CN116503811A - Image-based forklift violation monitoring method, medium and device - Google Patents
Image-based forklift violation monitoring method, medium and device Download PDFInfo
- Publication number
- CN116503811A CN116503811A CN202310551166.1A CN202310551166A CN116503811A CN 116503811 A CN116503811 A CN 116503811A CN 202310551166 A CN202310551166 A CN 202310551166A CN 116503811 A CN116503811 A CN 116503811A
- Authority
- CN
- China
- Prior art keywords
- forklift
- image
- frame difference
- target
- threshold value
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000004891 communication Methods 0.000 claims abstract description 8
- 238000004590 computer program Methods 0.000 claims description 9
- 238000013145 classification model Methods 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 4
- 230000010339 dilation Effects 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 24
- 238000003384 imaging method Methods 0.000 description 6
- 238000005530 etching Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
Abstract
The invention discloses a forklift illegal monitoring method, medium and device based on images, and relates to the technical field of forklift monitoring. Acquiring two images shot by a camera at intervals of a first preset duration; performing frame difference binarization processing on the two images to obtain a frame difference image; determining a minimum circumscribed rectangle of a target aiming at a communication area of the frame difference image; judging whether the width-to-length ratio value of the minimum circumscribed rectangle of each target is smaller than a first preset threshold value or not; if the width-to-length ratio value is smaller than a first preset threshold value, determining that the forklift corresponding to the minimum circumscribed rectangle of the target is illegal. And performing frame difference binarization processing on two images shot by the camera at intervals of a first preset duration to obtain a frame difference image, determining a target minimum circumscribed rectangle according to a connected region in the frame difference image, and judging whether a forklift illegal use behavior exists according to whether the width-to-length ratio value of the target minimum circumscribed rectangle is smaller than a first preset threshold value or not, so that consumption of network resources can be reduced, and labor cost is reduced.
Description
Technical Field
The invention relates to the technical field of forklift monitoring, in particular to an image-based forklift illegal monitoring method, medium and device.
Background
A forklift is an industrial transport vehicle, and is a wheeled transport vehicle for handling, stacking, and transporting goods in pallets. When distributing express, because the goods are heavier, fork truck workers generally use an electric small fork truck to carry out the moving operation of loading and unloading goods in the field. According to regulations, a forklift worker can only move one pallet at a time, and moving a plurality of pallets easily causes goods to drop and collide, so that the forklift worker pushes more than one pallet is illegal.
In order to avoid the occurrence of the above-mentioned violations, measures generally taken include the following two types:
one of them is to arrange the safety monitoring personnel to carry out on-site supervision on workers, which can lead to the improvement of labor cost, when the quantity of express delivery is increased suddenly, the quantity of forklift workers is increased, the safety monitoring personnel can not ensure that each worker can be monitored, the illegal action still occurs, the loss is brought to factories, and hidden danger is brought to the life safety of workers;
in addition, the monitoring is utilized to shoot and store the working process of the worker, a plurality of fragments are sampled and downloaded by a detector for inspection, the monitored pictures within a few minutes are almost identical in the low peak period of the worker operation, the occupation of the downloaded video to bandwidth and network resources is relatively high, if the video fragments are directly intercepted for inspection, not only the manpower is wasted, the resources are occupied, but also the monitoring efficiency is low.
Disclosure of Invention
In order to solve at least one technical problem mentioned in the background art, the invention aims to provide an image-based forklift illegal detection method, medium and device, which can monitor illegal use behaviors of a forklift, reduce labor cost and reduce consumption of network resources.
In order to achieve the above purpose, the present invention provides the following technical solutions:
in a first aspect, an embodiment of the present invention provides an image-based method for monitoring a forklift violation, including:
s101, acquiring two images shot by a camera at intervals of a first preset duration;
s102, performing frame difference binarization processing on the two images to obtain a frame difference image;
s103, determining a target minimum circumscribed rectangle for a connected region of the frame difference image, wherein the connected region is an image region formed by pixel points which have the same pixel value and are adjacent in position in the frame difference image;
s104, judging whether the width-to-length ratio value of each target minimum circumscribed rectangle is smaller than a first preset threshold value or not according to each target minimum circumscribed rectangle;
s105, if the width-to-length ratio value is smaller than a first preset threshold value, determining that the forklift corresponding to the minimum circumscribed rectangle of the target is illegal.
Further, the performing frame difference binarization processing on the two images to obtain a frame difference image includes:
performing frame difference binarization processing on the two images to obtain a first black-and-white image;
performing morphological corrosion operation on the first black-and-white image to obtain a second black-and-white image;
and performing morphological dilation operation on the second black-and-white image to obtain a frame difference image.
Further, the determining the minimum circumscribed rectangle of the target for the connected region of the frame difference image includes:
aiming at the communication area of the frame difference image, a plurality of sets of minimum circumscribed rectangles are obtained;
judging whether the area of each minimum circumscribed rectangle is smaller than a second preset threshold value or not;
if the area is smaller than a second preset threshold value, deleting the minimum circumscribed rectangle smaller than the second preset threshold value from the set;
and determining each minimum bounding rectangle in the deleted set of the plurality of minimum bounding rectangles as a target minimum bounding rectangle.
Further, the step of determining that the forklift corresponding to the minimum circumscribed rectangle of the target violates if the width-to-length ratio value is smaller than a first preset threshold value includes:
if the width-to-length ratio value of the target minimum circumscribed rectangle is smaller than a first preset threshold value, cutting the target minimum circumscribed rectangle area from two images corresponding to the frame difference image to which the target minimum circumscribed rectangle belongs to obtain two subgraphs;
inputting the two subgraphs into a classification model for classification to obtain a first subgraph containing a forklift;
and determining the forklift in the first subgraph as an illegal forklift.
Further, before the step of determining the forklift in the first sub-graph as the illegal forklift, the method further includes:
according to the monitoring time in the image of the first sub-image, video clips with second preset time length before and after the monitoring time are called;
acquiring two images of any adjacent frame in the video segment, repeating steps S101 to S104, and judging whether the distance between the center point of the target minimum external rectangle and the two images is larger than a third preset threshold value or not for the target minimum external rectangle with the width-to-length ratio smaller than a first preset threshold value;
and if the distance is greater than a third preset threshold value, determining the forklift in the first subgraph as an illegal forklift.
Further, the classification model is a deep learning model effect Net.
In a second aspect, an embodiment of the present invention further provides an image-based method for monitoring a violation of a forklift, where after the step of determining the forklift in the first sub-graph as a violation forklift, the method further includes:
obtaining an offence figure in the first subgraph;
inputting the violation figures into a face recognition model for comparison according to employee database information to obtain corresponding violation employee information, wherein the employee database information is obtained in advance;
and adding a violation label to the violation employee in the employee database information according to the violation employee information.
In a third aspect, embodiments of the present invention also provide a computer storage medium having stored thereon a computer program which, when executed by a processor, implements any of the image-based forklift violation monitoring methods described above.
In a fourth aspect, an embodiment of the present invention further provides a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements any of the image-based forklift violation monitoring methods described above when executing the computer program.
Compared with the prior art, the invention has the beneficial effects that: and performing frame difference binarization processing on two images shot by the camera at intervals of a first preset duration to obtain a frame difference image, determining a target minimum circumscribed rectangle according to a connected region in the frame difference image, and judging whether a forklift illegal use behavior exists according to whether the width-to-length ratio value of the target minimum circumscribed rectangle is smaller than a first preset threshold value or not, so that consumption of network resources can be reduced, and labor cost is reduced.
Drawings
Fig. 1 is a first flowchart of a forklift violation monitoring method based on an image according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a first acquired image according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a second image obtained after a 2 minute interval according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a frame difference image according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a frame difference image obtained by performing a corrosion-before-expansion operation according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a communication area according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a minimum bounding rectangle provided by an embodiment of the present invention;
FIG. 8 is a schematic diagram of all minimum bounding rectangles in a frame difference image according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a target minimum bounding rectangle according to an embodiment of the present invention;
fig. 10 is a second flowchart of an image-based method for monitoring a forklift violation according to an embodiment of the present invention;
FIG. 11 is a schematic diagram of a target minimum bounding rectangle in a first image according to an embodiment of the present invention;
FIG. 12 is a schematic diagram of a target minimum bounding rectangle in a second image according to an embodiment of the present invention;
FIG. 13 is a schematic diagram of a first sub-graph provided by an embodiment of the present invention;
fig. 14 is a schematic diagram of an embodiment of the present invention without a forklift;
fig. 15 is a third flowchart of an image-based method for monitoring a forklift violation according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the above problems in the prior art, the embodiment of the invention discloses an image-based forklift violation monitoring method, and it is to be noted that an execution subject of the embodiment of the invention may be a computer or any electronic device with data processing capability. For convenience of description, the following details will be respectively described with the electronic device as an execution body.
Embodiment one:
as shown in fig. 1, fig. 1 is a flowchart of a forklift violation monitoring method based on an image according to an embodiment of the present invention, including:
step S101, acquiring two images shot by a camera at intervals of a first preset duration.
In some working environments such as express distribution and the like, where illegal operation of a forklift is easy to occur, a monitoring camera is preset to conduct real-time monitoring shooting on the working site, and electronic equipment obtains two images of a first preset duration of interval shot by the camera.
Fig. 2 is a schematic diagram of a first image acquired according to an embodiment of the present invention, and fig. 3 is a schematic diagram of a second image acquired after 2 minutes of interval according to an embodiment of the present invention, as shown in fig. 2 and fig. 3. The monitoring time in fig. 2 shows 14:12, no forklift is present in the working site, the monitoring time in fig. 3 shows 14:14, and it can be seen that one illegally used forklift is present, and the two pallets are placed back and forth by an offender, so that the consequences of falling and colliding of cargoes are easily caused.
Step S102, performing frame difference binarization processing on the two images to obtain a frame difference image.
And (3) carrying out a frame difference algorithm on the two images obtained in the step (S101), when a moving object appears in a monitored scene, relatively obvious difference appears between frames, subtracting the two frames to obtain an absolute value of a brightness difference of the two frames, judging whether the absolute value is larger than a threshold value to analyze the motion characteristic of an image sequence, determining whether the object moves in the image sequence, if the object moves, carrying out binarization operation, setting the binarization threshold value as 30, namely setting the pixel value as 255, namely black, if the pixel value of a pixel point is larger than 30, otherwise setting the pixel value as 0, namely white, and obtaining the frame difference image.
Fig. 4 is a schematic diagram of a frame difference image according to an embodiment of the present invention, as shown in fig. 4. Because the new or moved object is captured by the frame difference algorithm in fig. 3, compared with fig. 2, the frame difference image obtained after binarization is a black-and-white picture.
Generally, one second of video consists of 24 images, so the downloaded video occupies a relatively high bandwidth and network resources compared to the downloaded picture. In the low peak period of operation, the monitoring pictures within a few minutes are almost identical, if video clips are directly intercepted for classification, time is consumed, network resources are consumed, and the invention utilizes two pictures with intervals of a plurality of minutes and combines frame difference binarization processing, so that the time period with unchanged monitoring content can be filtered, thereby saving time and network resources.
In one embodiment, the step S102 may be subdivided into the following steps:
step S1021, performing frame difference binarization processing on the two images to obtain a first black-and-white image.
In the same way as in step S102, the two images are subjected to frame difference binarization processing, and the obtained picture is used as a first black-and-white image, i.e., fig. 4.
In step S1022, morphological etching is performed on the first black-and-white image, so as to obtain a second black-and-white image.
And (3) carrying out corrosion operation on the first black-and-white image to obtain a second black-and-white image, wherein the corrosion effect is to thin the picture, and the principle is to take local minimum values in a small area of the original picture. Because of the binarized image, the pixel values are only 0 and 255, so that one value in a small area is 0, and the pixel value of the pixel point is 0.
Step S1023, performing morphological dilation operation on the second black-and-white image to obtain a frame difference image.
And performing expansion etching operation on the second black-and-white image to obtain a frame difference image, wherein expansion and etching are opposite, and the effect is that the picture is enlarged. The etching and then expanding can be used for eliminating white point impurities in a black background, as shown in fig. 5, fig. 5 is a schematic diagram of a frame difference image obtained through the etching and then expanding operation in the embodiment of the invention. Fig. 5, in comparison with fig. 4, eliminates some noise point interference.
Step S103, determining a target minimum circumscribed rectangle for a connected region of the frame difference image, wherein the connected region is an image region formed by pixel points which have the same pixel value and are adjacent in position in the frame difference image.
Taking fig. 6 as an example, fig. 6 is a schematic diagram of a communication area provided by the embodiment of the present invention, it is obvious that 3 image areas formed by adjacent pixel points with the same pixel value in fig. 6 are provided. The minimum bounding rectangle of the target is the minimum bounding rectangle of the communication area, as shown in fig. 7, fig. 7 is a schematic diagram of the minimum bounding rectangle provided in the embodiment of the present invention, the area similar to "3" in fig. 7 is the outline of the communication area, the green rectangle and the blue rectangle are both bounding rectangles of the communication area, but the blue rectangle is the minimum bounding rectangle, that is, the minimum bounding rectangle of the target.
In one embodiment, the step S103 may be subdivided into the following steps:
step S1031, aiming at the connected region of the frame difference image, obtaining a plurality of sets of minimum circumscribed rectangles;
as shown in fig. 8, fig. 8 is a schematic diagram of all minimum bounding rectangles in a frame difference image according to an embodiment of the present invention. And obtaining a plurality of minimum circumscribed rectangles aiming at all the connected areas of the frame difference image, and taking the plurality of minimum circumscribed rectangles as a set.
Step S1032, judging whether the area of each minimum circumscribed rectangle is smaller than a second preset threshold value.
Whether the area of the minimum circumscribed rectangle in step S1031 is smaller than the second preset threshold is determined, and in the embodiment of the present invention, the second preset threshold may be set to 2500, which is not limited. If the area of the smallest bounding rectangle is too small, it may be an interference item for pedestrians or goods, etc., so that it needs to be excluded.
Step S1033, if the area is smaller than the second preset threshold value, deleting the minimum circumscribed rectangle smaller than the second preset threshold value from the set;
if the area of the minimum bounding rectangle is smaller than the second preset threshold 2500, deleting the minimum bounding rectangle with the area smaller than 2500 from the set, and reserving the minimum bounding rectangle with the area larger than 2500.
Step S1034, determining each minimum bounding rectangle in the deleted set of the plurality of minimum bounding rectangles as a target minimum bounding rectangle.
And determining a plurality of minimum bounding rectangles with the area larger than 2500 as target minimum bounding rectangles. As shown in fig. 9, fig. 9 is a schematic diagram of a target minimum bounding rectangle according to an embodiment of the present invention.
Step S104, for each target minimum bounding rectangle, judging whether the width-to-length ratio value of the target minimum bounding rectangle is smaller than a first preset threshold value.
A pallet is pushed by a forklift normally, the ratio of the width to the length is about 0.5, the first preset threshold value is set to be 0.5, and the longer the pushed pallet is, the longer the length of the minimum circumscribed rectangle of the target is, the smaller the width-to-length ratio is. And judging whether the width-to-length ratio value of the minimum circumscribed rectangle of each target is smaller than 0.5 or not according to the minimum circumscribed rectangle of each target.
Step S105, if the width-to-length ratio value is smaller than a first preset threshold value, determining that the forklift corresponding to the minimum circumscribed rectangle of the target is illegal.
If the width-to-length ratio value is smaller than 0.5, the fact that a plurality of trays are connected to the forklift is indicated, and therefore the forklift corresponding to the minimum circumscribed rectangle of the target can be determined to be in illegal operation.
In one embodiment, as shown in fig. 10, fig. 10 is a second flowchart of the image-based method for monitoring the violation of a forklift according to the embodiment of the present invention, and step S105 may be subdivided into the following steps:
step S1051, if the width-to-length ratio value of the minimum circumscribed rectangle is smaller than the first preset threshold value, cutting the minimum circumscribed rectangle region of the target from the two images corresponding to the frame difference image to which the minimum circumscribed rectangle belongs, and obtaining two subgraphs.
The aspect ratio value of the minimum bounding rectangle of the target in fig. 9 is smaller than 0.5, and the positions of the minimum bounding rectangle of the target in the two corresponding images are shown in fig. 11 and 12, respectively, fig. 11 is a schematic diagram of the minimum bounding rectangle of the target in the first image, fig. 12 is a schematic diagram of the minimum bounding rectangle of the target in the second image, and in fig. 11 and 12, the minimum bounding rectangle of the target is cut off to obtain two subgraphs.
Step S1052, inputting the two subgraphs into a classification model for classification, and obtaining a first subgraph containing the forklift.
In one embodiment, the two subgraphs are input into a classification model effect Net for classification, whether the subgraphs contain a forklift or not can be detected, and a first subgraph containing the forklift is obtained, as shown in fig. 13 and fig. 14, fig. 13 is a schematic diagram of the first subgraph provided in the embodiment of the present invention, the first subgraph contains the forklift, and fig. 14 is a schematic diagram of the subgraph without the forklift provided in the embodiment of the present invention.
In step S1053, the forklift in the first sub-graph is determined as an offending forklift.
The electronic equipment determines the forklift displayed in the first sub-graph as an illegal forklift, and can store the first sub-graph into a memory for inspection personnel to review.
In one embodiment, as shown in fig. 15, fig. 15 is a third flowchart of the image-based method for monitoring the violation of a forklift according to the embodiment of the present invention, before step S1053, further includes:
step S0001, according to the monitoring time in the image of the first sub-graph, retrieving video clips with second preset time length before and after the monitoring time;
step S0002, acquiring two images of any adjacent frames in the video clip, and repeating steps S101 to S104;
step S0003, judging whether the distance between the center point of the target minimum circumscribed rectangle and the two images is larger than a third preset threshold value or not for the target minimum circumscribed rectangle with the width-length ratio value smaller than the first preset threshold value;
and if the distance between the center points in the two images is greater than a third preset threshold value, determining the forklift in the first sub-image as an illegal forklift.
The electronic equipment invokes the video clip, takes two images of any adjacent frame, repeats steps S101 to S104 to obtain two minimum circumscribed rectangles of targets, if the forklift in the first sub-graph is being pushed, the center point of the minimum circumscribed rectangles of the targets has a certain distance, and the third preset threshold value can be set to be 50.
Embodiment two:
after step S105 of the embodiment, further includes:
step S106, obtaining an offensive image in the first subgraph;
step S107, according to employee database information, inputting the violation figures into a face recognition model for comparison to obtain corresponding violation employee information, wherein the employee database information is obtained in advance;
and S108, adding rule breaking labels to the rule breaking staff in the staff database information according to the rule breaking staff information.
Embodiment III:
corresponding to the embodiment of the image-based forklift violation monitoring method, the embodiment of the invention also provides a computer storage medium, on which a computer program is stored, which when being executed by a processor, implements any of the image-based forklift violation monitoring methods.
Embodiment four:
corresponding to the embodiment of the image-based forklift violation monitoring method, the embodiment of the invention also provides a terminal device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes any one of the image-based forklift violation monitoring methods when executing the computer program.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (8)
1. The forklift violation monitoring method based on the image is characterized by comprising the following steps of:
s101, acquiring two images shot by a camera at intervals of a first preset duration;
s102, performing frame difference binarization processing on the two images to obtain a frame difference image;
s103, determining a target minimum circumscribed rectangle for a connected region of the frame difference image, wherein the connected region is an image region formed by pixel points which have the same pixel value and are adjacent in position in the frame difference image;
s104, judging whether the width-to-length ratio value of each target minimum circumscribed rectangle is smaller than a first preset threshold value or not according to each target minimum circumscribed rectangle;
s105, if the width-to-length ratio value is smaller than a first preset threshold value, determining that the forklift corresponding to the minimum circumscribed rectangle of the target is illegal.
2. The method for monitoring the violation of a forklift truck based on images according to claim 1, wherein the frame difference binarizing process is performed on two images to obtain a frame difference image, and the method comprises the following steps:
performing frame difference binarization processing on the two images to obtain a first black-and-white image;
performing morphological corrosion operation on the first black-and-white image to obtain a second black-and-white image;
and performing morphological dilation operation on the second black-and-white image to obtain a frame difference image.
3. The method for monitoring the violation of a forklift truck based on an image according to claim 1, wherein the determining a target minimum bounding rectangle for the connected region of the frame difference image comprises:
aiming at the communication area of the frame difference image, a plurality of sets of minimum circumscribed rectangles are obtained;
judging whether the area of each minimum circumscribed rectangle is smaller than a second preset threshold value or not;
if the area is smaller than a second preset threshold value, deleting the minimum circumscribed rectangle smaller than the second preset threshold value from the set;
and determining each minimum bounding rectangle in the deleted set of the plurality of minimum bounding rectangles as a target minimum bounding rectangle.
4. The method for monitoring the violation of a forklift truck based on an image as claimed in claim 1, wherein the step of determining the violation of the forklift truck corresponding to the minimum circumscribed rectangle of the target if the width-to-length ratio value is smaller than a first preset threshold value comprises the following steps:
if the width-to-length ratio value of the target minimum circumscribed rectangle is smaller than a first preset threshold value, cutting the target minimum circumscribed rectangle area from two images corresponding to the frame difference image to which the target minimum circumscribed rectangle belongs to obtain two subgraphs;
inputting the two subgraphs into a classification model for classification to obtain a first subgraph containing a forklift;
and determining the forklift in the first subgraph as an illegal forklift.
5. The method of claim 4, wherein prior to the step of determining the forklift in the first sub-graph as an offending forklift, further comprising:
according to the monitoring time in the image of the first sub-image, video clips with second preset time length before and after the monitoring time are called;
acquiring two images of any adjacent frame in the video segment, repeating steps S101 to S104, and judging whether the distance between the center point of the target minimum external rectangle and the two images is larger than a third preset threshold value or not for the target minimum external rectangle with the width-to-length ratio smaller than a first preset threshold value;
and if the distance is greater than a third preset threshold value, determining the forklift in the first subgraph as an illegal forklift.
6. The method for monitoring forklift violations based on images of claim 4, in which the classification model is a deep learning model effect Net.
7. A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a method as claimed in any one of claims 1 to 6.
8. A terminal device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any one of claims 1 to 6 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310551166.1A CN116503811A (en) | 2023-05-16 | 2023-05-16 | Image-based forklift violation monitoring method, medium and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310551166.1A CN116503811A (en) | 2023-05-16 | 2023-05-16 | Image-based forklift violation monitoring method, medium and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116503811A true CN116503811A (en) | 2023-07-28 |
Family
ID=87321491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310551166.1A Pending CN116503811A (en) | 2023-05-16 | 2023-05-16 | Image-based forklift violation monitoring method, medium and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503811A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116778438A (en) * | 2023-08-17 | 2023-09-19 | 苏州市吴江区盛泽镇人民政府 | Illegal forklift detection method and system based on large language model |
-
2023
- 2023-05-16 CN CN202310551166.1A patent/CN116503811A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116778438A (en) * | 2023-08-17 | 2023-09-19 | 苏州市吴江区盛泽镇人民政府 | Illegal forklift detection method and system based on large language model |
| CN116778438B (en) * | 2023-08-17 | 2023-11-14 | 苏州市吴江区盛泽镇人民政府 | Illegal forklift detection method and system based on large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9355308B2 (en) | Auditing video analytics through essence generation | |
| US8305440B2 (en) | Stationary object detection using multi-mode background modelling | |
| CN114119676B (en) | Target detection tracking identification method and system based on multi-feature information fusion | |
| CN116503811A (en) | Image-based forklift violation monitoring method, medium and device | |
| CN110083740B (en) | Video fingerprint extraction and video retrieval method, device, terminal and storage medium | |
| CN111783744A (en) | Operation site safety protection detection method and device | |
| EP2357615B1 (en) | Video processing | |
| CN112348791A (en) | Intelligent scrap steel detecting and judging method, system, medium and terminal based on machine vision | |
| CN110619308A (en) | Aisle sundry detection method, device, system and equipment | |
| CN109508621A (en) | Loading hatch method for monitoring state, device, equipment and its storage medium | |
| CN115497169A (en) | Warehouse operation behavior identification method, device and equipment | |
| Yedla et al. | Real-time scene change detection with object detection for automated stock verification | |
| CN111985269A (en) | Detection model construction method, detection device, server and medium | |
| CN116091450A (en) | Obstacle detection method, obstacle detection device, obstacle detection equipment, obstacle detection medium and obstacle detection product | |
| KR101848367B1 (en) | metadata-based video surveillance method using suspective video classification based on motion vector and DCT coefficients | |
| CN111666916B (en) | Kitchen violation identification method based on self-learning technology | |
| CN113610854B (en) | Cable defect detection method, terminal device and computer storage medium | |
| CN114842223A (en) | Method and device for identifying warehouse entry and exit and computer readable storage medium | |
| CN115082832A (en) | Information identification method, device and storage medium | |
| Li et al. | Computer vision based conveyor belt congestion recognition in logistics industrial parks | |
| CN116503812A (en) | Image-based express delivery and cargo throwing monitoring method, medium and device | |
| US11798284B2 (en) | System and method for rough handling recognition in a distribution center via a robust visual solution | |
| CN115937770A (en) | Garbage dumping behavior detection algorithm under outdoor scene | |
| CN117911943A (en) | Method, system and equipment for detecting operation state of coal conveying belt of intelligent power plant | |
| CN115294559A (en) | License plate state detection method and device and electronic equipment |
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 |