CN116152784A - Signal lamp early warning method and system based on image processing - Google Patents
Signal lamp early warning method and system based on image processing Download PDFInfo
- Publication number
- CN116152784A CN116152784A CN202310431016.7A CN202310431016A CN116152784A CN 116152784 A CN116152784 A CN 116152784A CN 202310431016 A CN202310431016 A CN 202310431016A CN 116152784 A CN116152784 A CN 116152784A
- Authority
- CN
- China
- Prior art keywords
- color
- signal lamp
- image
- image data
- area
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000008859 change Effects 0.000 claims description 50
- 238000004458 analytical method Methods 0.000 claims description 32
- 238000006243 chemical reaction Methods 0.000 claims description 30
- 239000003550 marker Substances 0.000 claims description 26
- 230000007613 environmental effect Effects 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 20
- 230000009467 reduction Effects 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 description 6
- 238000005286 illumination Methods 0.000 description 6
- 241000284156 Clerodendrum quadriloculare Species 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a signal lamp early warning method and system based on image processing. The invention can effectively reduce the delay of dynamic contrast switching and brightness adjustment, further improve the identification degree of the picture and greatly improve the efficiency of identifying and early warning the signal lamp.
Description
Technical Field
The invention relates to the field of image processing, in particular to a signal lamp early warning method and system based on image processing.
Background
In the signal lamp identification process of the rail transit, the signal lamp identification and early warning process of the rail transit is often hindered by a series of factors such as weather, illumination and the like, and the problems of overexposure of images, starburst, light spots, darkness and the like caused under complex light environments such as backlight, low illumination, tunnel entering and exiting and the like are often shown, so that a signal lamp early warning method with high adaptability and high efficiency is needed.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a signal lamp early warning method and system based on image processing.
The first aspect of the invention provides a signal lamp early warning method based on image processing, which comprises the following steps:
acquiring video data;
dynamic adjustment based on contrast and brightness is carried out according to video data;
performing image extraction and image preprocessing according to the video data, and performing color conversion adjustment through color difference analysis to obtain corresponding image data;
performing signal lamp color recognition analysis on the image data, obtaining a recognition result, and generating signal lamp early warning information based on the recognition result;
and sending the signal lamp early warning information to preset terminal equipment for display.
In this scheme, the dynamic adjustment based on contrast and brightness according to video data includes:
acquiring historical video data of a train;
intercepting target video data of the tunnel section from the historical video data;
dividing target video data according to the front, middle and rear three sections of the driving tunnel, and carrying out key image frame extraction and image noise reduction processing on the divided video data to obtain image data before the tunnel, image data in the tunnel and image data after the tunnel.
In this scheme, the dynamic adjustment based on contrast and brightness is performed according to video data, and further includes:
carrying out object recognition based on color characteristics on the image data before the tunnel to obtain contour information and color characteristic information of a plurality of objects;
according to the contour information and the color characteristic information of the object, calculating and analyzing the contour area and the color richness to obtain the contour area and the color richness of the corresponding object;
if the contour area is larger than the preset area and the color richness is larger than the preset richness, marking the corresponding object as a marker, and integrating the corresponding contour information and the color characteristic information to obtain the image characteristics of the marker.
In this scheme, the dynamic adjustment based on contrast and brightness is performed according to video data, and further includes:
dividing into a plurality of areas according to a picture size of the image data;
selecting an area, and calculating a contrast difference value and a brightness difference value in the image data before the tunnel and the image data in the tunnel based on the area;
if the contrast difference value is higher than a preset contrast change value, marking the area as a contrast adjustment area, and calculating a contrast adjustment parameter according to the contrast difference value and the preset contrast change value;
If the brightness difference value is higher than the preset brightness change value, marking the area as a brightness adjustment area, and calculating a brightness adjustment parameter according to the brightness difference value and the preset brightness change value;
and analyzing and calculating all the areas, and obtaining all the contrast adjustment areas and the brightness adjustment areas.
In this scheme, the dynamic adjustment based on contrast and brightness is performed according to video data, and further includes:
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
extracting features of the image data and comparing the features of the image data with the features of the marker image in a profile-color feature manner;
if the image data has the image characteristics of the marker, the contrast and the brightness of the multiple areas are adjusted according to the contrast adjusting area and the contrast adjusting parameter and the brightness adjusting area and the brightness adjusting parameter.
In this scheme, carry out image extraction and image preprocessing according to video data, carry out color conversion adjustment through color difference analysis, obtain corresponding image data, specifically be:
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
the image data is subjected to enhancement and noise reduction pretreatment, the outline of the object is identified, an object area is obtained, and areas outside the object area in the image are marked as background areas;
Subdividing the background area into a plurality of subareas, and calculating the color saturation of the plurality of subareas on the image in the background area to obtain a plurality of color saturation;
performing average value calculation on the plurality of color saturation to obtain the current environmental color saturation;
acquiring the ambient color chroma of the contrast image and marking the ambient color chroma as standard color chroma;
performing color difference degree comparison on the current environmental color degree and the standard color degree;
if the difference value is larger than the preset threshold value, the current environmental color chroma is taken as an original value, the standard color chroma is taken as a target value, and the color conversion between the original value and the target value is carried out, so that the corresponding color conversion parameters are obtained.
In this scheme, carry out signal lamp color recognition analysis to image data to obtain the recognition result, based on recognition result generates signal lamp early warning information, specifically do:
acquiring train position information and signal lamp position information based on a GPS;
setting a signal lamp detection track section according to the signal lamp position information and a preset distance, and marking the corresponding section as a preset track section;
judging whether the current train position enters a preset track section, and if so, acquiring corresponding image data;
performing color conversion on the image data according to the color conversion parameters to obtain second image data;
Based on the signal lamp area, performing image segmentation on the second image data to obtain image data corresponding to the signal lamp area and marking the image data as signal lamp image data;
according to the regional color, carrying out color boundary tracking and contour extraction on signal lamp image data to obtain one or more signal lamp contour regions;
taking a signal lamp outline area with the area larger than a preset threshold value as an identification area, wherein one or more identification areas are provided;
carrying out color average calculation on the image corresponding to the identification area to obtain average color chroma, and carrying out similarity calculation analysis on the average color chroma and a preset signal lamp color standard;
if the similarity is larger than a preset threshold value, acquiring a corresponding color identification result according to a preset signal lamp color standard, and acquiring signal lamp identification information according to the color identification result;
and generating signal early warning information in real time based on the signal lamp identification information.
The second aspect of the invention also provides a signal lamp early warning system based on image processing, which comprises: the system comprises a memory and a processor, wherein the memory comprises a signal lamp early warning program based on image processing, and the signal lamp early warning program based on the image processing realizes the following steps when being executed by the processor:
Acquiring video data;
dynamic adjustment based on contrast and brightness is carried out according to video data;
performing image extraction and image preprocessing according to the video data, and performing color conversion adjustment through color difference analysis to obtain corresponding image data;
performing signal lamp color recognition analysis on the image data, obtaining a recognition result, and generating signal lamp early warning information based on the recognition result;
and sending the signal lamp early warning information to preset terminal equipment for display.
In this scheme, the dynamic adjustment based on contrast and brightness is performed according to video data, and further includes:
acquiring historical video data of a train;
intercepting target video data of the tunnel section from the historical video data;
dividing target video data according to the front, middle and rear three sections of the driving tunnel, and carrying out key image frame extraction and image noise reduction processing on the divided video data to obtain image data before the tunnel, image data in the tunnel and image data after the tunnel.
In this scheme, the dynamic adjustment based on contrast and brightness is performed according to video data, and further includes:
carrying out object recognition based on color characteristics on the image data before the tunnel to obtain contour information and color characteristic information of a plurality of objects;
According to the contour information and the color characteristic information of the object, calculating and analyzing the contour area and the color richness to obtain the contour area and the color richness of the corresponding object;
if the contour area is larger than the preset area and the color richness is larger than the preset richness, marking the corresponding object as a marker, and integrating the corresponding contour information and the color characteristic information to obtain the image characteristics of the marker.
The invention discloses a signal lamp early warning method and system based on image processing. The invention can effectively reduce the delay of dynamic contrast switching and brightness adjustment, further improve the identification degree of the picture and greatly improve the efficiency of identifying and early warning the signal lamp.
Drawings
FIG. 1 shows a flow chart of a signal lamp early warning method based on image processing of the invention;
FIG. 2 illustrates a marker image feature acquisition flow chart of the present invention;
FIG. 3 is a flow chart showing the contrast adjustment region and brightness adjustment region acquisition of the present invention;
fig. 4 shows a block diagram of a signal lamp early warning system based on image processing according to the invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a signal lamp early warning method based on image processing.
As shown in fig. 1, a first aspect of the present invention provides a signal lamp early warning method based on image processing, including:
s102, acquiring video data;
s104, dynamically adjusting the contrast and brightness based on the video data;
S106, performing image extraction and image preprocessing according to the video data, and performing color conversion adjustment through color difference analysis to obtain corresponding image data;
s108, performing signal lamp color recognition analysis on the image data, obtaining a recognition result, and generating signal lamp early warning information based on the recognition result;
s110, the signal lamp early warning information is sent to preset terminal equipment for display.
It should be noted that the preset terminal device includes a computing device, a terminal device and a mobile terminal device.
According to an embodiment of the present invention, the performing dynamic adjustment based on contrast and brightness according to video data includes:
acquiring historical video data of a train;
intercepting target video data of the tunnel section from the historical video data;
dividing target video data according to the front, middle and rear three sections of the driving tunnel, and carrying out key image frame extraction and image noise reduction processing on the divided video data to obtain image data before the tunnel, image data in the tunnel and image data after the tunnel.
Fig. 2 shows a flowchart of the marker image feature acquisition of the present invention.
According to an embodiment of the present invention, the dynamic adjustment based on contrast and brightness according to video data further includes:
S202, carrying out object recognition based on color features on the image data before the tunnel to obtain contour information and color feature information of a plurality of objects;
s204, calculating and analyzing the outline area and the color richness according to the outline information and the color characteristic information of the object to obtain the outline area and the color richness of the corresponding object;
s206, if the outline area is larger than the preset area and the color richness is larger than the preset richness, marking the corresponding object as a marker, and integrating the corresponding outline information and the color characteristic information to obtain the image characteristics of the marker.
The tunnel section may be an above-ground or underground track section, or a track section with a large change in time from a picture under other complicated light environments. The color richness is specifically the product of the number of picture tone types and the saturation mean value. If the color richness of the object is higher, the outline area is larger, the accuracy of identifying the object is higher, and the identification time is shorter. The marker can be used for judging whether a train is ready to enter a tunnel or an underground track in real time, and further reducing the condition of low recognition rate caused by low illumination and low contrast of a picture by adjusting the contrast and brightness of the image in advance. In addition, the identifier is generally an object with a large recognition degree, such as a sign, a tree, a specific building, etc., in front of the tunnel section.
Fig. 3 shows a flowchart of the contrast adjustment region and brightness adjustment region acquisition of the present invention.
According to an embodiment of the present invention, the dynamic adjustment based on contrast and brightness according to video data further includes:
s302, dividing the image data into a plurality of areas according to the picture size of the image data;
s304, selecting an area, and calculating a contrast difference value and a brightness difference value in the image data before the tunnel and the image data in the tunnel based on the area;
s306, if the contrast difference value is higher than a preset contrast change value, marking the area as a contrast adjustment area, and calculating a contrast adjustment parameter according to the contrast difference value and the preset contrast change value;
s308, if the brightness difference value is higher than a preset brightness change value, marking the area as a brightness adjustment area, and calculating a brightness adjustment parameter according to the brightness difference value and the preset brightness change value;
s310, analyzing and calculating all areas, and obtaining all contrast adjustment areas and brightness adjustment areas.
In the image data, the image data before the tunnel, the image data in the tunnel and the image data after the tunnel correspond to the same size of the image, and the number of the areas divided into the plurality of areas can be 4, 9, 16 and the like, each area needs to ensure that the image size is the same, and the more the areas are divided, the finer the contrast and brightness adjustment of the image, and the larger the system calculation amount is. The specific numerical value of the contrast adjustment parameter is the difference between the contrast difference value and a preset contrast change value, and the specific numerical value of the brightness adjustment parameter is the difference between the brightness difference value and the preset brightness change value. In addition, one contrast adjustment region corresponds to one contrast adjustment parameter, one brightness adjustment region corresponds to one brightness adjustment parameter, and the contrast adjustment region and the brightness adjustment region may be the same region.
It is worth mentioning that when a train travels from a brighter area to a darker area in a tunnel or in a lower track during the traveling of the train based on tunnels, underground and above-ground tracks, the conditions of exposure, starburst, light spots, over darkness and the like of the picture can be caused due to the severe change of brightness and image contrast, which seriously affects the identification of signal lamps in the image.
According to an embodiment of the present invention, the dynamic adjustment based on contrast and brightness according to video data further includes:
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
extracting features of the image data and comparing the features of the image data with the features of the marker image in a profile-color feature manner;
if the image data has the image characteristics of the marker, the contrast and the brightness of the multiple areas are adjusted according to the contrast adjusting area and the contrast adjusting parameter and the brightness adjusting area and the brightness adjusting parameter.
If the image data has the image feature of the marker, it is determined that the current train is ready to enter the tunnel, and at this time, the contrast and brightness of the screen need to be adjusted in real time.
In addition, the invention carries out real-time judgment and picture adjustment in advance before the train enters the tunnel by recording the tunnel front identifier, thereby reducing the delay of dynamic switching contrast and brightness adjustment, further improving the identification degree of pictures and greatly improving the efficiency of identifying and early warning signal lamps in the follow-up process.
According to the embodiment of the invention, the image extraction and the image preprocessing are performed according to the video data, and the color conversion adjustment is performed through the color difference analysis to obtain the corresponding image data, specifically:
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
the image data is subjected to enhancement and noise reduction pretreatment, the outline of the object is identified, an object area is obtained, and areas outside the object area in the image are marked as background areas;
subdividing the background area into a plurality of subareas, and calculating the color saturation of the plurality of subareas on the image in the background area to obtain a plurality of color saturation;
performing average value calculation on the plurality of color saturation to obtain the current environmental color saturation;
acquiring the ambient color chroma of the contrast image and marking the ambient color chroma as standard color chroma;
performing color difference degree comparison on the current environmental color degree and the standard color degree;
if the difference value is larger than the preset threshold value, the current environmental color chroma is taken as an original value, the standard color chroma is taken as a target value, and the color conversion between the original value and the target value is carried out, so that the corresponding color conversion parameters are obtained.
The video data is obtained through a rail transit early warning camera, and the rail transit early warning camera is generally arranged at the front end of the rail train and used for obtaining images in front of the rail train in real time and identifying and early warning and analyzing signal lamps. In the identification of the object profile, specifically, the general object such as ground, platform, building and the like during the running of the train is identified, and the rest areas are marked as background areas except the object areas of the general object. The specific number of the plurality of sub-areas is typically set by the user. The contrast image is image data obtained in a normal weather state (namely, severe weather such as non-rain and snow) and a general illumination state (daytime), has good contrast effect, has high color recognition degree, and can be used as a standard color contrast image.
In addition, under the influence of severe weather such as rain, snow, wind and sand, the acquired image data often has the condition of large color deviation, and at the moment, the colors need to be dynamically converted so as to restore the colors of the real images. According to the invention, through the color and color analysis of the background area, standard difference analysis can be carried out on the current environmental color, and the environmental color, the object color and the standard color are different due to the difference of the environmental light, so that the acquisition and the identification of the color of the signal lamp can be influenced, and therefore, based on the current environmental color chroma, the current image is subjected to proper color conversion, and the color reduction degree and the identification rate of the signal lamp can be improved. The color conversion parameters include color adjustment parameters such as hue, brightness, saturation, and the like.
According to the embodiment of the invention, the image data is subjected to signal lamp color recognition analysis, a recognition result is obtained, and signal lamp early warning information is generated based on the recognition result, specifically:
acquiring train position information and signal lamp position information based on a GPS;
setting a signal lamp detection track section according to the signal lamp position information and a preset distance, and marking the corresponding section as a preset track section;
Judging whether the current train position enters a preset track section, and if so, acquiring corresponding image data;
performing color conversion on the image data according to the color conversion parameters to obtain second image data;
based on the signal lamp area, performing image segmentation on the second image data to obtain image data corresponding to the signal lamp area and marking the image data as signal lamp image data;
according to the regional color, carrying out color boundary tracking and contour extraction on signal lamp image data to obtain one or more signal lamp contour regions;
taking a signal lamp outline area with the area larger than a preset threshold value as an identification area, wherein one or more identification areas are provided;
carrying out color average calculation on the image corresponding to the identification area to obtain average color chroma, and carrying out similarity calculation analysis on the average color chroma and a preset signal lamp color standard;
if the similarity is larger than a preset threshold value, acquiring a corresponding color identification result according to a preset signal lamp color standard, and acquiring signal lamp identification information according to the color identification result;
and generating signal early warning information in real time based on the signal lamp identification information.
It should be noted that, the preset signal lamp color standards include five color standards of red, green, yellow, blue and white, and different signal lamp colors correspond to different early warning information, and are specifically set by a user.
According to an embodiment of the present invention, further comprising:
dividing into a plurality of areas according to a picture size of the image data;
selecting an area, and calculating a contrast difference value and a brightness difference value in the image data in the tunnel and the image data after the tunnel based on the area;
if the contrast difference value is higher than a preset contrast change value, marking the area as a contrast adjustment area, and calculating a contrast adjustment parameter according to the contrast difference value and the preset contrast change value;
if the brightness difference value is higher than the preset brightness change value, marking the area as a brightness adjustment area, and calculating a brightness adjustment parameter according to the brightness difference value and the preset brightness change value;
analyzing and calculating all areas, and obtaining all contrast adjustment areas and brightness adjustment areas;
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
judging brightness variation in a plurality of areas in the image data;
when the brightness change of a certain area is larger than a preset brightness change value, the contrast and brightness of multiple areas are adjusted according to the contrast adjusting area and the contrast adjusting parameter.
When the brightness change of a certain area is larger than the preset brightness change value, that is, when the train runs from the inside of the tunnel to the outside of the tunnel, the brightness is changed drastically, and at this time, the contrast and brightness of the picture can be adjusted in real time by comparing the brightness of a plurality of areas of the current image, so that the situations of exposure, starburst, light spots and the like are prevented.
According to an embodiment of the present invention, if the similarity is greater than a preset threshold, a corresponding color recognition result is obtained according to a preset signal lamp color standard, and signal lamp recognition information is obtained according to the color recognition result, which further includes:
carrying out color average calculation on the image corresponding to the identification area to obtain current average color chroma, and carrying out similarity calculation analysis on the average color chroma and a preset signal lamp color standard;
if the similarity is smaller than or equal to a preset threshold value and larger than or equal to a second preset threshold value, acquiring a plurality of corresponding historical images in the identification area to obtain a plurality of historical identification area images;
performing color average calculation on the plurality of history identification area images to obtain a plurality of average color saturation;
based on the image acquisition time sequence, sorting and color change analysis are carried out on a plurality of average color degrees and the current average color degree to obtain an average color degree change rate;
Judging whether the average color saturation change rate is larger than a preset change rate, and if so, generating signal lamp color early warning information in real time according to the image corresponding to the identification area.
It should be noted that, if the similarity is smaller than or equal to the preset threshold value and greater than or equal to the second preset threshold value, the color difference condition between the color of the signal lamp in the representative identification area and the standard color may occur, and further, through the judgment of the average color change rate, the condition that the color effect of the light of the signal lamp is inaccurate can be determined, that is, the higher color difference is achieved, at this time, the color pre-warning information of the signal lamp is generated in real time, so that the color condition of the light of the signal lamp in the current road section can be mastered in time, and the fault investigation is further performed on the signal lamp. The signal lamp color early warning information comprises a current identification area corresponding image and a current average color chroma.
Fig. 4 shows a block diagram of a signal lamp early warning system based on image processing according to the invention.
The second aspect of the present invention also provides a signal lamp early warning system 4 based on image processing, which comprises: the memory 41 and the processor 42, wherein the memory comprises a signal lamp early warning program based on image processing, and the signal lamp early warning program based on the image processing realizes the following steps when being executed by the processor:
Acquiring video data;
dynamic adjustment based on contrast and brightness is carried out according to video data;
performing image extraction and image preprocessing according to the video data, and performing color conversion adjustment through color difference analysis to obtain corresponding image data;
performing signal lamp color recognition analysis on the image data, obtaining a recognition result, and generating signal lamp early warning information based on the recognition result;
and sending the signal lamp early warning information to preset terminal equipment for display.
It should be noted that the preset terminal device includes a computing device, a terminal device and a mobile terminal device.
According to an embodiment of the present invention, the performing dynamic adjustment based on contrast and brightness according to video data includes:
acquiring historical video data of a train;
intercepting target video data of the tunnel section from the historical video data;
dividing target video data according to the front, middle and rear three sections of the driving tunnel, and carrying out key image frame extraction and image noise reduction processing on the divided video data to obtain image data before the tunnel, image data in the tunnel and image data after the tunnel.
According to an embodiment of the present invention, the dynamic adjustment based on contrast and brightness according to video data further includes:
Carrying out object recognition based on color characteristics on the image data before the tunnel to obtain contour information and color characteristic information of a plurality of objects;
according to the contour information and the color characteristic information of the object, calculating and analyzing the contour area and the color richness to obtain the contour area and the color richness of the corresponding object;
if the contour area is larger than the preset area and the color richness is larger than the preset richness, marking the corresponding object as a marker, and integrating the corresponding contour information and the color characteristic information to obtain the image characteristics of the marker.
The tunnel section may be an above-ground or underground track section, or a track section with a large change in time from a picture under other complicated light environments. The color richness is specifically the product of the number of picture tone types and the saturation mean value. If the color richness of the object is higher, the outline area is larger, the accuracy of identifying the object is higher, and the identification time is shorter. The marker can be used for judging whether a train is ready to enter a tunnel or an underground track in real time, and further reducing the condition of low recognition rate caused by low illumination and low contrast of a picture by adjusting the contrast and brightness of the image in advance. In addition, the identifier is generally an object with a large recognition degree, such as a sign, a tree, a specific building, etc., in front of the tunnel section.
According to an embodiment of the present invention, the dynamic adjustment based on contrast and brightness according to video data further includes:
dividing into a plurality of areas according to a picture size of the image data;
selecting an area, and calculating a contrast difference value and a brightness difference value in the image data before the tunnel and the image data in the tunnel based on the area;
if the contrast difference value is higher than a preset contrast change value, marking the area as a contrast adjustment area, and calculating a contrast adjustment parameter according to the contrast difference value and the preset contrast change value;
if the brightness difference value is higher than the preset brightness change value, marking the area as a brightness adjustment area, and calculating a brightness adjustment parameter according to the brightness difference value and the preset brightness change value;
and analyzing and calculating all the areas, and obtaining all the contrast adjustment areas and the brightness adjustment areas.
In the image data, the image data before the tunnel, the image data in the tunnel and the image data after the tunnel correspond to the same size of the image, and the number of the areas divided into the plurality of areas can be 4, 9, 16 and the like, each area needs to ensure that the image size is the same, and the more the areas are divided, the finer the contrast and brightness adjustment of the image, and the larger the system calculation amount is. The specific numerical value of the contrast adjustment parameter is the difference between the contrast difference value and a preset contrast change value, and the specific numerical value of the brightness adjustment parameter is the difference between the brightness difference value and the preset brightness change value. In addition, one contrast adjustment region corresponds to one contrast adjustment parameter, one brightness adjustment region corresponds to one brightness adjustment parameter, and the contrast adjustment region and the brightness adjustment region may be the same region.
It is worth mentioning that when a train travels from a brighter area to a darker area in a tunnel or in a lower track during the traveling of the train based on tunnels, underground and above-ground tracks, the conditions of exposure, starburst, light spots, over darkness and the like of the picture can be caused due to the severe change of brightness and image contrast, which seriously affects the identification of signal lamps in the image.
According to an embodiment of the present invention, the dynamic adjustment based on contrast and brightness according to video data further includes:
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
extracting features of the image data and comparing the features of the image data with the features of the marker image in a profile-color feature manner;
if the image data has the image characteristics of the marker, the contrast and the brightness of the multiple areas are adjusted according to the contrast adjusting area and the contrast adjusting parameter and the brightness adjusting area and the brightness adjusting parameter.
If the image data has the image feature of the marker, it is determined that the current train is ready to enter the tunnel, and at this time, the contrast and brightness of the screen need to be adjusted in real time.
In addition, the invention carries out real-time judgment and picture adjustment in advance before the train enters the tunnel by recording the tunnel front identifier, thereby reducing the delay of dynamic switching contrast and brightness adjustment, further improving the identification degree of pictures and greatly improving the efficiency of identifying and early warning signal lamps in the follow-up process.
According to the embodiment of the invention, the image extraction and the image preprocessing are performed according to the video data, and the color conversion adjustment is performed through the color difference analysis to obtain the corresponding image data, specifically:
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
the image data is subjected to enhancement and noise reduction pretreatment, the outline of the object is identified, an object area is obtained, and areas outside the object area in the image are marked as background areas;
subdividing the background area into a plurality of subareas, and calculating the color saturation of the plurality of subareas on the image in the background area to obtain a plurality of color saturation;
performing average value calculation on the plurality of color saturation to obtain the current environmental color saturation;
acquiring the ambient color chroma of the contrast image and marking the ambient color chroma as standard color chroma;
performing color difference degree comparison on the current environmental color degree and the standard color degree;
if the difference value is larger than the preset threshold value, the current environmental color chroma is taken as an original value, the standard color chroma is taken as a target value, and the color conversion between the original value and the target value is carried out, so that the corresponding color conversion parameters are obtained.
The video data is obtained through a rail transit early warning camera, and the rail transit early warning camera is generally arranged at the front end of the rail train and used for obtaining images in front of the rail train in real time and identifying and early warning and analyzing signal lamps. In the identification of the object profile, specifically, the general object such as ground, platform, building and the like during the running of the train is identified, and the rest areas are marked as background areas except the object areas of the general object. The specific number of the plurality of sub-areas is typically set by the user. The contrast image is image data obtained in a normal weather state (namely, severe weather such as non-rain and snow) and a general illumination state (daytime), has good contrast effect, has high color recognition degree, and can be used as a standard color contrast image.
In addition, under the influence of severe weather such as rain, snow, wind and sand, the acquired image data often has the condition of large color deviation, and at the moment, the colors need to be dynamically converted so as to restore the colors of the real images. According to the invention, through the color and color analysis of the background area, standard difference analysis can be carried out on the current environmental color, and the environmental color, the object color and the standard color are different due to the difference of the environmental light, so that the acquisition and the identification of the color of the signal lamp can be influenced, and therefore, based on the current environmental color chroma, the current image is subjected to proper color conversion, and the color reduction degree and the identification rate of the signal lamp can be improved. The color conversion parameters include color adjustment parameters such as hue, brightness, saturation, and the like.
According to the embodiment of the invention, the image data is subjected to signal lamp color recognition analysis, a recognition result is obtained, and signal lamp early warning information is generated based on the recognition result, specifically:
acquiring train position information and signal lamp position information based on a GPS;
setting a signal lamp detection track section according to the signal lamp position information and a preset distance, and marking the corresponding section as a preset track section;
Judging whether the current train position enters a preset track section, and if so, acquiring corresponding image data;
performing color conversion on the image data according to the color conversion parameters to obtain second image data;
based on the signal lamp area, performing image segmentation on the second image data to obtain image data corresponding to the signal lamp area and marking the image data as signal lamp image data;
according to the regional color, carrying out color boundary tracking and contour extraction on signal lamp image data to obtain one or more signal lamp contour regions;
taking a signal lamp outline area with the area larger than a preset threshold value as an identification area, wherein one or more identification areas are provided;
carrying out color average calculation on the image corresponding to the identification area to obtain average color chroma, and carrying out similarity calculation analysis on the average color chroma and a preset signal lamp color standard;
if the similarity is larger than a preset threshold value, acquiring a corresponding color identification result according to a preset signal lamp color standard, and acquiring signal lamp identification information according to the color identification result;
and generating signal early warning information in real time based on the signal lamp identification information.
It should be noted that, the preset signal lamp color standards include five color standards of red, green, yellow, blue and white, and different signal lamp colors correspond to different early warning information, and are specifically set by a user.
According to an embodiment of the present invention, further comprising:
dividing into a plurality of areas according to a picture size of the image data;
selecting an area, and calculating a contrast difference value and a brightness difference value in the image data in the tunnel and the image data after the tunnel based on the area;
if the contrast difference value is higher than a preset contrast change value, marking the area as a contrast adjustment area, and calculating a contrast adjustment parameter according to the contrast difference value and the preset contrast change value;
if the brightness difference value is higher than the preset brightness change value, marking the area as a brightness adjustment area, and calculating a brightness adjustment parameter according to the brightness difference value and the preset brightness change value;
analyzing and calculating all areas, and obtaining all contrast adjustment areas and brightness adjustment areas;
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
judging brightness variation in a plurality of areas in the image data;
when the brightness change of a certain area is larger than a preset brightness change value, the contrast and brightness of multiple areas are adjusted according to the contrast adjusting area and the contrast adjusting parameter.
When the brightness change of a certain area is larger than the preset brightness change value, that is, when the train runs from the inside of the tunnel to the outside of the tunnel, the brightness is changed drastically, and at this time, the contrast and brightness of the picture can be adjusted in real time by comparing the brightness of a plurality of areas of the current image, so that the situations of exposure, starburst, light spots and the like are prevented.
According to an embodiment of the present invention, if the similarity is greater than a preset threshold, a corresponding color recognition result is obtained according to a preset signal lamp color standard, and signal lamp recognition information is obtained according to the color recognition result, which further includes:
carrying out color average calculation on the image corresponding to the identification area to obtain current average color chroma, and carrying out similarity calculation analysis on the average color chroma and a preset signal lamp color standard;
if the similarity is smaller than or equal to a preset threshold value and larger than or equal to a second preset threshold value, acquiring a plurality of corresponding historical images in the identification area to obtain a plurality of historical identification area images;
performing color average calculation on the plurality of history identification area images to obtain a plurality of average color saturation;
based on the image acquisition time sequence, sorting and color change analysis are carried out on a plurality of average color degrees and the current average color degree to obtain an average color degree change rate;
Judging whether the average color saturation change rate is larger than a preset change rate, and if so, generating signal lamp color early warning information in real time according to the image corresponding to the identification area.
It should be noted that, if the similarity is smaller than or equal to the preset threshold value and greater than or equal to the second preset threshold value, the color difference condition between the color of the signal lamp in the representative identification area and the standard color may occur, and further, through the judgment of the average color change rate, the condition that the color effect of the light of the signal lamp is inaccurate can be determined, that is, the higher color difference is achieved, at this time, the color pre-warning information of the signal lamp is generated in real time, so that the color condition of the light of the signal lamp in the current road section can be mastered in time, and the fault investigation is further performed on the signal lamp. The signal lamp color early warning information comprises a current identification area corresponding image and a current average color chroma.
The invention discloses a signal lamp early warning method and system based on image processing. The invention can effectively reduce the delay of dynamic contrast switching and brightness adjustment, further improve the identification degree of the picture and greatly improve the efficiency of identifying and early warning the signal lamp.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The signal lamp early warning method based on image processing is characterized by comprising the following steps of:
acquiring video data;
dynamic adjustment based on contrast and brightness is carried out according to video data;
performing image extraction and image preprocessing according to the video data, and performing color conversion adjustment through color difference analysis to obtain corresponding image data;
performing signal lamp color recognition analysis on the image data, obtaining a recognition result, and generating signal lamp early warning information based on the recognition result;
and sending the signal lamp early warning information to preset terminal equipment for display.
2. The signal lamp pre-warning method based on image processing according to claim 1, wherein the performing the dynamic adjustment based on contrast and brightness according to video data comprises:
Acquiring historical video data of a train;
intercepting target video data of the tunnel section from the historical video data;
dividing target video data according to the front, middle and rear three sections of the driving tunnel, and carrying out key image frame extraction and image noise reduction processing on the divided video data to obtain image data before the tunnel, image data in the tunnel and image data after the tunnel.
3. The signal lamp pre-warning method based on image processing according to claim 2, wherein the dynamic adjustment based on contrast and brightness is performed according to video data, further comprising:
carrying out object recognition based on color characteristics on the image data before the tunnel to obtain contour information and color characteristic information of a plurality of objects;
according to the contour information and the color characteristic information of the object, calculating and analyzing the contour area and the color richness to obtain the contour area and the color richness of the corresponding object;
if the contour area is larger than the preset area and the color richness is larger than the preset richness, marking the corresponding object as a marker, and integrating the corresponding contour information and the color characteristic information to obtain the image characteristics of the marker.
4. The signal lamp pre-warning method based on image processing according to claim 3, wherein the dynamic adjustment based on contrast and brightness is performed according to video data, further comprising:
Dividing into a plurality of areas according to a picture size of the image data;
selecting an area, and calculating a contrast difference value and a brightness difference value in the image data before the tunnel and the image data in the tunnel based on the area;
if the contrast difference value is higher than a preset contrast change value, marking the area as a contrast adjustment area, and calculating a contrast adjustment parameter according to the contrast difference value and the preset contrast change value;
if the brightness difference value is higher than the preset brightness change value, marking the area as a brightness adjustment area, and calculating a brightness adjustment parameter according to the brightness difference value and the preset brightness change value;
and analyzing and calculating all the areas, and obtaining all the contrast adjustment areas and the brightness adjustment areas.
5. The signal lamp pre-warning method based on image processing according to claim 4, wherein the dynamic adjustment based on contrast and brightness is performed according to video data, further comprising:
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
extracting features of the image data and comparing the features of the image data with the features of the marker image in a profile-color feature manner;
if the image data has the image characteristics of the marker, the contrast and the brightness of the multiple areas are adjusted according to the contrast adjusting area and the contrast adjusting parameter and the brightness adjusting area and the brightness adjusting parameter.
6. The signal lamp early warning method based on image processing according to claim 1, wherein the image extraction and image preprocessing are performed according to video data, and the color conversion adjustment is performed through color difference analysis, so as to obtain corresponding image data, specifically:
acquiring video data in real time;
extracting an image key frame according to the video data to obtain image data;
the image data is subjected to enhancement and noise reduction pretreatment, the outline of the object is identified, an object area is obtained, and areas outside the object area in the image are marked as background areas;
subdividing the background area into a plurality of subareas, and calculating the color saturation of the plurality of subareas on the image in the background area to obtain a plurality of color saturation;
performing average value calculation on the plurality of color saturation to obtain the current environmental color saturation;
acquiring the ambient color chroma of the contrast image and marking the ambient color chroma as standard color chroma;
performing color difference degree comparison on the current environmental color degree and the standard color degree;
if the difference value is larger than the preset threshold value, the current environmental color chroma is taken as an original value, the standard color chroma is taken as a target value, and the color conversion between the original value and the target value is carried out, so that the corresponding color conversion parameters are obtained.
7. The signal lamp early warning method based on image processing according to claim 6, wherein the signal lamp color recognition analysis is performed on the image data, a recognition result is obtained, and signal lamp early warning information is generated based on the recognition result, specifically:
acquiring train position information and signal lamp position information based on a GPS;
setting a signal lamp detection track section according to the signal lamp position information and a preset distance, and marking the corresponding section as a preset track section;
judging whether the current train position enters a preset track section, and if so, acquiring corresponding image data;
performing color conversion on the image data according to the color conversion parameters to obtain second image data;
based on the signal lamp area, performing image segmentation on the second image data to obtain image data corresponding to the signal lamp area and marking the image data as signal lamp image data;
according to the regional color, carrying out color boundary tracking and contour extraction on signal lamp image data to obtain one or more signal lamp contour regions;
taking a signal lamp outline area with the area larger than a preset threshold value as an identification area, wherein one or more identification areas are provided;
Carrying out color average calculation on the image corresponding to the identification area to obtain average color chroma, and carrying out similarity calculation analysis on the average color chroma and a preset signal lamp color standard;
if the similarity is larger than a preset threshold value, acquiring a corresponding color identification result according to a preset signal lamp color standard, and acquiring signal lamp identification information according to the color identification result;
and generating signal early warning information in real time based on the signal lamp identification information.
8. A signal lamp early warning system based on image processing is characterized in that the system comprises: the system comprises a memory and a processor, wherein the memory comprises a signal lamp early warning program based on image processing, and the signal lamp early warning program based on the image processing realizes the following steps when being executed by the processor:
acquiring video data;
dynamic adjustment based on contrast and brightness is carried out according to video data;
performing image extraction and image preprocessing according to the video data, and performing color conversion adjustment through color difference analysis to obtain corresponding image data;
performing signal lamp color recognition analysis on the image data, obtaining a recognition result, and generating signal lamp early warning information based on the recognition result;
and sending the signal lamp early warning information to preset terminal equipment for display.
9. The signal lamp warning system based on image processing of claim 8, wherein the dynamic adjustment based on contrast and brightness is performed according to video data, further comprising:
acquiring historical video data of a train;
intercepting target video data of the tunnel section from the historical video data;
dividing target video data according to the front, middle and rear three sections of the driving tunnel, and carrying out key image frame extraction and image noise reduction processing on the divided video data to obtain image data before the tunnel, image data in the tunnel and image data after the tunnel.
10. The signal lamp warning system based on image processing of claim 8, wherein the dynamic adjustment based on contrast and brightness is performed according to video data, further comprising:
carrying out object recognition based on color characteristics on the image data before the tunnel to obtain contour information and color characteristic information of a plurality of objects;
according to the contour information and the color characteristic information of the object, calculating and analyzing the contour area and the color richness to obtain the contour area and the color richness of the corresponding object;
if the contour area is larger than the preset area and the color richness is larger than the preset richness, marking the corresponding object as a marker, and integrating the corresponding contour information and the color characteristic information to obtain the image characteristics of the marker.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310431016.7A CN116152784B (en) | 2023-04-21 | 2023-04-21 | Signal lamp early warning method and system based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310431016.7A CN116152784B (en) | 2023-04-21 | 2023-04-21 | Signal lamp early warning method and system based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116152784A true CN116152784A (en) | 2023-05-23 |
| CN116152784B CN116152784B (en) | 2023-07-07 |
Family
ID=86339265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310431016.7A Active CN116152784B (en) | 2023-04-21 | 2023-04-21 | Signal lamp early warning method and system based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116152784B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955705A (en) * | 2014-04-29 | 2014-07-30 | 银江股份有限公司 | Traffic signal lamp positioning, recognizing and classifying method based on video analysis |
| CN105160924A (en) * | 2015-08-25 | 2015-12-16 | 公安部第三研究所 | Video processing-based intelligent signal lamp state detection method and detection system |
| CN106507079A (en) * | 2016-11-03 | 2017-03-15 | 浙江宇视科技有限公司 | A kind of color rendition method and device |
| CN107886034A (en) * | 2016-09-30 | 2018-04-06 | 比亚迪股份有限公司 | Driving based reminding method, device and vehicle |
| US20190087673A1 (en) * | 2017-09-15 | 2019-03-21 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and apparatus for identifying traffic light |
| CN111209775A (en) * | 2018-11-21 | 2020-05-29 | 杭州海康威视数字技术股份有限公司 | Signal lamp image processing method, device, equipment and storage medium |
| CN111582216A (en) * | 2020-05-15 | 2020-08-25 | 安徽师范大学 | Unmanned vehicle-mounted traffic signal lamp identification system and method |
| CN111723625A (en) * | 2019-03-22 | 2020-09-29 | 上海海拉电子有限公司 | Traffic light image recognition processing method and device, auxiliary traffic system and storage medium |
| CN112380973A (en) * | 2020-11-12 | 2021-02-19 | 深兰科技（上海）有限公司 | Traffic signal lamp identification method and system |
| CN113971792A (en) * | 2020-07-06 | 2022-01-25 | 长沙智能驾驶研究院有限公司 | Character recognition method, device, equipment and storage medium for traffic sign board |
| WO2022030379A1 (en) * | 2020-08-07 | 2022-02-10 | 株式会社デンソー | Traffic signal recognition device, traffic signal recognition method, and vehicle control program |
| CN115100625A (en) * | 2022-05-27 | 2022-09-23 | 北京英泰智科技股份有限公司 | Method and system for identifying state of signal lamp |
| CN115131714A (en) * | 2022-07-19 | 2022-09-30 | 衢州职业技术学院 | Intelligent detection and analysis method and system for video image |
-
2023
- 2023-04-21 CN CN202310431016.7A patent/CN116152784B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955705A (en) * | 2014-04-29 | 2014-07-30 | 银江股份有限公司 | Traffic signal lamp positioning, recognizing and classifying method based on video analysis |
| CN105160924A (en) * | 2015-08-25 | 2015-12-16 | 公安部第三研究所 | Video processing-based intelligent signal lamp state detection method and detection system |
| CN107886034A (en) * | 2016-09-30 | 2018-04-06 | 比亚迪股份有限公司 | Driving based reminding method, device and vehicle |
| CN106507079A (en) * | 2016-11-03 | 2017-03-15 | 浙江宇视科技有限公司 | A kind of color rendition method and device |
| US20190087673A1 (en) * | 2017-09-15 | 2019-03-21 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and apparatus for identifying traffic light |
| CN111209775A (en) * | 2018-11-21 | 2020-05-29 | 杭州海康威视数字技术股份有限公司 | Signal lamp image processing method, device, equipment and storage medium |
| CN111723625A (en) * | 2019-03-22 | 2020-09-29 | 上海海拉电子有限公司 | Traffic light image recognition processing method and device, auxiliary traffic system and storage medium |
| CN111582216A (en) * | 2020-05-15 | 2020-08-25 | 安徽师范大学 | Unmanned vehicle-mounted traffic signal lamp identification system and method |
| CN113971792A (en) * | 2020-07-06 | 2022-01-25 | 长沙智能驾驶研究院有限公司 | Character recognition method, device, equipment and storage medium for traffic sign board |
| WO2022030379A1 (en) * | 2020-08-07 | 2022-02-10 | 株式会社デンソー | Traffic signal recognition device, traffic signal recognition method, and vehicle control program |
| CN112380973A (en) * | 2020-11-12 | 2021-02-19 | 深兰科技（上海）有限公司 | Traffic signal lamp identification method and system |
| CN115100625A (en) * | 2022-05-27 | 2022-09-23 | 北京英泰智科技股份有限公司 | Method and system for identifying state of signal lamp |
| CN115131714A (en) * | 2022-07-19 | 2022-09-30 | 衢州职业技术学院 | Intelligent detection and analysis method and system for video image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116152784B (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113850123A (en) | Video-based road monitoring method and device, storage medium and monitoring system | |
| CN111047874B (en) | Intelligent traffic violation management method and related product | |
| CN108062554B (en) | Method and device for identifying color of vehicle annual inspection label | |
| CN111931726B (en) | Traffic light detection method, device, computer storage medium and road side equipment | |
| US20240013453A1 (en) | Image generation method and apparatus, and storage medium | |
| CN111179302B (en) | Moving target detection method and device, storage medium and terminal equipment | |
| CN112528917A (en) | Zebra crossing region identification method and device, electronic equipment and storage medium | |
| CN103020930A (en) | Nighttime monitoring video enhancing method | |
| KR100903816B1 (en) | System and human face detection system and method in an image using fuzzy color information and multi-neural network | |
| CN110782409A (en) | Method for removing shadow of multi-motion object | |
| CN104299214A (en) | Method and system for detecting and removing raindrops in light rain scene video data | |
| CN104318537A (en) | Method and system for detecting and removing raindrop in heavy rain scene video data | |
| CN115424217A (en) | AI vision-based intelligent vehicle identification method and device and electronic equipment | |
| CN115171034A (en) | Road foreign matter detection method, and method and device for detecting foreign matters in scene | |
| CN115187954A (en) | Image processing-based traffic sign identification method in special scene | |
| CN108875641B (en) | Long-term parallel driving identification method and system for expressway | |
| Lashkov et al. | Edge-computing-facilitated nighttime vehicle detection investigations with CLAHE-enhanced images | |
| CN116152784B (en) | Signal lamp early warning method and system based on image processing | |
| CN107066929B (en) | Hierarchical recognition method for parking events of expressway tunnel integrating multiple characteristics | |
| CN112863194A (en) | Image processing method, device, terminal and medium | |
| CN109800693B (en) | Night vehicle detection method based on color channel mixing characteristics | |
| CN110688979A (en) | Illegal vehicle tracking method and device | |
| CN111192275A (en) | Highway fog visibility identification method based on dark channel prior theory | |
| CN110619335A (en) | License plate positioning and character segmentation method | |
| CN115797880A (en) | Method and device for determining driving behavior, storage medium and electronic device |
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 |