CN108346313B - Empty parking space detection method and system - Google Patents

Empty parking space detection method and system Download PDF

Info

Publication number
CN108346313B
CN108346313B CN201810354283.8A CN201810354283A CN108346313B CN 108346313 B CN108346313 B CN 108346313B CN 201810354283 A CN201810354283 A CN 201810354283A CN 108346313 B CN108346313 B CN 108346313B
Authority
CN
China
Prior art keywords
parking space
area
empty
image
parking
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
Application number
CN201810354283.8A
Other languages
Chinese (zh)
Other versions
CN108346313A (en
Inventor
袭肖明
于治楼
陈祥
杜亨方
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inspur Group Co Ltd
Original Assignee
Inspur Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Inspur Group Co Ltd filed Critical Inspur Group Co Ltd
Priority to CN201810354283.8A priority Critical patent/CN108346313B/en
Publication of CN108346313A publication Critical patent/CN108346313A/en
Application granted granted Critical
Publication of CN108346313B publication Critical patent/CN108346313B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
    • G08G1/146—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is a limited parking space, e.g. parking garage, restricted space
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image

Abstract

The invention discloses a method and a system for detecting an empty parking space, which are implemented by the steps of firstly acquiring a parking lot image through a camera; then processing and dividing the whole image, and dividing each parking space into a communication area; starting from the parking space in the first communication area, judging whether the parking space is an empty parking space or not and calculating the information of the area included in the empty parking space; calculating an adjacent connected region of the first connected region, acquiring information including the area of the adjacent connected region, and judging whether the parking space is an empty parking space by taking a difference value with the area of the first connected region; and (5) iteratively judging all the connected regions and outputting a judgment result. Compared with the prior art, the method and the system for detecting the empty parking space are simple and easy to implement, and can accurately find the empty parking space in real time. Therefore, the problem of difficulty in parking in public places is effectively solved, and the parking device has wide application prospect, strong practicability and wide application range.

Description

Empty parking space detection method and system
Technical Field
The invention relates to the technical field of parking space detection, in particular to an empty parking space detection method and system.
Background
With the continuous development of scientific and technical economy, the living standard of people is continuously improved, and the number of motor vehicles is also increased year by year, so that the serious parking problem is generated, the most serious problem is the parking difficulty, and therefore, the intelligent parking is the future parking development trend. Most of the existing intelligent parking is an underground parking lot and is realized by installing a large number of geomagnetic induction devices. However, installation of a large number of ground thorn sensing devices is high and is not easy to implement for a ground parking lot.
Therefore, how to use lower cost to finish the detection of the empty parking space of the ground parking lot has important significance for reducing the cost of enterprises and enhancing the competitiveness of products. In order to solve the problem, the patent provides an empty parking space detection method and system.
Disclosure of Invention
The technical task of the invention is to provide a method and a system for detecting an empty parking space aiming at the defects.
A method for detecting an empty parking space comprises the following steps,
firstly, acquiring a parking lot image through a camera;
secondly, processing and dividing the whole image, and dividing each parking space into a communication area;
step three, starting from the parking space in the first communication area, judging whether the parking space is an empty parking space or not and calculating the information of the area included in the empty parking space;
step four, calculating an adjacent communication area of the first communication area, acquiring information of the area included by the adjacent communication area, and judging whether the parking space is an empty parking space or not by taking a difference value with the area of the first communication area;
and step five, iteratively judging all the connected areas and outputting a judgment result.
The image segmentation process in the second step comprises the following steps:
1) firstly, graying an image;
2) and then carrying out connected region segmentation, namely drawing out vivid colors according to the gray level image.
The image graying in the step 1) is to gray the RGB image collected by the camera so that the original image is changed into a single-channel grayscale image from a three-channel grayscale image.
The dividing of the connected region in the step 2) refers to: firstly, setting a threshold value T for the color of the parking space boundary, then segmenting the whole image, and obtaining the segmented connected area as the parking space.
The judgment process of the first connected region in the third step is as follows:
firstly, determining the area S of a parking space and simultaneously determining an error interval of the parking space;
then the first left stall C is selected0Determining the actual area S0Then the actual area S0And subtracting the area S, wherein if the difference value is within the error interval, the parking space is an empty parking space, and if the difference value exceeds the error interval, the parking space is parked.
The judgment process of the adjacent connected areas in the fourth step is as follows:
firstly, determining the distance d between the central points of two adjacent parking spaces, simultaneously determining the error interval of the two adjacent parking spaces, and simultaneously determining the threshold value (0, T) of the area differences】；
Determining the first parking space C0Adjacent connected region, as parking space CiCenter and parking space C0When the center distance of the parking space C is within the d +/-error intervaliIs a parking space C0The nearest communication area, namely the adjacent parking spaces;
determining parking space CiArea S ofiWill area S0And area SiSubtract, when parking space C0When the parking space is empty, the area difference value is close to 0, the parking space is empty, otherwise, the parking space is non-empty; as parking space C0When the parking space is not empty, the area difference value is close to the threshold value TsAnd if not, the parking space is a non-empty parking space.
An empty parking space detection system comprises a parking space detection device,
the image acquisition module is used for acquiring a parking lot image;
the image preprocessing module is used for carrying out segmentation preprocessing on the acquired image so as to divide each parking space into a communication area;
the calculation comparison module is used for analyzing and judging whether the divided connected area is an empty parking space;
and the output module is used for outputting the judgment result of the calculation comparison module.
The image acquisition module acquires parking lot images through the network camera and transmits the acquired images to the image preprocessing module through a network.
The image preprocessing module carries out segmentation preprocessing on the image, and the segmentation preprocessing process comprises the following steps:
firstly, graying an image, namely graying an RGB image collected by a camera to change an original image from a three-channel grayscale image into a single-channel grayscale image;
and then, carrying out connected region segmentation, namely, drawing out bright colors according to the gray level image, setting a threshold value T for the color of the parking space boundary, and then segmenting the whole image, wherein the segmented connected region is the parking space.
The calculation and comparison module analyzes whether the divided communicated area is an empty parking space or not, namely, whether one parking space is an empty parking space or not is determined at first, then the adjacent parking space is compared with the adjacent parking space to obtain whether the adjacent parking space is an empty parking space or not, and finally, the sequence iteration is carried out until all the parking spaces are analyzed completely, and then the result is output through the output module.
The process that the calculation comparison module determines whether a parking space is an empty parking space is as follows:
firstly, determining the area S of a parking space and simultaneously determining an error interval of the parking space;
then selects the first parking space C0Determining the actual area S0Then the actual area S0And subtracting the area S, wherein if the difference value is within the error interval, the parking space is an empty parking space, and if the difference value exceeds the error interval, the parking space is parked.
The process that whether the adjacent parking spaces are determined to be empty by the calculation and comparison module is as follows:
firstly, determining the distance d between the central points of two adjacent parking spaces, simultaneously determining the error interval of the two adjacent parking spaces, and simultaneously determining the threshold value (0, T) of the area differences】；
Determining the first parking space C0Adjacent connected region, as parking space CiCenter and parking space C0When the center distance of the parking space C is within the d +/-error intervaliIs a parking space C0The nearest communication area, namely the adjacent parking spaces;
determining parking space CiArea S ofiWill area S0And area SiSubtract, when parking space C0When the parking space is empty, the area difference value is close to 0, the parking space is empty, otherwise, the parking space is non-empty; as parking space C0When the parking space is not empty, the area difference value is close to the threshold value TsAnd if not, the parking space is a non-empty parking space.
Compared with the prior art, the empty parking space detection method and the system have the following beneficial effects:
the invention relates to an empty parking space detection method and system, which are characterized in that firstly, a whole image is divided into a plurality of connected areas by using a threshold value method, then the connected areas meeting conditions are sequentially searched and used as empty parking spaces. Therefore, the problem of difficulty in parking in public places is effectively solved, and the parking device has wide application prospect, strong practicability and wide application range.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is an example gray scale map of an actual parking space.
Fig. 2 is an example segmentation of an actual parking space.
Fig. 3 is an exemplary diagram of the system implementation of the present invention.
Detailed Description
The present invention will be described in further detail with reference to specific embodiments in order to make the technical field better understand the scheme of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. 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.
A method for detecting an empty parking space comprises the steps of shooting images of a parking lot by a small number of cameras. In consideration of the fact that most of the existing parking spaces are depicted in a relatively clear color (e.g., white), the image is segmented by a threshold method. And finding a plurality of connected regions through the segmentation result. In the present invention, each parking space can be regarded as a connected region. The first parking space is found, information such as the area of a neighbor communication area of the first parking space is obtained by a neighbor statistical method, and the first parking space is iteratively judged to be empty or an existing vehicle.
The main idea of the invention is to regard each parking space as a communication area and to detect empty parking spaces by continuously searching for morphological similarity of adjacent communication areas.
The image is grayed first. Because most of the images acquired by the existing camera are RGB images, in order to reduce the calculation complexity, the invention grays the 3-channel RGB images into single-channel grayscale images, as shown in FIG. 1.
And dividing the connected region. Considering that the boundaries of parking spaces in a parking lot are all delineated by distinct colors (e.g., white, yellow, etc.), the threshold T is set based on the color of the parking space boundary, and the entire image is divided, so that the parking spaces can be divided as shown in fig. 2.
In the above steps, if a car is parked in some parking spaces, the area of the communication area obtained by the parking space is very small (shown in fig. 2), and the area difference between the empty parking space and the parking space parked in the car is relatively large. Therefore, a threshold value based on the area difference is set in this step to determine the empty space.
The specific implementation process is as follows,
firstly, acquiring a parking lot image through a camera;
secondly, processing and dividing the whole image, and dividing each parking space into a communication area;
step three, starting from the parking space in the first communication area, judging whether the parking space is an empty parking space or not and calculating the information of the area included in the empty parking space;
step four, calculating an adjacent communication area of the first communication area, acquiring information of the area included by the adjacent communication area, and judging whether the parking space is an empty parking space or not by taking a difference value with the area of the first communication area;
and step five, iteratively judging all the connected areas and outputting a judgment result.
The image segmentation process in the second step comprises the following steps:
1) firstly, graying an image;
2) and then carrying out connected region segmentation, namely drawing out vivid colors according to the gray level image.
The image graying in the step 1) is to gray the RGB image collected by the camera so that the original image is changed into a single-channel grayscale image from a three-channel grayscale image.
The dividing of the connected region in the step 2) refers to: firstly, setting a threshold value T for the color of the parking space boundary, then segmenting the whole image, and obtaining the segmented connected area as the parking space.
The judgment process of the first connected region in the third step is as follows:
firstly, determining the area S of a parking space and simultaneously determining an error interval of the parking space;
then the first left stall C is selected0Determining the actual area S0Then the actual area S0And subtracting the area S, wherein if the difference value is within the error interval, the parking space is an empty parking space, and if the difference value exceeds the error interval, the parking space is parked.
The judgment process of the adjacent connected areas in the fourth step is as follows:
firstly, determining the distance d between the central points of two adjacent parking spaces, simultaneously determining the error interval of the two adjacent parking spaces, and simultaneously determining the threshold value (0, T) of the area differences】；
Determining the first parking space C0Adjacent connected region, as parking space CiCenter and parking space C0When the center distance of the parking space C is within the d +/-error intervaliIs a parking space C0The nearest communication area, namely the adjacent parking spaces;
determining parking space CiArea S ofiWill area S0And area SiSubtract, when parking space C0When the parking space is empty, the area difference value is close to 0, the parking space is empty, otherwise, the parking space is non-empty; as parking space C0When the parking space is not empty, the area difference value is close to the threshold value TsThen, the parking space is empty, otherwise, the parking space is not empty。
As shown in fig. 3, an empty space detecting system includes,
the image acquisition module is used for acquiring a parking lot image;
the image preprocessing module is used for carrying out segmentation preprocessing on the acquired image so as to divide each parking space into a communication area;
the calculation comparison module is used for analyzing and judging whether the divided connected area is an empty parking space;
and the output module is used for outputting the judgment result of the calculation comparison module.
The image acquisition module acquires parking lot images through the network camera and transmits the acquired images to the image preprocessing module through a network.
The image preprocessing module carries out segmentation preprocessing on the image, and the segmentation preprocessing process comprises the following steps:
firstly, graying an image, namely graying an RGB image collected by a camera to change an original image from a three-channel grayscale image into a single-channel grayscale image;
and then, carrying out connected region segmentation, namely, drawing out bright colors according to the gray level image, setting a threshold value T for the color of the parking space boundary, and then segmenting the whole image, wherein the segmented connected region is the parking space.
The calculation and comparison module analyzes whether the divided communicated area is an empty parking space or not, namely, whether one parking space is an empty parking space or not is determined at first, then the adjacent parking space is compared with the adjacent parking space to obtain whether the adjacent parking space is an empty parking space or not, and finally, the sequence iteration is carried out until all the parking spaces are analyzed completely, and then the result is output through the output module.
The process that the calculation comparison module determines whether a parking space is an empty parking space is as follows:
firstly, determining the area S of a parking space and simultaneously determining an error interval of the parking space;
then selects the first parking space C0Determining the actual area S0Then the actual area S0Subtracting the area S, if the difference value is within the error interval, the parking space is an empty parking space, and if the difference value exceeds the error intervalAnd if the error interval is within the error interval, the parking space is already parked.
The process that whether the adjacent parking spaces are determined to be empty by the calculation and comparison module is as follows:
firstly, determining the distance d between the central points of two adjacent parking spaces, simultaneously determining the error interval of the two adjacent parking spaces, and simultaneously determining the threshold value (0, T) of the area differences】；
Determining the first parking space C0Adjacent connected region, as parking space CiCenter and parking space C0When the center distance of the parking space C is within the d +/-error intervaliIs a parking space C0The nearest communication area, namely the adjacent parking spaces;
determining parking space CiArea S ofiWill area S0And area SiSubtract, when parking space C0When the parking space is empty, the area difference value is close to 0, the parking space is empty, otherwise, the parking space is non-empty; as parking space C0When the parking space is not empty, the area difference value is close to the threshold value TsAnd if not, the parking space is a non-empty parking space.
The present invention can be easily implemented by those skilled in the art from the above detailed description. It should be understood, however, that the intention is not to limit the invention to the particular embodiments described. On the basis of the disclosed embodiments, a person skilled in the art can combine different technical features at will, thereby implementing different technical solutions.
In addition to the technical features described in the specification, the technology is known to those skilled in the art.

Claims (6)

1. A method for detecting an empty parking space is characterized by comprising the following steps of,
firstly, acquiring a parking lot image through a camera;
secondly, processing and dividing the whole image, and dividing each parking space into a communication area;
step three, starting from the parking space in the first communication area, judging whether the parking space is an empty parking space or not and calculating the information of the area included in the empty parking space;
step four, calculating an adjacent communication area of the first communication area, acquiring information of the area included by the adjacent communication area, and judging whether the parking space is an empty parking space or not by taking a difference value with the area of the first communication area;
step five, iteratively judging all connected regions, and outputting a judgment result;
the judgment process of the first connected region in the third step is as follows:
firstly, determining the area S of a parking space and simultaneously determining an error interval of the parking space;
then the first left stall C is selected0Determining the actual area S0Then the actual area S0Subtracting the area S, if the difference value is within the error interval, the parking space is an empty parking space, and if the difference value exceeds the error interval, the parking space is parked;
the judgment process of the adjacent connected areas in the fourth step is as follows:
firstly, determining the distance d between the central points of two adjacent parking spaces, simultaneously determining the error interval of the two adjacent parking spaces, and simultaneously determining the threshold value (0, T) of the area differences】；
Determining the first parking space C0Adjacent connected region, as parking space CiCenter and parking space C0When the center distance of the parking space C is within the d +/-error intervaliIs a parking space C0The nearest communication area, namely the adjacent parking spaces;
determining parking space CiArea S ofiWill area S0And area SiSubtract, when parking space C0When the parking space is empty, the area difference value is close to 0, the parking space is empty, otherwise, the parking space is non-empty; as parking space C0When the parking space is not empty, the area difference value is close to the threshold value TsAnd if not, the parking space is a non-empty parking space.
2. The empty space detection method according to claim 1, wherein the image segmentation process in the second step is as follows:
1) firstly, graying an image;
2) and then carrying out connected region segmentation, namely drawing out vivid colors according to the gray level image.
3. The empty parking space detection method according to claim 2, wherein the graying of the image in the step 1) is to gray the RGB image collected by the camera so that the original image is changed from a three-channel grayscale image to a single-channel grayscale image.
4. The empty space detection method according to claim 2, wherein the communication area division in step 2) is: firstly, setting a threshold value T for the color of the parking space boundary, then segmenting the whole image, and obtaining the segmented connected area as the parking space.
5. An empty parking space detection system is characterized by comprising,
the image acquisition module is used for acquiring a parking lot image;
the image preprocessing module is used for carrying out segmentation preprocessing on the acquired image so as to divide each parking space into a communication area;
the calculation comparison module is used for analyzing and judging whether the divided connected area is an empty parking space;
the output module is used for outputting the judgment result of the calculation comparison module;
the calculation and comparison module analyzes whether the divided communication area is an empty parking space or not, namely, firstly, whether one parking space is an empty parking space or not is determined, then, adjacent parking spaces are compared with the empty parking spaces to obtain whether the adjacent parking spaces are the empty parking spaces or not, finally, the sequence iteration is carried out until all the parking spaces are analyzed, and then, the result is output through the output module;
the process that the calculation comparison module determines whether a parking space is an empty parking space is as follows:
firstly, determining the area S of a parking space and simultaneously determining an error interval of the parking space;
then selects the first parking space C0Determining the actual area S0Then the actual area S0Subtracting the area S, if the difference value is within the error interval, the parking space is an empty parking space, and if the difference value exceeds the error interval, the parking space is parked;
the process that whether the adjacent parking spaces are determined to be empty by the calculation and comparison module is as follows:
firstly, determining the distance d between the central points of two adjacent parking spaces, simultaneously determining the error interval of the two adjacent parking spaces, and simultaneously determining the threshold value (0, T) of the area differences】；
Determining the first parking space C0Adjacent connected region, as parking space CiCenter and parking space C0When the center distance of the parking space C is within the d +/-error intervaliIs a parking space C0The nearest communication area, namely the adjacent parking spaces;
determining parking space CiArea S ofiWill area S0And area SiSubtract, when parking space C0When the parking space is empty, the area difference value is close to 0, the parking space is empty, otherwise, the parking space is non-empty; as parking space C0When the parking space is not empty, the area difference value is close to the threshold value TsAnd if not, the parking space is a non-empty parking space.
6. The empty parking space detection system according to claim 5, wherein the image acquisition module acquires images of a parking lot through a network camera and transmits the acquired images to the image preprocessing module through a network;
the image preprocessing module carries out segmentation preprocessing on the image, and the segmentation preprocessing process comprises the following steps:
firstly, graying an image, namely graying an RGB image collected by a camera to change an original image from a three-channel grayscale image into a single-channel grayscale image;
and then, carrying out connected region segmentation, namely, drawing out bright colors according to the gray level image, setting a threshold value T for the color of the parking space boundary, and then segmenting the whole image, wherein the segmented connected region is the parking space.
CN201810354283.8A 2018-04-19 2018-04-19 Empty parking space detection method and system Active CN108346313B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810354283.8A CN108346313B (en) 2018-04-19 2018-04-19 Empty parking space detection method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810354283.8A CN108346313B (en) 2018-04-19 2018-04-19 Empty parking space detection method and system

Publications (2)

Publication Number Publication Date
CN108346313A CN108346313A (en) 2018-07-31
CN108346313B true CN108346313B (en) 2020-10-09

Family

ID=62955000

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810354283.8A Active CN108346313B (en) 2018-04-19 2018-04-19 Empty parking space detection method and system

Country Status (1)

Country Link
CN (1) CN108346313B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111832454A (en) * 2020-06-30 2020-10-27 苏州罗伯特木牛流马物流技术有限公司 System and method for realizing ground goods space management by using industrial camera visual identification
CN115762234B (en) * 2023-01-10 2023-06-20 广东广宇科技发展有限公司 Smart community parking management method

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001126192A (en) * 1999-10-28 2001-05-11 Mitsubishi Heavy Ind Ltd Method for judging parked or vacancy state in parking space of parking lot
CN100449579C (en) * 2006-04-21 2009-01-07 浙江工业大学 All-round computer vision-based electronic parking guidance system
CN104112370B (en) * 2014-07-30 2016-08-17 哈尔滨工业大学深圳研究生院 Parking lot based on monitoring image intelligent car position recognition methods and system
MY188579A (en) * 2015-10-22 2021-12-22 Nissan Motor Parking space line detection method and device
CN107133591B (en) * 2017-05-05 2020-07-21 深圳前海华夏智信数据科技有限公司 Parking space detection method and device based on structured light
CN107610506A (en) * 2017-09-04 2018-01-19 浙江工商大学 The detection method and system of parking position state
CN108022431A (en) * 2017-12-04 2018-05-11 珠海横琴小可乐信息技术有限公司 A kind of method and system that parking stall is detected by video capture image

Also Published As

Publication number Publication date
CN108346313A (en) 2018-07-31

Similar Documents

Publication Publication Date Title
CN103077384B (en) A kind of method and system of vehicle-logo location identification
CN103605953B (en) Vehicle interest target detection method based on sliding window search
US9672434B2 (en) Video-based system and method for parking occupancy detection
EP3036714B1 (en) Unstructured road boundary detection
CN106128121B (en) Vehicle queue length fast algorithm of detecting based on Local Features Analysis
CN105160691A (en) Color histogram based vehicle body color identification method
CN108647664B (en) Lane line detection method based on look-around image
CN110175556B (en) Remote sensing image cloud detection method based on Sobel operator
CN109711379B (en) Complex environment traffic signal lamp candidate area extraction and identification method
CN102542244A (en) Face detection method and system and computer program product
CN104517095A (en) Head division method based on depth image
US11941878B2 (en) Automated computer system and method of road network extraction from remote sensing images using vehicle motion detection to seed spectral classification
CN108346313B (en) Empty parking space detection method and system
CN106815587A (en) Image processing method and device
CN111274964B (en) Detection method for analyzing water surface pollutants based on visual saliency of unmanned aerial vehicle
CN111915583A (en) Vehicle and pedestrian detection method based on vehicle-mounted thermal infrared imager in complex scene
Cheng et al. Image segmentation technology and its application in digital image processing
CN104217440A (en) Method for extracting built-up area from remote sensing image
CN108268866B (en) Vehicle detection method and system
CN116596428B (en) Rural logistics intelligent distribution system based on unmanned aerial vehicle
CN104463896A (en) Image corner point detection method and system based on kernel similar region distribution characteristics
CN112528994A (en) Free-angle license plate detection method, license plate identification method and identification system
CN115311241B (en) Underground coal mine pedestrian detection method based on image fusion and feature enhancement
TW201419168A (en) A method and system for license plate recognition under non-uniform illumination
Shao et al. 3D crowd surveillance and analysis using laser range scanners

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20200909

Address after: 250100 Ji'nan high tech Zone, Shandong, No. 1036 wave road

Applicant after: INSPUR GROUP Co.,Ltd.

Address before: 250100, Ji'nan province high tech Zone, Sun Village Branch Road, No. 2877, building, floor, building, on the first floor

Applicant before: JINAN INSPUR HI-TECH INVESTMENT AND DEVELOPMENT Co.,Ltd.

GR01 Patent grant
GR01 Patent grant