CN113781418A - Subway image anomaly detection method and system based on comparison and storage medium - Google Patents
Subway image anomaly detection method and system based on comparison and storage medium Download PDFInfo
- Publication number
- CN113781418A CN113781418A CN202111006454.6A CN202111006454A CN113781418A CN 113781418 A CN113781418 A CN 113781418A CN 202111006454 A CN202111006454 A CN 202111006454A CN 113781418 A CN113781418 A CN 113781418A
- Authority
- CN
- China
- Prior art keywords
- image
- current
- running vehicle
- vehicle
- template
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 48
- 230000002159 abnormal effect Effects 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000005457 optimization Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000008447 perception Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 16
- 238000010586 diagram Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a subway image anomaly detection method and system based on comparison and a storage medium. The method comprises the following steps: acquiring a current running vehicle image through a line scanning camera group; acquiring vehicle identification information through a current running vehicle image, and extracting a template picture corresponding to the current running vehicle based on the vehicle identification information; respectively detecting the characteristic points of the current running vehicle image and the template image, extracting the characteristic points of the current image and the characteristic points of the template image for matching, and aligning the current running vehicle image and the template image according to the position characteristics of the matched characteristic point pairs; and respectively extracting the contrast difference characteristic of each area by traversing the aligned current running vehicle image and template image through the contrast slide block, judging that the current area is abnormal when the contrast difference characteristic value is greater than a preset threshold value, and otherwise, judging that the current area is normal. The method and the device can realize the current subway image abnormity detection, so that the machine inspection is used for replacing the human inspection, the vehicle inspection efficiency is improved, and the labor cost is saved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a subway image anomaly detection method and system based on comparison and a storage medium.
Background
In recent years, the rapid development of urban rail transit is the most important component of urban traffic, and subways are more important in urban rail transit. In the long-term operation of the metro vehicle, the conditions of deformation, aging, abrasion or overhigh operation temperature and the like may occur to each part of the metro vehicle, and in order to ensure the safe running of the metro vehicle, a large number of operation and maintenance personnel are required to be configured to perform the train inspection operation every day.
However, the manual column inspection has the following problems:
1. the subway night warehouse-returning inspection vehicle consumes long time and has low efficiency
2. Has high requirements on the professional skills and the quality of the maintainers
3. Large personnel demand and high labor cost
4. The condition of missing detection is easy to occur due to visual fatigue and carelessness in manual operation.
The low-efficiency manual inspection mode seriously restricts the further development of the rail transit industry in China.
Disclosure of Invention
According to the technical problems of high intensity, high cost, low efficiency, poor real-time performance, high potential safety hazard and the like of manual inspection operation, the subway image anomaly detection method and system based on comparison and the storage medium are provided. The invention detects the abnormality of the current subway vehicle in a non-stop way through machine inspection, replaces human inspection with machine inspection, reduces the labor cost, greatly shortens the time for inspecting the subway and protects the driving for the safe running of the subway.
The technical means adopted by the invention are as follows:
the invention provides a subway image abnormity detection method based on comparison, which comprises the following steps:
acquiring a current running vehicle image through a line scanning camera set, wherein a line scanning camera in the line scanning camera set is set to be a shooting range covering any position of a vehicle body;
acquiring vehicle identification information through a current running vehicle image, and extracting a template picture corresponding to the current running vehicle based on the vehicle identification information;
respectively detecting the characteristic points of the current running vehicle image and the template image, extracting the characteristic points of the current image and the characteristic points of the template image for matching, and aligning the current running vehicle image and the template image according to the position characteristics of the matched characteristic point pairs;
and respectively extracting the contrast difference characteristic of each area by traversing the aligned current running vehicle image and template image through the contrast slide block, judging that the current area is abnormal when the contrast difference characteristic value is greater than a preset threshold value, and otherwise, judging that the current area is normal.
Further, acquiring vehicle identification information through a current running vehicle image, and extracting a template map corresponding to the current running vehicle based on the vehicle identification information, including:
recognizing a vehicle body and vehicle number character from a current running vehicle image based on a trained YOLO _ V3 target detection model, and integrating according to the sequence of front and rear positions of the recognized character to obtain a subway vehicle number, wherein the subway vehicle number corresponds to a unique subway vehicle;
and searching the previous vehicle passing time period of the metro vehicle corresponding to the subway number by the database according to the subway number, and taking the running vehicle image acquired by the linear scanning camera group in the time period as a template map.
Further, the feature point detection is respectively performed on the current running vehicle image and the template image, and the feature point detection comprises the following steps: and carrying out feature point detection on the current running vehicle image and the template image based on a Surf feature point detection algorithm in the OPENCV.
Further, extracting the current image feature points and the template image feature points for pairing comprises:
matching the current image characteristic points and the template image characteristic points by adopting a region K neighbor optimization matching algorithm;
sequencing the matched feature points in sequence from small to large according to the X coordinate position sequence;
dividing the feature points into a plurality of continuous areas according to image intervals, and screening the best feature points from each interval as representative feature points of the interval;
and eliminating potential abnormal points according to the distance relation of the interval representative characteristic points to obtain a final pairing result.
Further, the alignment of the image of the current running vehicle and the template image is realized according to the position characteristics of the matched characteristic point pairs, and the method comprises the following steps:
determining the overlapping area of the current detection image and the template image content according to the obtained matched characteristic point pairs;
and (4) carrying out remapping and splicing on the overlapped area image segments to ensure that the size of the overlapped area of the current detection image is completely consistent with that of the overlapped area of the template image.
Further, the step of respectively extracting the contrast difference characteristics of each region by comparing the current running vehicle image and the template image after the slider traversal alignment comprises the following steps:
respectively extracting a direction gradient histogram difference value and a perceptual hash difference value of each comparison area;
and carrying out weighted summation on the direction gradient histogram difference value and the perception hash difference value so as to obtain a contrast difference characteristic value of each area.
Further, performing weighted summation on the histogram of oriented gradients difference value and the perceptual hash difference value, including:
the histogram feature coefficient is set to 0.75 and the perceptual hash feature coefficient is set to 0.25.
The invention also provides a subway image abnormity detection system based on comparison, which comprises:
the system comprises a current image acquisition module, a line scan camera group and a control module, wherein the current image acquisition module is used for acquiring a current running vehicle image through the line scan camera group, and a line scan camera in the line scan camera group is set to be a shooting range covering any position of a vehicle body;
the template image acquisition module is used for acquiring vehicle identification information through a current running vehicle image and extracting a template image corresponding to the current running vehicle based on the vehicle identification information;
the image alignment module is used for respectively detecting the characteristic points of the current running vehicle image and the template image, extracting the characteristic points of the current image and the characteristic points of the template image for matching, and aligning the current running vehicle image and the template image according to the position characteristics of the matched characteristic point pairs;
and the image comparison module is used for respectively extracting the comparison difference characteristic of each area by comparing the current running vehicle image and the template image after the sliding block traversal alignment, judging that the current area is abnormal when the comparison difference characteristic value is greater than a preset threshold value, and otherwise, judging that the current area is normal.
The invention also provides a storage medium comprising a stored program, wherein the program when executed performs any of the methods described above.
Compared with the prior art, the invention has the following advantages:
the invention obtains a complete 24-bit true color image of each carriage of the subway vehicle in a non-stop mode through a line scanning camera, then respectively finds out a last-time passing template picture corresponding to the complete 24-bit true color image through vehicle number identification, respectively aligns the detection picture and the template picture through a characteristic matching mode, finally judges whether each sliding block area is abnormal or not through a sliding block comparison mode, and further judges whether the current vehicle is abnormal or not. The invention replaces human inspection with machine inspection, reduces labor cost, greatly shortens vehicle inspection time, and protects driving for safe driving of subways.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a subway image anomaly detection method based on comparison in an embodiment of the present invention.
FIG. 2 is a schematic diagram of the arrangement positions of the line scan cameras according to the embodiment of the present invention.
Fig. 3 is a schematic diagram of the number of the body of the land car extracted in the embodiment of the invention.
FIG. 4a is a diagram illustrating a template image before alignment according to an embodiment of the present invention.
FIG. 4b is a schematic view of an image of a currently running vehicle before alignment in an embodiment of the present invention.
Fig. 5a is a schematic diagram of aligned template images according to an embodiment of the present invention.
FIG. 5b is a schematic view of an aligned image of a currently operating vehicle according to an embodiment of the present invention.
FIG. 6a is a schematic diagram of a template image for comparison in an embodiment of the present invention.
FIG. 6b is a schematic view of a comparison of images of a currently operating vehicle according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
As shown in fig. 1, an embodiment of the present invention provides a subway image anomaly detection method based on comparison, which mainly includes:
and S1, acquiring the current running vehicle image through a line scanning camera set, wherein the line scanning camera in the line scanning camera set is set to be in a shooting range covering any position of the vehicle body.
And S2, acquiring vehicle identification information through the current running vehicle image, and extracting the template picture corresponding to the current running vehicle based on the vehicle identification information.
Specifically, the method is based on a trained YOLO _ V3 target detection model, a vehicle body and vehicle number character is recognized by a current running vehicle image, a subway vehicle number is obtained through sequential integration according to the front position and the rear position of the recognized character, then a database is used for searching a previous running time period of a subway vehicle corresponding to the vehicle number according to the subway vehicle number, and the running vehicle image obtained by a linear scanning camera set in the time period is used as a template image. Wherein the subway car number corresponds to a unique subway car.
And S3, respectively carrying out feature point detection on the current running vehicle image and the template image, extracting the feature points of the current image and the feature points of the template image for matching, and aligning the current running vehicle image and the template image according to the position features of the matched feature point pairs.
Specifically, feature point detection is carried out on the current running vehicle image and the template image based on a Surf feature point detection algorithm in OPENCV. Then, matching the current image feature points with the template image feature points by adopting a region K nearest neighbor optimization matching algorithm; sequencing the matched feature points in sequence from small to large according to the X coordinate position sequence; dividing the feature points into a plurality of continuous areas according to image intervals, and screening the best feature points from each interval as representative feature points of the interval; and eliminating potential abnormal points according to the distance relation of the interval representative characteristic points to obtain a final pairing result. Finally, determining the overlapping area of the current detection image and the template image content according to the obtained matched characteristic point pairs; and (4) carrying out remapping and splicing on the overlapped area image segments, so that the size of the overlapped area of the current detection image is completely consistent with that of the overlapped area of the template image, and realizing the alignment of the current detection image and the template image.
And S4, respectively extracting the contrast difference characteristic of each area by traversing the aligned current running vehicle image and template image through the contrast slider, judging that the current area is abnormal when the contrast difference characteristic value is greater than a preset threshold value, and otherwise, judging that the current area is normal.
Specifically, a difference value of a histogram of oriented gradients and a perceptual hash difference value of each comparison area are respectively extracted; and carrying out weighted summation on the direction gradient histogram difference value and the perception hash difference value so as to obtain a contrast difference characteristic value of each area.
The solution according to the invention is further illustrated by the following specific application examples.
As shown in the attached drawing 2, a plurality of line scanning cameras are arranged on a portal frame in the embodiment, so that the plurality of line scanning cameras can cover a subway body in a 360-degree dead angle-free manner, and a detection blind area is avoided.
Further, the template drawing is searched according to the car number. The method comprises the steps of identifying subway car body number characters through an existing YOLO _ V3 target detection model, and then integrating correct subway car numbers according to the front-back position sequence of the identified characters, wherein the subway car body number is shown in the attached figure 3. And then searching the last time of passing the train from the database according to the number of the subway train recognized in the last step, taking the subway image of the time as a comparison template picture, and paying attention to that the plurality of template pictures are in one-to-one correspondence with the current detection picture according to the camera number respectively.
Further, the Surf feature point detection algorithm in OPENCV is used to extract feature points of the current detection map and the template map, respectively.
Further, a K neighbor characteristic point matching algorithm is used for preliminarily confirming the matching point pairs. And then optimizing the matching point pairs by using an AKNNOMA (AREA KNN optimizapion MATCH ALGORITHM, AREA K neighbor OPTIMIZATION matching) ALGORITHM: firstly, sequencing matched feature points of K neighbors in sequence from small to large according to the X coordinate position sequence, then dividing the feature points into a plurality of continuous areas according to an image interval, for example, 0-20 columns of pixels are used as a first interval, 20-40 columns of pixels are used as a second interval, and so on, screening the best feature points from each interval as representative feature points of the interval, and finally further optimizing according to the distance relation of the representative feature points of the interval to eliminate potential abnormal points.
Further, determining the overlapping area of the current detection image and the template image content according to the obtained matching point pairs, then performing segmented remapping and splicing on images of the overlapping area, so that the size of the overlapping area of the current detection image is completely consistent with that of the overlapping area of the template image, and preparing for image comparison. The effect is shown in fig. 4a, 4b before the current inspection image is aligned with the template image, and in fig. 5a, 5b after alignment.
Further, a slide block comparison mode is adopted: each region of the current inspection map and the template map are compared sequentially from left to right, top to bottom. And respectively extracting the directional gradient histogram feature and the perceptual hash feature of each region. Comparing the comparison features extracted from the current area of the detection graph with the comparison features of the corresponding area of the template graph, respectively calculating a direction gradient histogram difference value and a Hash feature difference value, multiplying the two calculated difference values by different coefficients to perform weighted summation, wherein the general direction histogram feature coefficient is 0.75, the perceptual Hash feature coefficient is 0.25, finally comparing the weighted value with a preset threshold, if the weighted value is greater than the preset threshold, the current area is considered to be abnormal, otherwise, the current area is considered to be normal. The result of the abnormal alarm is shown in fig. 6.
The invention also provides a subway image abnormity detection system based on comparison, which is used for executing the subway image abnormity detection method based on comparison and comprises the following steps:
the system comprises a current image acquisition module, a line scan camera group and a control module, wherein the current image acquisition module is used for acquiring a current running vehicle image through the line scan camera group, and a line scan camera in the line scan camera group is set to be a shooting range covering any position of a vehicle body;
the template image acquisition module is used for acquiring vehicle identification information through a current running vehicle image and extracting a template image corresponding to the current running vehicle based on the vehicle identification information;
the image alignment module is used for respectively detecting the characteristic points of the current running vehicle image and the template image, extracting the characteristic points of the current image and the characteristic points of the template image for matching, and aligning the current running vehicle image and the template image according to the position characteristics of the matched characteristic point pairs;
and the image comparison module is used for respectively extracting the comparison difference characteristic of each area by comparing the current running vehicle image and the template image after the sliding block traversal alignment, judging that the current area is abnormal when the comparison difference characteristic value is greater than a preset threshold value, and otherwise, judging that the current area is normal.
For the embodiments of the present invention, the description is simple because it corresponds to the above embodiments, and for the related similarities, please refer to the description in the above embodiments, and the detailed description is omitted here.
The invention also provides a storage medium which comprises a stored program, wherein when the program runs, the subway image abnormity detection method based on the comparison is executed.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A subway image anomaly detection method based on comparison is characterized by comprising the following steps:
acquiring a current running vehicle image through a line scanning camera set, wherein a line scanning camera in the line scanning camera set is set to be a shooting range covering any position of a vehicle body;
acquiring vehicle identification information through a current running vehicle image, and extracting a template picture corresponding to the current running vehicle based on the vehicle identification information;
respectively detecting the characteristic points of the current running vehicle image and the template image, extracting the characteristic points of the current image and the characteristic points of the template image for matching, and aligning the current running vehicle image and the template image according to the position characteristics of the matched characteristic point pairs;
and respectively extracting the contrast difference characteristic of each area by traversing the aligned current running vehicle image and template image through the contrast slide block, judging that the current area is abnormal when the contrast difference characteristic value is greater than a preset threshold value, and otherwise, judging that the current area is normal.
2. A contrast-based subway image anomaly detection method as claimed in claim 1, wherein obtaining vehicle identification information from a currently running vehicle image and extracting a template map corresponding to a currently running vehicle based on said vehicle identification information comprises:
recognizing a vehicle body and vehicle number character from a current running vehicle image based on a trained YOLO _ V3 target detection model, and integrating according to the sequence of front and rear positions of the recognized character to obtain a subway vehicle number, wherein the subway vehicle number corresponds to a unique subway vehicle;
and searching the previous vehicle passing time period of the metro vehicle corresponding to the subway number by the database according to the subway number, and taking the running vehicle image acquired by the linear scanning camera group in the time period as a template map.
3. A method according to claim 1, wherein the detecting of the feature points of the image of the currently running vehicle and the template image respectively comprises: and carrying out feature point detection on the current running vehicle image and the template image based on a Surf feature point detection algorithm in the OPENCV.
4. A method according to claim 1, wherein extracting the current image feature points and the template image feature points for matching comprises:
matching the current image characteristic points and the template image characteristic points by adopting a region K neighbor optimization matching algorithm;
sequencing the matched feature points in sequence from small to large according to the X coordinate position sequence;
dividing the feature points into a plurality of continuous areas according to image intervals, and screening the best feature points from each interval as representative feature points of the interval;
and eliminating potential abnormal points according to the distance relation of the interval representative characteristic points to obtain a final pairing result.
5. A contrast-based subway image anomaly detection method as claimed in claim 1, wherein said aligning the currently running vehicle image with the template image according to the position features of the matched feature point pairs comprises:
determining the overlapping area of the current detection image and the template image content according to the obtained matched characteristic point pairs;
and (4) carrying out remapping and splicing on the overlapped area image segments to ensure that the size of the overlapped area of the current detection image is completely consistent with that of the overlapped area of the template image.
6. The contrast-based subway image anomaly detection method according to claim 1, wherein the step of respectively extracting contrast difference features of each region by traversing the aligned current running vehicle image and template image through a contrast slider comprises:
respectively extracting a direction gradient histogram difference value and a perceptual hash difference value of each comparison area;
and carrying out weighted summation on the direction gradient histogram difference value and the perception hash difference value so as to obtain a contrast difference characteristic value of each area.
7. A contrast-based subway image anomaly detection method as claimed in claim 6, wherein said weighted summation of histogram of oriented gradients difference and perceptual hash difference comprises:
the histogram feature coefficient is set to 0.75 and the perceptual hash feature coefficient is set to 0.25.
8. A subway image anomaly detection system based on contrast is characterized by comprising:
the system comprises a current image acquisition module, a line scan camera group and a control module, wherein the current image acquisition module is used for acquiring a current running vehicle image through the line scan camera group, and a line scan camera in the line scan camera group is set to be a shooting range covering any position of a vehicle body;
the template image acquisition module is used for acquiring vehicle identification information through a current running vehicle image and extracting a template image corresponding to the current running vehicle based on the vehicle identification information;
the image alignment module is used for respectively detecting the characteristic points of the current running vehicle image and the template image, extracting the characteristic points of the current image and the characteristic points of the template image for matching, and aligning the current running vehicle image and the template image according to the position characteristics of the matched characteristic point pairs;
and the image comparison module is used for respectively extracting the comparison difference characteristic of each area by comparing the current running vehicle image and the template image after the sliding block traversal alignment, judging that the current area is abnormal when the comparison difference characteristic value is greater than a preset threshold value, and otherwise, judging that the current area is normal.
9. A storage medium comprising a stored program, wherein the program when executed performs the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111006454.6A CN113781418A (en) | 2021-08-30 | 2021-08-30 | Subway image anomaly detection method and system based on comparison and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111006454.6A CN113781418A (en) | 2021-08-30 | 2021-08-30 | Subway image anomaly detection method and system based on comparison and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113781418A true CN113781418A (en) | 2021-12-10 |
Family
ID=78839889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111006454.6A Pending CN113781418A (en) | 2021-08-30 | 2021-08-30 | Subway image anomaly detection method and system based on comparison and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113781418A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115346127A (en) * | 2022-10-20 | 2022-11-15 | 成都大汇物联科技有限公司 | Dam safety detection method and system |
| CN116109839A (en) * | 2023-02-15 | 2023-05-12 | 北京拙河科技有限公司 | Picture difference comparison method and device |
| CN117367331A (en) * | 2023-12-04 | 2024-01-09 | 山西阳光三极科技股份有限公司 | Radar monitoring method and device for mining area earth surface deformation and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102323070A (en) * | 2011-06-10 | 2012-01-18 | 北京华兴致远科技发展有限公司 | Method and system for detecting abnormality of train |
| CN103512762A (en) * | 2012-06-29 | 2014-01-15 | 北京华兴致远科技发展有限公司 | Image processing method and device and train fault detection system |
| CN109151452A (en) * | 2017-06-15 | 2019-01-04 | 瑞萨电子株式会社 | Abnormal detector and Vehicular system |
-
2021
- 2021-08-30 CN CN202111006454.6A patent/CN113781418A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102323070A (en) * | 2011-06-10 | 2012-01-18 | 北京华兴致远科技发展有限公司 | Method and system for detecting abnormality of train |
| CN103512762A (en) * | 2012-06-29 | 2014-01-15 | 北京华兴致远科技发展有限公司 | Image processing method and device and train fault detection system |
| CN109151452A (en) * | 2017-06-15 | 2019-01-04 | 瑞萨电子株式会社 | Abnormal detector and Vehicular system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115346127A (en) * | 2022-10-20 | 2022-11-15 | 成都大汇物联科技有限公司 | Dam safety detection method and system |
| CN115346127B (en) * | 2022-10-20 | 2023-01-24 | 成都大汇物联科技有限公司 | Dam safety detection method and system |
| CN116109839A (en) * | 2023-02-15 | 2023-05-12 | 北京拙河科技有限公司 | Picture difference comparison method and device |
| CN117367331A (en) * | 2023-12-04 | 2024-01-09 | 山西阳光三极科技股份有限公司 | Radar monitoring method and device for mining area earth surface deformation and electronic equipment |
| CN117367331B (en) * | 2023-12-04 | 2024-03-12 | 山西阳光三极科技股份有限公司 | Radar monitoring method and device for mining area earth surface deformation and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113781418A (en) | Subway image anomaly detection method and system based on comparison and storage medium | |
| CN106709436B (en) | Track traffic panoramic monitoring-oriented cross-camera suspicious pedestrian target tracking system | |
| CN105913093B (en) | A kind of template matching method for Text region processing | |
| KR101403876B1 (en) | Method and Apparatus for Vehicle License Plate Recognition | |
| CN111292321B (en) | Transmission line insulator defect image identification method | |
| CN106610969A (en) | Multimodal information-based video content auditing system and method | |
| CN110781839A (en) | Sliding window-based small and medium target identification method in large-size image | |
| CN112364740B (en) | Unmanned aerial vehicle room monitoring method and system based on computer vision | |
| CN112966665A (en) | Pavement disease detection model training method and device and computer equipment | |
| CN113569863B (en) | Document checking method, system, electronic equipment and storage medium | |
| CN112381840B (en) | Method and system for marking vehicle appearance parts in loss assessment video | |
| CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
| CN110909657A (en) | Method for identifying apparent tunnel disease image | |
| CN110570422A (en) | Capsule defect visual detection method based on matrix analysis | |
| CN108460344A (en) | Dynamic area intelligent identifying system in screen and intelligent identification Method | |
| CN111105398A (en) | Transmission line component crack detection method based on visible light image data | |
| CN112307842B (en) | Video identification system and method for matching train operation monitoring record files | |
| CN112288682A (en) | Electric power equipment defect positioning method based on image registration | |
| CN115019294A (en) | Pointer instrument reading identification method and system | |
| CN103034997A (en) | Foreground detection method for separation of foreground and background of surveillance video | |
| CN116524725A (en) | Intelligent driving traffic sign image data identification system | |
| CN108734158B (en) | Real-time train number identification method and device | |
| Gao et al. | Anomaly detection of trackside equipment based on GPS and image matching | |
| CN110197181B (en) | Cable character detection method and system based on OCR | |
| CN112329783B (en) | Image processing-based coupler yoke break identification method |
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 |