CN109711375B - Signal lamp identification method and device - Google Patents
Signal lamp identification method and device Download PDFInfo
- Publication number
- CN109711375B CN109711375B CN201811647448.7A CN201811647448A CN109711375B CN 109711375 B CN109711375 B CN 109711375B CN 201811647448 A CN201811647448 A CN 201811647448A CN 109711375 B CN109711375 B CN 109711375B
- Authority
- CN
- China
- Prior art keywords
- signal lamp
- reference image
- signal
- images
- image
- 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 35
- 238000012545 processing Methods 0.000 claims abstract description 28
- 239000013589 supplement Substances 0.000 claims abstract description 6
- 238000013507 mapping Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000000295 complement effect Effects 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 21
- 238000004590 computer program Methods 0.000 description 10
- 238000012986 modification Methods 0.000 description 10
- 230000004048 modification Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000005484 gravity Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention relates to the technical field of data processing, in particular to a signal lamp identification method and a signal lamp identification device, which are used for solving the problem that image information of a signal lamp in a discrete scene cannot be supplemented by an image supplement method in the prior art. The embodiment of the invention comprises the following steps: acquiring N images shot for the same group of signal lamps in a preset time period; each image is used for identifying the signal lamp in a lighting state; determining reference signal lamps, wherein the reference signal lamps are arranged in the N images; for each reference image, determining a fourth position of the signal lamp to be supplemented in the reference image at least according to a first position of the reference signal lamp in the reference image, a second position of the reference signal lamp in the reference image and a third position of the signal lamp to be supplemented in the reference image; and determining the signal light information of the fourth position according to the signal light information of at least one third position.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a signal lamp identification method and device.
Background
When a server signal lamp is identified, due to signal lamp flickering and shooting angles, one image cannot acquire and reflect all information, or information displayed in some images is not clear enough, multiple images are required to be supplemented with each other, and some information in one image is supplemented to a corresponding position in the other image.
The image information is supplemented mainly by methods such as matching or repairing, and the repairing method in the prior art mainly extracts information such as frequency domain or gray scale according to the relevance between pixels and analyzes continuity for prediction. The problem of information supplement in a signal lamp discrete scene cannot be solved. In the image matching method, an algorithm represented by SIFT (Scale-invariant feature transform) is used for directly carrying out Gaussian Scale space processing on an image, a feature descriptor is formed by extracting main directions of related points, and matching is carried out by Euclidean distance calculation.
Disclosure of Invention
The application provides a signal lamp identification method and a signal lamp identification device, which are used for solving the problem that an image supplement method in the prior art cannot supplement signal lamp image information in a discrete scene.
The signal lamp identification method provided by the embodiment of the invention comprises the following steps:
acquiring N images shot for the same group of signal lamps in a preset time period; each image is used for identifying the signal lamp in a lighting state;
determining reference signal lamps, wherein the reference signal lamps are arranged in the N images;
for each reference image, determining a fourth position of the signal lamp to be supplemented in the reference image at least according to a first position of the reference signal lamp in the reference image, a second position of the reference signal lamp in the reference image and a third position of the signal lamp to be supplemented in the reference image; the reference image is any one of the N images, and the reference image is any one of the N images except the reference image; the signal lamp to be supplemented is any signal lamp except the reference signal lamp in the reference image;
and determining the signal light information of the fourth position according to the signal light information of at least one third position.
In an optional embodiment, the number of the reference signal lamps is at least 2;
the determination reference signal lamp comprises:
and selecting the signal lamps in the bright state in the N images as the reference signal lamps, wherein the two reference signal lamps in the same image and the signal lamp to be supplemented are not positioned on the same straight line.
In an alternative embodiment, the determining the fourth position of the signal lamp to be compensated in the reference image according to at least the first position of the reference signal lamp in the reference image, the second position of the reference signal lamp in the reference image, and the third position of the signal lamp to be compensated in the reference image includes:
determining a position mapping relation between the reference image and the reference image according to the first position and the second position;
and determining the fourth position according to the mapping relation between the third position and the position.
In an optional embodiment, the determining the signal light information of the fourth position according to the signal light information of at least one third position includes:
aiming at any one of N-1 reference images, acquiring signal light information of the reference image at a third position, wherein the signal light information comprises M pieces of sub information;
counting the number of sub information with the same content in the N-1 sub information corresponding to the N-1 reference images aiming at each piece of sub information; and taking the sub information with the largest number as the sub information of the signal lamp information at the fourth position.
In an optional embodiment, after acquiring the N images shot for the same group of signal lamps within a preset time period, the method further includes:
carrying out binarization processing on the N images and removing noise;
and determining the positions of all signal lamps on the N images by utilizing gradient calculation.
In an alternative embodiment, the N images are N frames of images in the same video stream, and the reference image is a first frame of image of the video stream.
The embodiment of the present invention further provides a device for identifying a signal lamp, including:
the acquisition unit is used for acquiring N images shot for the same group of signal lamps in a preset time period; each image is used for identifying the signal lamp in a lighting state;
the determining unit is used for determining reference signal lamps, and the reference signal lamps are arranged in the N images;
the calculation unit is used for determining a third position of a supplementary signal lamp in the reference image and a fourth position of a to-be-supplemented signal lamp of the same signal lamp as the supplementary signal lamp in the reference image according to at least a first position of the reference signal lamp in the reference image and a second position of the reference signal lamp in the reference image; the reference image is any one of the N images, and the reference image is any one of the N images except the reference image; the supplementary signal lamp is any signal lamp except the reference signal lamp in the reference image;
and the supplement unit is used for determining the signal light information of the fourth position according to the signal light information of at least one third position.
In an optional embodiment, the number of the reference signal lamps is at least 2;
the determining unit is specifically configured to:
and selecting the signal lamps in the N images which are all in the bright state as the reference signal lamps, wherein the two reference signal lamps in the same image and the supplementary signal lamps are not positioned on the same straight line.
In an optional embodiment, the computing unit is specifically configured to:
determining a position mapping relation between the reference image and the reference image according to the first position and the second position;
and determining the fourth position according to the mapping relation between the third position and the position.
In an optional embodiment, the supplementary unit is specifically configured to:
aiming at any one of N-1 reference images, acquiring signal light information of the reference image at a third position, wherein the signal light information comprises M pieces of sub information;
counting the number of sub information with the same content in the N-1 sub information corresponding to the N-1 reference images aiming at each piece of sub information; and taking the sub information with the largest number as the sub information of the signal lamp information at the fourth position.
In an optional embodiment, the apparatus further comprises a processing unit configured to:
carrying out binarization processing on the N images and removing noise;
and determining the positions of all signal lamps on the N images by utilizing gradient calculation.
In an alternative embodiment, the N images are N frames of images in the same video stream, and the reference image is a first frame of image of the video stream.
An embodiment of the present invention further provides an electronic device, including:
at least one processor; and the number of the first and second groups,
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 method as described above.
Embodiments of the present invention also provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method as described above.
In the embodiment of the invention, N images shot for the same group of signal lamps in a preset time period are obtained; each image is used to identify the signal light in the lit state. The signal light present in all N images is taken as the reference signal light. Any one of the N images is used as a reference image, and any one of the N images except the reference image is used as a reference image. And for each reference image, determining a fourth position of the signal lamp to be supplemented in the reference image according to the first position of the reference signal lamp in the reference image, the second position of the reference signal lamp in the reference image and the third position of the supplementary signal lamp in the reference image. And the signal lamp to be supplemented is any signal lamp except the reference signal lamp in the reference image. And determining the signal light information of the fourth position according to the signal light information of at least one third position. According to the embodiment of the invention, images shot at different angles and different time points are compared, the position characteristics of signal lamp distribution are effectively utilized, and the positions of the same signal lamp in different images are associated, so that signal lamp information in different images can be mutually supplemented, all signal lamps in a lighting state can be conveniently identified, the calculated amount is small, and the method is simple and efficient.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a signal lamp identification method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a binarized image according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a signal light arrangement of a cabinet according to an embodiment of the invention;
FIG. 4 is a schematic diagram illustrating a mapping relationship between signal lamps in the reference image and signal lamps in the reference image according to an embodiment of the present invention;
fig. 5 is a schematic flowchart of a signal lamp identification method according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an identification apparatus for a signal lamp according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The machine room intelligent inspection robot is an important leading-edge innovation technology which needs deep research and application for various large financial enterprises. Through understanding, the large-scale bank in China has started the research of the machine room intelligent inspection robot at present. The intelligent inspection robot identifies the signal lamp condition of the server by shooting or photographing the server, so that the state of the server is judged. However, due to the problems of flickering of the signal lamps and the shooting angle, one image may not accurately reflect the information of all the signal lamps. For example, some traffic lights are actually turned on within a predetermined time, but the time point when a certain image is captured coincides with the time point when the traffic light blinks, and therefore the state of the traffic light in some images is turned off. Therefore, multiple images are required to complement each other.
In order to solve the above problem, an embodiment of the present invention provides a method for identifying a signal lamp, as shown in fig. 1, the method for identifying a signal lamp provided by the embodiment of the present invention includes the following steps:
And 102, determining reference signal lamps, wherein the reference signal lamps are arranged in the N images.
103, for each reference image, determining a fourth position of the signal lamp to be compensated in the reference image at least according to the first position of the reference signal lamp in the reference image, the second position of the reference signal lamp in the reference image and the third position of the signal lamp to be compensated in the reference image; the reference image is any one of the N images, and the reference image is any one of the N images except the reference image; the supplementary signal lamp is any signal lamp except the reference signal lamp in the reference image.
And 104, determining the signal lamp information of the fourth position according to the signal lamp information of at least one third position.
In the embodiment of the invention, N images shot for the same group of signal lamps in a preset time period are obtained; each image is used to identify the signal light in the lit state. The signal light present in all N images is taken as the reference signal light. Any one of the N images is used as a reference image, and any one of the N images except the reference image is used as a reference image. And for each reference image, determining a third position of a supplementary signal lamp in the reference image and a fourth position of a to-be-supplemented signal lamp which is the same signal lamp as the supplementary signal lamp in the reference image according to the first position of the reference signal lamp in the reference image and the second position of the reference signal lamp in the reference image. The supplementary signal lamp is any signal lamp except the reference signal lamp in the reference image. And determining the signal light information of the fourth position according to the signal light information of at least one third position. According to the embodiment of the invention, images shot at different angles and different time points are compared, the position characteristics of signal lamp distribution are effectively utilized, and the positions of the same signal lamp in different images are associated, so that signal lamp information in different images can be mutually supplemented, all signal lamps in a lighting state can be conveniently identified, the calculated amount is small, and the method is simple and efficient.
The embodiment of the invention shoots the signal lamps on the server cabinet and shoots N images aiming at the same group of signal lamps. In order to perform the preliminary processing on the images, after the acquiring N images shot for the same group of signal lamps within the preset time period in step 101, the method further includes:
carrying out binarization processing on the N images and removing noise;
and determining the positions of all signal lamps on the N images by utilizing gradient calculation.
In the specific implementation process, firstly, the signal lamps in each image are preliminarily identified, and the preliminary position of each signal lamp is determined. The image is subjected to binarization processing, namely only the position information of the signal lamp is kept on the blackboard, and a binarization image of a black background and a white dot is formed, as shown in figure 2. The information of each signal lamp, including the state, color, belonging server and other information of the signal lamp, is correspondingly stored. The characteristics of the signal lamp can be effectively enhanced by utilizing the binarized image for identification, and noise reduction is facilitated. Since the signal lamp is easily confused with impurities, and the accuracy is reduced due to no noise reduction processing, the noise of the image is removed by using a Gaussian window after the binarization processing.
And then, determining the accurate position of the signal lamp in the binary image by utilizing gradient calculation, and replacing the corresponding signal lamp by utilizing each pixel point of the gravity center of the signal lamp for facilitating calculation to carry out analysis processing.
In the embodiment of the invention, the number of the reference signal lamps is at least 2. The determination reference signal lamp comprises:
and selecting the signal lamps in the bright state in the N images as the reference signal lamps, wherein the two reference signal lamps in the same image and the signal lamp to be supplemented are not positioned on the same straight line.
The cabinet's signal light arrangement is shown in fig. 3. Because the positions of the same signal lamp in different images are different due to shooting angles and the like, and because the position relationship between the signal lamps is different in different images due to the deformation of the images, the position mapping relationship of the signal lamps among different images needs to be established, the accurate position of the signal lamp to be supplemented is convenient to determine, and therefore the signal lamp to be supplemented in the reference image is found. The reference signal lamp is used for establishing a position mapping relation between the signal lamp in the reference image and the signal lamp in the reference image. In order to facilitate identification, the signal lamps in the N images which are all in the bright state are selected as reference signal lamps, and the two reference signal lamps and the signal lamp to be supplemented in the same image are not located on the same straight line. This is because if the reference signal lamp and the signal lamp to be supplemented are positioned on the same straight line, the deformations in different directions on the image cannot be reflected.
The step 103 of determining the fourth position of the signal lamp to be compensated in the reference image at least according to the first position of the reference signal lamp in the reference image, the second position of the reference signal lamp in the reference image, and the third position of the signal lamp to be compensated in the reference image includes:
determining a position mapping relation between the reference image and the reference image according to the first position and the second position;
and determining the fourth position according to the mapping relation between the third position and the position.
Specifically, any one of the N images is used as a reference image, and the rest N-1 images are all reference images. For any reference image, a position mapping relation between the reference image and the reference image needs to be established, so that the supplementary signal lamp in the reference image is in position relation with the signal lamp to be supplemented in the reference image. In the specific implementation process, the mapping relation between the positions of two reference signal lamps in the same image can be used for identifying the position of each reference signal lamp, a coordinate system is established in each image in a simpler and more convenient mode, the position coordinate of each signal lamp is determined, and the position of the corresponding signal lamp is identified by the coordinate.
For example, fig. 4 shows a mapping relationship between the positions of the signal lamps in the reference image and the signal lamps in the reference image. The signal lamp A and the signal lamp B are reference signal lamps, and the signal lamp C is a signal lamp to be supplemented. As shown in FIG. 4, A1、B1And C1To refer to the position of the signal light in the image, A2、B2And C2Is the signal light position in the reference image. Wherein A is1And A2Correspondingly, and corresponds to the signal lamp A; b is1And B2Correspondingly, and corresponds to the signal lamp B; c1And C2Correspondingly, and corresponds to signal lamp C. Determining the position of the signal lamp to be supplemented in the reference image according to the position of the reference signal lamp and the position of the signal lamp to be supplemented in the reference image, namely according to A1、B1、C1、A2And B2Determining C2. As can be seen from fig. 4, according to the spatial distribution characteristics of the signal lamps, the signal lamp a, the signal lamp B, and the signal lamp C in the same image form a triangle. For two different images, can be represented by A1Coordinate sum of (A)2Is obtained from the coordinates of A1A2The mapping relation between B and1coordinate sum of (A) and (B)2Is obtained from the coordinates of1B2The mapping relationship between them. According to A1A2The mapping relation between and B1B2The mapping relation between the C and the C can be obtained1C2The mapping relationship between them, then know C1Can determine C in the reference image2The coordinates of (a).
Further, the step 104 of determining the signal light information of the fourth position according to the signal light information of at least one third position includes:
aiming at any one of N-1 reference images, acquiring signal light information of the reference image at a third position, wherein the signal light information comprises M pieces of sub information;
counting the number of sub information with the same content in the N-1 sub information corresponding to the N-1 reference images aiming at each piece of sub information; and taking the sub information with the largest number as the sub information of the signal lamp information at the fourth position.
Specifically, after the position of the signal lamp to be supplemented in the reference image is determined, the information of the signal lamp to be supplemented in the reference image is supplemented by using the information of the signal lamp to be supplemented in the rest N-1 reference images. And each signal lamp information comprises M pieces of sub information, the quantity of each piece of sub information content in N-1 reference images is counted and sequenced aiming at each piece of sub information, and the sub information content with the largest quantity is selected as the sub information content of the signal lamp to be supplemented in the reference image. For example, the sub-information includes the status, color, and belonging server of the signal lamp. The sub information contents are bright and non-bright according to the state of the signal lamp, and of the 49 reference images, the sub information content of the signal lamp to be supplemented is not bright in 10 reference images, and the sub information content of the signal lamp to be supplemented is bright in the other 39 reference images. And selecting the content of the signal lamp state of the sub-information as bright, namely marking the signal lamp state of the signal lamp to be supplemented in the reference image as bright. For another example, the sub information content has three colors of red, yellow, and green for the color of the signal lamp. In 49 reference images, the sub information content of the signal lamp to be supplemented in 9 reference images is red, the sub information content of the signal lamp to be supplemented in 15 reference images is green, and the sub information content of the signal lamp to be supplemented in the rest 25 reference images is yellow, the content of the color of the selected sub information signal lamp is yellow, namely, the signal lamp color of the signal lamp to be supplemented in the reference image is marked as yellow. And traversing each signal lamp to be supplemented in the reference image, and performing information supplementation on the signal lamp to be supplemented in the reference image by using the signal lamp information of the rest N-1 reference images.
Besides photographing the signal lamps of the cabinet, videos can be photographed. The N images are N frames of images in the same video stream, and the reference image is the first frame of image of the video stream. The remaining frame images except the first frame are used as reference images.
In order to more clearly understand the present invention, the above flow is described in detail below with a specific embodiment, and the steps of the specific embodiment are shown in fig. 5, and include:
step 401: n images shot for the same group of signal lamps in a preset time period are obtained.
Step 402: any one of the N images is used as a reference image, and the rest N-1 images are used as reference images.
Step 403: and carrying out binarization processing on each image and carrying out denoising.
Step 404: and finding the position of the signal lamp in the binary image by utilizing gradient calculation, and analyzing and processing by replacing the signal lamp with the gravity center of the signal lamp to determine the gravity center position of the signal lamp.
Step 405: two signal lights which can be identified in all images are used as reference signal lights.
Step 406: and aiming at one signal lamp to be identified, establishing a position mapping relation between the signal lamp to be identified in the reference image and the signal lamp to be identified in any reference image. The position mapping relationship is established based on the position coordinates of the reference signal lamp in the reference image, and the position coordinates of the reference signal lamp in the reference image.
Step 407: and counting the number of the sub information contents of the signal lamp to be identified in all the reference images, and selecting the sub information content with the largest number as the sub information content of the signal lamp to be identified in the reference image.
Step 408: and traversing each signal lamp to be identified in the reference image, and determining the position and signal lamp information of each signal lamp to be identified.
An embodiment of the present invention further provides a device for identifying a signal lamp, as shown in fig. 6, including:
an obtaining unit 501, configured to obtain N images shot for the same group of signal lamps in a preset time period; each image is used for identifying the signal lamp in a lighting state;
a determining unit 502, configured to determine a reference signal lamp, where the reference signal lamp is present in each of the N images;
a calculating unit 503, configured to determine, for each reference image, a third position of a supplementary signal lamp in the reference image and a fourth position of a to-be-supplemented signal lamp of the same signal lamp as the supplementary signal lamp in the reference image according to at least a first position of the reference signal lamp in the reference image and a second position of the reference signal lamp in a reference image; the reference image is any one of the N images, and the reference image is any one of the N images except the reference image; the supplementary signal lamp is any signal lamp except the reference signal lamp in the reference image;
a supplementing unit 504, configured to determine the signal light information of the fourth location according to the signal light information of at least one third location.
Further, the number of the reference signal lamps is at least 2;
the determining unit 502 is specifically configured to:
and selecting the signal lamps in the N images which are all in the bright state as the reference signal lamps, wherein the two reference signal lamps in the same image and the supplementary signal lamps are not positioned on the same straight line.
Further, the calculating unit 503 is specifically configured to:
determining a position mapping relation between the reference image and the reference image according to the first position and the second position;
and determining the fourth position according to the mapping relation between the third position and the position.
Further, the supplementing unit 504 is specifically configured to:
aiming at any one of N-1 reference images, acquiring signal light information of the reference image at a third position, wherein the signal light information comprises M pieces of sub information;
counting the number of sub information with the same content in the N-1 sub information corresponding to the N-1 reference images aiming at each piece of sub information; and taking the sub information with the largest number as the sub information of the signal lamp information at the fourth position.
Further, a processing unit 505 is included for:
carrying out binarization processing on the N images and removing noise;
and determining the positions of all signal lamps on the N images by utilizing gradient calculation.
Further, the N images are N frames of images in the same video stream, and the reference image is a first frame of image of the video stream.
Based on the same principle, the present invention also provides an electronic device, as shown in fig. 7, including:
the system comprises a processor 601, a memory 602, a transceiver 603 and a bus interface 604, wherein the processor 601, the memory 602 and the transceiver 603 are connected through the bus interface 604;
the processor 601 is configured to read the program in the memory 602, and execute the following methods:
acquiring N images shot for the same group of signal lamps in a preset time period; each image is used for identifying the signal lamp in a lighting state;
determining reference signal lamps, wherein the reference signal lamps are arranged in the N images;
for each reference image, determining a fourth position of the signal lamp to be supplemented in the reference image at least according to a first position of the reference signal lamp in the reference image, a second position of the reference signal lamp in the reference image and a third position of the signal lamp to be supplemented in the reference image; the reference image is any one of the N images, and the reference image is any one of the N images except the reference image; the signal lamp to be supplemented is any signal lamp except the reference signal lamp in the reference image;
and determining the signal light information of the fourth position according to the signal light information of at least one third position.
Further, the number of the reference signal lamps is at least 2; the processor 601 is specifically configured to:
and selecting the signal lamps in the bright state in the N images as the reference signal lamps, wherein the two reference signal lamps in the same image and the signal lamp to be supplemented are not positioned on the same straight line.
Further, the processor 601 is specifically configured to:
determining a position mapping relation between the reference image and the reference image according to the first position and the second position;
and determining the fourth position according to the mapping relation between the third position and the position.
Further, the processor 601 is specifically configured to:
aiming at any one of N-1 reference images, acquiring signal light information of the reference image at a third position, wherein the signal light information comprises M pieces of sub information;
counting the number of sub information with the same content in the N-1 sub information corresponding to the N-1 reference images aiming at each piece of sub information; and taking the sub information with the largest number as the sub information of the signal lamp information at the fourth position.
Further, the processor 601 is further configured to:
carrying out binarization processing on the N images and removing noise;
and determining the positions of all signal lamps on the N images by utilizing gradient calculation.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (12)
1. A method for identifying a signal lamp, comprising:
acquiring N images shot for the same group of signal lamps in a preset time period; each image is used for identifying the signal lamp in a lighting state;
selecting signal lamps in the N images which are all in a bright state as reference signal lamps, wherein two reference signal lamps in the same image and signal lamps to be supplemented are not located on the same straight line, the N images are provided with the reference signal lamps, and the number of the reference signal lamps is at least 2;
for each reference image, determining a fourth position of the signal lamp to be supplemented in the reference image at least according to a first position of the reference signal lamp in the reference image, a second position of the reference signal lamp in the reference image and a third position of the signal lamp to be supplemented in the reference image; the reference image is any one of the N images, and the reference image is any one of the N images except the reference image; the signal lamp to be supplemented is any signal lamp except the reference signal lamp in the reference image;
and determining the signal light information of the fourth position according to the signal light information of at least one third position.
2. The method of claim 1, wherein determining the fourth position of the signal lamp to be compensated in the reference image based on at least the first position of the reference signal lamp in the reference image, the second position of the reference signal lamp in the reference image, and the third position of the signal lamp to be compensated in the reference image comprises:
determining a position mapping relation between the reference image and the reference image according to the first position and the second position;
and determining the fourth position according to the mapping relation between the third position and the position.
3. The method of claim 1, wherein said determining signal light information for said fourth location from signal light information for at least one third location comprises:
aiming at any one of N-1 reference images, acquiring signal light information of the reference image at a third position, wherein the signal light information comprises M pieces of sub information;
counting the number of sub information with the same content in the N-1 sub information corresponding to the N-1 reference images aiming at each piece of sub information; and taking the sub information with the largest number as the sub information of the signal lamp information at the fourth position.
4. The method of any one of claims 1 to 3, wherein said acquiring, after N images taken for the same set of signal lights within a preset time period, further comprises:
carrying out binarization processing on the N images and removing noise;
and determining the positions of all signal lamps on the N images by utilizing gradient calculation.
5. A method according to any one of claims 1 to 3, wherein said N pictures are N pictures in the same video stream, and said reference picture is the first picture in said video stream.
6. An apparatus for identifying a signal lamp, comprising:
the acquisition unit is used for acquiring N images shot for the same group of signal lamps in a preset time period; each image is used for identifying the signal lamp in a lighting state;
the determining unit is used for selecting the signal lamps in the bright state in the N images as reference signal lamps, two reference signal lamps in the same image and the signal lamp to be supplemented are not located on the same straight line, the N images are provided with the reference signal lamps, and the number of the reference signal lamps is at least 2;
the calculation unit is used for determining a fourth position of the signal lamp to be supplemented in the reference image according to at least a first position of the reference signal lamp in the reference image, a second position of the reference signal lamp in the reference image and a third position of the signal lamp to be supplemented in the reference image; the reference image is any one of the N images, and the reference image is any one of the N images except the reference image; the signal lamp to be supplemented is any signal lamp except the reference signal lamp in the reference image;
and the supplement unit is used for determining the signal light information of the fourth position according to the signal light information of at least one third position.
7. The apparatus of claim 6, wherein the computing unit is specifically configured to:
determining a position mapping relation between the reference image and the reference image according to the first position and the second position;
and determining the fourth position according to the mapping relation between the third position and the position.
8. The apparatus of claim 6, wherein the complementary unit is specifically configured to:
aiming at any one of N-1 reference images, acquiring signal light information of the reference image at a third position, wherein the signal light information comprises M pieces of sub information;
counting the number of sub information with the same content in the N-1 sub information corresponding to the N-1 reference images aiming at each piece of sub information; and taking the sub information with the largest number as the sub information of the signal lamp information at the fourth position.
9. The apparatus of any of claims 6 to 8, further comprising a processing unit to:
carrying out binarization processing on the N images and removing noise;
and determining the positions of all signal lamps on the N images by utilizing gradient calculation.
10. The apparatus according to any one of claims 6 to 8, wherein the N pictures are N frames of pictures in the same video stream, and the reference picture is a first frame of picture of the video stream.
11. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
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 method of any one of claims 1-5.
12. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811647448.7A CN109711375B (en) | 2018-12-29 | 2018-12-29 | Signal lamp identification method and device |
| PCT/CN2019/093201 WO2020133983A1 (en) | 2018-12-29 | 2019-06-27 | Signal light identification method, device, and electronic apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811647448.7A CN109711375B (en) | 2018-12-29 | 2018-12-29 | Signal lamp identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109711375A CN109711375A (en) | 2019-05-03 |
| CN109711375B true CN109711375B (en) | 2021-03-16 |
Family
ID=66260287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811647448.7A Active CN109711375B (en) | 2018-12-29 | 2018-12-29 | Signal lamp identification method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109711375B (en) |
| WO (1) | WO2020133983A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711375B (en) * | 2018-12-29 | 2021-03-16 | ***股份有限公司 | Signal lamp identification method and device |
| CN111192377B (en) * | 2020-01-08 | 2021-08-27 | ***股份有限公司 | Image processing method and device |
| CN112364740B (en) * | 2020-10-30 | 2024-04-19 | 交控科技股份有限公司 | Unmanned aerial vehicle room monitoring method and system based on computer vision |
| CN113129375B (en) * | 2021-04-21 | 2023-12-01 | 阿波罗智联(北京)科技有限公司 | Data processing method, device, equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103531022B (en) * | 2013-10-15 | 2015-09-09 | 浙江宇视科技有限公司 | A kind of traffic light color period statistical method |
| KR101806703B1 (en) * | 2016-06-01 | 2018-01-10 | 현대자동차주식회사 | Driver state monitoring apparatus |
| CN107743200A (en) * | 2017-10-31 | 2018-02-27 | 广东欧珀移动通信有限公司 | Method, apparatus, computer-readable recording medium and the electronic equipment taken pictures |
| CN108447091B (en) * | 2018-03-27 | 2022-09-06 | 北京颂泽科技有限公司 | Target positioning method and device, electronic equipment and storage medium |
| CN109711375B (en) * | 2018-12-29 | 2021-03-16 | ***股份有限公司 | Signal lamp identification method and device |
-
2018
- 2018-12-29 CN CN201811647448.7A patent/CN109711375B/en active Active
-
2019
- 2019-06-27 WO PCT/CN2019/093201 patent/WO2020133983A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020133983A1 (en) | 2020-07-02 |
| CN109711375A (en) | 2019-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711375B (en) | Signal lamp identification method and device | |
| CN111667520B (en) | Registration method and device for infrared image and visible light image and readable storage medium | |
| US9740967B2 (en) | Method and apparatus of determining air quality | |
| CN108549874B (en) | Target detection method, target detection equipment and computer-readable storage medium | |
| CN107492091B (en) | Label appearance detection method based on machine vision and terminal equipment | |
| CN108686978B (en) | ARM-based fruit category and color sorting method and system | |
| US8948533B2 (en) | Increased quality of image objects based on depth in scene | |
| CN111539311B (en) | Living body judging method, device and system based on IR and RGB double shooting | |
| CN111784675A (en) | Method and device for processing article texture information, storage medium and electronic equipment | |
| CN109934873B (en) | Method, device and equipment for acquiring marked image | |
| CN115908774B (en) | Quality detection method and device for deformed materials based on machine vision | |
| US11216905B2 (en) | Automatic detection, counting, and measurement of lumber boards using a handheld device | |
| CN110599453A (en) | Panel defect detection method and device based on image fusion and equipment terminal | |
| CN104749801B (en) | High Precision Automatic optical detecting method and system | |
| CN114577805A (en) | MiniLED backlight panel defect detection method and device | |
| CN113780484B (en) | Industrial product defect detection method and device | |
| CN108491857A (en) | A kind of multiple-camera target matching method of ken overlapping | |
| CN111723656A (en) | Smoke detection method and device based on YOLO v3 and self-optimization | |
| CN114758268A (en) | Gesture recognition method and device and intelligent equipment | |
| CN112863194B (en) | Image processing method, device, terminal and medium | |
| CN117218633A (en) | Article detection method, device, equipment and storage medium | |
| CN117253022A (en) | Object identification method, device and inspection equipment | |
| CN116681677A (en) | Lithium battery defect detection method, device and system | |
| CN114219758A (en) | Defect detection method, system, electronic device and computer readable storage medium | |
| CN113657316A (en) | Mobile traffic violation monitoring method, system, electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |