CN113888750B - Distributed image signal processing system - Google Patents
Distributed image signal processing system Download PDFInfo
- Publication number
- CN113888750B CN113888750B CN202111191988.0A CN202111191988A CN113888750B CN 113888750 B CN113888750 B CN 113888750B CN 202111191988 A CN202111191988 A CN 202111191988A CN 113888750 B CN113888750 B CN 113888750B
- Authority
- CN
- China
- Prior art keywords
- image
- block
- minor
- type
- final
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 42
- 230000007246 mechanism Effects 0.000 claims abstract description 32
- 230000009182 swimming Effects 0.000 claims abstract description 26
- 238000003384 imaging method Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 238000005192 partition Methods 0.000 claims abstract description 4
- 238000005457 optimization Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 4
- 230000001960 triggered effect Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000037237 body shape Effects 0.000 claims description 2
- 206010013647 Drowning Diseases 0.000 abstract description 4
- 238000000034 method Methods 0.000 abstract description 4
- 238000006731 degradation reaction Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000006260 foam Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a distributed image signal processing system, comprising: the real-time fitting mechanism is used for fitting a plurality of externally expanded pixel points respectively corresponding to each edge pixel point of the first type block into an externally expanded image block of the first type block; a layout parsing device for performing the following for each first type partition: and when the number of pixel points forming a certain second type block in the external expansion image block corresponding to the first type block is larger than or equal to a set number threshold, judging that the minor corresponding to the first type block is currently in a safe state, otherwise, judging that the minor is currently in a dangerous state. By the method and the device, the dangerous scene without the swimming circle body around the minors can be identified in real time by adopting the minor imaging block outward expansion and a targeted overlapping amplitude detection mechanism of the minor imaging block and the swimming circle body imaging block, so that drowning accidents are avoided.
Description
Technical Field
The invention relates to the field of image processing, in particular to a distributed image signal processing system.
Background
In image processing, image coding compression techniques can reduce the amount of data (i.e., the number of bits) describing an image in order to save image transmission, processing time, and reduce the amount of memory occupied. The compression can be obtained without distortion or can be carried out under allowable distortion conditions. Coding is the most important method in compression technology, and it is the earliest and more mature technology in image processing technology.
The purpose of image enhancement and restoration is to improve the quality of an image, such as removing noise, improving the sharpness of an image, and the like. Image enhancement highlights interesting parts of the image, regardless of the reason for image degradation. If the high-frequency component of the image is strengthened, the outline of an object in the image is clear, and the details are obvious; such as emphasizing low frequency components may reduce the noise contribution in the image. The image restoration requires some understanding of the reason for image degradation, and generally, a "degradation model" should be established according to the degradation process, and then a certain filtering method is adopted to restore or reconstruct the original image
At present, for an immature adult of an indoor swimming lane, although the depth of a water body is limited, the possibility of drowning is easy to exist due to insufficient experience in panic, so that parents are generally required to accompany the immature adult and wear an effectively inflated swimming ring body, however, in playing or improper management of the parents, a dangerous scene that the swimming ring body does not exist around the immature adult is easy to cause.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a distributed image signal processing system which can adopt a mechanism of detecting the external expansion of the minor imaging blocks and the overlapping amplitude of the targeted minor imaging blocks and the swimming circle body imaging blocks to identify dangerous scenes without swimming circles around the minor in real time, thereby providing valuable reference data for subsequent emergency measures.
For this reason, the present invention needs to have at least the following three important points:
(1) judging whether a relatively close swimming circle body exists around the minor in the indoor lane picture by adopting a targeted image recognition mechanism so as to determine whether the minor is in a safe state;
(2) specifically, the geometric shape of the edge closed curve of the image block in which the minor is located in the indoor lane picture is scaled to obtain a shape with the most overlapping geometric shape part of the body type corresponding to the body type feature of the minor as a geometric shape to be compared, and when the ratio of the geometric shape overlapping part of the body type corresponding to the geometric shape to be compared and the body type feature of the minor occupying the whole geometric shape to be compared is greater than or equal to a set ratio threshold, the geometric shape of the edge closed curve of the image block in which the minor is located is judged to be matched with the geometric shape of the body type corresponding to the body type feature of the minor;
(3) and effectively expanding the image blocks of the minors in the indoor lane picture to provide a detected image space for detecting whether a relatively close swimming circle body exists around.
According to an aspect of the present invention, there is provided a distributed image signal processing system, the system including:
the network video recording device is arranged above the indoor swimming lane and used for executing video recording action triggered based on a network instruction on the indoor swimming lane so as to obtain a corresponding current video recording image;
the primary optimization device is connected with the network video recording device and used for executing inclination correction processing on the received current video recording image so as to obtain a corresponding primary optimization image;
the middle-level optimizing device is connected with the primary optimizing device and used for carrying out sharpening processing on the received primary optimized image by using image data in the horizontal direction so as to obtain a corresponding middle-level optimized image;
a final stage optimizing device connected with the intermediate stage optimizing device and used for executing bilateral filtering processing on the received intermediate stage optimizing image and corresponding final stage optimizing image;
a content recognition mechanism, connected to the final optimization device, for recognizing, in the final optimized image, an image patch in which each minor is located as a first type patch based on an imaging characteristic of the minor;
the ring body detection mechanism is connected with the final-stage optimization device and is used for detecting an image block where each swim ring is located in the final-stage optimization image based on the circular or elliptical geometric shape of each swim ring to serve as a second type block;
the block judgment mechanism is respectively connected with the content identification mechanism and the ring body detection mechanism and is used for executing the following operations on each first type block: acquiring each edge pixel point forming the first type block, and outwards expanding a plurality of pixel points of a certain number in the direction opposite to the central position of the first type block on each edge pixel point to acquire a plurality of outwards expanded pixel points corresponding to the edge pixel points;
the real-time fitting mechanism is connected with the block judging mechanism and is used for fitting a plurality of externally expanded pixel points respectively corresponding to each edge pixel point of the first type block into an externally expanded image block of the first type block;
the layout analysis device is respectively connected with the block judgment mechanism and the ring body detection mechanism and is used for executing the following operations on each first type block: when the number of pixel points forming a certain second type block in the external expansion image block corresponding to the first type block is larger than or equal to a set number threshold, judging that the minor corresponding to the first type block is in a safe state currently;
wherein the layout analysis device is further configured to perform the following for each first type partition: and when the number of pixel points forming a certain second type block does not exist in the external expansion image block corresponding to the first type block is larger than or equal to a set number threshold, judging that the minor corresponding to the first type block is in a dangerous state currently.
Drawings
Embodiments of the invention will now be described with reference to the accompanying drawings, in which:
fig. 1 is a schematic view showing an outline configuration of a swim ring to which a distributed image signal processing system is applied according to an embodiment of the present invention.
Detailed Description
An embodiment of a distributed image signal processing system of the present invention will be described in detail below with reference to the accompanying drawings.
Swim rings are similar to life buoys and are used in water. When air is blown, the swim ring has buoyancy. The inside is all air. The waist sleeve is sleeved on the waist, and then the user jumps down to get the water. The swim ring can be used to assist in learning swimming.
The foam (swimming aid) must look around it relatively intact without damaging it, which is dangerous if such a foam lifebuoy cannot be used. According to the relevant regulations, the inflatable toy swimming ring sold in the market needs to be marked with safety prompting characters such as 'non-lifesaving equipment, needing to be used by children under adult monitoring' and the like at a striking position. Attention must be paid to viewing the logo, and tens of millions of people do not need to purchase the product of 'three nothing'. Meanwhile, the invoice should be requested and stored by attention when purchasing. To avoid accidents, all inflatable swim rings are not inflated excessively or with high pressure gas. It cannot contact sharp objects during carrying or inflation. Not to be used in deep sea and torrent places. If the swimming ring is placed for too long time, the phenomenon of slow deflation of the swimming ring occurs, so that the swimming ring needs to be inflated at any time. The expert thinks that most of the swimming rings made of the rubber inner tubes of the automobile are rough in texture, long and hard air valves, easily hurt the skin and are not suitable for being used as the swimming rings.
At present, for an immature adult of an indoor swimming lane, although the depth of a water body is limited, the possibility of drowning is easy to exist due to insufficient experience in panic, so that parents are generally required to accompany the immature adult and wear an effectively inflated swimming ring body, however, in playing or improper management of the parents, a dangerous scene that the swimming ring body does not exist around the immature adult is easy to cause.
In order to overcome the defects, the invention builds a distributed image signal processing system, and can effectively solve the corresponding technical problem.
Fig. 1 is a schematic view showing an outline configuration of a swim ring to which a distributed image signal processing system is applied according to an embodiment of the present invention.
A distributed image signal processing system shown according to an embodiment of the present invention includes:
the network video recording device is arranged above the indoor swimming lane and used for executing video recording action triggered based on a network instruction on the indoor swimming lane so as to obtain a corresponding current video recording image;
the primary optimization device is connected with the network video recording device and used for executing inclination correction processing on the received current video recording image so as to obtain a corresponding primary optimization image;
the middle-level optimizing device is connected with the primary optimizing device and used for carrying out sharpening processing on the received primary optimized image by using image data in the horizontal direction so as to obtain a corresponding middle-level optimized image;
a final stage optimizing device connected with the intermediate stage optimizing device and used for executing bilateral filtering processing on the received intermediate stage optimizing image and corresponding final stage optimizing image;
a content recognition mechanism, connected to the final optimization device, for recognizing, in the final optimized image, an image patch in which each minor is located as a first type patch based on an imaging characteristic of the minor;
the ring body detection mechanism is connected with the final-stage optimization device and is used for detecting an image block where each swim ring is located in the final-stage optimization image based on the circular or elliptical geometric shape of each swim ring to serve as a second type block;
the block judgment mechanism is respectively connected with the content identification mechanism and the ring body detection mechanism and is used for executing the following operations on each first type block: acquiring each edge pixel point forming the first type block, and outwards expanding a plurality of pixel points of a certain number in the direction opposite to the central position of the first type block on each edge pixel point to acquire a plurality of outwards expanded pixel points corresponding to the edge pixel points;
the real-time fitting mechanism is connected with the block judging mechanism and is used for fitting a plurality of externally expanded pixel points respectively corresponding to each edge pixel point of the first type block into an externally expanded image block of the first type block;
the layout analysis device is respectively connected with the block judgment mechanism and the ring body detection mechanism and is used for executing the following operations on each first type block: when the number of pixel points forming a certain second type block in the external expansion image block corresponding to the first type block is larger than or equal to a set number threshold, judging that the minor corresponding to the first type block is in a safe state currently;
wherein the layout analysis device is further configured to perform the following for each first type partition: and when the number of pixel points forming a certain second type block does not exist in the external expansion image block corresponding to the first type block is larger than or equal to a set number threshold, judging that the minor corresponding to the first type block is in a dangerous state currently.
Next, a detailed description of the distributed image signal processing system according to the present invention will be further continued.
In the distributed image signal processing system:
identifying in the final-stage-optimized image the image patch in which each minor is located based on the imaging characteristics of the minor comprises: the imaging characteristic of the minor is a body shape feature of the minor of the imaging characteristic of the minor.
In the distributed image signal processing system:
identifying in the final-stage-optimized image the image patch in which each minor is located based on the imaging characteristics of the minor comprises: and when an image block matched with the body type characteristics of the minor is identified in the final-stage optimized image, taking the identified image block as an image block where the minor is located.
In the distributed image signal processing system:
when an image block matching with the body type feature of the minor is identified in the final optimized image, taking the identified image block as an image block in which the minor is located comprises: the geometric shape of the edge closed curve of the identified image block is matched with the geometric shape of the body type corresponding to the body type characteristics of the minor.
In the distributed image signal processing system:
the matching of the geometric shape of the edge closed curve of the identified image block with the geometric shape of the body type corresponding to the body type characteristics of the minor comprises the following steps: and scaling the geometric shapes of the edge closed curves of the identified image blocks to obtain the shapes with the most overlapped geometric shapes of the body types corresponding to the body type characteristics of the minors as the geometric shapes to be compared.
In the distributed image signal processing system:
the matching of the geometry of the edge closed curve of the identified image block with the geometry of the body type corresponding to the body type features of the minor further comprises: and when the proportion of the geometric overlapping part of the geometric shape to be compared and the geometric shape of the body type corresponding to the body type feature of the minor occupies the whole geometric shape to be compared is larger than or equal to a set proportion threshold value, judging that the geometric shape of the edge closed curve of the identified image block is matched with the geometric shape of the body type corresponding to the body type feature of the minor.
In the distributed image signal processing system:
the network video recording device comprises a network transceiving interface, a video recording execution component, an optical component and a supporting component, wherein the video recording execution component is an image sensor.
In the distributed image signal processing system:
in the network video recording device, the network transmission/reception interface, the video recording execution section, and the optical section are all provided on the support section.
In the distributed image signal processing system:
in the network video recording device, the video recording execution component is connected with the network transceiving interface and is used for being triggered to carry out video recording operation when receiving a video recording starting instruction.
In the distributed image signal processing system:
in the network video recording device, the video recording execution component is further configured to stop the video recording operation when receiving the video recording stop instruction;
wherein, in the network video recording device, the optical part is disposed in front of the video recording execution part and includes an optical lens.
In addition, in the distributed image signal processing system, the matching of the geometry of the edge closed curve of the identified image patch with the geometry of the body type corresponding to the body type feature of the minor further comprises: and when the proportion of the geometric overlapping part of the geometric shape to be compared and the geometric shape of the body type corresponding to the body type feature of the minor occupies the whole geometric shape to be compared is smaller than the set proportion threshold, judging that the geometric shape of the edge closed curve of the identified image block is not matched with the geometric shape of the body type corresponding to the body type feature of the minor.
By adopting the distributed image signal processing system, aiming at the technical problem that the separation of the minor and the swim ring body is difficult to identify in the prior art, the minor imaging block extension and the targeted overlapping amplitude detection mechanism of the minor imaging block and the swim ring body imaging block can be adopted to identify the dangerous scene without the swim ring body around the minor in real time, thereby avoiding drowning accidents.
The invention has been described in considerable detail, so that various alterations and modifications will become apparent to others skilled in the art upon the reading and understanding of this specification. All such changes and modifications are intended to be included herein within the scope of the present invention and protected by the following claims.
Claims (6)
1. A distributed image signal processing system, the system comprising:
the network video recording device is arranged above the indoor swimming lane and used for executing video recording action triggered based on a network instruction on the indoor swimming lane so as to obtain a corresponding current video recording image;
the primary optimization device is connected with the network video recording device and used for executing inclination correction processing on the received current video recording image so as to obtain a corresponding primary optimization image;
the middle-level optimizing device is connected with the primary optimizing device and used for carrying out sharpening processing on the received primary optimized image by using image data in the horizontal direction so as to obtain a corresponding middle-level optimized image;
a final-stage optimizing device connected with the intermediate-stage optimizing device and used for executing bilateral filtering processing on the received intermediate-stage optimizing image to obtain a corresponding final-stage optimizing image;
a content recognition mechanism, connected to the final optimization device, for recognizing, in the final optimized image, an image patch in which each minor is located as a first type patch based on an imaging characteristic of the minor;
the ring body detection mechanism is connected with the final-stage optimization device and is used for detecting an image block where each swim ring is located in the final-stage optimization image based on the circular or elliptical geometric shape of each swim ring to serve as a second type block;
the block judgment mechanism is respectively connected with the content identification mechanism and the ring body detection mechanism and is used for executing the following operations on each first type block: acquiring each edge pixel point forming the first type block, and outwards expanding a plurality of pixel points of a certain number in the direction opposite to the central position of the first type block on each edge pixel point to acquire a plurality of outwards expanded pixel points corresponding to the edge pixel points;
the real-time fitting mechanism is connected with the block judging mechanism and is used for fitting a plurality of externally expanded pixel points respectively corresponding to each edge pixel point of the first type block into an externally expanded image block of the first type block;
the layout analysis device is respectively connected with the block judgment mechanism and the ring body detection mechanism and is used for executing the following operations on each first type block: when the number of pixel points forming a certain second type block in the external expansion image block corresponding to the first type block is larger than or equal to a set number threshold, judging that the minor corresponding to the first type block is in a safe state currently;
wherein the layout analysis device is further configured to perform the following for each first type partition: and when the number of pixel points forming a certain second type block does not exist in the external expansion image block corresponding to the first type block is larger than or equal to a set number threshold, judging that the minor corresponding to the first type block is in a dangerous state currently.
2. The distributed image signal processing system of claim 1, wherein:
identifying in the final-stage-optimized image the image patch in which each minor is located based on the imaging characteristics of the minor comprises: the imaging characteristic of the minor is a body shape feature of the minor of the imaging characteristic of the minor.
3. The distributed image signal processing system of claim 2, wherein:
identifying in the final-stage-optimized image the image patch in which each minor is located based on the imaging characteristics of the minor comprises: and when an image block matched with the body type characteristics of the minor is identified in the final-stage optimized image, taking the identified image block as an image block where the minor is located.
4. The distributed image signal processing system of claim 3, wherein:
when an image block matching with the body type feature of the minor is identified in the final optimized image, taking the identified image block as an image block in which the minor is located comprises: the geometric shape of the edge closed curve of the identified image block is matched with the geometric shape of the body type corresponding to the body type characteristics of the minor.
5. The distributed image signal processing system of claim 4, wherein:
the matching of the geometric shape of the edge closed curve of the identified image block with the geometric shape of the body type corresponding to the body type characteristics of the minor comprises the following steps: and scaling the geometric shapes of the edge closed curves of the identified image blocks to obtain the shapes with the most overlapped geometric shapes of the body types corresponding to the body type characteristics of the minors as the geometric shapes to be compared.
6. The distributed image signal processing system of claim 5, wherein:
the matching of the geometry of the edge closed curve of the identified image block with the geometry of the body type corresponding to the body type features of the minor further comprises: and when the proportion of the geometric overlapping part of the geometric shape to be compared and the geometric shape of the body type corresponding to the body type feature of the minor occupies the whole geometric shape to be compared is larger than or equal to a set proportion threshold value, judging that the geometric shape of the edge closed curve of the identified image block is matched with the geometric shape of the body type corresponding to the body type feature of the minor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111191988.0A CN113888750B (en) | 2021-10-13 | 2021-10-13 | Distributed image signal processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111191988.0A CN113888750B (en) | 2021-10-13 | 2021-10-13 | Distributed image signal processing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113888750A CN113888750A (en) | 2022-01-04 |
| CN113888750B true CN113888750B (en) | 2022-04-15 |
Family
ID=79002657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111191988.0A Active CN113888750B (en) | 2021-10-13 | 2021-10-13 | Distributed image signal processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113888750B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2108435A (en) * | 1981-10-30 | 1983-05-18 | Maertin Klaus P H | Floating seat |
| CN201172480Y (en) * | 2007-12-05 | 2008-12-31 | 金承铉 | Baby swim ring |
| CN109166011A (en) * | 2018-09-11 | 2019-01-08 | 锐马（福建）电气制造有限公司 | A kind of water life jacket wearing management method and system |
| CN210083501U (en) * | 2019-05-05 | 2020-02-18 | 南京信息工程大学 | Outdoor children's water wing of suggestion safety information |
| CN113095143A (en) * | 2021-03-15 | 2021-07-09 | 刘鹏鹏 | Signal equipment arrangement state recognition system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10789826B2 (en) * | 2018-10-12 | 2020-09-29 | International Business Machines Corporation | Real-time safety detection and alerting |
-
2021
- 2021-10-13 CN CN202111191988.0A patent/CN113888750B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2108435A (en) * | 1981-10-30 | 1983-05-18 | Maertin Klaus P H | Floating seat |
| CN201172480Y (en) * | 2007-12-05 | 2008-12-31 | 金承铉 | Baby swim ring |
| CN109166011A (en) * | 2018-09-11 | 2019-01-08 | 锐马（福建）电气制造有限公司 | A kind of water life jacket wearing management method and system |
| CN210083501U (en) * | 2019-05-05 | 2020-02-18 | 南京信息工程大学 | Outdoor children's water wing of suggestion safety information |
| CN113095143A (en) * | 2021-03-15 | 2021-07-09 | 刘鹏鹏 | Signal equipment arrangement state recognition system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113888750A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| LU102284B1 (en) | Method and system for detecting insulator defect based on zero-shot learning | |
| CN111598066A (en) | Helmet wearing identification method based on cascade prediction | |
| KR101463085B1 (en) | Method and apparatus for detecting objects of interest in soccer video by color segmentation and shape analysis | |
| CN103119625B (en) | Video character separation method and device | |
| CN113888750B (en) | Distributed image signal processing system | |
| CN111768401A (en) | Rapid grading method for freshness of iced pomfret based on deep learning | |
| CN103093443B (en) | Based on the image salt-pepper noise adaptive filter method of GA-BP neural network | |
| CN112733929A (en) | Improved method for detecting small target and shielded target of Yolo underwater image | |
| CN111223034A (en) | High-capacity printing/shooting resistant blind watermark system and method based on deep learning | |
| CN109858438B (en) | Lane line detection method based on model fitting | |
| CN110009621B (en) | Tamper video detection method, tamper video detection device, tamper video detection equipment and readable storage medium | |
| CN113569756A (en) | Abnormal behavior detection and positioning method, system, terminal equipment and readable storage medium | |
| CN111477219A (en) | Keyword distinguishing method and device, electronic equipment and readable storage medium | |
| CN108109124A (en) | Indefinite position picture watermark restorative procedure based on deep learning | |
| CN111428696A (en) | Intelligent abnormity detection emergency rescue method, device and system | |
| CN111008608A (en) | Night vehicle detection method based on deep learning | |
| KR101523765B1 (en) | Enhanced Method for Detecting Iris from Smartphone Images in Real-Time | |
| CN114821452A (en) | Colored drawing train number identification method, system and medium | |
| CN107944393B (en) | Human face nose tip positioning method | |
| CN104200194A (en) | Face recognition method | |
| CN106254723A (en) | A kind of method of real-time monitoring video noise interference | |
| US11954917B2 (en) | Method of segmenting abnormal robust for complex autonomous driving scenes and system thereof | |
| CN114612936B (en) | Non-supervision abnormal behavior detection method based on background suppression | |
| Lu et al. | Image coding based on classified side-match vector quantization | |
| CN111557653A (en) | Portable self-rescue device, and swimmer protection method, equipment and system based on device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |