light group in the target images of the successive frames. The traffic light status of the traffic light may refer to color attribute information of the traffic light.
For example, the first traffic light group includes two traffic lights, namely, a traffic light for indicating left turn and a traffic light for indicating straight going. The color attribute information of the two traffic lights in the first traffic light group in the previously collected target image is red and green respectively, and the color attribute information of the two traffic lights in the first traffic light group in the currently collected target image is red and yellow respectively. At this time, the color attribute information of the traffic lights for indicating straight running is changed, and the state change result of the traffic lights for indicating straight running in the first traffic light group can be changed from green to red.
In this embodiment, the traffic light state of the traffic light in the first traffic light group that decides to advance or stop, which should be focused by the driver on the vehicle driving route, is accurately identified and tracked, so that the state change result of the traffic light in the first traffic light group can be obtained, and the driving prompt is performed based on the state change result of the traffic light in the first traffic light group. Therefore, the dependence of global positioning system information, map information, road side transmission signals and the like can be eliminated, the judging capability and early warning consciousness of the driver side on the road condition in front of the vehicle driving route are enhanced, and the safety of vehicle driving is improved.
In order to more clearly illustrate the embodiments of the present application, the following describes in detail all the procedures of the traffic light identification method of the embodiments of the present application.
Fig. 3 is a flow chart of a specific example of a traffic light identification method in an embodiment of the present application, and as shown in fig. 3, the whole flow frame of the traffic light identification method includes five stages, namely a detection stage, a correction stage, a tracking stage, an identification stage and a clustering stage, where the identification stage may include a first identification stage and a second identification stage, and specifically includes the following processes:
And acquiring an image to be identified at a certain frequency, and intercepting an area including a traffic light in the image to be identified to obtain a target image.
The image data of the traffic lights in the target image are detected in the detection stage, coarse positioning of the image data of the traffic lights in the target image is realized, the result in the detection stage is locally and accurately adjusted in the correction stage, the effect of fine positioning is achieved, and finally the image data of M traffic lights in the target image is obtained.
Wherein, in the detection stage and the correction stage, the image data of the traffic light in the target image can be detected and corrected using the deep learning model, and for the purpose of achieving high efficiency, the detection and correction can be performed once at fixed intervals in the acquired image.
Then, in the tracking stage, traffic lights in the target image can be tracked for the target image acquired by each frame.
In the first recognition stage, the detected and tracked traffic lights are recognized, and attribute information of the traffic lights is determined.
In the clustering stage, the M traffic lights can be clustered according to the distance information among the M traffic lights to obtain N traffic light groups.
In a second recognition phase, a first traffic light group is recognized from the N traffic light groups.
And then, judging whether the states of the traffic lights in the first traffic light group are changed or not and prompting the state based on the states of the traffic lights before the traffic lights in the first traffic light group and the current states of the traffic lights.
Second embodiment
As shown in fig. 4, the present application provides a traffic light recognition device 400, comprising:
the acquiring module 401 is configured to acquire a target image acquired during a vehicle driving process, where the target image includes image data of M traffic lights, and M is a positive integer;
an identification module 402, configured to identify attribute information of the M traffic lights based on image data of the M traffic lights;
the clustering module 403 is configured to cluster the M traffic lights according to distance information between the M traffic lights, to obtain N traffic light groups, where the distance information is determined based on image data of the M traffic lights, and N is a positive integer less than or equal to M;
and the determining module 404 is configured to determine a first traffic light group from the N traffic light groups based on the attribute information of the M traffic lights, where the first traffic light group is a traffic light group corresponding to a vehicle driving route.
Optionally, the determining module 404 includes:
the filtering unit is used for filtering second traffic light groups from the N traffic light groups based on the attribute information of the M traffic lights to obtain P traffic light groups, wherein the second traffic light groups are traffic light groups irrelevant to a vehicle driving route, and P is a positive integer less than or equal to N;
And the determining unit is used for determining a first traffic light group from the P traffic light groups.
Optionally, the determining unit is specifically configured to obtain, for each traffic light group in the P traffic light groups, L sorting priorities of the traffic light groups corresponding to L dimensions, where L is a positive integer; determining the comprehensive sequencing priority of a target traffic light group based on L sequencing priorities of the target traffic light group, wherein the target traffic light group is any traffic light group in the P traffic light groups; and determining the traffic light group with the highest comprehensive sequencing priority among the P traffic light groups as the first traffic light group.
Optionally, the acquiring module 401 includes:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring an image to be identified acquired by a camera in the running process of a vehicle, and the image to be identified comprises image data of traffic lights;
and the intercepting unit is used for intercepting the area including the traffic light in the image to be identified to obtain the target image.
Optionally, the apparatus further includes:
the detection module is used for detecting the image data of the traffic lights in the target image to obtain the image data of Q traffic lights in the target image, wherein Q is a positive integer less than or equal to M;
And the correction module is used for correcting the image data of the Q traffic lights in the target image based on the cluster characteristics of the traffic lights on the vehicle driving route to obtain the image data of the M traffic lights in the target image.
Optionally, the apparatus further includes:
the tracking module is used for tracking the traffic light states of the traffic lights in the first traffic light group in the target image so as to obtain a state conversion result of the traffic lights in the first traffic light group;
and the prompting module is used for prompting the running based on the state conversion result of the traffic lights in the first traffic light group.
The traffic light identification device 400 provided by the application can realize each process realized by the traffic light identification method embodiment, and can achieve the same beneficial effects, and in order to avoid repetition, the description is omitted here.
According to embodiments of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.
Fig. 5 illustrates a schematic block diagram of an example electronic device 500 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the applications described and/or claimed herein.
As shown in fig. 5, the apparatus 500 includes a computing unit 501 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, ROM502, and RAM503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Various components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, etc.; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508 such as a magnetic disk, an optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 501 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as a traffic light identification method. For example, in some embodiments, the traffic light identification method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM502 and/or the communication unit 509. When the computer program is loaded into RAM503 and executed by computing unit 501, one or more steps of the traffic light identification method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the traffic light identification method by any other suitable method (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out the methods of the present disclosure can be written in any combination of one or more editing languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed embodiments are achieved, and are not limited herein.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.
Claims (10)
1. A traffic light identification method comprising:
acquiring a target image acquired in the running process of a vehicle, wherein the target image comprises image data of M traffic lights, and M is a positive integer;
identifying attribute information of the M traffic lights based on the image data of the M traffic lights;
clustering the M traffic lights according to the distance information among the M traffic lights to obtain N traffic light groups, wherein the distance information is determined based on the image data of the M traffic lights, and N is a positive integer less than or equal to M;
Determining a first traffic light group from the N traffic light groups based on the attribute information of the M traffic lights, wherein the first traffic light group is a traffic light group corresponding to a vehicle driving route;
the determining a first traffic light group from the N traffic light groups based on the attribute information of the M traffic lights includes:
filtering second traffic light groups from the N traffic light groups based on the attribute information of the M traffic lights to obtain P traffic light groups, wherein the second traffic light groups are traffic light groups irrelevant to a vehicle driving route, and P is a positive integer less than or equal to N;
determining a first traffic light group from the P traffic light groups;
the determining a first traffic light group from the P traffic light groups includes:
for each traffic light group in the P traffic light groups, acquiring L sorting priorities corresponding to L dimensions of the traffic light groups respectively, wherein L is a positive integer; determining the comprehensive sequencing priority of a target traffic light group based on L sequencing priorities of the target traffic light group, wherein the target traffic light group is any traffic light group in the P traffic light groups; determining the traffic light group with highest comprehensive sequencing priority among the P traffic light groups as the first traffic light group; or,
Selecting a traffic light group with the largest traffic light number from the P traffic light groups as a first traffic light group; or,
and selecting the traffic light group with the highest distance between the traffic light and the ground from the P traffic light groups as a first traffic light group.
2. The method of claim 1, wherein the acquiring the target image acquired during the driving of the vehicle comprises:
acquiring an image to be identified acquired by a camera in the running process of a vehicle, wherein the image to be identified comprises image data of a traffic light;
and intercepting the area including the traffic light in the image to be identified to obtain the target image.
