CN113822242A - Image recognition technology-based helmet wearing recognition method and device - Google Patents
Image recognition technology-based helmet wearing recognition method and device Download PDFInfo
- Publication number
- CN113822242A CN113822242A CN202111384138.2A CN202111384138A CN113822242A CN 113822242 A CN113822242 A CN 113822242A CN 202111384138 A CN202111384138 A CN 202111384138A CN 113822242 A CN113822242 A CN 113822242A
- Authority
- CN
- China
- Prior art keywords
- image
- human body
- constructor
- detection
- inputting
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The invention discloses a method and a device for identifying the wearing of a safety helmet based on an image identification technology, wherein the method comprises the following steps: collecting video data in real time; the video data comprises constructor images of a construction area; inputting the video data into a human body detection model adopting an opencast network to identify a human body image in the constructor image; inputting the human body image into a depth nerve detection image SSD network model, and generating a constructor head image detection frame with the category of constructors; and inputting the head image of the constructor in the constructor head image detection frame into the trained ResNet network model to generate a detection result of whether the constructor wears the safety helmet or not. Therefore, the method has higher environmental adaptability and detection accuracy, and can carry out dynamic identification and monitoring of the wearing of the safety helmet at higher speed and higher identification rate, thereby ensuring the wearing condition of the safety helmet for construction units to automatically identify and ensuring the safe production of workers.
Description
Technical Field
The invention relates to the technical field of construction engineering construction, in particular to a helmet wearing identification method and device based on an image identification technology.
Background
The safety helmet is a protective article for preventing impact objects from hurting the head, and people entering a construction place need to wear the safety helmet to protect the head and prevent the damage of objects falling accidentally. However, the safety helmet is often not worn correctly by the personnel entering the construction site, and in order to avoid the situation, it is important to monitor the construction site in real time and detect whether the safety helmet is worn according to the regulations.
Disclosure of Invention
The invention provides a safety helmet wearing identification method and device based on an image identification technology.
According to an aspect of the invention, a method for identifying wearing of a safety helmet based on an image identification technology is provided, which comprises the following steps: collecting video data in real time; the video data comprises constructor images of a construction area; inputting the video data into a human body detection model adopting an opencast network to identify a human body image in the constructor image; inputting the human body image into a depth nerve detection image SSD network model, and generating a constructor head image detection frame with the category of constructors; and inputting the head image of the constructor in the constructor head image detection frame into the trained ResNet network model to generate a detection result of whether the constructor wears the safety helmet or not.
According to a second aspect of the present invention, there is provided a helmet wearing identification apparatus based on image identification technology, comprising: the device comprises a data acquisition unit, a first processing unit, a second processing unit and a detection unit.
The data acquisition unit is used for acquiring video data in real time; the video data comprises constructor images of a construction area; the first processing unit is used for inputting the video data into a human body detection model adopting an openposition network so as to identify a human body image in the constructor image; the second processing unit is used for inputting the human body image into the SSD network model of the depth nerve detection image and generating a constructor head image detection frame with the category of constructors; and the detection unit is used for inputting the head images of the constructors in the constructor head image detection frame into the trained ResNet network model so as to generate a detection result of whether the constructors wear the safety helmets.
The technical scheme provided by the embodiment of the invention at least has the following beneficial effects:
collecting video data in real time; the video data comprises constructor images of a construction area; inputting the video data into a human body detection model adopting an opencast network to identify a human body image in the constructor image; inputting the human body image into a depth nerve detection image SSD network model, and generating a constructor head image detection frame with the category of constructors; and inputting the head image of the constructor in the constructor head image detection frame into the trained ResNet network model to generate a detection result of whether the constructor wears the safety helmet or not. Therefore, the method has high environmental adaptability and detection accuracy, can realize automatic identification and detection (including various weather conditions and complex sites) of the wearing condition of the safety helmet of the working personnel in the construction area, can assist all levels of construction area safety supervision units to carry out intelligent supervision on the construction area, and improves the safety supervision informatization level of the construction area. Meanwhile, dynamic identification and monitoring of safety helmet wearing can be carried out at a high speed and a high identification rate, so that the wearing condition of the safety helmet for construction units is guaranteed, and safety production of workers is guaranteed.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the invention. Wherein:
fig. 1 is a flowchart of a method for identifying wearing of a safety helmet based on an image identification technology according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating sub-steps of step S2 according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating sub-steps of step S3 according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for identifying the wearing of a helmet based on image recognition technology according to an embodiment of the present invention;
FIG. 5 is a flowchart of the sub-steps of step S100 provided by an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a helmet wearing identification device based on an image identification technology according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of another helmet wearing identification device based on image identification technology according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of another helmet wearing identification device based on image identification technology according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The invention provides a helmet wearing identification method based on an image identification technology, and FIG. 1 is a flow chart according to a first embodiment of the invention.
