CN110188724B - Method and system for helmet positioning and color recognition based on deep learning - Google Patents
Method and system for helmet positioning and color recognition based on deep learning Download PDFInfo
- Publication number
- CN110188724B CN110188724B CN201910484745.2A CN201910484745A CN110188724B CN 110188724 B CN110188724 B CN 110188724B CN 201910484745 A CN201910484745 A CN 201910484745A CN 110188724 B CN110188724 B CN 110188724B
- Authority
- CN
- China
- Prior art keywords
- helmet
- safety helmet
- image
- target
- position information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Abstract
The invention provides a method and a system for helmet positioning and color recognition based on deep learning, wherein the method comprises the following steps: acquiring image information, acquiring a moving object image in the image information, and taking the moving object image as an interested area; inputting the region of interest into a pre-established convolutional neural network model, and carrying out multi-target parallel detection on the image information according to a preset target classification; acquiring parallel detection results, wherein the detection results at least comprise position information of the head of a human body and position information of a safety helmet; judging the situation that the person in the collected image information wears the safety helmet according to the parallel detection result, and sending alarm information when the fact that the person does not wear the safety helmet is judged; the invention can continuously and effectively monitor the designated area, prevent safety accidents caused by the fact that people do not wear safety helmets, replace manual work to carry out intelligent analysis and processing and send out alarm signals in real time, and improve the problems of low universality, stability and accuracy of security video monitoring.
Description
Technical Field
The invention relates to the field of computer application, in particular to a method and a system for helmet positioning and color recognition based on deep learning.
Background
Along with the popularization of security monitoring cameras, the identification requirements under various different scenes also come up, in particular to the identification requirements in the aspect of personnel safety. For construction sites, factories and other specific occasions, related workers and external visitors are required to wear safety helmets, the areas need to be monitored in real time for 24 hours through security monitoring cameras, and if a human body enters the areas and the safety helmets are not worn correctly, the safety helmets can be reminded or alarm signals can be sent out timely.
The traditional security video monitoring means adopts a manual mode to distinguish large batches of monitoring videos, but the mode is difficult to work continuously for 24 hours and is easy to miss the situation. For the problem, most of the existing monitoring modes are the safety helmet wearing judgment through a serial mode of human body identification and safety helmet identification, namely, whether a human body exists in a picture is identified, an image of the human body is cut out, and then whether a safety helmet exists in the cut image is judged. The biggest limitation of such serial identification methods is that if the first step of human body identification is problematic, subsequent helmet identification operations cannot be performed. In a real scene, a human body is easily shielded in a video picture, and the angle of the image acquisition device also has great influence on the accuracy of human body identification, so that false identification and missed detection are easily caused. Therefore, the versatility, stability and accuracy of this serial approach are not high. Therefore, a new monitoring mode is needed to improve the universality, stability and accuracy of security video monitoring.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention provides a method and system for helmet positioning and color recognition based on deep learning, so as to solve the above-mentioned technical problems.
The invention provides a method for positioning and identifying colors of safety helmets based on deep learning, which comprises the following steps:
acquiring image information, acquiring a moving object image in the image information, and taking the moving object image as an interested area;
inputting the region of interest into a pre-established convolutional neural network model, and carrying out multi-target parallel detection on the image information according to preset target classification;
acquiring parallel detection results, wherein the detection results at least comprise position information of the head of a human body and position information of a safety helmet;
and judging the situation that the person in the collected image information wears the safety helmet according to the parallel detection result, and sending alarm information when judging that the person does not wear the safety helmet.
Optionally, the object classification comprises at least a human head and a safety helmet;
when the detected region of interest is only the head of a human body, judging that a person does not wear a safety helmet;
when only the safety helmet is detected in the region of interest, judging that the safety helmet is worn correctly;
and when the detected interesting area has the human head and the safety helmet at the same time, judging whether the safety helmet is worn correctly or not according to the position information of the human head and the position information of the safety helmet.
Optionally, when the detected region of interest has both the human head and the safety helmet, the position relationship between the human head and the safety helmet and the distance between the central points of the human head and the safety helmet are obtained according to the position information of the human head and the position information of the safety helmet, when the position of the safety helmet is above the human head and the distance between the central points of the human head and the safety helmet does not exceed a preset distance threshold, it is determined that the safety helmet is worn correctly, and otherwise, it is determined that the safety helmet is not worn correctly.
Optionally, according to the acquired image information, obtaining a continuous frame image, obtaining a difference value between each pixel point in the current frame image and each pixel point in the previous frame image, comparing the difference value with a preset threshold, when the difference value exceeds a preset threshold range, taking the corresponding pixel point as a foreground image, otherwise, taking the corresponding pixel point as a background image, and obtaining a moving object image in the image information through the foreground image.
Optionally, the detection result further includes a confidence level of the target, the confidence level of the target at least includes a confidence level of the head of the human body and a confidence level of the safety helmet, a confidence level threshold is preset, when the confidence level of the target in the detection result is greater than the preset confidence level threshold, the target is used as a trusted result, otherwise, the target is used as an untrusted result, and the target is ignored.
Optionally, after the safety helmet is correctly worn, the color of the image in the position information area of the safety helmet is identified, and the color of the safety helmet of the detection target is obtained.
The invention also provides a system for helmet positioning and color recognition based on deep learning, which comprises:
the image acquisition module is used for acquiring image information;
the image processing module is used for acquiring a moving object image in the image information and taking the moving object image as an interested area;
the convolutional neural network model is used for carrying out multi-target parallel detection on the image information according to preset target classification to obtain a parallel detection result, and the detection result at least comprises human head position information and position information of a safety helmet;
the judgment module is used for judging the situation that the person wearing the safety helmet in the collected image information according to the parallel detection result;
and the alarm module is used for sending alarm information when the situation that the person does not wear the safety helmet is judged.
Optionally, the method further includes:
the color identification module is used for carrying out color identification on the image in the position information area of the safety helmet after the safety helmet is judged to be worn correctly, and obtaining the color of the safety helmet of the detection target;
and the counting module is used for counting the number of the personnel wearing the safety helmet in the image information.
The invention also provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method of any one of the above.
The present invention also provides an electronic terminal, comprising: a processor and a memory;
the memory is adapted to store a computer program and the processor is adapted to execute the computer program stored by the memory to cause the terminal to perform the method as defined in any one of the above.
The invention has the beneficial effects that: according to the method and the system for helmet positioning and color recognition based on deep learning, intelligent alarm of dangerous areas in a monitoring video is achieved, an appointed area can be continuously and effectively monitored, and safety accidents caused by the fact that people do not wear helmets are prevented; the invention can uninterruptedly carry out intelligent visual identification and identification analysis on the security monitoring video within twenty-four hours, replaces manual work to carry out intelligent analysis processing and send out an alarm signal in real time aiming at the area which can be shot by the video image, and improves the problems of low universality, stability and accuracy of the security video monitoring.
Drawings
Fig. 1 is a schematic flow chart of a method for deep learning-based helmet positioning and color recognition in an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a system for helmet positioning and color identification based on deep learning in an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
In the following description, numerous details are set forth to provide a more thorough explanation of embodiments of the present invention, however, it will be apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details, and in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring embodiments of the present invention.
As shown in fig. 1, the method for positioning and identifying colors of a safety helmet based on a deep learning algorithm in this embodiment includes:
acquiring image information, acquiring a moving object image in the image information, and taking the moving object image as an interested area;
inputting the region of interest into a pre-established convolutional neural network model, and carrying out multi-target parallel detection on the image information according to preset target classification;
acquiring parallel detection results, wherein the detection results at least comprise position information of the head of a human body and position information of a safety helmet;
and judging the situation that the person in the collected image information wears the safety helmet according to the parallel detection result, and sending alarm information when judging that the person does not wear the safety helmet.
In this embodiment, an area to be monitored, for example, a scene such as a security or a factory on a construction site, may be image-captured by an image capturing device such as a monitoring camera to obtain corresponding real-time image information, and first, a changed portion, that is, a moving object, in a real-time video image is identified; if a moving object appears in the video image, performing target detection on the human head and target detection on the safety helmet by utilizing a convolutional neural network model based on a deep learning algorithm aiming at the partial image; then logically judging the situation that the person wears the safety helmet according to the recognition results of the target detection of the head of the person and the target detection of the safety helmet; if the person who does not wear the safety helmet is detected, alarm information is sent out; and if the person who correctly wears the safety helmet is detected, identifying the color of the safety helmet through an image identification algorithm, and carrying out statistics on the wearing of the safety helmet by the corresponding person.
In this embodiment, the region of interest is input to a pre-established convolutional neural network model, and the image information is subjected to multi-target parallel detection according to a preset target classification, that is, whether a human head or a safety helmet exists in the region of interest of the image is identified at the same time. If only the head of the person is identified and the safety helmet is not identified, indicating that the safety helmet is not worn in the region of interest; if the head of the person and the safety helmet are identified at the same time, judging whether the safety helmet is worn correctly or not according to the position information of the head of the person and the position information of the safety helmet; because the head of a person can be shielded after the safety helmet is worn correctly, if only the safety helmet is recognized, the safety helmet is worn correctly, the condition that the person wears the safety helmet in the video image is intelligently recognized in the mode, and corresponding statistical analysis is carried out according to the result.
In another embodiment, the identity of the person who does not wear the safety helmet can be judged by combining technologies such as face recognition or physical recognition, or by combining a positioning technology, an identity recognition device and a positioning device are arranged on the safety helmet in advance, after the person who does not wear the safety helmet is detected, the person who does not wear the safety helmet is subjected to identity recognition and positioning, the safety helmet can be bound with a mobile communication device, and the person who does not wear the safety helmet or does not wear the safety helmet correctly is warned through the mobile communication device.
In this embodiment, optionally, the region of interest may be obtained by using a "foreground and background segmentation" algorithm, that is, a difference between each pixel point of the "current frame" image and a corresponding pixel point of the "background frame" image adaptively updated based on a KNN (k-nearest neighbor) algorithm is calculated, if the difference exceeds a set threshold, the pixel point is considered as a foreground image, and otherwise, the pixel point is set as a background image. Through the algorithm, a moving object region in the image is extracted, and the region is set as a region of interest (ROI) of the image, so that subsequent image identification processing is facilitated.
In this embodiment, when the detected region of interest has both the human head and the safety helmet, the position relationship between the human head and the safety helmet and the distance between the central points of the human head and the safety helmet are obtained according to the position information of the human head and the position information of the safety helmet, and when the position of the safety helmet is above the human head and the distance between the central points of the human head and the safety helmet does not exceed a preset distance threshold, it is determined that the safety helmet is worn correctly, otherwise, it is determined that the safety helmet is not worn correctly. Optionally, in this embodiment, a convolutional neural network model based on a deep learning algorithm is used, and for an area of interest, multi-classification target detection of two categories, namely, the human head and the safety helmet, is performed to obtain position information and confidence of the human head and the safety helmet in an image, where each human head or each safety helmet part has its corresponding position information and confidence. And setting a designated confidence threshold, and when the confidence of the detected target is greater than the confidence threshold, regarding the target as a human head or a safety helmet, and otherwise, ignoring the target. For the detected position information of the head and the safety helmet of the person, whether the person wears the safety helmet or not is judged through logic, and the following three conditions can be divided: 1. only the safety helmet is identified in the region of interest, and the person is considered to wear the safety helmet; 2. only the head of a person is recognized in the region of interest, and the person is considered to be unworn; 3. and if the safety helmet position is positioned above the head position of the person and the distance between the central points does not exceed a set distance threshold, the person is considered to correctly wear the safety helmet, and otherwise, the person is considered to incorrectly wear the safety helmet.
In this embodiment, after it is determined that the helmet is worn correctly, the color of the helmet of the detection target is obtained by performing color recognition on the image in the position information area of the helmet. Optionally, for example, the safety helmet in a certain monitoring area only has four colors of red, yellow, blue and white, if a person correctly wears the safety helmet, the color of the safety helmet can be identified through an HSV image identification algorithm, that is, an HSV value of an image in the safety helmet position information area is calculated and compared with HSV values of the four colors of red, yellow, blue and white, if a difference value of the HSV values is smaller than a threshold value, the color of the safety helmet is judged to be red, yellow, blue or white, and the number of the persons wearing the safety helmet in a picture is counted.
As shown in fig. 2, correspondingly, the present embodiment further provides a system for positioning and identifying colors of a safety helmet based on a deep learning algorithm, including:
the image acquisition module is used for acquiring image information;
the image processing module is used for acquiring a moving object image in the image information and taking the moving object image as an interested area;
the convolutional neural network model is used for carrying out multi-target parallel detection on the image information according to preset target classification to obtain a parallel detection result, and the detection result at least comprises human head position information and position information of a safety helmet;
the judgment module is used for judging the situation that the person wearing the safety helmet in the collected image information according to the parallel detection result;
and the alarm module is used for sending alarm information when the situation that the person does not wear the safety helmet is judged.
The color identification module is used for carrying out color identification on the image in the position information area of the safety helmet after the safety helmet is judged to be worn correctly, and obtaining the color of the safety helmet of the detection target;
and the counting module is used for counting the number of the personnel wearing the safety helmet in the image information.
The embodiment can effectively solve the problems of stability and accuracy in a serial method through parallel multi-target identification of the human head and the safety helmet. From the generality of the algorithm, no matter how the angle of the image acquisition device is (overlooking or looking up), the characteristics of the head and the safety helmet are very obvious and can be effectively identified; from the judgment logic, if only the head of the person is identified and the safety helmet is not identified, the fact that the person does not wear the safety helmet is indicated; if the head and the safety helmet are identified at the same time, whether the safety helmet is worn correctly is judged according to the position relation of the head and the safety helmet; because the head of a person is shielded after the safety helmet is worn correctly, if only the safety helmet is identified, the safety helmet is worn correctly. The above-mentioned judgement logic is more rigorous than that of the serial method for identifying whether the safety helmet exists in the upper half part of the human body image, and if someone takes the safety helmet by hand or carries the safety helmet by shoulder, the incorrect wearing of the safety helmet can be identified to a limited extent.
The present embodiment also provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements any of the methods in the present embodiments.
The present embodiment further provides an electronic terminal, including: a processor and a memory;
the memory is used for storing computer programs, and the processor is used for executing the computer programs stored by the memory so as to enable the terminal to execute the method in the embodiment.
The computer-readable storage medium in the present embodiment can be understood by those skilled in the art as follows: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The electronic terminal provided by the embodiment comprises a processor, a memory, a transceiver and a communication interface, wherein the memory and the communication interface are connected with the processor and the transceiver and are used for completing mutual communication, the memory is used for storing a computer program, the communication interface is used for carrying out communication, and the processor and the transceiver are used for operating the computer program so that the electronic terminal can execute the steps of the method.
In this embodiment, the Memory may include a Random Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In the above-described embodiments, reference in the specification to "the embodiment," "an embodiment," "another embodiment," or "other embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiments is included in at least some embodiments, but not necessarily all embodiments. The various appearances of the phrase "the present embodiment," "one embodiment," or "another embodiment" are not necessarily all referring to the same embodiment. If the specification states a component, feature, structure, or characteristic "may", "might", or "could" be included, that particular component, feature, structure, or characteristic is not required to be included. If the specification or claim refers to "a" or "an" element, that does not mean there is only one of the element. If the specification or claim refers to "a further" element, that does not preclude there being more than one of the further element.
In the embodiments described above, although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. The embodiments of the invention are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (9)
1. A method for helmet positioning and color recognition based on deep learning is characterized by comprising the following steps:
acquiring image information, acquiring a moving object image in the image information, and taking the moving object image as an interested area;
inputting the region of interest into a pre-established convolutional neural network model, and carrying out multi-target parallel detection on the image information according to preset target classification; the target classification at least comprises a human head and a safety helmet;
acquiring parallel detection results, wherein the detection results at least comprise human head position information and safety helmet position information;
judging the wearing condition of the safety helmet by the person in the acquired image information according to the parallel detection result, and sending alarm information when the situation that the person does not wear the safety helmet is judged;
when the detected interesting area is only the head of a human body, judging that a person does not wear a safety helmet;
when only the safety helmet is detected in the region of interest, judging that the safety helmet is worn correctly;
and when the detected interesting area has the human head and the safety helmet at the same time, judging whether the safety helmet is worn correctly or not according to the position information of the human head and the position information of the safety helmet.
2. The method for helmet positioning and color recognition based on deep learning of claim 1, wherein when the detected region of interest has both the human head and the helmet, the position relationship between the human head and the helmet and the distance between the central points of the human head and the helmet are obtained according to the position information of the human head and the position information of the helmet, and when the position of the helmet is above the human head and the distance between the central points of the human head and the helmet does not exceed a preset distance threshold, it is determined that the helmet is worn correctly, otherwise, it is determined that the helmet is not worn correctly.
3. The method for helmet positioning and color identification based on deep learning of claim 1, wherein according to the collected image information, obtaining continuous frame images, obtaining a difference value of each pixel point in a current frame image and a previous frame image, comparing the difference value with a preset threshold, when the difference value exceeds a preset threshold range, taking the corresponding pixel point as a foreground image, otherwise, taking the corresponding pixel point as a background image, and obtaining a moving object image in the image information through the foreground image.
4. The method for helmet localization and color recognition based on deep learning of claim 1, wherein the detection result further includes confidence of the target, the confidence of the target at least includes confidence of the human head and confidence of the helmet, a confidence threshold is preset, when the confidence of the target in the detection result is greater than the preset confidence threshold, the target is regarded as a trusted result, otherwise, the target is regarded as an untrusted result, and the target is ignored.
5. The method for helmet positioning and color identification based on deep learning of claim 2, wherein when the helmet is determined to be worn correctly, the color of the helmet of the detection target is obtained by performing color identification on the image in the position information area of the helmet.
6. A system for helmet localization and color identification based on deep learning, comprising:
the image acquisition module is used for acquiring image information;
the image processing module is used for acquiring a moving object image in the image information and taking the moving object image as an interested area;
the convolutional neural network model is used for carrying out multi-target parallel detection on the image information according to preset target classification to obtain parallel detection results, the detection results at least comprise position information of the head of a human body and position information of a safety helmet, and the target classification at least comprises the head of the human body and the safety helmet;
the judgment module is used for judging the situation that the person wearing the safety helmet in the collected image information according to the parallel detection result;
the alarm module is used for sending alarm information when the fact that the safety helmet is not worn by a person is judged;
when the detected region of interest is only the head of a human body, judging that a person does not wear a safety helmet;
when only the safety helmet is detected in the region of interest, judging that the safety helmet is worn correctly;
and when the human head and the safety helmet exist in the detected interesting area at the same time, judging whether the safety helmet is worn correctly or not according to the position information of the human head and the position information of the safety helmet.
7. The deep learning based system for hard hat localization and color identification according to claim 6, wherein: further comprising:
the color identification module is used for carrying out color identification on the image in the position information area of the safety helmet after the safety helmet is judged to be worn correctly, and obtaining the color of the safety helmet of the detection target;
and the counting module is used for counting the number of the personnel wearing the safety helmet in the image information.
8. A computer-readable storage medium having stored thereon a computer program, characterized in that: the program when executed by a processor implements the method of any one of claims 1 to 5.
9. An electronic terminal, comprising: a processor and a memory;
the memory is for storing a computer program and the processor is for executing the computer program stored by the memory to cause the terminal to perform the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910484745.2A CN110188724B (en) | 2019-06-05 | 2019-06-05 | Method and system for helmet positioning and color recognition based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910484745.2A CN110188724B (en) | 2019-06-05 | 2019-06-05 | Method and system for helmet positioning and color recognition based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110188724A CN110188724A (en) | 2019-08-30 |
| CN110188724B true CN110188724B (en) | 2023-02-28 |
Family
ID=67720379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910484745.2A Active CN110188724B (en) | 2019-06-05 | 2019-06-05 | Method and system for helmet positioning and color recognition based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110188724B (en) |
Families Citing this family (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110728264A (en) * | 2019-10-24 | 2020-01-24 | 名创优品（横琴）企业管理有限公司 | Wearing condition detection method and system for accessory wearable product |
| CN110929608A (en) * | 2019-11-12 | 2020-03-27 | 国网天津市电力公司 | Safety helmet wearing detection method and system |
| CN111091535A (en) * | 2019-11-22 | 2020-05-01 | 三一重工股份有限公司 | Factory management method and system based on deep learning image semantic segmentation |
| CN111223255A (en) * | 2019-11-25 | 2020-06-02 | 创新奇智(上海)科技有限公司 | Intelligent elevator monitoring system and monitoring equipment |
| CN111079731A (en) * | 2019-12-03 | 2020-04-28 | 中冶赛迪重庆信息技术有限公司 | Configuration system, method, equipment and medium based on safety helmet identification monitoring system |
| CN111178212A (en) * | 2019-12-23 | 2020-05-19 | 深圳供电局有限公司 | Image recognition method and device, computer equipment and storage medium |
| CN111191581B (en) * | 2019-12-27 | 2024-04-12 | 深圳供电局有限公司 | Safety helmet detection method and device based on electric power construction and computer equipment |
| CN111199200A (en) * | 2019-12-27 | 2020-05-26 | 深圳供电局有限公司 | Wearing detection method and device based on electric protection equipment and computer equipment |
| CN111079699A (en) * | 2019-12-30 | 2020-04-28 | 北京每日优鲜电子商务有限公司 | Commodity identification method and device |
| CN111161260A (en) * | 2020-01-02 | 2020-05-15 | 中冶赛迪重庆信息技术有限公司 | Hot-rolled strip steel surface defect detection method and device based on deep learning |
| JP2021163260A (en) * | 2020-03-31 | 2021-10-11 | 株式会社小松製作所 | Detection system and detection method |
| CN111597985A (en) * | 2020-05-15 | 2020-08-28 | 全程(上海)智能科技有限公司 | Dynamic identification method and device for equipment wearing and electronic equipment |
| CN111623751B (en) * | 2020-05-31 | 2021-11-30 | 上海域唯医疗科技有限公司 | System for identifying the inclination of a visor and corresponding terminal |
| CN111652128B (en) * | 2020-06-02 | 2023-09-01 | 浙江大华技术股份有限公司 | High-altitude power operation safety monitoring method, system and storage device |
| CN111738106B (en) * | 2020-06-04 | 2023-09-19 | 东莞市度润光电科技有限公司 | Detection method, detection device and storage medium for infrared lamp shade |
| CN111768100A (en) * | 2020-06-30 | 2020-10-13 | 山东浪潮通软信息科技有限公司 | Intelligent employee management system and method |
| CN112101288B (en) * | 2020-09-25 | 2024-02-13 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for detecting wearing of safety helmet |
| CN112329532A (en) * | 2020-09-30 | 2021-02-05 | 浙江汉德瑞智能科技有限公司 | Automatic tracking safety helmet monitoring method based on YOLOv4 |
| CN112184773A (en) * | 2020-09-30 | 2021-01-05 | 华中科技大学 | Helmet wearing detection method and system based on deep learning |
| CN112329554A (en) * | 2020-10-19 | 2021-02-05 | 通辽发电总厂有限责任公司 | Low-resolution image helmet identification method and device |
| CN112308073B (en) * | 2020-11-06 | 2023-08-25 | 中冶赛迪信息技术(重庆)有限公司 | Method, system, equipment and medium for identifying loading and unloading and transferring states of scrap steel train |
| CN112911255B (en) * | 2020-11-10 | 2021-12-07 | 江苏国兴建设项目管理有限公司 | Building site safety state detecting system |
| CN112487963A (en) * | 2020-11-27 | 2021-03-12 | 新疆爱华盈通信息技术有限公司 | Wearing detection method and system for safety helmet |
| CN113408365B (en) * | 2021-05-26 | 2023-09-08 | 广东能源集团科学技术研究院有限公司 | Safety helmet identification method and device under complex scene |
| CN113537296A (en) * | 2021-06-22 | 2021-10-22 | 广州云从鼎望科技有限公司 | Feature detection method, feature detection device and computer storage medium |
| CN113469043A (en) * | 2021-06-30 | 2021-10-01 | 南方科技大学 | Method and device for detecting wearing state of safety helmet, computer equipment and storage medium |
| CN113516082A (en) * | 2021-07-19 | 2021-10-19 | 曙光信息产业(北京)有限公司 | Detection method and device of safety helmet, computer equipment and storage medium |
| CN113487227B (en) * | 2021-07-27 | 2024-03-26 | 安徽云森物联网科技有限公司 | Intelligent safety helmet-based duty management method, system and storage medium |
| CN113792665B (en) * | 2021-09-16 | 2023-08-08 | 山东大学 | Forbidden area intrusion detection method aiming at different role authorities |
| CN113838094B (en) * | 2021-09-28 | 2024-03-05 | 贵州乌江水电开发有限责任公司 | Safety early warning method based on intelligent video identification |
| CN113837138B (en) * | 2021-09-30 | 2023-08-29 | 重庆紫光华山智安科技有限公司 | Dressing monitoring method, dressing monitoring system, dressing monitoring medium and electronic terminal |
| CN113963436A (en) * | 2021-10-14 | 2022-01-21 | 山东大学 | Helmet identification incremental learning and role judgment method based on deep learning |
| CN115050125B (en) * | 2022-05-20 | 2023-08-29 | 劢微机器人科技(深圳)有限公司 | 2d camera-based safety early warning method, device, equipment and storage medium |
| CN114882370A (en) * | 2022-07-07 | 2022-08-09 | 西安超嗨网络科技有限公司 | Intelligent commodity identification method and device, terminal and storage medium |
| CN115690673B (en) * | 2022-09-30 | 2023-06-06 | 广东康君环安技术股份有限公司 | Safety helmet monitoring method and system for safety operation of construction site |
| CN115985044B (en) * | 2022-11-21 | 2024-04-05 | 重庆市信息通信咨询设计院有限公司 | Method and system for monitoring wearing state of safety helmet |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104036575A (en) * | 2014-07-01 | 2014-09-10 | 江苏省南京市公路管理处公路科学研究所 | Safety helmet wearing condition monitoring method on construction site |
| CN104504369A (en) * | 2014-12-12 | 2015-04-08 | 无锡北邮感知技术产业研究院有限公司 | Wearing condition detection method for safety helmets |
| CN106372662A (en) * | 2016-08-30 | 2017-02-01 | 腾讯科技（深圳）有限公司 | Helmet wearing detection method and device, camera, and server |
| CN107679524A (en) * | 2017-10-31 | 2018-02-09 | 天津天地伟业信息系统集成有限公司 | A kind of detection method of the safety cap wear condition based on video |
| CN108319926A (en) * | 2018-02-12 | 2018-07-24 | 安徽金禾软件股份有限公司 | A kind of the safety cap wearing detecting system and detection method of building-site |
| CN108921159A (en) * | 2018-07-26 | 2018-11-30 | 北京百度网讯科技有限公司 | Method and apparatus for detecting the wear condition of safety cap |
| CN109034215A (en) * | 2018-07-09 | 2018-12-18 | 东北大学 | A kind of safety cap wearing detection method based on depth convolutional neural networks |
| CN109670441A (en) * | 2018-12-14 | 2019-04-23 | 广东亿迅科技有限公司 | A kind of realization safety cap wearing knows method for distinguishing, system, terminal and computer readable storage medium |
| CN109697430A (en) * | 2018-12-28 | 2019-04-30 | 成都思晗科技股份有限公司 | The detection method that working region safety cap based on image recognition is worn |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016373A (en) * | 2017-04-12 | 2017-08-04 | 广东工业大学 | The detection method and device that a kind of safety cap is worn |
-
2019
- 2019-06-05 CN CN201910484745.2A patent/CN110188724B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104036575A (en) * | 2014-07-01 | 2014-09-10 | 江苏省南京市公路管理处公路科学研究所 | Safety helmet wearing condition monitoring method on construction site |
| CN104504369A (en) * | 2014-12-12 | 2015-04-08 | 无锡北邮感知技术产业研究院有限公司 | Wearing condition detection method for safety helmets |
| CN106372662A (en) * | 2016-08-30 | 2017-02-01 | 腾讯科技（深圳）有限公司 | Helmet wearing detection method and device, camera, and server |
| CN107679524A (en) * | 2017-10-31 | 2018-02-09 | 天津天地伟业信息系统集成有限公司 | A kind of detection method of the safety cap wear condition based on video |
| CN108319926A (en) * | 2018-02-12 | 2018-07-24 | 安徽金禾软件股份有限公司 | A kind of the safety cap wearing detecting system and detection method of building-site |
| CN109034215A (en) * | 2018-07-09 | 2018-12-18 | 东北大学 | A kind of safety cap wearing detection method based on depth convolutional neural networks |
| CN108921159A (en) * | 2018-07-26 | 2018-11-30 | 北京百度网讯科技有限公司 | Method and apparatus for detecting the wear condition of safety cap |
| CN109670441A (en) * | 2018-12-14 | 2019-04-23 | 广东亿迅科技有限公司 | A kind of realization safety cap wearing knows method for distinguishing, system, terminal and computer readable storage medium |
| CN109697430A (en) * | 2018-12-28 | 2019-04-30 | 成都思晗科技股份有限公司 | The detection method that working region safety cap based on image recognition is worn |
Non-Patent Citations (2)
| Title |
|---|
| 刘云波等.施工现场安全帽佩戴情况监控技术研究.《电子科技》.2015,第28卷(第4期),第69-72页. * |
| 王忠玉.智能视频监控下的安全帽佩戴检测系统的设计与实现.《中国优秀硕士学位论文全文数据库 信息科技辑》.2018,(第（2018）10期),I136-461. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110188724A (en) | 2019-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110188724B (en) | Method and system for helmet positioning and color recognition based on deep learning | |
| Fang et al. | Detecting non-hardhat-use by a deep learning method from far-field surveillance videos | |
| KR101808587B1 (en) | Intelligent integration visual surveillance control system by object detection and tracking and detecting abnormal behaviors | |
| CN111898514B (en) | Multi-target visual supervision method based on target detection and action recognition | |
| CN112396658B (en) | Indoor personnel positioning method and system based on video | |
| CN101465033B (en) | Automatic tracking recognition system and method | |
| CN110309719A (en) | A kind of electric network operation personnel safety cap wears management control method and system | |
| CN106341661B (en) | Patrol robot | |
| CN103942850A (en) | Medical staff on-duty monitoring method based on video analysis and RFID (radio frequency identification) technology | |
| CN113223046B (en) | Method and system for identifying prisoner behaviors | |
| CN108376246A (en) | A kind of identification of plurality of human faces and tracking system and method | |
| CN111507317A (en) | Vision-based rotary equipment operation glove wearing detection method and system | |
| Jin et al. | DWCA-YOLOv5: An improve single shot detector for safety helmet detection | |
| CN112287823A (en) | Facial mask identification method based on video monitoring | |
| CN113111771A (en) | Method for identifying unsafe behaviors of power plant workers | |
| CN114155557B (en) | Positioning method, positioning device, robot and computer-readable storage medium | |
| CN113506416A (en) | Engineering abnormity early warning method and system based on intelligent visual analysis | |
| CN112560727A (en) | Crane line-crossing safety early warning method and device based on artificial intelligence | |
| CN116682162A (en) | Robot detection algorithm based on real-time video stream | |
| CN111723725A (en) | Multi-dimensional analysis system based on video AI | |
| CN116778673A (en) | Water area safety monitoring method, system, terminal and storage medium | |
| CN111291728A (en) | Detection system, detection equipment and detection method for illegal crossing of transmission belt behavior | |
| CN115953815A (en) | Monitoring method and device for infrastructure site | |
| Zhang et al. | The method for recognizing recognition helmet based on color and shape | |
| CN112329621A (en) | Processing method, system, terminal and medium for abnormal behavior early warning data |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 401329 No. 5-6, building 2, No. 66, Nongke Avenue, Baishiyi Town, Jiulongpo District, Chongqing Applicant after: MCC CCID information technology (Chongqing) Co.,Ltd. Address before: 401122 No. 11 Huijin Road, North New District of Chongqing Applicant before: CISDI CHONGQING INFORMATION TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |