CN118033768A - Method for detecting falling articles of carry-on luggage basket of passenger - Google Patents
Method for detecting falling articles of carry-on luggage basket of passenger Download PDFInfo
- Publication number
- CN118033768A CN118033768A CN202410128286.5A CN202410128286A CN118033768A CN 118033768 A CN118033768 A CN 118033768A CN 202410128286 A CN202410128286 A CN 202410128286A CN 118033768 A CN118033768 A CN 118033768A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- basket
- characteristic points
- luggage
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000000926 separation method Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000007689 inspection Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
Classifications
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Image Processing (AREA)
Abstract
The method for detecting the falling articles of the carry-on luggage basket of the passenger comprises the following steps: s1: collecting basket images of luggage in different time periods, and marking characteristic points and detection ranges; s2: preprocessing a luggage basket empty basket image to obtain pixel coordinates of characteristic points on the row Li Kuang empty basket image, and dividing the luggage basket empty basket image according to time periods to form template group images of different time periods; s3: inputting a luggage basket image acquired in real time as an image to be detected, separating an image to be detected from an image channel, merging after single-channel processing, selecting a template group image with the same time period, and matching characteristic points on the template group image on the image to be detected to obtain matching degree, angle and pixel coordinate information of the characteristic points on the image to be detected; s4: judging whether the image to be detected is matched with the corresponding characteristic points or not, judging whether articles exist in the luggage basket or not according to a judging result, matching after optimizing the image to be detected, reducing the influence of external environment light on the image, and judging for multiple times to improve the detection accuracy.
Description
Technical Field
The invention belongs to the technical field of security inspection, and particularly relates to a detection method for falling articles of a carry-on luggage basket of a passenger.
Background
When a passenger carries out the safety inspection, the passenger usually adopts a luggage basket to place the passenger's carry-on luggage, then pushes the luggage basket into an X-ray machine for safety inspection, after the safety inspection passes, the passenger takes the carry-on luggage out of the luggage basket, the empty luggage basket is sent back to the front end of a safety inspection channel for recycling, and small articles such as identity cards, keys, bank cards, air tickets and the like often occur during the process of taking out the luggage from the tail end of the safety inspection channel, so as to cause trouble and inconvenience for the traveling of the passenger.
Application number 201910386423.4 discloses an empty box intelligent identification system and an identification method, and particularly discloses an empty box intelligent identification method, wherein the method comprises the following steps:
Step one, a conveyor belt conveys a security inspection box to pass through a photoelectric sensor;
Step two, the photoelectric sensor senses the security inspection box and triggers an imaging device to image the security inspection box;
Step three, the imaging device transmits imaging information to a visual processing module of the industrial control integrated machine, and the visual processing module compares and identifies the imaging information with a preset empty box photo; if the comparison results are different, indicating that the security inspection box is provided with the left-behind articles, controlling the warning equipment to give a warning, displaying the current image in the security inspection box through the display interface of the industrial control integrated machine, and marking the positions of the left-behind articles; and if the imaging information is consistent with the comparison of the empty box photo, the conveyor belt automatically sends the security inspection box without the left-over articles to a lower layer return line body.
Although the above patent can identify whether there are left articles in the security inspection box, simply rely on the photo of taking to compare, because the overall dimension of the article that falls behind, the uncertainty of material, and the environmental illuminance interference of different time periods in the security inspection passageway one day can cause the recognition result inaccurate.
Therefore, the technical problems to be solved by the invention are as follows: when the above patent detects whether there are left articles in the luggage basket, the comparison is carried out by simply relying on the photographed photos, and the recognition result is inaccurate due to the uncertainty of the external dimensions and materials of the left articles and the ambient illuminance interference of different time periods in the day of the security inspection channel.
Disclosure of Invention
In order to solve the technical problem that when the patent detects whether the luggage basket has the left articles or not, the detection result is inaccurate due to the fact that the appearance size and the material uncertainty of the left articles and the ambient illuminance interference of different time periods in one day of the security inspection channel are simply compared by virtue of the shot photos, the invention provides a detection method for the left articles of the luggage basket for passengers.
The specific scheme is as follows:
The detection method of the falling articles of the carry-on luggage basket of the passenger specifically comprises the following steps:
step S1: collecting image data of the empty basket of the passenger in different time periods, and marking characteristic points and detection ranges on the empty basket images of the passenger;
Step S2: preprocessing a luggage basket empty basket image to obtain pixel coordinates of characteristic points on the row Li Kuang empty basket image, and dividing the luggage basket empty basket image according to time periods to form template group images of different time periods;
Step S3: inputting a luggage basket image acquired in real time as an image to be detected, carrying out channel separation on the image to be detected, merging after single-channel processing, optimizing the image to be detected, selecting a template group image with the same time period, and matching characteristic points on the template group image on the image to be detected to obtain the matching degree, angle and pixel coordinate information of the characteristic points on the image to be detected;
Step S4: judging whether the image to be detected is matched with the corresponding characteristic points or not, and judging whether articles exist in the luggage basket or not according to a judging result.
The step S4 specifically includes:
S41: if the corresponding characteristic points are not matched, the characteristic points are shielded by articles in the luggage basket, and the articles are in the luggage basket;
s42: if the corresponding characteristic points are matched, after corresponding processing is carried out, whether articles exist in the luggage basket or not is continuously judged.
The step S42 specifically includes:
S421: carrying out affine transformation on the image rubber to be detected according to the characteristic point information on the image to be detected and the characteristic point information on the matched template group image, and aligning the characteristic points of the image to be detected with the corresponding characteristic points on the template group image;
S422: performing difference processing on the aligned to-be-detected image and the template group image to obtain a difference part of the to-be-detected image and the template group image;
S423: performing median filtering, clipping and threshold segmentation on the difference part to obtain a binarized difference graph;
s424: screening a binarized difference graph;
S425: judging whether the pixel area of the difference map is larger than a preset pixel area value, and judging whether articles exist in the luggage basket according to a judging result.
The step S424 specifically includes:
S4241: judging whether the difference map is in a detection range marked in advance according to the screening conditions, and judging whether articles exist in the luggage basket according to a judging result;
S4242: if the difference map is not in the detection range marked in advance, judging that no article exists in the luggage basket;
S4243: if the difference map is within the detection range marked in advance, step S425 is performed.
The step S425 specifically includes:
s4251: if the pixel area of the difference map is larger than the preset pixel area value, articles exist in the luggage basket;
s4252: if the pixel area of the difference image is not larger than the preset pixel area value, judging whether a plurality of difference parts with similar distances exist or not, and judging whether articles exist in the luggage basket or not according to the judging result.
The step S4252 specifically includes:
S42521: if a plurality of difference parts with similar distances exist, articles exist in the luggage basket;
s42522: if there are no more than one distinct portions with similar distances, then no items are present in the basket.
In step S3, the image of the luggage basket acquired in real time is input as the image rubber to be detected, the image rubber to be detected is subjected to channel separation processing to form images of three channels of the R channel, the G channel and the B channel, the image of the R channel is subjected to gaussian filtering processing to enhance image contrast, the images of the G channel and the B channel are subjected to histogram equalization, the images of the image to be detected are combined after single channel processing, the image rubber to be detected is optimized, the template group image of the same time period is searched, the characteristic points on the template group image are intercepted, the characteristic points on the template group image are matched on the image rubber to be detected, the matching degree of the characteristic points on the image to be detected is obtained, the corresponding template group image is selected according to the matching degree, namely, the template group image with the luggage basket being placed or being placed upside down is determined, the characteristic points on the template group image are recorded according to the selected template group image, and the pixel coordinates and angles of the corresponding characteristic points on the image rubber to be detected are obtained.
The beneficial effects of the invention are as follows:
According to the invention, through carrying out channel separation on the image rubber to be detected, respectively processing different channels and merging the channels to obtain the optimized image, so that the objects on the image are clearer, and the influence of external environment light on the image is reduced; comparing and identifying the optimized image with the template group image in the corresponding time period, wherein the identification is more accurate; in order to reduce the influence of neglected area in the process of dividing the article into a plurality of small target areas due to uneven color distribution and uneven light distribution on the surface of the article during threshold segmentation, the invention judges the small target areas, improves the identification rate of the target objects under extreme conditions, judges whether the article left in the luggage basket for multiple times, and improves the detection accuracy.
Drawings
Fig. 1 is a flowchart of a method for detecting a basket based on image recognition according to an embodiment of the present invention.
FIG. 2 is a diagram of a process for labeling template groups for the present invention.
Fig. 3 is a view showing a result of detecting the basket according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. It will be apparent to those skilled in the art that the described embodiments are only a part, but not all, of the implementations of the invention, and that all other embodiments, based on which those skilled in the art will come to lie within the scope of the invention without making any inventive effort.
As shown in fig. 1, the invention provides a method for detecting the articles left behind a luggage basket carried by a passenger, which specifically comprises the following steps:
step S1: collecting image data of the empty basket of the passenger in different time periods, and marking characteristic points and detection ranges on the empty basket images of the passenger;
Step S2: preprocessing a luggage basket empty basket image to obtain pixel coordinates of characteristic points on the row Li Kuang empty basket image, and dividing the luggage basket empty basket image according to time periods to form template group images of different time periods;
Step S3: inputting a luggage basket image acquired in real time as an image to be detected, carrying out channel separation on the image to be detected, merging after single-channel processing, optimizing the image to be detected, selecting a template group image with the same time period, and matching characteristic points on the template group image on the image to be detected to obtain the matching degree, angle and pixel coordinate information of the characteristic points on the image to be detected;
Step S4: judging whether the image to be detected is matched with the corresponding characteristic points or not, and judging whether articles exist in the luggage basket or not according to a judging result.
According to the invention, through carrying out channel separation on the image rubber to be detected, respectively processing different channels and merging the channels to obtain the optimized image, so that the objects on the image are clearer, and the influence of external environment light on the image is reduced; comparing and identifying the optimized image with the template group image in the corresponding time period, wherein the identification is more accurate; in order to reduce the influence of neglected area in the process of dividing the article into a plurality of small target areas due to uneven color distribution and uneven light distribution on the surface of the article during threshold segmentation, the invention judges the small target areas, improves the identification rate of the target objects under extreme conditions, judges whether the article left in the luggage basket for multiple times, and improves the detection accuracy.
The step S4 specifically includes:
S41: if the corresponding characteristic points are not matched, the characteristic points are shielded by articles in the luggage basket, and the articles are in the luggage basket;
s42: if the corresponding characteristic points are matched, after corresponding processing is carried out, whether articles exist in the luggage basket or not is continuously judged.
The matching characteristic points are that corresponding characteristic points are searched on the diagram rubber to be checked according to the characteristic points marked on the empty basket image of the luggage basket, and matching is carried out according to the characteristic point information, so that the identification result is more accurate.
The step S42 specifically includes:
S421: according to the characteristic point information on the image to be detected and the characteristic point information on the matched template group image, the image to be detected is displayed on the display screen
Carrying out affine transformation, and aligning the characteristic points of the image to be detected with the corresponding characteristic points on the template group image;
S422: performing difference processing on the aligned to-be-detected image and the template group image to obtain a difference part of the to-be-detected image and the template group image;
S423: performing median filtering, clipping and threshold segmentation on the difference part to obtain a binarized difference graph;
s424: screening a binarized difference graph;
s425: judging whether the pixel area of the difference map is larger than a preset pixel area value, and judging whether the pixel area of the difference map is in the luggage basket according to the judging result
And judging whether the article exists.
Carrying out affine transformation on the image to be detected through the matching information, aligning the characteristic points on the image to be detected with the characteristic points on the template group image, further aligning the image to be detected with the template group image, and carrying out difference processing on the aligned image to be detected and the template group image, namely subtracting the image rubber to be detected after affine transformation from the template group image rubber, and removing the same part to obtain a difference part of the image to be detected and the template group image, wherein the left difference part can be an article in a luggage basket.
Extracting the difference part through threshold segmentation, performing binarization processing to make the difference part more obvious, and extracting
And carrying out median filtering on the difference part area to remove noise points caused by uneven distribution of pipelines, wherein the noise points can be light influence or influence caused by background stains and abrasion in the luggage basket.
The step S424 specifically includes:
S4241: judging whether the difference map is in a detection range marked in advance according to the screening conditions, and carrying out basket matching according to the judgment result
Judging whether an article exists or not;
S4242: if the difference map is not in the detection range marked in advance, judging that no article exists in the luggage basket;
S4243: if the difference map is within the detection range marked in advance, step S425 is performed.
And judging whether the difference part is in the detection range according to the detection range marked in advance so as to remove the influence caused by sundries outside the luggage basket.
The step S425 specifically includes:
s4251: if the pixel area of the difference map is larger than the preset pixel area value, articles exist in the luggage basket;
S4252: if the pixel area of the difference image is not greater than the preset pixel area value, judging whether a plurality of distances are similar or not
And the difference part is used for judging whether articles exist in the luggage basket according to the judging result.
The step S4252 specifically includes:
S42521: if a plurality of difference parts with similar distances exist, articles exist in the luggage basket;
s42522: if there are no more than one distinct portions with similar distances, then no items are present in the basket.
According to the set area size, the difference part is screened according to the area size, articles in the luggage basket can be considered to exist in the area exceeding a certain area, when the area of the difference part is too small, whether a plurality of difference parts with too small areas exist in the similar area is further judged, if the articles exist in the luggage basket, and the detection result is more accurate through multiple judgment.
In the step S1, the luggage basket empty basket image data is the image data when no articles exist in the luggage basket during security check, and the luggage basket empty basket image data in different time periods comprises luggage basket empty basket images acquired respectively according to time sequence in one day and images of different luggage basket background advertisements; the characteristic points are unique markers in the background of the luggage basket and are obvious characteristics of the image; the detection range is the position where the article possibly appears in the blank basket image of the row Li Kuang, and is actually the area inside the frame of the luggage basket; the image data of the empty basket of the luggage in a plurality of different time periods is collected and used as a registered database, so that the image data are conveniently matched with images to be detected.
In the step S2, the preprocessing refers to performing shape matching on the labeled feature points in the row Li Kuang empty basket image, and recording pixel coordinate information of the feature points in the row Li Kuang empty basket image; the template group images are luggage basket empty basket images with different light influences in different time periods, each template group comprises a front image and a back image of the same time period, the situation that luggage basket is placed forward or placed backward is dealt with, the luggage basket empty basket template group images of the same time period are selected for matching, the luggage basket empty basket template group images have the same external light intensity, unnecessary errors are reduced in the image processing process, and the luggage basket identification accuracy is improved.
In the step S3, the image of the luggage basket acquired in real time is input as an image rubber to be detected, the image rubber to be detected is subjected to channel separation processing to form images of three channels of an R channel, a G channel and a B channel, the image of the R channel is subjected to gaussian filtering processing to enhance image contrast, the images of the G channel and the image of the B channel are subjected to histogram equalization, and the images to be detected are combined after being subjected to single channel processing, so that the influence caused by light is removed.
Searching template group images in the same time period, intercepting characteristic points on the template group images, matching the characteristic points on the image to be detected by utilizing the characteristic points on the template group images, obtaining the matching degree of the characteristic points on the image to be detected, selecting the corresponding template group images according to the matching degree, namely determining to select the template group images with the luggage basket being placed forwards or backwards, recording the characteristic points on the template group images according to the selected template group images, and obtaining detection results according to pixel coordinates and angles of the characteristic points corresponding to the image to be detected.
The process diagram of the labeling template group image of the invention is shown in fig. 2, the visual diagram of the detection result of the luggage basket of the invention is shown in fig. 3, and the detection result can be seen from the diagram, so that the existence of the left-over articles in the luggage basket is proved.
When the image of the luggage basket is detected, the accuracy of detecting the luggage basket is improved through multiple judgment; and carry out the passageway separation to the picture rubber that awaits measuring, the single channel is handled the back respectively and is merged to this optimizes the picture rubber that awaits measuring, gets rid of the influence that ambient light brought, and the detection requirement such as being directed against all-weather different periods, luggage basket different backgrounds, the mark of being surveyed article profile, adaptation ambient light's illuminance interference, identifiable marked article includes: identification cards, keys, bank cards, air tickets, wallets, headphones, pens, and the like.
The technical means disclosed by the scheme of the invention is not limited to the technical means disclosed by the embodiment, and also comprises the technical scheme formed by any combination of the technical features. It should be noted that modifications and adaptations to the invention may occur to one skilled in the art without departing from the principles of the present invention and are intended to be within the scope of the present invention.
Claims (7)
1. A detection method for the falling objects of a carry-on luggage basket of a passenger is characterized in that:
The method specifically comprises the following steps:
step S1: collecting image data of the empty basket of the passenger in different time periods, and marking characteristic points and detection ranges on the empty basket images of the passenger;
Step S2: preprocessing a luggage basket empty basket image to obtain pixel coordinates of characteristic points on the row Li Kuang empty basket image, and dividing the luggage basket empty basket image according to time periods to form template group images of different time periods;
Step S3: inputting a luggage basket image acquired in real time as an image to be detected, carrying out channel separation on the image to be detected, merging after single-channel processing, optimizing the image to be detected, selecting a template group image with the same time period, and matching characteristic points on the template group image on the image to be detected to obtain the matching degree, angle and pixel coordinate information of the characteristic points on the image to be detected;
Step S4: judging whether the image to be detected is matched with the corresponding characteristic points or not, and judging whether articles exist in the luggage basket or not according to a judging result.
2. The method for detecting the missing items of the carry-on luggage basket of the passenger according to claim 1, wherein:
the step S4 specifically includes:
S41: if the corresponding characteristic points are not matched, the characteristic points are shielded by articles in the luggage basket, and the articles are in the luggage basket;
s42: if the corresponding characteristic points are matched, after corresponding processing is carried out, whether articles exist in the luggage basket or not is continuously judged.
3. The method for detecting the missing items of the carry-on luggage basket of the passenger according to claim 2, wherein:
The step S42 specifically includes:
S421: according to the characteristic point information on the image to be detected and the characteristic point information on the matched template group image, the image to be detected is displayed on the display screen
Carrying out affine transformation, and aligning the characteristic points of the image to be detected with the corresponding characteristic points on the template group image;
S422: performing difference processing on the aligned to-be-detected image and the template group image to obtain a difference part of the to-be-detected image and the template group image;
S423: performing median filtering, clipping and threshold segmentation on the difference part to obtain a binarized difference graph;
s424: screening a binarized difference graph;
s425: judging whether the pixel area of the difference map is larger than a preset pixel area value, and judging whether the pixel area of the difference map is in the luggage basket according to the judging result
And judging whether the article exists.
4. A method for detecting a missing article of luggage for a traveler as in claim 3, wherein:
the step S424 specifically includes:
S4241: judging whether the difference map is in a detection range marked in advance according to the screening conditions, and carrying out basket matching according to the judgment result
Judging whether an article exists or not;
S4242: if the difference map is not in the detection range marked in advance, judging that no article exists in the luggage basket;
S4243: if the difference map is within the detection range marked in advance, step S425 is performed.
5. A method for detecting a missing article of luggage for a traveler as in claim 3, wherein:
the step S425 specifically includes:
s4251: if the pixel area of the difference map is larger than the preset pixel area value, articles exist in the luggage basket;
S4252: if the pixel area of the difference image is not greater than the preset pixel area value, judging whether a plurality of distances are similar or not
And the difference part is used for judging whether articles exist in the luggage basket according to the judging result.
6. The method for detecting the missing items of the carry-on luggage basket of the passenger according to claim 5, wherein the method comprises the following steps:
the step S4252 specifically includes:
S42521: if a plurality of difference parts with similar distances exist, articles exist in the luggage basket;
s42522: if there are no more than one distinct portions with similar distances, then no items are present in the basket.
7. The method for detecting the missing items of the carry-on luggage basket of the passenger according to claim 1, wherein:
in step S3, the image of the luggage basket acquired in real time is input as the image rubber to be detected, the image rubber to be detected is subjected to channel separation processing to form images of three channels of the R channel, the G channel and the B channel, the image of the R channel is subjected to gaussian filtering processing to enhance image contrast, the images of the G channel and the B channel are subjected to histogram equalization, the images of the image to be detected are combined after single channel processing, the image rubber to be detected is optimized, the template group image of the same time period is searched, the characteristic points on the template group image are intercepted, the characteristic points on the template group image are matched on the image rubber to be detected, the matching degree of the characteristic points on the image to be detected is obtained, the corresponding template group image is selected according to the matching degree, namely, the template group image with the luggage basket being placed or being placed upside down is determined, the characteristic points on the template group image are recorded according to the selected template group image, and the pixel coordinates and angles of the corresponding characteristic points on the image rubber to be detected are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410128286.5A CN118033768A (en) | 2024-01-30 | 2024-01-30 | Method for detecting falling articles of carry-on luggage basket of passenger |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410128286.5A CN118033768A (en) | 2024-01-30 | 2024-01-30 | Method for detecting falling articles of carry-on luggage basket of passenger |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118033768A true CN118033768A (en) | 2024-05-14 |
Family
ID=90988715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410128286.5A Pending CN118033768A (en) | 2024-01-30 | 2024-01-30 | Method for detecting falling articles of carry-on luggage basket of passenger |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118033768A (en) |
-
2024
- 2024-01-30 CN CN202410128286.5A patent/CN118033768A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115082419B (en) | Blow-molded luggage production defect detection method | |
| CN105809655B (en) | Vehicle inspection method and system | |
| US9245203B2 (en) | Collecting information relating to identity parameters of a vehicle | |
| US20090309966A1 (en) | Method of detecting moving objects | |
| Torabi et al. | Local self-similarity-based registration of human ROIs in pairs of stereo thermal-visible videos | |
| CN108629319B (en) | Image detection method and system | |
| CN104951784A (en) | Method of detecting absence and coverage of license plate in real time | |
| Albiol Colomer et al. | Who is who at different cameras: people re-identification using depth cameras | |
| CN102426649A (en) | Simple steel seal digital automatic identification method with high accuracy rate | |
| CN107025716B (en) | Method and device for detecting contamination of paper money crown word number | |
| Xia et al. | A novel algorithm for ship detection based on dynamic fusion model of multi-feature and support vector machine | |
| CN111126393A (en) | Vehicle appearance refitting judgment method and device, computer equipment and storage medium | |
| CN101383005A (en) | Method for separating passenger target image and background by auxiliary regular veins | |
| CN114639078A (en) | Vehicle type recognition method, device and system | |
| CN111239142A (en) | Paste appearance defect detection device and method | |
| Ahmed et al. | Traffic sign detection and recognition model using support vector machine and histogram of oriented gradient | |
| Aung et al. | Automatic license plate detection system for myanmar vehicle license plates | |
| CN106204616B (en) | Method and device for identifying currency value of Iran paper money | |
| KR102030768B1 (en) | Poultry weight measuring method using image, recording medium and device for performing the method | |
| CN114332622A (en) | Label detection method based on machine vision | |
| CN107545565B (en) | Solar screen plate detection method | |
| EP3311333A1 (en) | Pairing of images of postal articles with descriptors of singularities of the gradient field | |
| CN118033768A (en) | Method for detecting falling articles of carry-on luggage basket of passenger | |
| Park et al. | Binarization of text region based on fuzzy clustering and histogram distribution in signboards | |
| CN116503912A (en) | Security check early warning method based on electronic graph bag |
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 |