3. The method of claim 1, the identifying attribute information of the M traffic lights based on the image data of the M traffic lights further comprising:
detecting the image data of the traffic lights in the target image to obtain the image data of Q traffic lights in the target image, wherein Q is a positive integer less than or equal to M;
and correcting the image data of the Q traffic lights in the target image based on cluster characteristics of the traffic lights on the vehicle driving route to obtain the image data of the M traffic lights in the target image.
4. The method of claim 1, the determining a first traffic light group from the N traffic light groups based on the attribute information of the M traffic lights further comprising:
tracking the traffic light states of the traffic lights in the first traffic light group in the target image to obtain a state conversion result of the traffic lights in the first traffic light group;
and carrying out driving prompt based on the state conversion result of the traffic lights in the first traffic light group.
5. A traffic light identification device comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a target image acquired in the running process of a vehicle, the target image comprises image data of M traffic lights, and M is a positive integer;
the identification module is used for identifying attribute information of the M traffic lights based on the image data of the M traffic lights;
the clustering module is used for clustering the M traffic lights according to the distance information among the M traffic lights to obtain N traffic light groups, the distance information is determined based on the image data of the M traffic lights, and N is a positive integer less than or equal to M;
the determining module is used for determining a first traffic light group from the N traffic light groups based on the attribute information of the M traffic lights, wherein the first traffic light group is a traffic light group corresponding to a vehicle driving route;
The determining module includes:
the filtering unit is used for filtering second traffic light groups from the N traffic light groups based on the attribute information of the M traffic lights to obtain P traffic light groups, wherein the second traffic light groups are traffic light groups irrelevant to a vehicle driving route, and P is a positive integer less than or equal to N;
a determining unit, configured to determine a first traffic light group from the P traffic light groups;
the determining unit is specifically configured to:
for each traffic light group in the P traffic light groups, acquiring L sorting priorities corresponding to L dimensions of the traffic light groups respectively, wherein L is a positive integer; determining the comprehensive sequencing priority of a target traffic light group based on L sequencing priorities of the target traffic light group, wherein the target traffic light group is any traffic light group in the P traffic light groups; determining the traffic light group with highest comprehensive sequencing priority among the P traffic light groups as the first traffic light group; or,
selecting a traffic light group with the largest traffic light number from the P traffic light groups as a first traffic light group; or,
and selecting the traffic light group with the highest distance between the traffic light and the ground from the P traffic light groups as a first traffic light group.
6. The apparatus of claim 5, wherein the acquisition module comprises:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring an image to be identified acquired by a camera in the running process of a vehicle, and the image to be identified comprises image data of traffic lights;
and the intercepting unit is used for intercepting the area including the traffic light in the image to be identified to obtain the target image.
7. The apparatus of claim 5, further comprising:
the detection module is used for detecting the image data of the traffic lights in the target image to obtain the image data of Q traffic lights in the target image, wherein Q is a positive integer less than or equal to M;
and the correction module is used for correcting the image data of the Q traffic lights in the target image based on the cluster characteristics of the traffic lights on the vehicle driving route to obtain the image data of the M traffic lights in the target image.
8. The apparatus of claim 5, further comprising:
the tracking module is used for tracking the traffic light states of the traffic lights in the first traffic light group in the target image so as to obtain a state conversion result of the traffic lights in the first traffic light group;
and the prompting module is used for prompting the running based on the state conversion result of the traffic lights in the first traffic light group.
9. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.
10. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011577703.2A CN112699773B (en) | 2020-12-28 | 2020-12-28 | Traffic light identification method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011577703.2A CN112699773B (en) | 2020-12-28 | 2020-12-28 | Traffic light identification method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112699773A CN112699773A (en) | 2021-04-23 |
| CN112699773B true CN112699773B (en) | 2023-09-01 |
Family
ID=75512271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011577703.2A Active CN112699773B (en) | 2020-12-28 | 2020-12-28 | Traffic light identification method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112699773B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114333380A (en) * | 2021-12-13 | 2022-04-12 | 重庆长安汽车股份有限公司 | Traffic light identification method and system based on camera and V2x, and vehicle |
| CN117152718B (en) * | 2023-10-31 | 2024-03-15 | 广州小鹏自动驾驶科技有限公司 | Traffic light response method, device, vehicle and computer readable storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408944A (en) * | 2014-11-10 | 2015-03-11 | 天津市市政工程设计研究院 | Lamp group based mixed traffic flow signal timing optimization method |
| CN108305475A (en) * | 2017-03-06 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of traffic lights recognition methods and device |
| CN110543814A (en) * | 2019-07-22 | 2019-12-06 | 华为技术有限公司 | Traffic light identification method and device |
| CN110706494A (en) * | 2019-10-30 | 2020-01-17 | 北京百度网讯科技有限公司 | Control method, device, equipment and storage medium for automatic driving vehicle |
| CN110930715A (en) * | 2019-11-21 | 2020-03-27 | 浙江大华技术股份有限公司 | Method and system for identifying red light running of non-motor vehicle and violation processing platform |
| CN111079563A (en) * | 2019-11-27 | 2020-04-28 | 北京三快在线科技有限公司 | Traffic signal lamp identification method and device, electronic equipment and storage medium |
| CN111292531A (en) * | 2020-02-06 | 2020-06-16 | 北京百度网讯科技有限公司 | Tracking method, device and equipment of traffic signal lamp and storage medium |
| CN111428647A (en) * | 2020-03-25 | 2020-07-17 | 浙江浙大中控信息技术有限公司 | Traffic signal lamp fault detection method |
| CN111627233A (en) * | 2020-06-09 | 2020-09-04 | 上海商汤智能科技有限公司 | Method and device for coordinating passing route for vehicle |
| CN111627241A (en) * | 2020-05-27 | 2020-09-04 | 北京百度网讯科技有限公司 | Method and device for generating vehicle queuing information |
| CN111661054A (en) * | 2020-05-08 | 2020-09-15 | 东软睿驰汽车技术（沈阳）有限公司 | Vehicle control method, device, electronic device and storage medium |
| CN112016344A (en) * | 2019-05-28 | 2020-12-01 | 深圳市商汤科技有限公司 | State detection method and device of signal indicator lamp and driving control method and device |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2643861C1 (en) * | 2014-03-10 | 2018-02-06 | Ниссан Мотор Ко., Лтд. | Device for detecting light signals and method for detecting light signals |
| BR112017000267B1 (en) * | 2014-07-08 | 2021-12-28 | Nissan Motor Co., Ltd | TRAFFIC SIGNAL DETECTION DEVICE AND TRAFFIC SIGNAL DETECTION METHOD |
| US10055655B2 (en) * | 2015-04-08 | 2018-08-21 | Nissan Motor Co., Ltd. | Traffic light detection device and traffic light detection method |
| US10074272B2 (en) * | 2015-12-28 | 2018-09-11 | Here Global B.V. | Method, apparatus and computer program product for traffic lane and signal control identification and traffic flow management |
| US10699142B2 (en) * | 2017-04-20 | 2020-06-30 | GM Global Technology Operations LLC | Systems and methods for traffic signal light detection |
| CN109508580B (en) * | 2017-09-15 | 2022-02-25 | 阿波罗智能技术(北京)有限公司 | Traffic signal lamp identification method and device |
| CN111212772B (en) * | 2017-10-23 | 2023-05-23 | 宝马股份公司 | Method and device for determining a driving strategy of a vehicle |
| CN110660254B (en) * | 2018-06-29 | 2022-04-08 | 北京市商汤科技开发有限公司 | Traffic signal lamp detection and intelligent driving method and device, vehicle and electronic equipment |
-
2020
- 2020-12-28 CN CN202011577703.2A patent/CN112699773B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408944A (en) * | 2014-11-10 | 2015-03-11 | 天津市市政工程设计研究院 | Lamp group based mixed traffic flow signal timing optimization method |
| CN108305475A (en) * | 2017-03-06 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of traffic lights recognition methods and device |
| CN112016344A (en) * | 2019-05-28 | 2020-12-01 | 深圳市商汤科技有限公司 | State detection method and device of signal indicator lamp and driving control method and device |
| CN110543814A (en) * | 2019-07-22 | 2019-12-06 | 华为技术有限公司 | Traffic light identification method and device |
| CN110706494A (en) * | 2019-10-30 | 2020-01-17 | 北京百度网讯科技有限公司 | Control method, device, equipment and storage medium for automatic driving vehicle |
| CN110930715A (en) * | 2019-11-21 | 2020-03-27 | 浙江大华技术股份有限公司 | Method and system for identifying red light running of non-motor vehicle and violation processing platform |
| CN111079563A (en) * | 2019-11-27 | 2020-04-28 | 北京三快在线科技有限公司 | Traffic signal lamp identification method and device, electronic equipment and storage medium |
| CN111292531A (en) * | 2020-02-06 | 2020-06-16 | 北京百度网讯科技有限公司 | Tracking method, device and equipment of traffic signal lamp and storage medium |
| CN111428647A (en) * | 2020-03-25 | 2020-07-17 | 浙江浙大中控信息技术有限公司 | Traffic signal lamp fault detection method |
| CN111661054A (en) * | 2020-05-08 | 2020-09-15 | 东软睿驰汽车技术（沈阳）有限公司 | Vehicle control method, device, electronic device and storage medium |
| CN111627241A (en) * | 2020-05-27 | 2020-09-04 | 北京百度网讯科技有限公司 | Method and device for generating vehicle queuing information |
| CN111627233A (en) * | 2020-06-09 | 2020-09-04 | 上海商汤智能科技有限公司 | Method and device for coordinating passing route for vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 汽车辅助驾驶系统交通信号灯识别;李海霞;罗芳芳;;电子技术与软件工程(第13期);250-252 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112699773A (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11694430B2 (en) | Brake light detection | |
| CN108875603B (en) | Intelligent driving control method and device based on lane line and electronic equipment | |
| WO2020038091A1 (en) | Intelligent driving control method and apparatus, electronic device, program and medium | |
| CN111428663B (en) | Traffic light state identification method and device, electronic equipment and storage medium | |
| CN112699773B (en) | Traffic light identification method and device and electronic equipment | |
| JP2022507077A (en) | Compartment line attribute detection methods, devices, electronic devices and readable storage media | |
| WO2021013227A1 (en) | Image processing method and apparatus for target detection | |
| JP2021168174A (en) | Method and apparatus for identifying vehicle alignment information, electronic device, roadside device, cloud control platform, storage medium, and computer program product | |
| CN112580571A (en) | Vehicle running control method and device and electronic equipment | |
| CN112541475B (en) | Sensing data detection method and device | |
| CN114973687B (en) | Traffic information processing method, device, equipment and medium | |
| CN112818792A (en) | Lane line detection method, lane line detection device, electronic device, and computer storage medium | |
| CN110634324A (en) | Vehicle-mounted terminal based reminding method and system for courtesy pedestrians and vehicle-mounted terminal | |
| CN113792106B (en) | Road state updating method and device, electronic equipment and storage medium | |
| CN111814724B (en) | Lane number identification method, device, equipment and storage medium | |
| CN104318783A (en) | Method for analyzing night traffic flow through car lamp detection | |
| CN114379587B (en) | Method and device for avoiding pedestrians in automatic driving | |
| CN115782919A (en) | Information sensing method and device and electronic equipment | |
| CN115923780A (en) | Vehicle night collision avoidance protection method and device, electronic equipment and storage medium | |
| CN115973190A (en) | Decision-making method and device for automatically driving vehicle and electronic equipment | |
| CN114972731A (en) | Traffic light detection and identification method and device, moving tool and storage medium | |
| CN116264038A (en) | Signal lamp control method and device, electronic equipment and storage medium | |
| CN112036220B (en) | Lane line tracking method and system | |
| CN115908838B (en) | Vehicle presence detection method, device, equipment and medium based on radar fusion | |
| CN116434166A (en) | Target area identification method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211012 Address after: 100176 101, floor 1, building 1, yard 7, Ruihe West 2nd Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Applicant after: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. Address before: 2 / F, baidu building, 10 Shangdi 10th Street, Haidian District, Beijing 100085 Applicant before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |