CN115457387A - Special scene early warning shielding method and device, electronic equipment and storage medium - Google Patents
Special scene early warning shielding method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115457387A CN115457387A CN202211039365.6A CN202211039365A CN115457387A CN 115457387 A CN115457387 A CN 115457387A CN 202211039365 A CN202211039365 A CN 202211039365A CN 115457387 A CN115457387 A CN 115457387A
- Authority
- CN
- China
- Prior art keywords
- identified
- image
- special scene
- fire
- determining
- 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 40
- 230000009466 transformation Effects 0.000 claims abstract description 11
- 238000012423 maintenance Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 14
- 230000000873 masking effect Effects 0.000 claims description 7
- 230000002457 bidirectional effect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 239000000779 smoke Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 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
- 231100000862 numbness Toxicity 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a special scene early warning shielding method, a special scene early warning shielding device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a fire image to be identified and a special scene reference image; determining a matching feature point between the fire image to be identified and the special scene reference image by adopting a preset scale invariant feature transformation algorithm, and determining a Housdov distance between the fire image to be identified and the special scene reference image according to the matching feature point; judging the size relationship between the Hausdorff distance and a preset threshold value; and if the Hausdorff distance is smaller than the preset threshold value, determining that the fire image to be identified is a special scene image, and starting a fire early warning shielding program. The invention solves the technical problem that repeated alarm is frequently received in special scenes such as fire operation, fire drill, facility maintenance and the like in the prior art.
Description
Technical Field
The invention relates to the technical field of fire-fighting early warning, in particular to a special scene early warning shielding method and device, electronic equipment and a storage medium.
Background
The automatic fire alarm converts the physical quantities of smoke, heat, light radiation and the like generated by combustion into electric signals through a fire detector for sensing temperature, smoke, light and the like at the initial stage of a fire, transmits the electric signals to a fire alarm controller, simultaneously displays the position of the fire and records the time of the fire. The automatic fire alarm system plays an important role in building fire prevention.
Along with the wide application of urban fire-fighting remote monitoring system, the problem that the fire-fighting remote monitoring system receives the alarm of the automatic fire alarm system also appears: when special scenes such as fire operation, fire drilling, regular facility maintenance and the like occur, the urban fire-fighting remote monitoring system can frequently receive repeated alarm in a certain area of a fire-fighting host in a short time, and needs related personnel to make a call to determine the real situation of the site and continuously perform alarm handling operation. In the repeated alarm processing process, the numbness of the alarm information by related personnel is easily caused, and other real alarm conditions can be determined as false alarms, so that unnecessary accidents and loss are caused.
Therefore, it is very necessary to research a special scene early warning shielding method by combining the internet of things and the artificial intelligence technology.
Disclosure of Invention
The invention aims to overcome the technical defects, provides a special scene early warning shielding method, a special scene early warning shielding device, electronic equipment and a storage medium, and solves the technical problem that repeated warning is frequently received in special scenes such as fire operation, fire drill, facility maintenance and the like in the prior art.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a special scene early warning shielding method, including:
acquiring a fire image to be identified and a special scene reference image;
determining a matching feature point between the fire image to be identified and the special scene reference image by adopting a preset scale invariant feature transformation algorithm, and determining a Housdov distance between the fire image to be identified and the special scene reference image according to the matching feature point;
judging the size relationship between the Hausdorff distance and a preset threshold value;
and if the Hausdorff distance is smaller than the preset threshold value, determining that the fire image to be identified is a special scene image, and starting a fire early warning shielding program.
In some embodiments, the determining the hausdorff distance between the fire image to be identified and the special scene reference image by using a preset scale-invariant feature transform algorithm includes:
determining the characteristic points to be identified of the fire images to be identified and the reference characteristic points of the reference images of the special scenes by adopting a preset Gaussian differential function, wherein the characteristic points to be identified and the reference characteristic points are matched with each other pairwise;
and determining the bidirectional Housdov distance between the feature point to be identified and the reference feature point.
In some embodiments, the determining the characteristic points to be identified of the fire image to be identified and the reference characteristic points of the special scene reference image based on the preset gaussian differential function includes:
extracting characteristic points to be identified of the fire image to be identified and reference characteristic points of a special scene reference image based on a preset Gaussian differential function;
determining the positions of the feature points to be identified and the reference feature points, and the direction of the feature points to be identified and the direction of the reference feature points;
constructing a feature vector to be identified based on the position of the feature point to be identified and the direction of the feature to be identified;
constructing a reference feature vector based on the position of the reference feature point and the reference feature direction;
and determining the feature points to be identified and the reference feature points which are matched with each other pairwise according to the feature vectors to be identified and the reference feature vectors.
In some embodiments, the gaussian derivative function may be expressed by the following equation:
where σ is a parameter related to size, x and y represent coordinates of image information pixels, and m and n are parameters related to feature points.
In some embodiments, the determining the bidirectional hausdorff distance between the feature point to be identified and the reference feature point includes:
constructing an identification set of the feature points to be identified and a reference set of reference feature points;
traversing all the feature points to be identified in the identification set, calculating the distances between the feature points to be identified and all the feature points in the reference set, determining corresponding first shortest distances, and constructing a first target set of the plurality of first shortest distances;
traversing the reference characteristic points in the reference set, calculating the distances between the reference characteristic points and all the characteristic points in the identification set, determining corresponding second shortest distances, and constructing a second target set of the plurality of second shortest distances;
determining a first one-way Hausdorff distance according to the first target set, and determining a second one-way Hausdorff distance according to the second target set;
and determining the larger one of the first one-way Hausdorff distance and the second one-way Hausdorff distance as the two-way Hausdorff distance.
In some embodiments, the acquiring a special scene reference image includes:
acquiring original images under a plurality of different scenes, wherein the different scenes comprise a fire operation scene, a fire drill and a regular facility maintenance;
and constructing the plurality of original images into a special scene reference image set.
In some embodiments, the determining, based on the scale-invariant feature transform algorithm, a difference value between the fire image to be recognized and the special scene reference image further includes determining a difference value between the fire image to be recognized and each original image in the special scene reference image set.
In a second aspect, the present invention further provides a special scene early warning shielding device, including:
the acquisition module is used for acquiring a fire image to be identified and a special scene reference image set;
the Hausdorff distance determining module is used for determining matching feature points between the fire image to be identified and the special scene reference image by adopting a preset scale invariant feature transformation algorithm, and determining the Hausdorff distance between the fire image to be identified and the special scene reference image according to the matching feature points;
the judging module is used for judging the size relation between the Hausdorff distance and a threshold value;
and the target module is used for determining that the fire image to be identified is a special scene image and starting a fire early warning shielding program if the Hausdorff distance is smaller than the threshold value.
In a third aspect, the present invention further provides an electronic device, including: a processor and a memory;
the memory has stored thereon a computer readable program executable by the processor;
the processor, when executing the computer readable program, implements the steps in the special scene early warning masking method as described above.
In a fourth aspect, the present invention also provides a computer-readable storage medium storing one or more programs, which are executable by one or more processors to implement the steps of the special scene early warning masking method as described above.
Compared with the prior art, the special scene early warning shielding method, the special scene early warning shielding device, the electronic equipment and the storage medium provided by the invention firstly determine the special scene which does not need fire alarm early warning, acquire the special scene reference image, acquire the fire image to be recognized, then determine the matching feature point between the fire image to be recognized and the special scene reference image by adopting a preset scale invariant feature transformation algorithm, determine the Hausdorff distance between the fire image to be recognized and the special scene reference image by matching the feature point, finally determine the similarity between the fire image to be recognized and the special scene reference image by comparing the size relationship between the Hausdorff distance and a preset threshold value, and determine whether the actual scene corresponding to the fire image to be recognized is the special scene or not by the size of the similarity, wherein when the Hausdorff distance is smaller than the preset threshold value, the similarity between the fire image to be recognized and the special scene reference image is maximum, namely, the actual application corresponding to the fire image to be recognized is possible to be a fire operation, equipment maintenance and other non-fire scene shielding programs, so that the system can not receive the fire alarm information immediately.
Drawings
FIG. 1 is a flowchart of an embodiment of a special-scene early-warning shielding method provided by the present invention;
fig. 2 is a flowchart of an embodiment of step S102 in the special scene early warning shielding method provided in the present invention;
fig. 3 is a flowchart of an embodiment of step S201 in the special scene early warning shielding method provided in the present invention;
fig. 4 is a flowchart of an embodiment of step S202 in the special scene early warning shielding method provided in the present invention;
FIG. 5 is a schematic diagram of an embodiment of a special case warning shield apparatus provided in the present invention;
fig. 6 is a schematic operating environment diagram of an embodiment of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
The special scene early warning shielding method, the special scene early warning shielding device, the electronic equipment and the storage medium can be applied to various industries and places, such as large-scale warehouses, office buildings, shops, hotels, streets and the like, and a fire early warning system can monitor surrounding environmental conditions in real time to reject potential hazards; at present, the fire detector has different fire detection parameters, mainly including: the fire alarm system comprises detectors for sensing temperature, sensing light, sensing smoke, sensing gas, a composite type detector and the like, and a fire alarm system and a public monitoring system are connected together, so that fire can be timely and accurately found and early warned, and loss can be maximally reduced.
However, in some special situations such as fire-driving operation, equipment maintenance or fire drilling, fire early warning is not needed, and in these situations, if too frequent fire early warning occurs, the workers may be tired, the vigilance of the workers may be reduced, and the fire early warning work may not be facilitated. The method, apparatus, device or computer readable storage medium of the present invention may be integrated with the above system or may be relatively independent.
Fig. 1 is a flowchart of a special scene early warning shielding method according to an embodiment of the present invention, and referring to fig. 1, the special scene early warning shielding method includes:
s101, acquiring a fire image to be identified and a special scene reference image;
s102, determining matching feature points between the fire image to be identified and the special scene reference image by adopting a preset scale invariant feature transformation algorithm, and determining a Housdov distance between the fire image to be identified and the special scene reference image according to the matching feature points;
s103, judging the size relation between the Hausdorff distance and a preset threshold;
and S104, if the Hausdorff distance is smaller than the preset threshold value, determining that the fire image to be identified is a special scene image, and starting a fire early warning shielding program.
In the embodiment, a special scene which does not need fire alarm early warning is determined, image acquisition is carried out on the special scene to form a special scene reference image, a fire image to be identified is obtained, a preset scale-invariant feature transformation algorithm is adopted to determine matching feature points between the fire image to be identified and the special scene reference image, a Hausdorff distance between the fire image to be identified and the special scene reference image is determined through the matching feature points, finally, the similarity between the fire image to be identified and the special scene reference image is determined by comparing the size relationship between the Hausdorff distance and a preset threshold value, whether an actual scene corresponding to the image to be identified is the special scene or not is judged through the similarity, when the Hausdorff distance is smaller than the preset threshold value, the similarity between the fire image to be identified and the special scene reference image is the maximum, namely, the actual application scene corresponding to the fire image to be identified is possibly a non-fire scene such as fire operation, equipment maintenance and the like, and a shielding program is selected to be started, so that the system can not receive alarm information in the area any more.
In some embodiments, referring to fig. 2, the determining the matching feature points between the fire image to be identified and the special scene reference image by using a preset scale-invariant feature transformation algorithm includes:
s201, determining characteristic points to be recognized of the fire images to be recognized and reference characteristic points of reference images of special scenes by adopting a preset Gaussian differential function, wherein the characteristic points to be recognized and the reference characteristic points are matched with each other pairwise;
s202, determining the bidirectional Hausdorff distance between the feature point to be identified and the reference feature point.
In the embodiment, a to-be-identified feature point of a to-be-identified fire image and a reference feature point of a special scene reference image are extracted through an SIFT algorithm (i.e., a scale invariant feature transform algorithm), wherein the to-be-identified feature point is a feature point which can most embody an actual scene represented by the image on the to-be-identified fire image, that is, the to-be-identified feature point can visually reflect the similarity between the to-be-identified fire image and the special scene reference image, and the reference feature point is a feature point which can most embody an actual scene represented by the image on the special scene reference image; and calculating the bidirectional Hausdorf distance between the characteristic point to be identified and the reference characteristic point, reflecting the similarity between the fire image to be identified and the special scene reference image through the Hausdorf distance, and judging the fire condition of the fire position to be identified so as to guide the work of the fire alarm.
In some embodiments, referring to fig. 3, the determining the feature points to be identified of the fire image to be identified and the reference feature points of the reference image of the special scene based on the preset gaussian differential function includes:
s301, extracting characteristic points to be identified of the fire image to be identified and reference characteristic points of a special scene reference image based on a preset Gaussian differential function;
s302, determining the positions of the feature points to be identified and the reference feature points, and the direction of the feature points to be identified and the direction of the reference feature points;
s303, constructing a feature vector to be identified based on the position of the feature point to be identified and the direction of the feature to be identified;
s304, constructing a reference characteristic vector based on the position and the reference characteristic direction of the reference characteristic point;
s305, determining pairwise matched feature points to be identified and reference feature points according to the feature vectors to be identified and the reference feature vectors.
In the present embodiment, the feature points to be identified and the reference feature points are extracted in order to search for image positions on all scale spacesAnd identifying potential points of interest with scale and rotation invariance by a preset gaussian differential function, wherein the preset gaussian differential function can be expressed by the following formula:
where σ is a parameter related to size, x and y represent coordinates of pixels of image information, and m and n are parameters related to feature points, e.g., m and n may be randomly set parameter values, which meet the requirement of defining parameters of the gaussian differential function.
It should be noted that, at each candidate position, the positions and scales of the feature point to be identified and the reference feature point are determined by a fitting fine model, and then one or more directions are assigned to each feature point position based on the local gradient direction of the image;
further, according to the position and the direction of the feature point, a feature vector to be recognized and a reference feature vector are respectively constructed, and finally, the feature points in the feature vector to be recognized and the feature points in the reference feature vector are compared to find out a plurality of feature points to be recognized and reference feature points which are matched with each other pairwise.
In some embodiments, referring to fig. 4, the determining the bidirectional hausdorff distance between the feature point to be identified and the reference feature point includes:
s401, constructing an identification set of the feature points to be identified and a reference set of reference feature points;
s402, traversing all feature points to be identified in the identification set, calculating the distance between the feature points to be identified and all feature points in a reference set, determining corresponding first shortest distances, and constructing a first target set of the plurality of first shortest distances;
s403, traversing the reference feature points in the reference set, calculating the distances between the reference feature points and all the feature points in the identification set, determining corresponding second shortest distances, and constructing a second target set of the plurality of second shortest distances;
s404, determining a first one-way Hausdorff distance according to the first target set, and determining a second one-way Hausdorff distance according to the second target set;
s405, the larger one of the first one-way Hausdorff distance and the second one-way Hausdorff distance is determined to be the two-way Hausdorff distance.
In this embodiment, the identification set and the reference set are respectively constructed based on the feature points to be identified and the reference feature points that are matched with each other in pairs in the feature vector to be identified and the reference feature vector, specifically, the feature points to be identified in the identification set are points that can be matched with the reference feature points, and the reference feature points in the reference set are points that can be matched with the feature points to be identified.
In a specific embodiment, if the identification set is a = { a1, a2, \8230;, an }, and the reference set is B = { B1, B2, \8230;, bn }, then the process of determining the bidirectional hausdov distance is the following steps:
firstly, taking a point a1 in the set A, calculating the distance from the point a1 to all the points in the set B, and keeping the shortest distance d1;
then, traversing all points in the set A, and calculating d2, \8230;, dn;
then all the distances { d1, d2, \ 8230;, dn } are compared, and the longest distance dx, namely the one-way Hausdorff distance of A → B, is selected and is marked as h (A, B);
then according to the steps, calculating the one-way Hausdorff distance of B → A, and recording the one-way Hausdorff distance as h (B, A);
and finally, selecting the longest distance of h (A, B) and h (B, A), namely the bidirectional Hausdorff distance of the A, B set.
In some embodiments, the acquiring the special scene reference image further includes:
acquiring original images under a plurality of different scenes, wherein the different scenes comprise a fire operation scene, a fire drill and a regular facility maintenance;
and constructing the plurality of original images into a special scene reference image set.
In this embodiment, for different special scenes, including but not limited to fire work, equipment maintenance, or fire drill, corresponding sample images need to be collected to form a special scene reference image set, so as to avoid the situation of selection omission in the actual determination process.
In some embodiments, the determining, based on the scale-invariant feature transform algorithm, a difference value between the fire image to be identified and the special scene reference image further includes determining a difference value between the fire image to be identified and each original image in the special scene reference image set.
In the embodiment, similarity comparison is carried out on each picture in the fire image to be identified and the special scene reference image set until the most similar picture is found or comparison with all pictures is completed.
Based on the above-mentioned special scene early warning shielding method, the embodiment of the present invention further provides a special scene early warning shielding apparatus 500 accordingly, please refer to fig. 5, where the special scene early warning shielding apparatus 500 includes an obtaining module 510, a hausdov distance determining module 520, a judging module 530, and an object module 540.
An obtaining module 510, configured to obtain a fire image to be identified and a special scene reference image set;
a hausdorff distance determining module 520, configured to determine matching feature points between the fire image to be identified and the special scene reference image by using a preset scale invariant feature transformation algorithm, and determine a hausdorff distance between the fire image to be identified and the special scene reference image according to the matching feature points;
a judging module 530, configured to judge a size relationship between the hausdorff distance and a threshold;
and the target module 540 determines that the fire image to be identified is a special scene image if the hausdov distance is smaller than the threshold, and starts a fire early warning shielding program.
As shown in fig. 6, based on the special scene early warning shielding method, the invention further provides an electronic device, which may be a mobile terminal, a desktop computer, a notebook, a palmtop computer, a server, or other computing devices. The electronic device includes a processor 610, a memory 620, and a display 630. Fig. 6 shows only some of the components of the electronic device, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
The storage 620 may in some embodiments be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device. The memory 620 may also be an external storage device of the electronic device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the electronic device. Further, the memory 620 may also include both internal storage units of the electronic device and external storage devices. The memory 620 is used for storing application software installed in the electronic device and various data, such as program codes for installing the electronic device. The memory 620 may also be used to temporarily store data that has been output or is to be output. In an embodiment, the memory 620 stores a special scene early warning masking program 640, and the special scene early warning masking program 640 can be executed by the processor 610, so as to implement the special scene early warning masking method according to the embodiments of the present application.
The processor 610 may be a Central Processing Unit (CPU), microprocessor or other data Processing chip in some embodiments, and is configured to execute program codes stored in the memory 620 or process data, such as executing special scene warning masking methods.
The display 630 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch panel, or the like in some embodiments. The display 630 is used for displaying information on the special scene early warning shielding device and for displaying a visual user interface. The components 610-630 of the electronic device communicate with each other via a system bus.
Of course, it can be understood by those skilled in the art that all or part of the processes in the methods of the embodiments described above can be implemented by instructing relevant hardware (such as a processor, a controller, etc.) by a computer program, and the program can be stored in a computer-readable storage medium, and when executed, the program can include the processes of the embodiments of the methods described above. The storage medium may be a memory, a magnetic disk, an optical disk, etc.
The above-described embodiments of the present invention should not be construed as limiting the scope of the present invention. Any other corresponding changes and modifications made according to the technical idea of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A special scene early warning shielding method is characterized by comprising the following steps:
acquiring a fire image to be identified and a special scene reference image;
determining matching feature points between the fire image to be identified and the special scene reference image by adopting a preset scale invariant feature transformation algorithm, and determining a Housdov distance between the fire image to be identified and the special scene reference image according to the matching feature points;
judging the size relationship between the Hausdorff distance and a preset threshold value;
and if the Hausdorff distance is smaller than the preset threshold value, determining that the fire image to be identified is a special scene image, and starting a fire early warning shielding program.
2. The special scene early warning shielding method according to claim 1, wherein the determining matching feature points between the fire image to be recognized and the special scene reference image by using a preset scale invariant feature transformation algorithm comprises:
and determining the characteristic points to be identified of the fire image to be identified and the reference characteristic points of the reference image of the special scene by adopting a preset Gaussian differential function, wherein the characteristic points to be identified and the reference characteristic points are matched with each other pairwise.
3. The special scene early warning shielding method according to claim 2, wherein the determining the characteristic points to be identified of the fire images to be identified and the reference characteristic points of the special scene reference images by using a preset gaussian differential function comprises:
extracting the characteristic points to be identified of the fire image to be identified and the reference characteristic points of the reference image of the special scene based on a preset Gaussian differential function;
determining the positions of the feature points to be identified and the reference feature points, and the direction of the feature points to be identified and the direction of the reference feature points;
constructing a feature vector to be identified based on the position of the feature point to be identified and the direction of the feature to be identified;
constructing a reference feature vector based on the position of the reference feature point and the reference feature direction;
and determining pairwise matched feature points to be identified and reference feature points according to the feature vectors to be identified and the reference feature vectors.
4. The special scene early warning shielding method according to claim 3, wherein the Gaussian differential function can be expressed by the following formula:
where σ is a parameter related to the size, x and y represent coordinates of image information pixels, and m and n are parameters related to feature points.
5. The special scene early warning shielding method according to claim 2, wherein determining the Hausdorff distance between the fire image to be identified and the special scene reference image according to the matching feature points comprises:
constructing an identification set of the feature points to be identified and a reference set of reference feature points;
traversing all the feature points to be identified in the identification set, calculating the distances between the feature points to be identified and all the feature points in the reference set, determining corresponding first shortest distances, and constructing a first target set of the plurality of first shortest distances;
traversing the reference characteristic points in the reference set, calculating the distances between the reference characteristic points and all the characteristic points in the identification set, determining corresponding second shortest distances, and constructing a second target set of the plurality of second shortest distances;
determining a first one-way Hausdorff distance according to the first target set, and determining a second one-way Hausdorff distance according to the second target set;
and determining the larger one of the first one-way Hausdorff distance and the second one-way Hausdorff distance as the two-way Hausdorff distance.
6. The special scene early warning shielding method according to claim 1, wherein the obtaining of the special scene reference image further comprises:
acquiring original images under a plurality of different scenes, wherein the different scenes comprise a fire operation scene, a fire drill and a regular facility maintenance;
and constructing the plurality of original images into a special scene reference image set.
7. The special scene early warning shielding method according to claim 6, wherein the difference value between the fire image to be identified and the special scene reference image is determined based on a scale invariant feature transform algorithm, and further comprising determining the difference value between the fire image to be identified and each original image in the special scene reference image set.
8. The utility model provides a special scene early warning shield assembly which characterized in that includes:
the acquisition module is used for acquiring a fire image to be identified and a special scene reference image set;
the Hausdorff distance determining module is used for determining matching feature points between the fire image to be identified and the special scene reference image by adopting a preset scale invariant feature transformation algorithm, and determining the Hausdorff distance between the fire image to be identified and the special scene reference image according to the matching feature points;
the judging module is used for judging the size relation between the Hausdorff distance and a threshold value;
and the target module is used for determining that the fire image to be identified is a special scene image and starting a fire early warning shielding program if the Hausdorff distance is smaller than the threshold value.
9. An electronic device, comprising: a processor and a memory;
the memory has stored thereon a computer readable program executable by the processor;
the processor, when executing the computer readable program, implements the steps in the special scene early warning shielding method as described above.
10. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs, which are executable by one or more processors to implement the steps in the special scene early warning masking method as described above.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211039365.6A CN115457387A (en) | 2022-08-29 | 2022-08-29 | Special scene early warning shielding method and device, electronic equipment and storage medium |
| PCT/CN2022/119597 WO2024045229A1 (en) | 2022-08-29 | 2022-09-19 | Early-warning blocking method and apparatus for special scenario, and electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211039365.6A CN115457387A (en) | 2022-08-29 | 2022-08-29 | Special scene early warning shielding method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115457387A true CN115457387A (en) | 2022-12-09 |
Family
ID=84301112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211039365.6A Pending CN115457387A (en) | 2022-08-29 | 2022-08-29 | Special scene early warning shielding method and device, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115457387A (en) |
| WO (1) | WO2024045229A1 (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8483427B2 (en) * | 2010-09-28 | 2013-07-09 | Futurewei Technologies, Inc. | System and method for image authentication |
| JP7049983B2 (en) * | 2018-12-26 | 2022-04-07 | 株式会社日立製作所 | Object recognition device and object recognition method |
| JP7253573B2 (en) * | 2020-04-09 | 2023-04-06 | センスタイム インターナショナル ピーティーイー．リミテッド | Matching method, device, electronic device and computer readable storage medium |
| CN112446431B (en) * | 2020-11-27 | 2024-08-27 | 鹏城实验室 | Feature point extraction and matching method, network, device and computer storage medium |
| CN113486942A (en) * | 2021-06-30 | 2021-10-08 | 武汉理工光科股份有限公司 | Repeated fire alarm determination method and device, electronic equipment and storage medium |
| CN114119645B (en) * | 2021-11-25 | 2022-10-21 | 推想医疗科技股份有限公司 | Method, system, device and medium for determining image segmentation quality |
-
2022
- 2022-08-29 CN CN202211039365.6A patent/CN115457387A/en active Pending
- 2022-09-19 WO PCT/CN2022/119597 patent/WO2024045229A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024045229A1 (en) | 2024-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10937144B2 (en) | Pipe feature identification using pipe inspection data analysis | |
| US10839197B2 (en) | Monitoring system, monitoring camera, and management device | |
| US20160350583A1 (en) | Image search system and image search method | |
| US20140226857A1 (en) | Information processing system, information processing method and program | |
| CN112861673A (en) | False alarm removal early warning method and system for multi-target detection of surveillance video | |
| CN114005140B (en) | Personnel identification method, device, equipment, pedestrian monitoring system and storage medium | |
| US20240201835A1 (en) | Information processing apparatus, information processing method, and storage medium for person search | |
| CN115719436A (en) | Model training method, target detection method, device, equipment and storage medium | |
| CN113378836A (en) | Image recognition method, apparatus, device, medium, and program product | |
| CN114723972A (en) | Safety management and control method and safety management and control system based on data and image comparison | |
| Barlybayev et al. | Personal protective equipment detection using YOLOv8 architecture on object detection benchmark datasets: a comparative study | |
| CN113570622A (en) | Obstacle determination method and device, electronic equipment and storage medium | |
| CN113361420A (en) | Mine fire monitoring method, device and equipment based on robot and storage medium | |
| JP4292371B2 (en) | Mobile monitoring device | |
| CN114299366A (en) | Image detection method and device, electronic equipment and storage medium | |
| CN115457387A (en) | Special scene early warning shielding method and device, electronic equipment and storage medium | |
| JP7348575B2 (en) | Deterioration detection device, deterioration detection system, deterioration detection method, and program | |
| CN113505704A (en) | Image recognition personnel safety detection method, system, equipment and storage medium | |
| US20180144482A1 (en) | Behavior analysis apparatus and behavior analysis method | |
| CN112857746A (en) | Tracking method and device of lamplight detector, electronic equipment and storage medium | |
| CN112785658A (en) | Fire early warning method and device based on image processing | |
| CN112802288A (en) | Comprehensive alarm information pushing method and system, storage medium and computer equipment | |
| CN112766118A (en) | Object identification method, device, electronic equipment and medium | |
| CN115810132B (en) | Crack orientation identification method, device, equipment and storage medium | |
| CN113920460B (en) | Method, device, equipment and medium based on video scene matching algorithm |
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 |