CN113129375A - Data processing method, device, equipment and storage medium - Google Patents
Data processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113129375A CN113129375A CN202110432270.XA CN202110432270A CN113129375A CN 113129375 A CN113129375 A CN 113129375A CN 202110432270 A CN202110432270 A CN 202110432270A CN 113129375 A CN113129375 A CN 113129375A
- Authority
- CN
- China
- Prior art keywords
- lamp
- image
- traffic indicator
- position information
- halo
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 27
- 125000001475 halogen functional group Chemical group 0.000 claims abstract description 224
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000002372 labelling Methods 0.000 claims description 21
- 239000003086 colorant Substances 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 230000007613 environmental effect Effects 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000013135 deep learning Methods 0.000 abstract description 2
- 230000008447 perception Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000008602 contraction Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 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
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 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
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Abstract
The present disclosure provides a data processing method, apparatus, device and storage medium, which relates to the technical field of computers, and further relates to artificial intelligence technologies such as intelligent transportation, roadside perception and deep learning. The specific implementation scheme is as follows: determining lamp frame size information of a target group of traffic indicator lamps related to the lamp halos in the image to be processed according to the position information of the lamp halos presented by the traffic indicator lamps in the image to be processed and a reference image of the image to be processed; determining the position information of the traffic indicator lights of the target group in the image to be processed according to the size information of the lamp frame of the traffic indicator lights of the target group, the color information and the position information of the lamp halo; and marking the image to be processed according to the position information of the traffic indicator lamp of the target group in the image to be processed, and taking the marked image as a training sample. Through the embodiment, the method for processing the lamp halo image data is provided, sample data is enriched, and the accuracy of the model is further improved.
Description
Technical Field
The present disclosure relates to the field of computer technology, and more particularly to the field of artificial intelligence, and more particularly to the field of intelligent transportation, roadside awareness, and deep learning.
Background
With the development of artificial intelligence technology, the use scenes of the neural network model become more and more extensive. For example, in a scene where traffic indicator detection and light color recognition are required, it is common to acquire an image including a traffic indicator on a road by using a road side sensing device (such as a road side camera), and train a neural network model by using the acquired image data to obtain a traffic indicator detection model and a light color recognition model.
However, when training the neural network, the training sample only considers the image data of the traffic indicator light which does not show the halo, so that the training sample is single, and the accuracy of the trained model is low, and improvement is needed.
Disclosure of Invention
The disclosure provides a data processing method, a device, equipment and a storage medium.
According to an aspect of the present disclosure, there is provided a data processing method, the method including:
determining lamp frame size information of a target group of traffic indicator lamps related to the lamp halos in the image to be processed according to the position information of the lamp halos presented by the traffic indicator lamps in the image to be processed and a reference image of the image to be processed; the reference image and the image to be processed are collected at the same position by the same roadside sensing equipment at the same angle, and a traffic indicator lamp in the reference image is not displayed with a lamp halo;
determining the position information of the target group traffic indicator lamp in the image to be processed according to the size information of the lamp frame of the target group traffic indicator lamp, and the color information and the position information of the lamp halo;
and marking the image to be processed according to the position information of the traffic indicator lamp of the target group in the image to be processed, and taking the marked image as a training sample.
According to another aspect of the present disclosure, there is provided a data processing apparatus including:
the lamp frame size information determining module is used for determining lamp frame size information of a target group traffic indicator lamp related to the lamp halos in the image to be processed according to the position information of the lamp halos presented by the traffic indicator lamp in the image to be processed and the reference image of the image to be processed; the reference image and the image to be processed are collected at the same position by the same roadside sensing equipment at the same angle, and a traffic indicator lamp in the reference image is not displayed with a lamp halo;
the position information determining module is used for determining the position information of the target group traffic indicator lamp in the image to be processed according to the size information of the lamp frame of the target group traffic indicator lamp, the color information and the position information of the lamp halo;
and the processing module is used for labeling the image to be processed according to the position information of the traffic indicator lights of the target group in the image to be processed and taking the image after labeling as a training sample.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a data processing method according to any one of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform a data processing method according to any one of the embodiments of the present disclosure.
According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the data processing method of any of the embodiments of the present disclosure.
According to the technology disclosed by the invention, the processing method for the image data of the halo is provided, the image data containing the halo is used as the sample for model training, the sample data is enriched, and the accuracy of the model is further improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a flow chart of a data processing method provided according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of another data processing method provided in accordance with an embodiment of the present disclosure;
FIG. 3 is a flow chart of yet another data processing method provided in accordance with an embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of a data processing apparatus provided in accordance with an embodiment of the present disclosure;
fig. 5 is a block diagram of an electronic device for implementing a data processing method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as 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 present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a flowchart of a data processing method provided according to an embodiment of the present disclosure. The embodiment of the disclosure is applicable to the situation of how to process image data, and is particularly applicable to the situation of processing images which comprise traffic indicator lamps and the traffic indicator lamps present lamp halos. The embodiment may be performed by a data processing apparatus configured in an electronic device, which may be implemented in software and/or hardware. As shown in fig. 1, the data processing method includes:
s101, determining lamp frame size information of a target group of traffic indicator lamps related to the lamp halos in the image to be processed according to the position information of the lamp halos presented by the traffic indicator lamps in the image to be processed and the reference image of the image to be processed.
In this embodiment, the traffic light is also called a traffic signal light or a traffic light, which is a basic language of road traffic; optionally, the set of traffic lights includes at least three traffic lights, for example, the set of traffic lights is composed of three colors of red, yellow and green.
The image to be processed is an image which needs to be processed, and particularly is an image which comprises a traffic light and the traffic light presents a halo (which may also be called halo). Optionally, in this embodiment, the image to be processed is acquired by road side sensing equipment (such as a road side camera) fixedly deployed at a road junction in an environment with poor imaging quality; among these, environments with poor imaging quality include, but are not limited to, nighttime environments, foggy environments, and the like.
Optionally, images acquired by a plurality of roadside sensing devices may be acquired in advance, and interesting traffic indicator lights are marked in the acquired images; further, for a group of traffic lights that can see the light frame, the group of traffic lights may be labeled in the image by a labeling frame, and attribute information of the light frame may be labeled (for example, a road side sensing device identifier, light frame position information, color information of the group of traffic lights, and the like that collect the image); for a group of traffic lights, only the halo can be seen, the halo can be marked in the image by a marking frame, and attribute information of the halo can be marked (for example, road side sensing equipment identification for collecting the image, position information of the halo, color information of the halo, and the like). And if the image with the lamp halo in the marked image is identified, the image is taken as the image to be processed. Further, the number of the images to be processed may be one or more, and in a scenario for training the traffic light detection model and the light color recognition model, the number of the images to be processed is preferably multiple.
It should be noted that, in general, only one light of a group of traffic indicator lights (for example, traffic lights at a road intersection) is on at a time, that is, if the roadside sensing device can only shoot a group of traffic indicator lights, there is a halo associated with the group of traffic indicator lights in the image to be processed collected by the roadside sensing device. Furthermore, if a group of traffic lights has two or more lights on at a time in a particular scenario, there may be two or more halos associated with the group of traffic lights in the pending image. The scheme of the present embodiment can be applied regardless of the number of halos associated with a group of traffic lights, and the present embodiment and the following embodiments are described by taking an example that only one of the group of traffic lights is turned on at a time.
For example, after the images to be processed are acquired, a reference image associated with each image to be processed may be acquired. The reference image and the image to be processed are collected by the same roadside sensing device at the same position and at the same angle, and the traffic indicator lamp in the reference image is presented without lamp halos. Specifically, for each image to be processed, the road-side sensing device identifier may be obtained from the attribute information of the halo in the image to be processed, and then other labeled images collected by the road-side sensing device associated with the road-side sensing device identifier are obtained, and an image which does not present the halo and can see the lamp frame is selected from the labeled images to be used as a reference image of the image to be processed. The road side sensing device comprises a road side sensing device and at least one group of traffic indicator lamps, wherein the road side sensing device is used for acquiring two images of a scene comprising at least one group of traffic indicator lamps at the same position and the same angle at different moments, the image with the traffic indicator lamps presenting halos serves as an image to be processed, and the other image without the halos serves as a reference image of the image to be processed.
It can be understood that, in the case where the size of the lamp frame of a group of traffic indication lamps is fixed, the size information of the lamp frame of the same group of traffic indication lamps in different images taken at the same position and at the same angle by the same roadside sensing device is the same. And for each image to be processed, after acquiring the reference image of the image to be processed, determining the lamp frame size information of the target group traffic indicator lamp associated with the lamp halo from the reference image according to the position information of the lamp halo in the image to be processed and the reference image of the image to be processed. The position information of the halo may be a pixel coordinate of the halo in the image to be processed, and specifically may be a pixel coordinate of a labeling frame labeling the halo, for example, the pixel coordinates of four vertexes of the labeling frame, or the pixel coordinates of two vertexes of any diagonal of the labeling frame; in this embodiment, a group of traffic lights where a certain traffic light or some traffic lights showing a halo in an image to be processed is located is taken as a target group of traffic lights, wherein a lamp frame of the target group of traffic lights is not displayed in the image to be processed; the bezel size information may include length information and width information of the bezel.
For example, if there is only one group of traffic lights in the reference image of the image to be processed, the distance between the group of traffic lights and the halo can be determined according to the position information of the lamp frame of the group of traffic lights and the position information of the halo; if the distance is smaller than the set threshold value, it is indicated that the target traffic indicator lamp associated with the halo in the image to be processed is the same group of traffic indicator lamps in the actual scene as the group of traffic indicator lamps in the reference image, and further, the size information of the lamp frame of the target indicator lamp associated with the halo can be determined according to the position information of the lamp frame of the group of traffic indicator lamps in the reference image. The position information of the lamp frame may be pixel coordinates of the lamp frame in the reference image, and specifically may be pixel coordinates of a labeling frame labeling the lamp frame, for example, pixel coordinates of four vertices of the labeling frame, or pixel coordinates of two vertices of any diagonal of the labeling frame.
Optionally, the length information and the width information of the group of traffic indicator lamps may be determined according to the lamp frame position information of the group of traffic indicator lamps in the reference image, and then the length information and the width information of the target traffic indicator lamp associated with the halo in the image to be processed, that is, the size information of the lamp frame may be determined.
Further, if the reference image of the image to be processed includes two or more sets of traffic lights, the same set of traffic lights of the target set of traffic lights associated with the halo may be selected from the multiple sets of traffic lights, and then the bezel size information of the target set of traffic lights associated with the halo may be determined according to the bezel position information of the same set of traffic lights.
S102, determining the position information of the target group traffic indicator lamp in the image to be processed according to the size information of the lamp frame of the target group traffic indicator lamp, the color information and the position information of the lamp halo.
It should be noted that, in an actual scene, the relative position relationship among the indicator lights in a group of traffic indicator lights is fixed; for example, the relative position relationship among the red, yellow and green indicator lights is fixed.
Furthermore, after the frame size information of the traffic indicator in the target group is determined, if the color information of the halo is any one of the known colors, i.e., the colors of the traffic indicator (such as any one of red, yellow and green), the color information and the position information of the halo and the frame size information of the traffic indicator in the target group can be input into a position determination model trained in advance, so that the position information of the traffic indicator in the target group in the image to be processed can be obtained. In this embodiment, the position information of the target group traffic indicator in the image to be processed is the pixel coordinates of the light frame indicated by the target group traffic indicator in the image to be processed, for example, the pixel coordinates of four vertices of the light frame.
For example, if the color information of the halo is an unknown color, in the case that a group of traffic indicator lamps has multiple colors, the color information of the halo may be sequentially assumed to be one of the colors of the traffic indicator lamps, and the position information of the target traffic indicator lamp in the image to be processed in different color cases may be determined based on the position information of the halo and the assumed color information of the halo, and the size information of the lamp frame of the target group of traffic indicator lamps; then, an image which is acquired by the roadside sensing device for acquiring the image to be processed and does not present the halo in the same environment (such as at night) as the acquired image to be processed can be acquired, the determined position information of the target traffic indicator lamp in the image to be processed under the condition of different colors is compared with the obtained position information of the lamp frame of each group of traffic indicator lamps in the image to be processed respectively, and then the position information of the target group of traffic indicator lamps in the image to be processed and the color information of the halo can be determined according to the comparison result. For example, if the determined position information of the target traffic light in the image to be processed under a certain color is close to the position information of the lamp frame of a group of traffic lights in the acquired image, or the difference between the two is small, it indicates that the target traffic light and the group of traffic lights in the acquired image are the same group of traffic lights in the actual scene, and at this time, the position information of the target traffic light in the image to be processed determined under the condition that the light is faint with the color may be used as the position information of the final target group of traffic lights in the image to be processed.
And S103, labeling the image to be processed according to the position information of the traffic indicator light of the target group in the image to be processed, and taking the image after labeling as a training sample.
Specifically, after the position information of the target group traffic indicator in the image to be processed is determined, the light frames of the target group traffic indicator may be labeled in the image to be processed by using the labeling frame according to the position information of the target group traffic indicator in the image to be processed. Meanwhile, attribute information of the lamp frame can be marked, such as position information, color information, roadside sensing equipment identification for collecting the image and the like. The color information of the lamp frame is the color information of the lamps which are lighted in the traffic indicating lamps of the target group, namely the color information of the lamp halos.
Optionally, after the image to be processed is labeled, the labeled image may be used as a training sample for training a traffic indicator light detection model and a light color recognition model.
It should be noted that, in the existing traffic indicator detection model and light color recognition model, when the model is trained, the adopted training sample only considers the image data that the traffic indicator does not show halo, so that the model accuracy is lower; on the basis of the prior art, the image data of the traffic indicator lamp presenting the lamp halo is processed, the processed image is used as a training sample, and compared with the prior art, the training sample is enriched, and the accuracy of the model is further improved.
In addition, it is noted that, in a roadside sensing scene, roadside sensing equipment (such as a roadside sensing camera) is deployed on the roadside, the position between the roadside sensing camera and a traffic indicator lamp is relatively kept unchanged, and at present, a way mainly adopted when performing lamp color recognition is to take out a corresponding image from a specified position in the image and perform lamp color recognition, wherein the specified position is the position of the traffic indicator lamp marked in advance in the image. Because the position of the road sensing device in an actual scene may change (for example, the base or the supporting rod slightly deforms), or the position of the traffic indicator lamp changes (for example, the base or the supporting rod slightly deforms), the existing method for identifying the color of the traffic indicator lamp cannot directly take out a complete group of traffic indicator lamps from a specified position.
In the embodiment, the influence of factors such as thermal expansion and cold contraction and deformation of a support rod on the positions of road side sensing equipment and traffic indicator lamps in an actual scene is fully considered, and the size information of a lamp frame of a target group of traffic indicator lamps related to the lamp halos is determined from the reference image of the image to be processed by taking the reference image of the image to be processed as a standard and combining the position information of the lamp halos; meanwhile, in the process of determining the position information of the target group traffic indicator lamp in the image to be processed, the relative position relationship inside the group of traffic indicator lamps is fully considered, namely the position information of the target group traffic indicator lamp in the image to be processed is determined based on the size information of the lamp frame of the target group traffic indicator lamp, the position information of the lamp halo and the color information, the accuracy of the determined position information is improved, and a foundation is laid for obtaining a high-accuracy model subsequently.
According to the technical scheme, the standard image of the image to be processed is used as a standard, the position information of the lamp halos is combined, the size information of the lamp frame of the target group traffic indicator lamp related to the lamp halos is determined from the standard image of the image to be processed, the position information of the target group traffic indicator lamp in the image to be processed is determined based on the size information of the lamp frame of the target group traffic indicator lamp, the position information of the lamp halos and the color information of the lamp halos, the image to be processed is labeled based on the position information of the target group traffic indicator lamp in the image to be processed, and the labeled image is used as a sample for training a traffic indicator lamp detection model and a lamp color recognition model. Compared with the prior art, the scheme processes the image data of the traffic indicator lamp with the lamp halo, and takes the processed image as the training sample, so that the training sample is enriched, and the accuracy of the model is improved.
Fig. 2 is a flowchart of another data processing method provided according to an embodiment of the present disclosure. The present embodiment further explains how to determine the size information of the lamp frame of the traffic light of the target group on the basis of the above-described embodiments. As shown in fig. 2, the data processing method includes:
s201, according to the position information of the lamp halos presented by the traffic indicator lamps in the image to be processed and the lamp frame position information of at least two groups of traffic indicator lamps in the reference image of the image to be processed, the same group of traffic indicator lamps of the target group of traffic indicator lamps related to the lamp halos are determined from the at least two groups of traffic indicator lamps.
In this embodiment, the traffic indicator light of the same group and the traffic indicator light of the target group are the same group in an actual scene.
Optionally, when the reference image of the image to be processed includes two or more sets of traffic lights, the same set of traffic lights of the target set of traffic lights may be selected from the multiple sets of traffic lights. For example, for each group of traffic indicator lamps in the reference image, the distance between the lamp halo and the group of traffic indicator lamps can be determined according to the position information of the group of traffic indicator lamps and the position information of the lamp halo, and then the same group of traffic indicator lamps of the target group of traffic indicator lamps can be selected from the plurality of groups of traffic indicator lamps in the reference image according to the distance between each group of traffic indicator lamps in the reference image and the lamp halo.
Further, as an optional manner of the embodiment of the present disclosure, determining the same group of traffic indicator lamps of the target group of traffic indicator lamps may be determining coordinates of a center point of a lamp halo according to position information of the lamp halo; determining coordinates of center points of lamp frames of at least two groups of traffic indicator lamps according to the position information of the lamp frames of at least two groups of traffic indicator lamps in the reference image; respectively calculating the distance between the coordinates of the central point of the lamp halo and the coordinates of the central points of the lamp frames of at least two groups of traffic indicator lamps; determining the same group of traffic indicator lamps of the target group of traffic indicator lamps associated with the lamp halos according to the distance from at least two groups of traffic indicator lamps.
Specifically, the coordinates of the central point of the halo are determined according to the pixel coordinates of the labeling frame for labeling the halo; meanwhile, for each group of traffic indicator lamps in the reference image, the coordinate of the center point of the lamp frame of the group of traffic indicator lamps can be determined according to the pixel coordinate of the marking frame marking the lamp frame of the group of traffic indicator lamps, and the distance between the coordinate of the center point of the lamp frame of the group of traffic indicator lamps and the coordinate of the center point of the lamp halo, namely the distance between the group of traffic indicator lamps and the lamp halo, is calculated; then, the same traffic indicator lamp of the target group of traffic indicator lamps can be selected from the multiple groups of traffic indicator lamps in the reference image according to the distance between each group of traffic indicator lamps and the lamp halo in the reference image. For example, a group of traffic lights in the reference image corresponding to the minimum distance may be selected as the same group of traffic lights as the target group of traffic lights. Further, in order to ensure accuracy, the minimum distance in the distances between each group of traffic indicator lamps and the lamp halo in the reference image may be compared with a set threshold, and if the minimum distance is smaller than the set threshold, it is indicated that the target group of traffic indicator lamps associated with the lamp halo are the same group of traffic indicator lamps in the actual scene as the group of traffic indicator lamps in the reference image corresponding to the minimum distance, and the group of traffic indicator lamps in the reference image corresponding to the minimum distance may be used as the same group of traffic indicator lamps of the target group of traffic indicator lamps.
As another optional way of the embodiment of the present disclosure, the coordinates of the center point of the halo may be determined according to the position information of the halo; meanwhile, for the lamp frame position information of each group of traffic indicator lamps in the reference image and the relative position relationship inside the group of traffic indicator lamps, the position information of each traffic indicator lamp inside the group of traffic indicator lamps can be determined, that is, the position information of the lighted lamp (such as a red lamp) in the group of traffic indicator lamps can be determined, further, the center point coordinate (namely the lamp head center point coordinate) of the lighted lamp in the group of traffic indicator lamps can be determined, and the distance between the center point coordinate of the lamp halo and the center point coordinate of the lighted lamp in the group of traffic indicator lamps is calculated; then, the same group of traffic indicator lamps of the target group of traffic indicator lamps can be selected from the multiple groups of traffic indicator lamps in the reference image according to the distance between the center point coordinates of the lighted lamps in each group of traffic indicator lamps and the center point coordinates of the lamp halo.
S202, determining the size information of the lamp frames of the traffic indicator lamps of the target group according to the position information of the lamp frames of the traffic indicator lamps of the same group.
Specifically, after the same group of traffic indicator lamps of the target group of traffic indicator lamps are determined, the length information and the width information of the same group of traffic indicator lamps can be determined according to the position information of lamp frames of the same group of traffic indicator lamps; because the target group traffic indicator lamp and the same group traffic indicator lamp are the same group traffic indicator lamp in the actual scene, the length information and the width information of the target group traffic indicator lamp, namely the size information of the lamp frame, can be further determined.
S203, determining the position information of the target group traffic indicator lamp in the image to be processed according to the size information of the lamp frame of the target group traffic indicator lamp, the color information and the position information of the lamp halo.
And S204, labeling the image to be processed according to the position information of the traffic indicator light of the target group in the image to be processed, and taking the image after labeling as a training sample.
According to the technical scheme of the embodiment, under the condition that the reference image of the image to be processed contains two or more groups of traffic indicator lamps, the same group of traffic indicator lamps of the target group of traffic indicator lamps related to the lamp halos are determined from the reference image of the image to be processed, the lamp frame size information of the target group of traffic indicator lamps can be accurately determined according to the lamp frame position information of the same group of traffic indicator lamps, the position information of the target group of traffic indicator lamps in the image to be processed can be determined by combining the lamp frame size information of the target group of traffic indicator lamps, the position information of the lamp halos, the color information and the like, the position information of the target group of traffic indicator lamps in the image to be processed can be determined, and then the target group of traffic indicator lamps can be marked in the image to be processed based on the position information and used for subsequently training the training samples of the traffic indicator lamp detection. According to the technical scheme, under the condition that the reference image of the image to be processed contains two or more groups of traffic indicator lamps, the same group of traffic indicator lamps of the target group can be accurately determined, and then the size information of the lamp frame of the traffic indicator lamps of the target group can be determined based on the position information of the lamp frame of the same group of traffic indicator lamps, so that an optional mode is provided for determining the size information of the lamp frame of the traffic indicator lamps of the target group.
Fig. 3 is a flowchart of another data processing method provided according to an embodiment of the present disclosure. The present embodiment further explains how to determine the position information of the target group traffic lights in the image to be processed on the basis of the above-described embodiments. As shown in fig. 3, the data processing method includes:
s301, determining lamp frame size information of a target group of traffic indicator lamps related to the lamp halos in the image to be processed according to the position information of the lamp halos presented by the traffic indicator lamps in the image to be processed and the reference image of the image to be processed.
In this embodiment, the reference image and the image to be processed are collected by the same roadside sensing device at the same position and at the same angle, and the traffic indicator lamp in the reference image is not shown in halo.
S302, identifying whether the color information of the lamp halo is an unknown color; if yes, executing S303; if not, go to S306.
And S303, acquiring the same scene image of the image to be processed.
In the embodiment, the influence of factors such as thermal expansion and cold contraction and deformation of the support rod on the positions of the road side sensing equipment and the traffic indicator light in an actual scene is fully considered, and the same-scene image of the image to be processed is introduced. The same scene image and the image to be processed are collected by the same roadside sensing equipment under the same environmental scene, and the traffic indicator lamp in the same scene image has no halo; for example, the image to be processed and the image in the same scene are both collected by the roadside perception camera fixedly arranged at a certain road intersection at different times at night, a traffic indicator lamp presents a lamp halo in the image to be processed, and the traffic indicator lamp presents a lamp halo phenomenon and a lamp frame can be seen in the image in the same scene.
It can be understood that, in the case that the reference image of the image to be processed is the same as the acquisition environment of the image to be processed, the reference image is the same scene image of the image to be processed, and the processes of S304 and S305 can be directly performed without performing S303.
And S304, updating the color information of the lamp halos according to the position information of the lamp halos and the position information of the single traffic indicator lamp in the same scene image.
Specifically, all the single traffic indicator lamps in the same scene image can be traversed, if the position information of a certain traffic indicator lamp in the same scene image is identified to be the same as the position information of the halo, or the difference is smaller, the traffic indicator lamp presenting the halo in the image to be processed is indicated, and the traffic indicator lamp is the same as the certain traffic indicator lamp in the same scene image in the actual scene, at this time, the color information of the traffic indicator lamp in the same scene image, which is the same as the position information of the halo, can be used as the color information of the halo. For example, if the color information of the traffic indicator light in the same scene image as the position information of the halo is red, the red is taken as the color information of the halo.
Optionally, as an optional manner of the embodiment of the present disclosure, the updating of the color information of the halo may be to determine a height difference between the halo and a single traffic light in the same-scene image according to the position information of the halo and the position information of the single traffic light in the same-scene image; determining a target lamp related to the lamp halo from the single traffic indicating lamp of the scene image according to the height difference; and updating the color information of the lamp halo according to the color information of the target lamp.
Specifically, the coordinates of the central point of the halo are determined according to the position information of the halo; for each traffic indicator in the same scene image, according to the position information of the traffic indicator, the coordinate of the central point of the traffic indicator (namely the coordinate of the central point of the lamp head) can be determined, and the height difference between the coordinate of the central point of the traffic indicator and the coordinate of the central point of the lamp halo, namely the difference value of the traffic indicator and the lamp halo in the horizontal height can be calculated; and then, selecting the traffic indicator lamp in the same scene image corresponding to the minimum height difference as the target lamp. Further, in order to ensure accuracy, the minimum height difference among the height differences between all traffic indicator lights and the lamp halos in the same scene image can be compared with a set height threshold, if the minimum height difference is smaller than the set height threshold, the traffic indicator light presenting the lamp halos in the image to be processed and a target light in the same scene image are the same traffic indicator light in an actual scene, and then the traffic indicator light in the same scene image corresponding to the minimum height difference can be used as the target light related to the lamp halos; and the color information of the target lamp can be used as the color information of the halo.
It is worth noting that in the embodiment, fine-grained division is performed on the group traffic indicator lamps, a concept of a single traffic indicator lamp is introduced, a target lamp related to the lamp halo is determined from the scene image, and then the color information of the lamp halo is updated according to the color information of the target lamp, so that the accuracy of updating the color information of the lamp halo is further improved, and a foundation is laid for obtaining a more accurate model.
S305, determining the position information of the traffic indicator lights of the target group in the image to be processed according to the coordinates of the central point of the lamp halos, the updated color information of the lamp halos, the size information of the lamp frames of the traffic indicator lights of the target group and the relative position relationship inside the traffic indicator lights of the target group.
In this embodiment, the relative position relationship inside the group of traffic lights is the relative position relationship between the indicator lights inside the group of traffic lights, or in other words, the relative position relationship between the indicator lights of different colors inside the group of traffic lights; for example, the relative position relationship between three indicator lights with different colors of red, yellow and green.
Specifically, the coordinates of the central point of the halo, the updated color information, the size information of the lamp frame of the traffic indicator lamp of the target group, the relative position relationship inside the traffic indicator lamp of the target group and the like are input into a pre-trained position determination model, and the position information of the traffic indicator lamp of the target group in the image to be processed can be obtained.
Further, other traffic indicator lamps except the traffic indicator lamp presenting the halo in the target group traffic indication can be determined according to the updated color information of the halo and the relative position relationship inside the target group traffic indicator lamp, and the up-down distribution condition (or the left-right distribution condition) of the traffic indicator lamp presenting the halo is determined; and according to the coordinates of the central point of the lamp halo, the size information of the lamp frame of the traffic indicator lamp of the target group and the vertical distribution condition (or the horizontal distribution condition), the position information of the traffic indicator lamp of the target group in the image to be processed can be determined.
S306, determining the coordinates of the central point of the lamp halo according to the position information of the lamp halo.
S307, determining the position information of the traffic indicator light of the target group in the image to be processed according to the coordinate and the color information of the central point of the halo, the size information of the lamp frame of the traffic indicator light of the target group and the relative position relationship inside the traffic indicator light of the target group.
In this embodiment, the manner of determining the position information of the target group traffic indicator in the to-be-processed image in step S307 is the same as the manner of determining the position information of the target group traffic indicator in the to-be-processed image in step S305, and S307 can be implemented only by replacing the color information of the halo after updating in step S305 with the color information of the halo, which is not described herein again.
According to the technical scheme of the embodiment of the disclosure, the standard image of the image to be processed is used as a standard, and the position information of the lamp halo is combined to determine the lamp frame size information of the target group traffic indicator lamp related to the lamp halo from the standard image of the image to be processed; then when the color information of the lamp halos is identified to be any one of the colors of the traffic indicator lamps, determining the position information of the traffic indicator lamps in the target group in the image to be processed based on the size information of the lamp frames of the traffic indicator lamps in the target group, the position information of the lamp halos and the color information; meanwhile, under the condition that the color information of the lamp halos is recognized to be unknown, the influence of factors such as thermal expansion and cold contraction and support rod deformation on the positions of the road side sensing equipment and the traffic indicator lamp in an actual scene is fully considered, the same-scene image of the image to be processed is introduced to determine the position information of the traffic indicator lamp of the target group in the image to be processed, the accuracy of the determined position information is further improved, and a foundation is laid for obtaining a more accurate model. In addition, this embodiment labels the image to be processed based on the positional information of the traffic indicator in the image to be processed of the target group, and uses the image after labeling as the sample of the traffic indicator detection model and the light color recognition model, enriches the training sample, and then promotes the accuracy of the model.
Fig. 4 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present disclosure. The embodiment of the disclosure is applicable to the situation of how to process image data, and is particularly applicable to the situation of processing images which comprise traffic indicator lamps and the traffic indicator lamps present lamp halos. The apparatus can be implemented by software and/or hardware, and the apparatus can implement the data processing method according to any embodiment of the disclosure. As shown in fig. 4, the data processing apparatus includes:
a lamp frame size information determining module 401, configured to determine, according to position information of a lamp halo displayed by a traffic indicator in the image to be processed and a reference image of the image to be processed, lamp frame size information of a target group of traffic indicators related to the lamp halo in the image to be processed; the reference image and the image to be processed are collected at the same position by the same roadside sensing equipment at the same angle, and a traffic indicator lamp in the reference image is not displayed in a halo manner;
a position information determining module 402, configured to determine position information of the target group traffic indicator in the image to be processed according to the size information of the lamp frame of the target group traffic indicator, and the color information and the position information of the halo;
and the processing module 403 is configured to label the image to be processed according to the position information of the target group traffic indicator in the image to be processed, and use the labeled image as a training sample.
According to the technical scheme, the standard image of the image to be processed is used as a standard, the position information of the lamp halos is combined, the size information of the lamp frame of the target group traffic indicator lamp related to the lamp halos is determined from the standard image of the image to be processed, the position information of the target group traffic indicator lamp in the image to be processed is determined based on the size information of the lamp frame of the target group traffic indicator lamp, the position information of the lamp halos and the color information of the lamp halos, the image to be processed is labeled based on the position information of the target group traffic indicator lamp in the image to be processed, and the labeled image is used as a sample for training a traffic indicator lamp detection model and a lamp color recognition model. Compared with the prior art, the scheme processes the image data of the traffic indicator lamp with the lamp halo, and takes the processed image as the training sample, so that the training sample is enriched, and the accuracy of the model is improved.
Illustratively, the light box size information determining module 401 includes:
the target group lamp determining unit is used for determining the same group of traffic indicator lamps of the target group traffic indicator lamps related to the lamp halos from the at least two groups of traffic indicator lamps according to the position information of the lamp halos and the lamp frame position information of the at least two groups of traffic indicator lamps in the reference image;
and the lamp frame size information determining unit is used for determining the lamp frame size information of the traffic indicating lamps of the target group according to the lamp frame position information of the traffic indicating lamps of the same group.
Illustratively, the target group light determination unit is specifically configured to:
determining the coordinates of the central point of the lamp halo according to the position information of the lamp halo;
determining coordinates of center points of lamp frames of at least two groups of traffic indicator lamps according to the position information of the lamp frames of at least two groups of traffic indicator lamps in the reference image;
respectively calculating the distance between the coordinates of the central point of the lamp halo and the coordinates of the central points of the lamp frames of at least two groups of traffic indicator lamps;
determining the same group of traffic indicator lamps of the target group of traffic indicator lamps associated with the lamp halos according to the distance from at least two groups of traffic indicator lamps.
Illustratively, the location information determining module 402 is specifically configured to:
if the color information of the lamp halos is any one of the colors of the traffic indicator lamps, determining the coordinates of the center points of the lamp halos according to the position information of the lamp halos;
and determining the position information of the traffic indicator lights of the target group in the image to be processed according to the coordinates and the color information of the central point of the lamp halo, the size information of the lamp frame of the traffic indicator lights of the target group and the relative position relationship inside the traffic indicator lights of the target group.
Illustratively, the location information determining module 402 includes:
the image acquisition unit is used for acquiring the same scene image of the image to be processed if the color information of the lamp halo is an unknown color; the same scene image and the image to be processed are collected by the same roadside sensing equipment under the same environmental scene, and a traffic indicator lamp in the same scene image has no halo;
the color information updating unit is used for updating the color information of the lamp halos according to the position information of the lamp halos and the position information of the single traffic indicator lamp in the same scene image;
the position information determining unit is used for determining the position information of the target group traffic indicator lamps in the image to be processed according to the coordinates of the central points of the lamp halos, the updated color information of the lamp halos, the size information of lamp frames of the target group traffic indicator lamps and the relative position relation inside the target group traffic indicator lamps;
wherein, the traffic light in a group includes three traffic light at least.
Illustratively, the color information updating unit is specifically configured to:
determining the height difference between the lamp halo and the single traffic indicator lamp in the same scene image according to the position information of the lamp halo and the position information of the single traffic indicator lamp in the same scene;
determining a target lamp related to the lamp halo from the single traffic indicating lamp of the scene image according to the height difference;
and updating the color information of the lamp halo according to the color information of the target lamp.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 5 illustrates a schematic block diagram of an example electronic device 500 that can 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 phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 5, the electronic device 500 includes a computing unit 501, which can perform various appropriate 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 RAM 403, various programs and data required for the operation of the electronic device 500 can also be stored. The calculation unit 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
A number of components in the electronic device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, 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 electronic device 500 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 501 executes the respective methods and processes described above, such as the data processing method. For example, in some embodiments, the data processing method may be implemented as a computer software program tangibly embodied in 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 electronic device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the data processing method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a 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 that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes 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 codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. 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. A 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 a pointing device (e.g., a mouse or a 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 can 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, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end 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 back-end, 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), blockchain networks, and the internet.
The computer system may include clients and servers. A client and server are generally 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 host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (15)
1. A method of data processing, comprising:
determining lamp frame size information of a target group of traffic indicator lamps related to the lamp halos in the image to be processed according to the position information of the lamp halos presented by the traffic indicator lamps in the image to be processed and a reference image of the image to be processed; the reference image and the image to be processed are collected at the same position by the same roadside sensing equipment at the same angle, and a traffic indicator lamp in the reference image is not displayed with a lamp halo;
determining the position information of the target group traffic indicator lamp in the image to be processed according to the size information of the lamp frame of the target group traffic indicator lamp, and the color information and the position information of the lamp halo;
and marking the image to be processed according to the position information of the traffic indicator lamp of the target group in the image to be processed, and taking the marked image as a training sample.
2. The method according to claim 1, wherein the determining the lamp frame size information of the target group of traffic indicator lamps associated with the lamp halos in the image to be processed according to the position information of the lamp halos presented by the traffic indicator lamps in the image to be processed and the reference image of the image to be processed comprises:
determining the same group of traffic indicator lamps of a target group of traffic indicator lamps related to the lamp halos from the at least two groups of traffic indicator lamps according to the position information of the lamp halos and the lamp frame position information of the at least two groups of traffic indicator lamps in the reference image;
and determining the size information of the lamp frame of the traffic indicator lamp of the target group according to the position information of the lamp frame of the traffic indicator lamp of the same group.
3. The method of claim 2, wherein the determining a same set of traffic lights of a target set of traffic lights associated with the halo from the at least two sets of traffic lights according to the position information of the halo and the bezel position information of the at least two sets of traffic lights in the reference image comprises:
determining the coordinates of the central point of the lamp halo according to the position information of the lamp halo;
determining the coordinates of the center points of the lamp frames of at least two groups of traffic indicator lamps according to the position information of the lamp frames of at least two groups of traffic indicator lamps in the reference image;
respectively calculating the distance between the coordinates of the central point of the lamp halo and the coordinates of the central points of the lamp frames of the at least two groups of traffic indicator lamps;
and determining the same group of traffic indicator lamps of the target group of traffic indicator lamps related to the lamp halo from the at least two groups of traffic indicator lamps according to the distance.
4. The method of claim 1, wherein the determining the position information of the target group traffic indicator in the image to be processed according to the size information of the lamp frame of the target group traffic indicator and the color information and the position information of the lamp halo comprises:
if the color information of the lamp halos is any one of the colors of the traffic indicator lamps, determining the coordinates of the central points of the lamp halos according to the position information of the lamp halos;
and determining the position information of the traffic indicator lights of the target group in the image to be processed according to the coordinates and the color information of the central point of the lamp halo, the size information of the lamp frame of the traffic indicator lights of the target group and the relative position relationship inside the traffic indicator lights of the target group.
5. The method of claim 1, wherein the determining the position information of the target group traffic indicator in the image to be processed according to the size information of the lamp frame of the target group traffic indicator and the color information and the position information of the lamp halo comprises:
if the color information of the lamp halos is unknown color, acquiring the same scene image of the image to be processed; the same-scene image and the image to be processed are collected by the same roadside sensing equipment under the same environmental scene, and a traffic indicator lamp in the same-scene image has no halo;
updating the color information of the lamp halos according to the position information of the lamp halos and the position information of the single traffic indicator lamp in the image of the same scene;
determining the position information of the traffic indicator lights of the target group in the image to be processed according to the coordinates of the central point of the lamp halo, the updated color information of the lamp halo, the size information of the lamp frame of the traffic indicator lights of the target group and the relative position relationship inside the traffic indicator lights of the target group;
wherein, the traffic light in a group includes three traffic light at least.
6. The method of claim 5, wherein the updating the color information of the halo according to the position information of the halo and the position information of the single traffic light in the same scene image comprises:
determining the height difference between the lamp halo and the single traffic indicator lamp in the same scene image according to the position information of the lamp halo and the position information of the single traffic indicator lamp in the same scene image;
determining a target lamp associated with the lamp halo from the single traffic indicating lamp of the scene image according to the height difference;
and updating the color information of the lamp halo according to the color information of the target lamp.
7. A data processing apparatus comprising:
the lamp frame size information determining module is used for determining lamp frame size information of a target group traffic indicator lamp related to the lamp halos in the image to be processed according to the position information of the lamp halos presented by the traffic indicator lamp in the image to be processed and the reference image of the image to be processed; the reference image and the image to be processed are collected at the same position by the same roadside sensing equipment at the same angle, and a traffic indicator lamp in the reference image is not displayed with a lamp halo;
the position information determining module is used for determining the position information of the target group traffic indicator lamp in the image to be processed according to the size information of the lamp frame of the target group traffic indicator lamp, the color information and the position information of the lamp halo;
and the processing module is used for labeling the image to be processed according to the position information of the traffic indicator lights of the target group in the image to be processed and taking the image after labeling as a training sample.
8. The apparatus of claim 7, wherein the bezel size information determination module comprises:
a target group lamp determining unit, configured to determine, according to the position information of the lamp halo and the lamp frame position information of at least two groups of traffic indicator lamps in the reference image, a same group of traffic indicator lamps of a target group of traffic indicator lamps associated with the lamp halo from the at least two groups of traffic indicator lamps;
and the lamp frame size information determining unit is used for determining the lamp frame size information of the target group of traffic indicator lamps according to the lamp frame position information of the same group of traffic indicator lamps.
9. The apparatus according to claim 8, wherein the target group light determination unit is specifically configured to:
determining the coordinates of the central point of the lamp halo according to the position information of the lamp halo;
determining the coordinates of the center points of the lamp frames of at least two groups of traffic indicator lamps according to the position information of the lamp frames of at least two groups of traffic indicator lamps in the reference image;
respectively calculating the distance between the coordinates of the central point of the lamp halo and the coordinates of the central points of the lamp frames of the at least two groups of traffic indicator lamps;
and determining the same group of traffic indicator lamps of the target group of traffic indicator lamps related to the lamp halo from the at least two groups of traffic indicator lamps according to the distance.
10. The apparatus of claim 7, wherein the location information determining module is specifically configured to:
if the color information of the lamp halos is any one of the colors of the traffic indicator lamps, determining the coordinates of the central points of the lamp halos according to the position information of the lamp halos;
and determining the position information of the traffic indicator lights of the target group in the image to be processed according to the coordinates and the color information of the central point of the lamp halo, the size information of the lamp frame of the traffic indicator lights of the target group and the relative position relationship inside the traffic indicator lights of the target group.
11. The apparatus of claim 7, wherein the location information determining module comprises:
the image acquisition unit is used for acquiring the same scene image of the image to be processed if the color information of the lamp halo is an unknown color; the same-scene image and the image to be processed are collected by the same roadside sensing equipment under the same environmental scene, and a traffic indicator lamp in the same-scene image has no halo;
the color information updating unit is used for updating the color information of the lamp halos according to the position information of the lamp halos and the position information of the single traffic indicator lamp in the same scene image;
the position information determining unit is used for determining the position information of the target group traffic indicator lamps in the image to be processed according to the coordinates of the central points of the lamp halos, the updated color information of the lamp halos, the size information of lamp frames of the target group traffic indicator lamps and the relative position relationship inside the target group traffic indicator lamps;
wherein, the traffic light in a group includes three traffic light at least.
12. The apparatus according to claim 11, wherein the color information updating unit is specifically configured to:
determining the height difference between the lamp halo and the single traffic indicator lamp in the same scene image according to the position information of the lamp halo and the position information of the single traffic indicator lamp in the same scene;
determining a target lamp associated with the lamp halo from the single traffic indicating lamp of the scene image according to the height difference;
and updating the color information of the lamp halo according to the color information of the target lamp.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the data processing method of any one of claims 1-6.
14. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the data processing method according to any one of claims 1 to 6.
15. A computer program product comprising a computer program which, when executed by a processor, implements a data processing method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110432270.XA CN113129375B (en) | 2021-04-21 | 2021-04-21 | Data processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110432270.XA CN113129375B (en) | 2021-04-21 | 2021-04-21 | Data processing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113129375A true CN113129375A (en) | 2021-07-16 |
| CN113129375B CN113129375B (en) | 2023-12-01 |
Family
ID=76778837
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110432270.XA Active CN113129375B (en) | 2021-04-21 | 2021-04-21 | Data processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113129375B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2119614A2 (en) * | 2008-05-15 | 2009-11-18 | Siemens Schweiz AG | Signalling unit with LED redundancy |
| CN102568242A (en) * | 2012-01-17 | 2012-07-11 | 杭州海康威视系统技术有限公司 | Signal lamp state detection method and system based on video processing |
| CN104574960A (en) * | 2014-12-25 | 2015-04-29 | 宁波中国科学院信息技术应用研究院 | Traffic light recognition method |
| JP2017004295A (en) * | 2015-06-11 | 2017-01-05 | 株式会社ミツバ | Traffic light recognition apparatus and traffic light recognition method |
| CN107273838A (en) * | 2017-06-08 | 2017-10-20 | 浙江大华技术股份有限公司 | Traffic lights capture the processing method and processing device of picture |
| KR20180031421A (en) * | 2016-09-20 | 2018-03-28 | 강정열 | A traffic light |
| US20180211120A1 (en) * | 2017-01-25 | 2018-07-26 | Ford Global Technologies, Llc | Training An Automatic Traffic Light Detection Model Using Simulated Images |
| CN108876858A (en) * | 2018-07-06 | 2018-11-23 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling image |
| CN110084111A (en) * | 2019-03-19 | 2019-08-02 | 江苏大学 | A kind of quick vehicle detection at night method applied to adaptive high beam |
| JP2019139801A (en) * | 2019-04-25 | 2019-08-22 | 株式会社ミツバ | Traffic light machine recognition device, signal recognition system, and traffic light machine recognition method |
| US20190347767A1 (en) * | 2018-05-11 | 2019-11-14 | Boe Technology Group Co., Ltd. | Image processing method and device |
| CN110992725A (en) * | 2019-10-24 | 2020-04-10 | 合肥讯图信息科技有限公司 | Method, system and storage medium for detecting traffic signal lamp fault |
| CN111127358A (en) * | 2019-12-19 | 2020-05-08 | 苏州科达科技股份有限公司 | Image processing method, device and storage medium |
| WO2020133983A1 (en) * | 2018-12-29 | 2020-07-02 | 中国银联股份有限公司 | Signal light identification method, device, and electronic apparatus |
| CN111598006A (en) * | 2020-05-18 | 2020-08-28 | 北京百度网讯科技有限公司 | Method and device for labeling objects |
| CN111931726A (en) * | 2020-09-23 | 2020-11-13 | 北京百度网讯科技有限公司 | Traffic light detection method and device, computer storage medium and road side equipment |
| CN112307970A (en) * | 2020-10-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Training data acquisition method and device, electronic equipment and storage medium |
-
2021
- 2021-04-21 CN CN202110432270.XA patent/CN113129375B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2119614A2 (en) * | 2008-05-15 | 2009-11-18 | Siemens Schweiz AG | Signalling unit with LED redundancy |
| CN102568242A (en) * | 2012-01-17 | 2012-07-11 | 杭州海康威视系统技术有限公司 | Signal lamp state detection method and system based on video processing |
| CN104574960A (en) * | 2014-12-25 | 2015-04-29 | 宁波中国科学院信息技术应用研究院 | Traffic light recognition method |
| JP2017004295A (en) * | 2015-06-11 | 2017-01-05 | 株式会社ミツバ | Traffic light recognition apparatus and traffic light recognition method |
| KR20180031421A (en) * | 2016-09-20 | 2018-03-28 | 강정열 | A traffic light |
| US20180211120A1 (en) * | 2017-01-25 | 2018-07-26 | Ford Global Technologies, Llc | Training An Automatic Traffic Light Detection Model Using Simulated Images |
| CN107273838A (en) * | 2017-06-08 | 2017-10-20 | 浙江大华技术股份有限公司 | Traffic lights capture the processing method and processing device of picture |
| US20190347767A1 (en) * | 2018-05-11 | 2019-11-14 | Boe Technology Group Co., Ltd. | Image processing method and device |
| CN108876858A (en) * | 2018-07-06 | 2018-11-23 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling image |
| WO2020133983A1 (en) * | 2018-12-29 | 2020-07-02 | 中国银联股份有限公司 | Signal light identification method, device, and electronic apparatus |
| CN110084111A (en) * | 2019-03-19 | 2019-08-02 | 江苏大学 | A kind of quick vehicle detection at night method applied to adaptive high beam |
| JP2019139801A (en) * | 2019-04-25 | 2019-08-22 | 株式会社ミツバ | Traffic light machine recognition device, signal recognition system, and traffic light machine recognition method |
| CN110992725A (en) * | 2019-10-24 | 2020-04-10 | 合肥讯图信息科技有限公司 | Method, system and storage medium for detecting traffic signal lamp fault |
| CN111127358A (en) * | 2019-12-19 | 2020-05-08 | 苏州科达科技股份有限公司 | Image processing method, device and storage medium |
| CN111598006A (en) * | 2020-05-18 | 2020-08-28 | 北京百度网讯科技有限公司 | Method and device for labeling objects |
| CN111931726A (en) * | 2020-09-23 | 2020-11-13 | 北京百度网讯科技有限公司 | Traffic light detection method and device, computer storage medium and road side equipment |
| CN112307970A (en) * | 2020-10-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Training data acquisition method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 魏海林: "基于图像识别的信号灯路口辅助驾驶方法", 《浙江大学学报（工学版）》, vol. 51, no. 6, pages 1090 - 1096 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113129375B (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11105638B2 (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| CN109284801B (en) | Traffic indicator lamp state identification method and device, electronic equipment and storage medium | |
| CN109285181B (en) | Method and apparatus for recognizing image | |
| CN113688935A (en) | High-precision map detection method, device, equipment and storage medium | |
| CN113792061A (en) | Map data updating method and device and electronic equipment | |
| CN115719436A (en) | Model training method, target detection method, device, equipment and storage medium | |
| CN114140592A (en) | High-precision map generation method, device, equipment, medium and automatic driving vehicle | |
| CN114186007A (en) | High-precision map generation method and device, electronic equipment and storage medium | |
| CN113971723B (en) | Method, device, equipment and storage medium for constructing three-dimensional map in high-precision map | |
| CN113591580B (en) | Image annotation method and device, electronic equipment and storage medium | |
| CN112883236B (en) | Map updating method and device, electronic equipment and storage medium | |
| CN114565908A (en) | Lane line detection method and device, electronic device and storage medium | |
| CN113011298A (en) | Truncated object sample generation method, target detection method, road side equipment and cloud control platform | |
| CN116758503A (en) | Automatic lane line marking method, device, equipment and storage medium | |
| US20220309763A1 (en) | Method for identifying traffic light, device, cloud control platform and vehicle-road coordination system | |
| CN113129375B (en) | Data processing method, device, equipment and storage medium | |
| CN114724113B (en) | Road sign recognition method, automatic driving method, device and equipment | |
| US11792514B2 (en) | Method and apparatus for stabilizing image, roadside device and cloud control platform | |
| CN113450794B (en) | Navigation broadcasting detection method and device, electronic equipment and medium | |
| CN115147561A (en) | Pose graph generation method, high-precision map generation method and device | |
| CN115035481A (en) | Image object distance fusion method, device, equipment and storage medium | |
| CN114565906A (en) | Obstacle detection method, obstacle detection device, electronic device, and storage medium | |
| CN114429631A (en) | Three-dimensional object detection method, device, equipment and storage medium | |
| CN113378836A (en) | Image recognition method, apparatus, device, medium, and program product | |
| CN113591569A (en) | Obstacle detection method, obstacle detection device, electronic apparatus, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |