CN113989692A - Wearing scene recognition system and method based on channel analysis - Google Patents
Wearing scene recognition system and method based on channel analysis Download PDFInfo
- Publication number
- CN113989692A CN113989692A CN202111061440.4A CN202111061440A CN113989692A CN 113989692 A CN113989692 A CN 113989692A CN 202111061440 A CN202111061440 A CN 202111061440A CN 113989692 A CN113989692 A CN 113989692A
- Authority
- CN
- China
- Prior art keywords
- picture
- target
- human body
- pixel points
- target imaging
- 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.)
- Withdrawn
Links
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a wearing scene recognition system based on channel analysis, which comprises: the intelligent recording mechanism is arranged on the shore and comprises steering equipment, a camera shooting part, vector recognition equipment and picture analysis equipment, wherein the camera shooting part is used for executing recording operation of a water surface environment in a direction deviating from the shore; and the integral identification device is connected with the content judgment device and is used for taking the ship body target corresponding to the target imaging area as a wearing invalid ship body to highlight in the sequence mapping picture when the wearing invalid human body target exists in a certain target imaging area. The invention also relates to a wearing scene identification method based on the channel analysis. By the aid of the method, the multiple near ship bodies close to the shore can be simultaneously subjected to on-site identification on whether each human body effectively wears the life jacket or not in a targeted electronic detection mode, and accordingly synchronous and effective safety monitoring on the multiple ship bodies can be completed.
Description
Technical Field
The invention relates to the field of color channel analysis, in particular to a wearing scene recognition system and method based on channel analysis.
Background
The RGB space is the most common model in life, and most of tv sets, CRT displays of computers, and the like use this model. Any color in nature can be formed by mixing red, green and blue lights, and most of colors seen by people in real life are mixed colors.
The RGB color space is based on three basic colors of R (Red), G (Green) and B (Blue) and is superposed to different degrees to generate rich and wide colors, so the RGB color space is commonly called a three-primary-color mode. There are an infinite number of different colors in nature, and the human eye can only distinguish a limited number of different colors, and the RGB pattern can represent more than one thousand, six hundred and ten thousand different colors, which are very close to the colors of nature seen by the human eye, and is also called a natural color pattern. Red, green and blue represent three basic colors in the visible spectrum or three primary colors, each of which is classified into 256 levels according to its brightness. When the three primary colors of the color lights overlap, various intermediate colors can be generated due to different color mixing ratios, and for example, the three primary colors are added to generate white. The RGB scheme is an additive color process. The basis of screen display is the RGB model, which cannot be used to generate various colors for color prints, and therefore, RGB model is commonly used for video, multimedia and web page design.
At present, an artificial eye detection mode or an electronic detection mode aiming at a single ship body is generally adopted in a detection mode of whether a plurality of ship body executors effectively wear the life jacket on the water surface, although the coverage of the artificial eye detection mode is wide, the artificial eye detection mode can simultaneously detect a plurality of ship bodies, the detection precision and the speed cannot meet the requirements, and although the precision of the electronic detection mode is reliable, the detection surface is narrow, and an independent electronic detection system needs to be arranged for each ship body.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a wearing scene recognition system and method based on channel analysis, which can adopt a targeted electronic detection mode to simultaneously carry out on-site recognition on whether each human body effectively wears the life jacket or not on a plurality of near ship bodies close to the bank, thereby simultaneously meeting the requirements of detection speed and detection precision.
Compared with the prior art, the invention has the following two prominent substantive characteristics:
(1) the intelligent shooting mechanism with a customized structure comprising steering equipment, a shooting component, vector recognition equipment and picture analysis equipment is arranged on the shore and used for keeping a nearest ship body target as a collection operation of a viewpoint, so that a high-quality picture is provided for subsequent recognition;
(2) and judging whether the corresponding human body target effectively wears the survival suit or not according to the red channel value distribution state of each human body imaging area in each ship body target in the lightest depth of field range, thereby improving the efficiency and precision of the inspection of the survival suit.
According to an aspect of the present invention, there is provided a wearing scene recognition system based on channel analysis, the system including:
the intelligent shooting mechanism is arranged on the shore and comprises a steering device, a shooting part, a vector recognition device and a picture analysis device, wherein the shooting part is used for executing the shooting operation of a water surface environment in the direction deviating from the shore so as to obtain a water surface shooting picture, the picture analysis device is connected with the shooting part and is used for detecting each hull target in the water surface shooting picture and the depth of field corresponding to each hull target, the vector recognition device is connected with the picture analysis device and is used for converting the corresponding displacement and target direction based on the distance and direction of the hull target with the shallowest depth of field deviating from the midpoint position of the water surface shooting picture, the shooting part is installed on the steering device and is used for driving the shooting part to rotate according to the received displacement and target direction so that the hull target with the shallowest depth of field is in the center position of the field of the shooting part, the camera shooting component outputs the latest water surface recording picture as a directional recording picture after executing rotation;
the order mapping mechanism comprises a picture receiving device, a picture output device, a data correction device and a signal filtering device, wherein the picture receiving device, the data correction device, the signal filtering device and the picture output device are sequentially connected and are used for executing geometric correction and combined filtering operation on a received directional shooting picture so as to obtain a corresponding order mapping picture;
the region analysis equipment is connected with the sequence mapping mechanism and used for identifying regions where more than one ship body targets with the depth of field being higher than the preset depth of field limit are respectively located in the sequence mapping picture so as to serve as more than one target imaging region to be output;
the content judgment device is connected with the area analysis device and is used for executing the following operations on each target imaging area: acquiring each human body target in the target imaging area, analyzing pixel points with the over-limit red color channel value in the human body target imaging blocks as life jacket pixel points, taking pixel points with the over-limit red color channel value in the human body target imaging blocks as non-life jacket pixel points, and taking the human body target as a worn invalid human body target when the percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging blocks is lower than or equal to a preset percentage value;
the integral identification device is connected with the content judgment device and is used for taking the ship body target corresponding to a certain target imaging area as a wearing invalid ship body to highlight in the sequence mapping picture when the wearing invalid human body target exists in the certain target imaging area;
and the integral identification equipment is also used for taking the ship body target corresponding to the target imaging area as a worn effective ship body to carry out low-brightness marking in the sequence mapping picture when no worn ineffective human body target exists in a certain target imaging area.
According to another aspect of the present invention, there is also provided a wearing scene recognition method based on channel analysis, the method including:
the intelligent shooting mechanism is arranged on the shore and comprises a steering device, a shooting part, a vector recognition device and a picture analysis device, wherein the shooting part is used for executing the shooting operation of a water surface environment in the direction deviating from the shore to obtain a water surface shooting picture, the picture analysis device is connected with the shooting part and is used for detecting each hull target in the water surface shooting picture and the depth of field corresponding to each hull target, the vector recognition device is connected with the picture analysis device and is used for converting the corresponding displacement and target direction based on the distance and direction of the hull target with the shallowest depth of field deviating from the midpoint position of the water surface shooting picture, the shooting part is installed on the steering device and is used for driving the shooting part to rotate according to the received displacement and target direction so that the hull target with the shallowest depth of field is in the center position of the visual field of the shooting part, the camera shooting component outputs the latest water surface recording picture as a directional recording picture after executing rotation;
the using order mapping mechanism comprises a picture receiving device, a picture output device, a data correcting device and a signal filtering device, wherein the picture receiving device, the data correcting device, the signal filtering device and the picture output device are sequentially connected and are used for executing geometric correction and combined filtering operation on a received directional shooting picture so as to obtain a corresponding order mapping picture;
using area analysis equipment, connected with the sequence mapping mechanism, for identifying the areas where more than one ship body objects with the depth of field being less than the preset depth of field limit are respectively located in the sequence mapping picture so as to output the areas as more than one object imaging areas;
a content-of-use determination device, connected to the region analysis device, for performing the following operations for each target imaging region: acquiring each human body target in the target imaging area, analyzing pixel points with the over-limit red color channel value in the human body target imaging blocks as life jacket pixel points, taking pixel points with the over-limit red color channel value in the human body target imaging blocks as non-life jacket pixel points, and taking the human body target as a worn invalid human body target when the percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging blocks is lower than or equal to a preset percentage value;
using integral identification equipment, connecting with the content judgment equipment, and taking the hull target corresponding to a target imaging area as a wearing invalid hull to highlight in the sequence mapping picture when the wearing invalid human body target exists in the target imaging area;
and the integral identification equipment is also used for taking the ship body target corresponding to the target imaging area as a worn effective ship body to carry out low-brightness marking in the sequence mapping picture when no worn ineffective human body target exists in a certain target imaging area.
Drawings
Embodiments of the invention will now be described with reference to the accompanying drawings, in which:
fig. 1 is a diagram illustrating an internal structure of a steering apparatus used in a wearing scene recognition system and method based on channel analysis according to an embodiment of the present invention.
Detailed Description
Embodiments of the wearing scene recognition method based on channel analysis according to the present invention will be described in detail below with reference to the accompanying drawings.
Image recognition, which refers to a technique for processing, analyzing and understanding images by a computer to recognize various different patterns of objects and objects, is a practical application of applying a deep learning algorithm. Image recognition technology at present is generally divided into face recognition and commodity recognition, and the face recognition is mainly applied to security inspection, identity verification and mobile payment; the commodity identification is mainly applied to the commodity circulation process, in particular to the field of unmanned retail such as unmanned goods shelves and intelligent retail cabinets. The traditional image identification process is divided into four steps: image acquisition → image preprocessing → feature extraction → image recognition.
At present, an artificial eye detection mode or an electronic detection mode aiming at a single ship body is generally adopted in a detection mode of whether a plurality of ship body executors effectively wear the life jacket on the water surface, although the coverage of the artificial eye detection mode is wide, the artificial eye detection mode can simultaneously detect a plurality of ship bodies, the detection precision and the speed cannot meet the requirements, and although the precision of the electronic detection mode is reliable, the detection surface is narrow, and an independent electronic detection system needs to be arranged for each ship body.
In order to overcome the defects, the invention builds the wearing scene recognition system and the wearing scene recognition method based on channel analysis, and can effectively solve the corresponding technical problems.
The wearing scene recognition system based on the channel analysis comprises the following components:
the intelligent shooting mechanism is arranged on the shore and comprises a steering device, a shooting part, a vector recognition device and a picture analysis device, wherein the shooting part is used for executing the shooting operation of a water surface environment in the direction deviating from the shore so as to obtain a water surface shooting picture, the picture analysis device is connected with the shooting part and is used for detecting each hull target in the water surface shooting picture and the depth of field corresponding to each hull target, the vector recognition device is connected with the picture analysis device and is used for converting the corresponding displacement and target direction based on the distance and direction of the hull target with the shallowest depth of field deviating from the midpoint position of the water surface shooting picture, the shooting part is installed on the steering device and is used for driving the shooting part to rotate according to the received displacement and target direction so that the hull target with the shallowest depth of field is in the center position of the field of the shooting part, the camera shooting component outputs the latest water surface recording picture as a directional recording picture after executing rotation;
wherein the internal structure of the steering device is as shown in fig. 1;
the order mapping mechanism comprises a picture receiving device, a picture output device, a data correction device and a signal filtering device, wherein the picture receiving device, the data correction device, the signal filtering device and the picture output device are sequentially connected and are used for executing geometric correction and combined filtering operation on a received directional shooting picture so as to obtain a corresponding order mapping picture;
the region analysis equipment is connected with the sequence mapping mechanism and used for identifying regions where more than one ship body targets with the depth of field being higher than the preset depth of field limit are respectively located in the sequence mapping picture so as to serve as more than one target imaging region to be output;
the content judgment device is connected with the area analysis device and is used for executing the following operations on each target imaging area: acquiring each human body target in the target imaging area, analyzing pixel points with the over-limit red color channel value in the human body target imaging blocks as life jacket pixel points, taking pixel points with the over-limit red color channel value in the human body target imaging blocks as non-life jacket pixel points, and taking the human body target as a worn invalid human body target when the percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging blocks is lower than or equal to a preset percentage value;
the integral identification device is connected with the content judgment device and is used for taking the ship body target corresponding to a certain target imaging area as a wearing invalid ship body to highlight in the sequence mapping picture when the wearing invalid human body target exists in the certain target imaging area;
and the integral identification equipment is also used for taking the ship body target corresponding to the target imaging area as a worn effective ship body to carry out low-brightness marking in the sequence mapping picture when no worn ineffective human body target exists in a certain target imaging area.
Next, a detailed structure of the wearing scene recognition system based on channel analysis according to the present invention will be further described.
The wearing scene recognition system based on channel analysis can further comprise:
and the instant display mechanism is connected with the integral identification equipment and is used for instantly displaying the sequence mapping picture after the ship body target corresponding to each target imaging area is marked as an output picture.
In the channel analysis-based wearable scene recognition system:
analyzing the pixel points with the over-limit red color channel value in the human body target imaging block as life jacket pixel points, and taking the pixel points with the over-limit red color channel value in the human body target imaging block as non-life jacket pixel points comprises the following steps: and taking the pixel points of which the red color channel values in the human body target imaging blocks exceed the preset red channel limit as life jacket pixel points, and taking the pixel points of which the red color channel values in the human body target imaging blocks do not exceed the preset red channel limit as life jacket pixel points.
In the channel analysis-based wearable scene recognition system:
acquiring each human target in the target imaging region comprises: identifying each human target in the target imaging region based on a human imaging profile;
wherein, in the order mapping mechanism, the data correction device is configured to perform a geometric correction operation of the received pictures, and the signal filtering device is connected to the data correction device and configured to perform a combined filtering operation on the received pictures to obtain corresponding order mapped pictures.
In the channel analysis-based wearable scene recognition system:
and in the content judgment equipment, when the number percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging block is lower than or equal to a preset percentage value, taking the human body target as a wearable effective human body target.
The wearing scene recognition method based on the channel analysis comprises the following steps:
the intelligent shooting mechanism is arranged on the shore and comprises a steering device, a shooting part, a vector recognition device and a picture analysis device, wherein the shooting part is used for executing the shooting operation of a water surface environment in the direction deviating from the shore to obtain a water surface shooting picture, the picture analysis device is connected with the shooting part and is used for detecting each hull target in the water surface shooting picture and the depth of field corresponding to each hull target, the vector recognition device is connected with the picture analysis device and is used for converting the corresponding displacement and target direction based on the distance and direction of the hull target with the shallowest depth of field deviating from the midpoint position of the water surface shooting picture, the shooting part is installed on the steering device and is used for driving the shooting part to rotate according to the received displacement and target direction so that the hull target with the shallowest depth of field is in the center position of the visual field of the shooting part, the camera shooting component outputs the latest water surface recording picture as a directional recording picture after executing rotation;
wherein the internal structure of the steering device is as shown in fig. 1;
the using order mapping mechanism comprises a picture receiving device, a picture output device, a data correcting device and a signal filtering device, wherein the picture receiving device, the data correcting device, the signal filtering device and the picture output device are sequentially connected and are used for executing geometric correction and combined filtering operation on a received directional shooting picture so as to obtain a corresponding order mapping picture;
using area analysis equipment, connected with the sequence mapping mechanism, for identifying the areas where more than one ship body objects with the depth of field being less than the preset depth of field limit are respectively located in the sequence mapping picture so as to output the areas as more than one object imaging areas;
a content-of-use determination device, connected to the region analysis device, for performing the following operations for each target imaging region: acquiring each human body target in the target imaging area, analyzing pixel points with the over-limit red color channel value in the human body target imaging blocks as life jacket pixel points, taking pixel points with the over-limit red color channel value in the human body target imaging blocks as non-life jacket pixel points, and taking the human body target as a worn invalid human body target when the percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging blocks is lower than or equal to a preset percentage value;
using integral identification equipment, connecting with the content judgment equipment, and taking the hull target corresponding to a target imaging area as a wearing invalid hull to highlight in the sequence mapping picture when the wearing invalid human body target exists in the target imaging area;
and the integral identification equipment is also used for taking the ship body target corresponding to the target imaging area as a worn effective ship body to carry out low-brightness marking in the sequence mapping picture when no worn ineffective human body target exists in a certain target imaging area.
Next, the specific steps of the wearing scene recognition method based on channel analysis according to the present invention will be further described.
The wearing scene recognition method based on channel analysis may further include:
and an instant display mechanism is used and connected with the integral identification equipment and is used for instantly displaying the sequence mapping picture after the ship body target corresponding to each target imaging area is marked as an output picture.
The wearing scene recognition method based on channel analysis may further include:
analyzing the pixel points with the over-limit red color channel value in the human body target imaging block as life jacket pixel points, and taking the pixel points with the over-limit red color channel value in the human body target imaging block as non-life jacket pixel points comprises the following steps: and taking the pixel points of which the red color channel values in the human body target imaging blocks exceed the preset red channel limit as life jacket pixel points, and taking the pixel points of which the red color channel values in the human body target imaging blocks do not exceed the preset red channel limit as life jacket pixel points.
The wearing scene recognition method based on channel analysis may further include:
acquiring each human target in the target imaging region comprises: identifying each human target in the target imaging region based on a human imaging profile;
wherein, in the order mapping mechanism, the data correction device is configured to perform a geometric correction operation of the received pictures, and the signal filtering device is connected to the data correction device and configured to perform a combined filtering operation on the received pictures to obtain corresponding order mapped pictures.
In the wearing scene recognition method based on channel analysis:
and in the content judgment equipment, when the number percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging block is lower than or equal to a preset percentage value, taking the human body target as a wearable effective human body target.
In addition, in the wearing scene recognition system and method based on channel analysis, the signal filtering device is connected to the data correction device, and configured to perform a combined filtering operation on the received pictures to obtain corresponding order-mapped pictures, including: the signal filtering device is connected with the data correction device and is used for sequentially executing midpoint filtering operation and combined filtering operation on the received pictures so as to obtain corresponding order mapping pictures.
By adopting the wearing scene recognition system and method based on the channel analysis, aiming at the technical problem that whether the life jacket worn by personnel on each ship body is effective and difficult to analyze in parallel and reliably in the prior art, the field recognition that whether each human body wears the life jacket effectively is carried out on a plurality of near ship bodies close to the shore simultaneously by adopting a targeted electronic detection mode, so that the synchronous and effective safety monitoring of the ship bodies can be completed.
The above embodiments are merely examples for carrying out the present invention, and the present invention is not limited thereto, and various modifications of these embodiments are possible within the scope of the present invention, and it is apparent from the above description that various other embodiments are possible within the scope of the present invention.
Claims (10)
1. A wearable scene recognition system based on channel analysis, the system comprising:
the intelligent shooting mechanism is arranged on the shore and comprises a steering device, a shooting part, a vector recognition device and a picture analysis device, wherein the shooting part is used for executing the shooting operation of a water surface environment in the direction deviating from the shore so as to obtain a water surface shooting picture, the picture analysis device is connected with the shooting part and is used for detecting each hull target in the water surface shooting picture and the depth of field corresponding to each hull target, the vector recognition device is connected with the picture analysis device and is used for converting the corresponding displacement and target direction based on the distance and direction of the hull target with the shallowest depth of field deviating from the midpoint position of the water surface shooting picture, the shooting part is installed on the steering device and is used for driving the shooting part to rotate according to the received displacement and target direction so that the hull target with the shallowest depth of field is in the center position of the field of the shooting part, the camera shooting component outputs the latest water surface recording picture as a directional recording picture after executing rotation;
the order mapping mechanism comprises a picture receiving device, a picture output device, a data correction device and a signal filtering device, wherein the picture receiving device, the data correction device, the signal filtering device and the picture output device are sequentially connected and are used for executing geometric correction and combined filtering operation on a received directional shooting picture so as to obtain a corresponding order mapping picture;
the region analysis equipment is connected with the sequence mapping mechanism and used for identifying regions where more than one ship body targets with the depth of field being higher than the preset depth of field limit are respectively located in the sequence mapping picture so as to serve as more than one target imaging region to be output;
the content judgment device is connected with the area analysis device and is used for executing the following operations on each target imaging area: acquiring each human body target in the target imaging area, analyzing pixel points with the over-limit red color channel value in the human body target imaging blocks as life jacket pixel points, taking pixel points with the over-limit red color channel value in the human body target imaging blocks as non-life jacket pixel points, and taking the human body target as a worn invalid human body target when the percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging blocks is lower than or equal to a preset percentage value;
the integral identification device is connected with the content judgment device and is used for taking the ship body target corresponding to a certain target imaging area as a wearing invalid ship body to highlight in the sequence mapping picture when the wearing invalid human body target exists in the certain target imaging area;
and the integral identification equipment is also used for taking the ship body target corresponding to the target imaging area as a worn effective ship body to carry out low-brightness marking in the sequence mapping picture when no worn ineffective human body target exists in a certain target imaging area.
2. The wearing scene recognition system based on channel analysis of claim 1, further comprising:
and the instant display mechanism is connected with the integral identification equipment and is used for instantly displaying the sequence mapping picture after the ship body target corresponding to each target imaging area is marked as an output picture.
3. The wearing scene recognition system based on channel analysis of claim 1, characterized in that:
analyzing the pixel points with the over-limit red color channel value in the human body target imaging block as life jacket pixel points, and taking the pixel points with the over-limit red color channel value in the human body target imaging block as non-life jacket pixel points comprises the following steps: and taking the pixel points of which the red color channel values in the human body target imaging blocks exceed the preset red channel limit as life jacket pixel points, and taking the pixel points of which the red color channel values in the human body target imaging blocks do not exceed the preset red channel limit as life jacket pixel points.
4. The wearing scene recognition system based on channel analysis of claim 1, characterized in that:
acquiring each human target in the target imaging region comprises: identifying each human target in the target imaging region based on a human imaging profile;
wherein, in the order mapping mechanism, the data correction device is configured to perform a geometric correction operation of the received pictures, and the signal filtering device is connected to the data correction device and configured to perform a combined filtering operation on the received pictures to obtain corresponding order mapped pictures.
5. The wearing scene recognition system based on channel analysis of claim 1, characterized in that:
and in the content judgment equipment, when the number percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging block is lower than or equal to a preset percentage value, taking the human body target as a wearable effective human body target.
6. A wearing scene recognition method based on channel analysis is characterized by comprising the following steps:
the intelligent shooting mechanism is arranged on the shore and comprises a steering device, a shooting part, a vector recognition device and a picture analysis device, wherein the shooting part is used for executing the shooting operation of a water surface environment in the direction deviating from the shore to obtain a water surface shooting picture, the picture analysis device is connected with the shooting part and is used for detecting each hull target in the water surface shooting picture and the depth of field corresponding to each hull target, the vector recognition device is connected with the picture analysis device and is used for converting the corresponding displacement and target direction based on the distance and direction of the hull target with the shallowest depth of field deviating from the midpoint position of the water surface shooting picture, the shooting part is installed on the steering device and is used for driving the shooting part to rotate according to the received displacement and target direction so that the hull target with the shallowest depth of field is in the center position of the visual field of the shooting part, the camera shooting component outputs the latest water surface recording picture as a directional recording picture after executing rotation;
the using order mapping mechanism comprises a picture receiving device, a picture output device, a data correcting device and a signal filtering device, wherein the picture receiving device, the data correcting device, the signal filtering device and the picture output device are sequentially connected and are used for executing geometric correction and combined filtering operation on a received directional shooting picture so as to obtain a corresponding order mapping picture;
using area analysis equipment, connected with the sequence mapping mechanism, for identifying the areas where more than one ship body objects with the depth of field being less than the preset depth of field limit are respectively located in the sequence mapping picture so as to output the areas as more than one object imaging areas;
a content-of-use determination device, connected to the region analysis device, for performing the following operations for each target imaging region: acquiring each human body target in the target imaging area, analyzing pixel points with the over-limit red color channel value in the human body target imaging blocks as life jacket pixel points, taking pixel points with the over-limit red color channel value in the human body target imaging blocks as non-life jacket pixel points, and taking the human body target as a worn invalid human body target when the percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging blocks is lower than or equal to a preset percentage value;
using integral identification equipment, connecting with the content judgment equipment, and taking the hull target corresponding to a target imaging area as a wearing invalid hull to highlight in the sequence mapping picture when the wearing invalid human body target exists in the target imaging area;
and the integral identification equipment is also used for taking the ship body target corresponding to the target imaging area as a worn effective ship body to carry out low-brightness marking in the sequence mapping picture when no worn ineffective human body target exists in a certain target imaging area.
7. The wearing scene recognition method based on channel analysis as claimed in claim 6, further comprising:
and an instant display mechanism is used and connected with the integral identification equipment and is used for instantly displaying the sequence mapping picture after the ship body target corresponding to each target imaging area is marked as an output picture.
8. The wearing scene recognition method based on channel analysis as claimed in claim 6, characterized in that:
analyzing the pixel points with the over-limit red color channel value in the human body target imaging block as life jacket pixel points, and taking the pixel points with the over-limit red color channel value in the human body target imaging block as non-life jacket pixel points comprises the following steps: and taking the pixel points of which the red color channel values in the human body target imaging blocks exceed the preset red channel limit as life jacket pixel points, and taking the pixel points of which the red color channel values in the human body target imaging blocks do not exceed the preset red channel limit as life jacket pixel points.
9. The wearing scene recognition method based on channel analysis as claimed in claim 6, characterized in that:
acquiring each human target in the target imaging region comprises: identifying each human target in the target imaging region based on a human imaging profile;
wherein, in the order mapping mechanism, the data correction device is configured to perform a geometric correction operation of the received pictures, and the signal filtering device is connected to the data correction device and configured to perform a combined filtering operation on the received pictures to obtain corresponding order mapped pictures.
10. The wearing scene recognition method based on channel analysis as claimed in claim 6, characterized in that:
and in the content judgment equipment, when the number percentage of the life jacket pixel points occupying all the pixel points of the human body target imaging block is lower than or equal to a preset percentage value, taking the human body target as a wearable effective human body target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111061440.4A CN113989692A (en) | 2021-09-10 | 2021-09-10 | Wearing scene recognition system and method based on channel analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111061440.4A CN113989692A (en) | 2021-09-10 | 2021-09-10 | Wearing scene recognition system and method based on channel analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113989692A true CN113989692A (en) | 2022-01-28 |
Family
ID=79735602
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111061440.4A Withdrawn CN113989692A (en) | 2021-09-10 | 2021-09-10 | Wearing scene recognition system and method based on channel analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113989692A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115512284A (en) * | 2022-09-21 | 2022-12-23 | 江阴市花园铝塑包装有限公司 | System and method for analyzing integrity of milk sealing film of plastic bottle |
| CN118230477A (en) * | 2024-03-26 | 2024-06-21 | 宿迁奇曼佳建材有限公司 | Building site potential safety hazard identification system |
| CN118225009A (en) * | 2024-04-17 | 2024-06-21 | 南京角载溪建筑工程有限公司 | Dimension standard identification system for flat steel bars |
| CN118279760A (en) * | 2024-03-25 | 2024-07-02 | 连云港苏吉网络科技有限公司 | Big data intelligent analysis system of contact state |
| CN118506260A (en) * | 2024-04-23 | 2024-08-16 | 南京脉期尔电气有限公司 | Intelligent identification system for different target contact scenes of power distribution network |
-
2021
- 2021-09-10 CN CN202111061440.4A patent/CN113989692A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115512284A (en) * | 2022-09-21 | 2022-12-23 | 江阴市花园铝塑包装有限公司 | System and method for analyzing integrity of milk sealing film of plastic bottle |
| CN115512284B (en) * | 2022-09-21 | 2023-04-07 | 江阴市花园铝塑包装有限公司 | System and method for analyzing integrity of milk sealing film of plastic bottle |
| CN118279760A (en) * | 2024-03-25 | 2024-07-02 | 连云港苏吉网络科技有限公司 | Big data intelligent analysis system of contact state |
| CN118230477A (en) * | 2024-03-26 | 2024-06-21 | 宿迁奇曼佳建材有限公司 | Building site potential safety hazard identification system |
| CN118225009A (en) * | 2024-04-17 | 2024-06-21 | 南京角载溪建筑工程有限公司 | Dimension standard identification system for flat steel bars |
| CN118506260A (en) * | 2024-04-23 | 2024-08-16 | 南京脉期尔电气有限公司 | Intelligent identification system for different target contact scenes of power distribution network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113989692A (en) | Wearing scene recognition system and method based on channel analysis | |
| CN107240112B (en) | Individual X corner extraction method in complex scene | |
| CN109523551B (en) | Method and system for acquiring walking posture of robot | |
| CN106548467A (en) | The method and device of infrared image and visual image fusion | |
| CN108629343A (en) | A kind of license plate locating method and system based on edge detection and improvement Harris Corner Detections | |
| CN108765333B (en) | Depth map perfecting method based on depth convolution neural network | |
| CN102930334A (en) | Video recognition counter for body silhouette | |
| CN106529556B (en) | A kind of vision detection system of meter lamp | |
| CN110021029A (en) | A kind of real-time dynamic registration method and storage medium suitable for RGBD-SLAM | |
| CN110298893A (en) | A kind of pedestrian wears the generation method and device of color identification model clothes | |
| CN102567969B (en) | Color image edge detection method | |
| CN110120073B (en) | Method for guiding recovery of unmanned ship based on lamp beacon visual signal | |
| CN101561316B (en) | On-line test visual data processing system based on region of interest (ROI) | |
| CN104813341B (en) | Image processing system and image processing method | |
| Shah et al. | Context enhancement to reveal a camouflaged target and to assist target localization by fusion of multispectral surveillance videos | |
| Pawar et al. | Recognition of Indian currency note based on HSV parameters | |
| Chae et al. | Subpixel rendering for the pentile display based on the human visual system | |
| Stone et al. | Forward looking anomaly detection via fusion of infrared and color imagery | |
| EP3296957B1 (en) | Method and apparatus for judging image brightness background, and display apparatus | |
| CN106683044A (en) | Image splicing method and device for multi-channel optical detection system | |
| CN105335980A (en) | Method suitable for image SIFT feature matching in converting color image to brightness image | |
| Hossain et al. | Extending GLCM to include color information for texture recognition | |
| CN109523594A (en) | A kind of vision tray characteristic point coordinate location method and system | |
| Zarkasi et al. | Implementation color filtering and Harris corner method on pattern recognition system | |
| CN102682275B (en) | Image matching method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220128 |
|
| WW01 | Invention patent application withdrawn after publication |