As shown in fig. 1, the method includes, but is not limited to, the following steps:
s1: collecting video data in real time; the video data comprises constructor images of the construction area.
In the embodiment of the invention, the video acquisition device can be arranged at a construction site or in a specific area (including various weather conditions and complex sites) of the construction site, and the video acquisition device can be a camera exemplarily.
It should be noted that the foregoing examples are merely illustrative and not intended to specifically limit the embodiments of the present invention, and those skilled in the art may adopt any other mode to implement the functions described above as needed.
In the embodiment of the invention, the image acquisition device is arranged at the position capable of acquiring the image of the constructor in the construction area, so that the video data including the image of the constructor in the construction area is acquired through the image acquisition device.
It can be understood that the range of the construction area is large, the positions of the constructors are scattered, and the positions of the constructors are far away from the image acquisition devices, so that the constructors cannot acquire complete video data acquired by one image acquisition device or cannot acquire unclear images of the constructors by the video data. Based on this, in the embodiment of the invention, a plurality of image acquisition devices can be arranged, and each image acquisition device acquires video data including a part of constructor images, so that clear and complete constructor images in a construction area can be acquired, and whether constructors wear safety helmets or not in the constructor area in the construction area can be conveniently detected subsequently.
S2: and inputting the video data into a human body detection model adopting an opencast network so as to identify human body images in the constructor images.
It can be understood that, in the embodiment of the present invention, the human body detection model adopts an openposition network, and the human body detection model is input as the collected constructor image and output as the detected human body image, so as to be used for subsequent detection of the human body joint points and the human body trunk.
And S3, inputting the human body image into the SSD network model of the depth nerve detection image, and generating a constructor head image detection frame with the type of constructor.
The invention firstly trains a human body detection model by using an openfuse network, and obtains the position information of a human body through the detected human body joint point information, thereby intercepting the human body in the image. And then inputting the intercepted human body image into an SSD network to train a safety helmet detection model so as to generate a constructor head image detection frame with the category as constructor.
It will be appreciated that SSDs are simpler because SSDs encapsulate all computations completely in one network. The SSD uses VGG16 as a feature extractor (equivalent to CNN in fast RCNN), which makes the SSD easy to train, fast to detect, and can be directly integrated into systems that require real-time detection. The SSD adopts a characteristic pyramid hierarchical structure and has high detection speed.
S4: and inputting the head image of the constructor in the constructor head image detection frame into the trained ResNet network model to generate a detection result of whether the constructor wears the safety helmet or not.
In the embodiment of the invention, after video data is input into a trained safety helmet detection model and a constructor head image detection frame with the type of constructor is obtained, the head image part in the obtained constructor head image detection frame is input into a trained ResNet network model for classification operation, the obtained classifications include two types, and constructor head region images with a helmet label and a head label can be obtained, namely, the constructor head region images are used for wearing a safety helmet and a safety helmet which is not worn, so that the detection of whether the constructor wears the safety helmet or not is realized.
According to the helmet wearing identification method based on the image identification technology, video data are collected in real time; the video data comprises constructor images of a construction area; inputting the video data into a human body detection model adopting an opencast network to identify a human body image in the constructor image; inputting the human body image into a depth nerve detection image SSD network model, and generating a constructor head image detection frame with the category of constructors; and inputting the head image of the constructor in the constructor head image detection frame into the trained ResNet network model to generate a detection result of whether the constructor wears the safety helmet or not. Therefore, automatic identification and detection (including various weather conditions and complex sites) of the wearing condition of the safety helmet of the working personnel in the construction area can be realized, intelligent supervision of the construction area can be assisted by safety supervision units of all levels of the construction area, and the safety supervision informatization level of the construction area is improved. Meanwhile, dynamic identification and monitoring of safety helmet wearing can be carried out at a high speed and a high identification rate, so that the wearing condition of the safety helmet for construction units is guaranteed, and safety production of workers is guaranteed.
Fig. 2 is a flowchart illustrating sub-steps of step S2 according to an embodiment of the present invention.
As shown in fig. 2, S2 in the embodiment of the present invention includes, but is not limited to, the following sub-steps:
s21: and intercepting a plurality of pictures from the video data.
In the embodiment of the invention, a plurality of pictures are intercepted in the video data collected in real time, and illustratively, one picture can be intercepted every second.
S22: and inputting the plurality of pictures into the human body detection model, and detecting all human body joint points in the plurality of pictures.
In the embodiment of the invention, for a human body detection part, a human body posture recognition openposition network is adopted to detect all human body joint points in an image, and based on human body postures of human bodies in different application scenes, joint points at various positions of shoulders, legs, steps and the like of the human bodies are detected by recognizing key points.
S23: detecting human body trunks in a plurality of pictures, and correspondingly forming human body joint points and the human body trunks into a single human body image through a specific algorithm.
In the embodiment of the invention, the input image is identified, the human body trunk in the image is detected, illustratively, an openposition network is adopted, all human body joint points in the image are detected firstly, then all human body trunks in the image are detected, a person is formed by the corresponding joint points and the trunks through a specific algorithm, and the formed single human body image is the formed image corresponding to the joint points and the human body trunk. The specific algorithm can be set by those skilled in the art according to actual requirements, and the invention is not particularly limited.
S24: and identifying the human body image in the constructor image based on the single human body image, and storing the position information of each joint point of the human body image.
In the embodiment of the invention, after the human body in the image is identified, the position information of each joint point of the human body is stored for subsequent human body image interception. The human body detection model adopting the openposition network can ensure the real-time performance and accuracy of recognition, and can still obtain better recognition effect on various postures and shielded human bodies.
As shown in fig. 3, S3 in the embodiment of the present invention includes, but is not limited to, the following sub-steps:
s31: and intercepting the human body image according to the stored position information of each joint point of the human body image.
S32: and corresponding the position information of the marked safety helmet to the intercepted human body image, inputting the position information as the input of a human body head detection part to the SSD network model of the deep nerve detection image, and generating a constructor head image detection frame with the category of constructors.
It will be appreciated that the output space of the bounding box is discretized into a set of default boxes, which are the initial detection boxes, having different aspect ratios and scales at each feature map location. In prediction, the network will generate a score for each default box that all object classes exist and adjust the default box to better match the shape of the object, i.e., the final detection box. Thereby, the constructor head image detection frame of which the category is the constructor can be generated.
As shown in fig. 4, the method for identifying wearing of a safety helmet based on an image identification technology provided in the embodiment of the present invention further includes:
s100: a training data set is obtained.
It can be understood that the helmet wearing identification method based on the image identification technology provided in the embodiment of the present invention includes training the human body detection model, the helmet detection model, and the ResNet network model, respectively, to obtain the trained human body detection model, helmet detection model, and ResNet network model.
In the embodiment of the present invention, a training sample set is obtained, and it can be understood that the training samples are enough in number to enable the training model to have higher recognition accuracy.
S200: inputting the training data set into the human body detection model, the safety helmet detection model and the ResNet network model, and training the human body detection model, the safety helmet detection model and the ResNet network model to generate the trained human body detection model, the safety helmet detection model and the ResNet network model.
As shown in fig. 5, S100 in the embodiment of the present invention includes, but is not limited to, the following sub-steps:
s101: sample video data is collected.
In the embodiment of the present invention, the manner of acquiring the sample video data may be the same as the manner of acquiring the video data in real time, and details are not repeated here.
S102: and intercepting a plurality of sample pictures from the sample video data.
In the embodiment of the invention, a plurality of sample pictures are intercepted from the sample video data, and it can be understood that the sample pictures comprise sample pictures of a safety helmet detection model and sample pictures of a human body detection model and a ResNet network model.
It can be understood that the same sample picture can be used for the sample picture of the helmet detection model and the sample pictures of the human body detection model and the ResNet network model, and the sample picture of the ResNet network model is a sample picture of a worn helmet marked as helmet and/or a sample picture of an unworn helmet marked as head, wherein both the sample pictures include images of construction personnel, so that different marks of the sample picture of the ResNet network model can be combined into one mark and input into the helmet detection model to train the helmet detection model.
The sample picture of the safety helmet detection model can be a sample picture marked as a constructor and/or a sample picture marked as a non-constructor; the sample pictures of the ResNet network model can be a sample picture of a worn helmet marked as helmet and/or a sample picture of an unworn helmet marked as head.
S103: and marking the constructor part in the sample picture by using marking software, and marking the constructor part as a safety helmet or a safety helmet which is not worn, so as to generate a training data set.
In the embodiment of the invention, data set labeling software can be used for manual labeling, the image part of the constructor in the sample picture is labeled, and the image of the constructor is labeled as a safety helmet worn or a safety helmet not worn, so that a training sample set is generated.
Fig. 6 is a schematic structural diagram of a helmet wearing identification device based on an image identification technology according to an embodiment of the present invention.
As shown in fig. 6, the helmet wearing identification device 1 based on the image identification technology is provided in the embodiment of the present invention. This safety helmet wearing identification device includes: a data acquisition unit 11, a first processing unit 12, a second processing unit 13 and a detection unit 14.
The data acquisition unit 11 is used for acquiring video data in real time; the video data comprises constructor images of a construction area;
the first processing unit 12 is configured to input the video data to a human body detection model adopting an openposition network, so as to identify a human body image in the constructor image;
the second processing unit 13 is configured to input the human body image into the SSD network model of the deep neural inspection image, and generate a detection frame of the head image of the constructor with the category of the constructor;
and the detection unit 14 is used for inputting the head images of the constructors in the constructor head image detection frame into the trained ResNet network model so as to generate a detection result of whether the constructors wear the safety helmets.
As shown in fig. 7, in the embodiment of the present invention, the first processing unit 12 includes:
a picture acquiring unit 121, configured to capture multiple pictures from video data;
a joint point detection unit 122, configured to input the multiple pictures into the human body detection model, and detect all human body joint points in the multiple pictures; and the number of the first and second groups,
the trunk detection unit 123 is configured to detect a human trunk in multiple pictures, and form a single human body image by using a specific algorithm to correspond the human body joint points and the human trunk;
and an identification holding unit 124 for identifying a human body image among the constructor images based on the single human body image and holding position information of each joint point of the human body image.
As shown in fig. 8, in the embodiment of the present invention, the second processing unit 13 includes:
a joint processing unit 131 for intercepting the human body image according to the position information of each joint of the stored human body image;
and a detection frame generating unit 132, configured to correspond the position information of the labeled helmet to the captured human body image, and input the position information as an input of a human body head detection part to the SSD network model of the deep neural detection image, so as to generate a constructor head image detection frame of which the category is constructor.
It should be noted that the foregoing explanation of the method for identifying wearing a helmet based on an image recognition technology is also applicable to the device for identifying wearing a helmet based on an image recognition technology of this embodiment, and is not repeated herein.
According to the helmet wearing identification device based on the image identification technology, provided by the embodiment of the invention, the data acquisition unit is used for acquiring video data in real time; the video data comprises constructor images of a construction area; the first processing unit is used for inputting the video data into a human body detection model adopting an openposition network so as to identify a human body image in the constructor image; the second processing unit is used for inputting the human body image into the SSD network model of the depth nerve detection image and generating a constructor head image detection frame with the category of constructors; and the detection unit is used for inputting the head images of the constructors in the constructor head image detection frame into the trained ResNet network model so as to generate a detection result of whether the constructors wear the safety helmets.
Therefore, the method has high environmental adaptability and detection accuracy, can realize automatic identification and detection of the wearing condition of the safety helmet of the working personnel in the construction area, can assist the safety supervision units in various construction areas to carry out intelligent supervision on the construction areas, and improves the safety supervision informatization level of the construction areas. Meanwhile, dynamic identification and monitoring of safety helmet wearing can be carried out at a high speed and a high identification rate, so that the wearing condition of the safety helmet for construction units is guaranteed, and safety production of workers is guaranteed.
Throughout the specification and claims, the term "comprising" is to be interpreted as open-ended, inclusive, meaning that it is "including, but not limited to," unless the context requires otherwise. In the description herein, the terms "some embodiments," "exemplary embodiments," "examples," and the like are intended to indicate that a particular feature, structure, material, or characteristic described in connection with the embodiments or examples is included in at least one embodiment or example of the invention. The schematic representations of the above terms are not necessarily referring to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be included in any suitable manner in any one or more embodiments or examples.
"plurality" means two or more unless otherwise specified. The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.
The use of "for" herein means open and inclusive language that does not exclude devices adapted or configured to perform additional tasks or steps.
Additionally, the use of "based on" means open and inclusive, as a process, step, calculation, or other action that is "based on" one or more stated conditions or values may in practice be based on additional conditions or values beyond those stated.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A safety helmet wearing identification method based on an image identification technology is characterized by comprising the following steps:
collecting video data in real time; the video data comprises constructor images of a construction area;
inputting the video data into a human body detection model adopting an opencast network to identify a human body image in the constructor image;
inputting the human body image into a depth nerve detection image SSD network model, and generating a constructor head image detection frame with the category of constructors;
and inputting the head image of the constructor in the constructor head image detection frame into the trained ResNet network model to generate a detection result of whether the constructor wears the safety helmet or not.
2. The method of claim 1, wherein the inputting the video data into a human detection model using an opencast network to identify human images among the images of the constructors comprises:
intercepting a plurality of pictures from the video data;
inputting the multiple pictures into a human body detection model adopting an openposition network, and detecting all human body joint points in the multiple pictures; and the number of the first and second groups,
detecting human body trunks in the multiple pictures, and correspondingly forming the human body joint points and the human body trunks into a single human body image through a specific algorithm;
and identifying a human body image in the constructor image based on the single human body image, and storing the position information of each joint point of the human body image.
3. The method of claim 2, wherein the inputting the human body image into a depth neural detection image (SSD) network model, and generating a constructor head image detection frame of the constructor type comprises:
intercepting the human body image according to the stored position information of each joint point of the human body image;
and corresponding the position information of the marked safety helmet to the intercepted human body image, inputting the position information as the input of a human body head detection part to the SSD network model of the deep nerve detection image, and generating a constructor head image detection frame with the category of constructors.
4. The method of any of claims 1 to 3, further comprising:
acquiring a training data set;
inputting the training data set into a human body detection model, a safety helmet detection model and a ResNet network model, and training the human body detection model, the safety helmet detection model and the ResNet network model to generate the trained human body detection model, the safety helmet detection model and the ResNet network model.
5. The method of claim 4, wherein the obtaining a training data set comprises:
collecting sample video data;
intercepting a plurality of sample pictures from the sample video data;
and marking the head image part of the constructor in the sample picture by using marking software, and marking the head image part as a safety helmet or a safety helmet which is not worn to generate the training data set.
6. A helmet wearing identification device based on image identification technology is characterized by comprising:
the data acquisition unit is used for acquiring video data in real time; the video data comprises constructor images of a construction area;
the first processing unit is used for inputting the video data into a human body detection model adopting an openposition network so as to identify a human body image in the constructor image;
the second processing unit is used for inputting the human body image into a depth nerve detection image SSD network model and generating a constructor head image detection frame with the category of constructors;
and the detection unit is used for inputting the head images of the constructors in the constructor head image detection frame into the trained ResNet network model so as to generate a detection result of whether the constructors wear the safety helmets.
7. The apparatus of claim 6, wherein the first processing unit comprises:
the image acquisition unit is used for intercepting a plurality of images from the video data;
the joint point detection unit is used for inputting the plurality of pictures into a human body detection model and detecting all human body joint points in the plurality of pictures; and the number of the first and second groups,
the trunk detection unit is used for detecting the human trunk in the multiple pictures and correspondingly forming a single human body image by the human body joint points and the human body trunk through a specific algorithm;
and the identification and storage unit is used for identifying the human body image in the constructor image based on the single human body image and storing the position information of each joint point of the human body image.
8. The apparatus of claim 7, wherein the second processing unit comprises:
the joint point processing unit is used for intercepting the human body image according to the position information of each joint point of the stored human body image;
and the detection frame generation unit is used for corresponding the marked position information of the safety helmet to the intercepted human body image, inputting the position information as the input of a human body head detection part to the SSD network model of the deep nerve detection image and generating the constructor head image detection frame with the type of constructor.
9. The apparatus of claim 6, further comprising:
an acquisition unit for acquiring a training data set;
and the training unit is used for inputting the training data set into a human body detection model, a safety helmet detection model and a ResNet network model, and training the human body detection model, the safety helmet detection model and the ResNet network model to generate the trained human body detection model, the safety helmet detection model and the ResNet network model.
10. The apparatus of claim 9, wherein the obtaining unit comprises:
the data acquisition unit is used for acquiring sample video data;
the picture intercepting unit is used for intercepting a plurality of sample pictures from the sample video data;
and the image marking unit is used for marking the head image part of the constructor in the sample picture through marking software, marking the head image part as a safety helmet to be worn or not worn, and generating the training data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111384138.2A CN113822242B (en) | 2021-11-19 | 2021-11-19 | Image recognition technology-based helmet wearing recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111384138.2A CN113822242B (en) | 2021-11-19 | 2021-11-19 | Image recognition technology-based helmet wearing recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113822242A true CN113822242A (en) | 2021-12-21 |
| CN113822242B CN113822242B (en) | 2022-02-25 |
Family
ID=78918052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111384138.2A Active CN113822242B (en) | 2021-11-19 | 2021-11-19 | Image recognition technology-based helmet wearing recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113822242B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114724080A (en) * | 2022-03-31 | 2022-07-08 | 慧之安信息技术股份有限公司 | Construction site intelligent safety identification method and device based on security video monitoring |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279483A (en) * | 2015-09-28 | 2016-01-27 | 华中科技大学 | Fall-down behavior real-time detection method based on depth image |
| 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 |
| CN110502965A (en) * | 2019-06-26 | 2019-11-26 | 哈尔滨工业大学 | A kind of construction safety helmet wearing monitoring method based on the estimation of computer vision human body attitude |
| CN110569722A (en) * | 2019-08-01 | 2019-12-13 | 江苏濠汉信息技术有限公司 | Visual analysis-based constructor dressing standard detection method and device |
| CN111666917A (en) * | 2020-06-19 | 2020-09-15 | 北京市商汤科技开发有限公司 | Attitude detection and video processing method and device, electronic equipment and storage medium |
| CN112633111A (en) * | 2020-12-17 | 2021-04-09 | 常州大学 | Method and device for detecting wearing of safety helmet and storage medium |
| CN112651291A (en) * | 2020-10-01 | 2021-04-13 | 新加坡依图有限责任公司(私有) | Video-based posture estimation method, device, medium and electronic equipment |
| CN112990149A (en) * | 2021-05-08 | 2021-06-18 | 创新奇智(北京)科技有限公司 | Multi-mode-based high-altitude safety belt detection method, device, equipment and storage medium |
| CN113392707A (en) * | 2021-05-13 | 2021-09-14 | 上海湃道智能科技有限公司 | Wearing safety helmet recognition system |
| CN113536842A (en) * | 2020-04-15 | 2021-10-22 | 普天信息技术有限公司 | Electric power operator safety dressing identification method and device |
-
2021
- 2021-11-19 CN CN202111384138.2A patent/CN113822242B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279483A (en) * | 2015-09-28 | 2016-01-27 | 华中科技大学 | Fall-down behavior real-time detection method based on depth image |
| 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 |
| CN110502965A (en) * | 2019-06-26 | 2019-11-26 | 哈尔滨工业大学 | A kind of construction safety helmet wearing monitoring method based on the estimation of computer vision human body attitude |
| CN110569722A (en) * | 2019-08-01 | 2019-12-13 | 江苏濠汉信息技术有限公司 | Visual analysis-based constructor dressing standard detection method and device |
| CN113536842A (en) * | 2020-04-15 | 2021-10-22 | 普天信息技术有限公司 | Electric power operator safety dressing identification method and device |
| CN111666917A (en) * | 2020-06-19 | 2020-09-15 | 北京市商汤科技开发有限公司 | Attitude detection and video processing method and device, electronic equipment and storage medium |
| CN112651291A (en) * | 2020-10-01 | 2021-04-13 | 新加坡依图有限责任公司(私有) | Video-based posture estimation method, device, medium and electronic equipment |
| CN112633111A (en) * | 2020-12-17 | 2021-04-09 | 常州大学 | Method and device for detecting wearing of safety helmet and storage medium |
| CN112990149A (en) * | 2021-05-08 | 2021-06-18 | 创新奇智(北京)科技有限公司 | Multi-mode-based high-altitude safety belt detection method, device, equipment and storage medium |
| CN113392707A (en) * | 2021-05-13 | 2021-09-14 | 上海湃道智能科技有限公司 | Wearing safety helmet recognition system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114724080A (en) * | 2022-03-31 | 2022-07-08 | 慧之安信息技术股份有限公司 | Construction site intelligent safety identification method and device based on security video monitoring |
| CN114724080B (en) * | 2022-03-31 | 2023-10-27 | 慧之安信息技术股份有限公司 | Building site intelligent safety identification method and device based on security video monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113822242B (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110613B (en) | Track traffic abnormal personnel detection method based on motion recognition | |
| CN111144263B (en) | Construction worker high-falling accident early warning method and device | |
| Fang et al. | Detecting non-hardhat-use by a deep learning method from far-field surveillance videos | |
| CN110502965B (en) | Construction safety helmet wearing monitoring method based on computer vision human body posture estimation | |
| CN108216252B (en) | Subway driver vehicle-mounted driving behavior analysis method, vehicle-mounted terminal and system | |
| Han et al. | A vision-based motion capture and recognition framework for behavior-based safety management | |
| CN110263686A (en) | A kind of construction site safety of image cap detection method based on deep learning | |
| CN108319926A (en) | A kind of the safety cap wearing detecting system and detection method of building-site | |
| CN108596221B (en) | Image recognition method and device for scale reading | |
| CN111726586A (en) | Production system operation standard monitoring and reminding system | |
| CN112347916B (en) | Video image analysis-based power field operation safety monitoring method and device | |
| CN111598040A (en) | Construction worker identity identification and safety helmet wearing detection method and system | |
| CN109598229A (en) | Monitoring system and its method based on action recognition | |
| CN107256386A (en) | Human behavior analysis method based on deep learning | |
| Xie et al. | A convolutional neural network based approach towards real-time hard hat detection | |
| CN110688980B (en) | Human body posture classification method based on computer vision | |
| CN113822242B (en) | Image recognition technology-based helmet wearing recognition method and device | |
| CN112396658A (en) | Indoor personnel positioning method and positioning system based on video | |
| CN108960071A (en) | A kind of eye opening closed-eye state detection method | |
| CN113920326A (en) | Tumble behavior identification method based on human skeleton key point detection | |
| CN109389040B (en) | Inspection method and device for safety dressing of personnel in operation field | |
| CN113780342A (en) | Intelligent detection method and device based on self-supervision pre-training and robot | |
| CN109308444A (en) | A kind of abnormal behaviour recognition methods under indoor environment | |
| Jiang et al. | Vision-guided active tactile perception for crack detection and reconstruction | |
| CN112597903A (en) | Electric power personnel safety state intelligent identification method and medium based on stride measurement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information |
Inventor after: Shen Yongli Inventor after: Zhou Qiwen Inventor after: Li Xingang Inventor after: Jia Runzhi Inventor before: Shen Yongli Inventor before: Zhou Qiwen Inventor before: Li Xingang |
|
| CB03 | Change of inventor or designer information |