CN114298138A - Wearing identification method and device of safety helmet, computer equipment and storage medium - Google Patents
Wearing identification method and device of safety helmet, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114298138A CN114298138A CN202111348999.5A CN202111348999A CN114298138A CN 114298138 A CN114298138 A CN 114298138A CN 202111348999 A CN202111348999 A CN 202111348999A CN 114298138 A CN114298138 A CN 114298138A
- Authority
- CN
- China
- Prior art keywords
- image
- helmet
- personnel
- person
- wearing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Alarm Systems (AREA)
Abstract
The application relates to a wearing identification method and device of a safety helmet, computer equipment and a storage medium. The method comprises the following steps: acquiring a field image acquired by monitoring equipment in real time; extracting a personnel image from the live image; detecting whether a crash helmet is worn based on the person image; and if the safety helmet is detected not to be worn, giving an alarm. Thereby can detect whether constructor wears to have the safety helmet through image recognition's mode, need not artifical supervision, discernment is more accurate but efficiency is higher to can in time send out the police dispatch newspaper and remind when detecting constructor does not wear the safety helmet, make constructor in time wear the safety helmet, improve the security of construction operation.
Description
Technical Field
The present application relates to the field of helmet identification technologies, and in particular, to a method and an apparatus for identifying wearing of a helmet, a computer device, and a storage medium.
Background
With the progress of society, the safety of human bodies is more and more important, in the construction industry, many high-risk works need to be completed manually, but some related constructors have weak safety consciousness, and do not wear safety helmets in the construction process. Therefore, for the safety of the constructors, how to identify whether the constructors wear the safety helmets is a problem to be solved at present.
In the conventional technology, a construction supervisor determines a constructor who does not wear the safety helmet through visual observation or by looking up a camera.
However, the conventional method still has the possibility that the constructor does not wear the safety helmet but is not found due to the negligence that the supervisor may have, and the constructor checks whether the constructor wears the safety helmet by using the manual work, which is time-consuming, labor-consuming and inefficient.
Disclosure of Invention
In view of the above, it is necessary to provide a method and an apparatus for identifying wearing of a helmet, a computer device, and a storage medium, which can automatically identify whether a worker wears the helmet.
A method of wear identification of a hard hat, the method comprising: acquiring a field image acquired by monitoring equipment in real time; extracting a personnel image from the live image; detecting whether a crash helmet is worn based on the person image; and if the safety helmet is detected not to be worn, giving an alarm.
In one embodiment, the extracting the person image from the live image includes: inputting the field image into an SVM classifier to obtain the position coordinates of the personnel image in the field image; and extracting a person image from the live image based on the position coordinates.
In one embodiment, the extracting the person image from the live image based on the position coordinates includes: performing multi-window maximization processing on the personnel images, and combining the overlapped personnel images into the same personnel image; and carrying out normalization processing on the personnel image, and adjusting the contrast of the personnel image to be within a preset range.
In one embodiment, the detecting whether a safety helmet is worn based on the person image includes: and inputting the personnel image into a cascade classifier to obtain a detection result of whether the safety helmet is worn.
In one embodiment, the method further comprises: obtaining sample images, wherein the sample images comprise images of persons wearing safety helmets and images of persons not wearing safety helmets; training the cascade classifier based on the sample image until an output result of whether the cascade classifier is wearing a helmet is consistent with the sample image.
In one embodiment, the number of images of the person wearing the headgear is greater than the number of images of the person not wearing the headgear.
A wear identification device for a hard hat, the device comprising: the image acquisition module is used for acquiring field images acquired by the monitoring equipment in real time; the image extraction module is used for extracting a personnel image from the live image; a wearing detection module for detecting whether a crash helmet is worn based on the person image; and the alarm module is used for giving an alarm if the safety helmet is detected not to be worn.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program: acquiring a field image acquired by monitoring equipment in real time; extracting a personnel image from the live image; detecting whether a crash helmet is worn based on the person image; and if the safety helmet is detected not to be worn, giving an alarm.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of: acquiring a field image acquired by monitoring equipment in real time; extracting a personnel image from the live image; detecting whether a crash helmet is worn based on the person image; and if the safety helmet is detected not to be worn, giving an alarm.
A computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of: acquiring a field image acquired by monitoring equipment in real time; extracting a personnel image from the live image; detecting whether a crash helmet is worn based on the person image; and if the safety helmet is detected not to be worn, giving an alarm.
According to the wearing identification method and device of the safety helmet, the computer equipment and the storage medium, the real-time monitoring of the construction site is realized by acquiring the site image from the monitoring equipment in real time. The personnel images are extracted from the field images, so that the personnel in the field images are accurately screened out, and whether the personnel wear the safety helmet or not is conveniently detected. Whether a person in the image wears a safety helmet or not is determined by carrying out image detection on the person image, and if the fact that the person in the image does not wear the safety helmet is detected, an alarm is sent out to remind. Thereby can detect whether constructor wears to have the safety helmet through image recognition's mode, need not artifical supervision, discernment is more accurate but efficiency is higher to can in time send out the police dispatch newspaper and remind when detecting constructor does not wear the safety helmet, make constructor in time wear the safety helmet, improve the security of construction operation.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments or the conventional technologies of the present application, the drawings used in the descriptions of the embodiments or the conventional technologies will be briefly introduced below, it is obvious that the drawings in the following descriptions are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart illustrating a method for identifying the wearing of a helmet in one embodiment;
FIG. 2 is a block diagram of a wear identification device for a helmet in one embodiment;
FIG. 3 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Embodiments of the present application are set forth in the accompanying drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
As used herein, the singular forms "a", "an" and "the" may include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises/comprising," "includes" or "including," etc., specify the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof.
As described in the background art, the supervision of whether a safety helmet is worn by a constructor in a construction site in the prior art is not strict, and the constructor who does not wear the safety helmet is easy to miss. The inventor researches and discovers that the problem occurs because in the prior art, whether a construction worker wears a safety helmet is identified and supervised by a construction supervisor, and because the construction supervisor has limited energy, a plurality of constructors and complex construction site personnel, whether each constructor wears a safety helmet cannot be accurately identified.
For the above reasons, the present invention provides a method and apparatus for identifying wearing of a helmet, a computer device, and a storage medium, which can automatically identify whether a worker wears the helmet.
In one embodiment, as shown in fig. 1, there is provided a wearing recognition method of a helmet, the method including:
and S100, acquiring a field image acquired by the monitoring equipment in real time.
Illustratively, the monitoring device may be a camera or the like fixedly installed in advance in a construction area for acquiring image data of the corresponding monitoring area. The monitoring equipment can also be movable, such as but not limited to a movable robot, a monitoring vehicle and the like, and can acquire image data of the construction area from multiple angles.
In step S110, a person image is extracted from the live image.
Step S120, whether the safety helmet is worn or not is detected based on the person image.
In step S130, if it is detected that the safety helmet is not worn, an alarm is given.
In the embodiment, the real-time monitoring of the construction site is realized by acquiring the image of the site from the monitoring equipment in real time. The personnel images are extracted from the field images, so that the personnel in the field images are accurately screened out, and whether the personnel wear the safety helmet or not is conveniently detected. Whether a person in the image wears a safety helmet or not is determined by carrying out image detection on the person image, and if the fact that the person in the image does not wear the safety helmet is detected, an alarm is sent out to remind. Thereby can detect whether constructor wears to have the safety helmet through image recognition's mode, need not artifical supervision, discernment is more accurate but efficiency is higher to can in time send out the police dispatch newspaper and remind when detecting constructor does not wear the safety helmet, make constructor in time wear the safety helmet, improve the security of construction operation.
In one embodiment, step S110 includes:
step S1102, inputting the live image into an SVM (support vector machines) classifier, and obtaining the position coordinates of the person image in the live image.
Illustratively, the live image is input into an SVM classifier, an HOGDescriptor in opencv is called, and a getDefaultPopleDetector () function detects the human body of the live image and acquires the position coordinates of the personnel image in the live image. And selecting the position range of the human head by using the rectangular frame, and determining the coordinates of the head of the person.
Illustratively, the human head position comprises a first coordinate and a second coordinate, and the first coordinate and the second coordinate are used for determining a corresponding area in the image to be recognized. For example, when the region corresponding to the head position is a rectangle, the first coordinate and the second coordinate are coordinates of the rectangle that are diagonal to each other. And according to a preset proportion, according to the first coordinate and the second coordinate of the initial area map, obtaining the first coordinate and the second coordinate of the expanded initial area map (namely the head area map). For example, when the initial region map is a rectangle, the first coordinate of the upper left corner of the initial region map is (X1, Y1), the second coordinate of the lower right corner of the initial region map is (X2, Y2), and the preset proportion is 20%, that is, the head region map is obtained by expanding the size of 20% upward, downward, left, and right of the initial region map. The first coordinate of the upper left corner of the head region map is (X3, Y3), and the second coordinate of the lower right corner of the head region map is (X4, Y4) then:
X3＝X1–(X2-X1)*0.2；
Y3＝Y1–(Y2-Y1)*0.2；
X4＝X2+(X2-X1)*0.2；
Y4＝Y2+(Y2-Y1)*0.2。
illustratively, the human detection model may be one of a plurality of algorithmic models. For example, the human body detection model may be a neural network model or the like. The neural network model may include at least one of a VGG (visual Geometry Group network) model, a Faster R-CNN model, an SSD (Single Shot MultiBox Detector) model, a BP neural network model, and a YOLO model.
In step S1104, a person image is extracted from the live image based on the position coordinates.
Specifically, the multi-window maximization processing is performed on the personnel images, and the overlapped personnel images are combined into the same personnel image, so that when the personnel images are overlapped and difficult to distinguish, the personnel images are selected by using one large rectangular frame, and the precision of personnel image identification can be improved. The personnel image is normalized, and the contrast of the personnel image is adjusted to be within a preset range, so that the influence caused by local shadow and lighting change of the image is reduced, and meanwhile, the interference of noise can be inhibited.
In this embodiment, the position coordinates of the person image are extracted from the live image by the SVM classifier, so as to determine the person image in the live image. Thereby providing a detection sample for detecting whether the safety helmet is worn by a person.
In one embodiment, step S120 includes:
and step S1202, inputting the personnel image into the cascade classifier to obtain a detection result of whether the safety helmet is worn.
Illustratively, the cascade classifier may be an OpenCV self-contained cascade classification trainer OpenCV _ raincascade. The cascade classification trainer opencv _ training may be a HAAR-like features training classifier, an LBP (Local Binary Pattern) features training classifier, and an HOG (Histogram of Oriented gradients) features training classifier.
In the present embodiment, the person image is detected by the feature training classifier, so that it can be determined whether the person image is wearing a helmet.
In one embodiment, the wearing identification method of the helmet further comprises:
and step S200, acquiring sample images, wherein the sample images comprise images of persons wearing safety helmets and images of persons not wearing safety helmets.
Specifically, the sample image includes positive sample data including at least an image of a person wearing a hard hat, and negative sample data including an image of a person not wearing a hard hat.
Specifically, since a person image with a helmet that is not standard for wearing a helmet may also exist in the positive sample data and is considered to be an unworn helmet, the number of images of the person wearing a helmet is greater than the number of images of the person without a helmet.
Illustratively, the number of images of a person wearing a crash helmet is 3000, and the number of images of a person not wearing a crash helmet is 2000.
Illustratively, the sample image is processed by one or more image amplification modes of inversion transformation, random pruning, translation transformation, scale transformation, noise disturbance and rotation transformation to obtain an amplification image.
And step S220, training the cascade classifier based on the sample image until the output result of the cascade classifier on whether the safety helmet is worn is consistent with the sample image.
Specifically, an AdaBoost algorithm is used to train a preset feature training classifier, and the weights of training samples of the preset feature training classifier and the number of the preset feature training classifiers are adjusted until the error rate of training images of the preset feature training classifier is zero or the number of the preset feature training classifiers reaches a preset value. The AdaBoost algorithm is a combined classification method algorithm for improving classification accuracy. The method is an iterative algorithm, and the core idea is to train different classifiers, namely weak classifiers, aiming at the same training set, and then to assemble the weak classifiers to construct a stronger final classifier. The algorithm is implemented by changing data distribution, and determines the weight of each sample according to whether the classification of each sample in each training set is correct and the accuracy of the last overall classification. And sending new data for modifying the weight to a lower-layer classifier for training, and then fusing the classifiers obtained by each training to serve as a final decision classifier.
In this embodiment, the cascade classifier is trained based on the sample image data, so that the cascade classifier can accurately identify a person wearing a helmet and a person not wearing a helmet, and the accuracy of identification of the cascade classifier is improved by using the AdaBoost algorithm, so that the cascade classifier can more accurately identify whether the person wears a helmet. Compared with the traditional method using deep learning to identify whether a person wears a safety helmet or not, the GPU is used for accelerating identification, and the method has the advantages of low requirement on hardware equipment, lower cost and stable algorithm.
In one embodiment, the wearing identification method of the helmet further comprises:
and step S300, carrying out face recognition on the personnel image to acquire the face characteristics of the personnel image.
Specifically, an ArcFace (Additive Angular Margin Loss) algorithm is used for carrying out face recognition on the person image, the face is mapped into a feature space, and the cosine distance is used for calculating the similarity of the face image. The dot product between the deep convolutional neural network feature and the last fully connected layer is equal to the cosine distance after feature and weight normalization. And calculating an included angle between the face feature and the target weight by utilizing a cosine function (arc-cosine function). Then, an additional angular margin is added to the target angle, and the target logit is obtained again by a cosine function. Therefore, the angle distance is more directly influenced on the angle than the cosine distance, and the human face features are more accurately distinguished.
And step S320, comparing the human face features with a preset human face library, and determining the personnel corresponding to the personnel image.
Step S340, if the safety helmet is not worn on the personnel image, an alarm is given, and the alarm at least comprises the name of the personnel corresponding to the personnel image.
Specifically, the alarm may be specifically a text prompt message, may also be a sound prompt message, and may also be a combination of the text prompt message and the sound prompt message. And sending the generated alarm to the alarm equipment corresponding to the information type, so that the alarm equipment displays the corresponding alarm. For example, the alarm device may display text prompt information through a corresponding display interface, and display voice prompt information through a speaker, thereby prompting.
In the embodiment, through the face recognition algorithm, the personnel who do not wear the safety helmet can be identified, and the identity of the personnel who do not wear the safety helmet is determined, so that the prompt is pointed, constructors can be effectively reminded of wearing the safety helmet, and the hidden danger of accidents in construction is reduced.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
In one embodiment, as shown in fig. 2, there is provided a wearing recognition device of a helmet, including: image acquisition module 901, image extraction module 902, wear detection module 903 and alarm module 904, wherein:
the image obtaining module 901 is configured to obtain a field image acquired by the monitoring device in real time.
An image extraction module 902, configured to extract a person image from the live image.
And a wearing detection module 903 for detecting whether the safety helmet is worn based on the person image.
And an alarm module 904 for giving an alarm if the non-wearing of the safety helmet is detected.
For specific definition of the wearing identification device of the safety helmet, reference may be made to the above definition of the wearing identification method of the safety helmet, and details are not repeated here. The various modules in the wearing identification device of the helmet can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.
In one embodiment, a computer device is provided, the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of wear identification of a safety helmet.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the above-described method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
In the description herein, references to the description of "some embodiments," "other embodiments," "desired embodiments," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, a schematic description of the above terminology may not necessarily refer to the same embodiment or example.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for identifying wearing of a helmet, the method comprising:
acquiring a field image acquired by monitoring equipment in real time;
extracting a personnel image from the live image;
detecting whether a crash helmet is worn based on the person image;
and if the safety helmet is detected not to be worn, giving an alarm.
2. The method of claim 1, wherein said extracting a person image from said live image comprises:
inputting the field image into an SVM classifier to obtain the position coordinates of the personnel image in the field image;
and extracting a person image from the live image based on the position coordinates.
3. The method of claim 2, wherein extracting the image of the person from the live image based on the location coordinates comprises:
performing multi-window maximization processing on the personnel images, and combining the overlapped personnel images into the same personnel image;
and carrying out normalization processing on the personnel image, and adjusting the contrast of the personnel image to be within a preset range.
4. The method of any of claims 1 to 3, wherein the detecting whether to wear a hard hat based on the person image comprises:
and inputting the personnel image into a cascade classifier to obtain a detection result of whether the safety helmet is worn.
5. The method of claim 4, further comprising:
obtaining sample images, wherein the sample images comprise images of persons wearing safety helmets and images of persons not wearing safety helmets;
training the cascade classifier based on the sample image until an output result of whether the cascade classifier is wearing a helmet is consistent with the sample image.
6. The method of claim 5, wherein the number of images of the person wearing the hard hat is greater than the number of images of the person without the hard hat.
7. A wearing recognition device for a helmet, the device comprising:
the image acquisition module is used for acquiring field images acquired by the monitoring equipment in real time;
the image extraction module is used for extracting a personnel image from the live image;
a wearing detection module for detecting whether a crash helmet is worn based on the person image;
and the alarm module is used for giving an alarm if the safety helmet is detected not to be worn.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111348999.5A CN114298138A (en) | 2021-11-15 | 2021-11-15 | Wearing identification method and device of safety helmet, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111348999.5A CN114298138A (en) | 2021-11-15 | 2021-11-15 | Wearing identification method and device of safety helmet, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114298138A true CN114298138A (en) | 2022-04-08 |
Family
ID=80963822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111348999.5A Pending CN114298138A (en) | 2021-11-15 | 2021-11-15 | Wearing identification method and device of safety helmet, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114298138A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152863A (en) * | 2023-04-19 | 2023-05-23 | 尚特杰电力科技有限公司 | Personnel information identification method and device, electronic equipment and storage medium |
| CN116740819A (en) * | 2023-08-14 | 2023-09-12 | 中通信息服务有限公司 | Method and device for identifying construction abnormal behavior in construction site based on AI algorithm |
| CN116934091A (en) * | 2023-07-25 | 2023-10-24 | 广东至衡工程管理有限公司 | Construction site monitoring method and device, computer equipment and storage medium |
-
2021
- 2021-11-15 CN CN202111348999.5A patent/CN114298138A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152863A (en) * | 2023-04-19 | 2023-05-23 | 尚特杰电力科技有限公司 | Personnel information identification method and device, electronic equipment and storage medium |
| CN116934091A (en) * | 2023-07-25 | 2023-10-24 | 广东至衡工程管理有限公司 | Construction site monitoring method and device, computer equipment and storage medium |
| CN116740819A (en) * | 2023-08-14 | 2023-09-12 | 中通信息服务有限公司 | Method and device for identifying construction abnormal behavior in construction site based on AI algorithm |
| CN116740819B (en) * | 2023-08-14 | 2023-12-19 | 中通信息服务有限公司 | Method and device for identifying construction abnormal behavior in construction site based on AI algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114298138A (en) | Wearing identification method and device of safety helmet, computer equipment and storage medium | |
| US11961227B2 (en) | Method and device for detecting and locating lesion in medical image, equipment and storage medium | |
| CN108875833B (en) | Neural network training method, face recognition method and device | |
| CN109086711B (en) | Face feature analysis method and device, computer equipment and storage medium | |
| WO2015165365A1 (en) | Facial recognition method and system | |
| WO2019232862A1 (en) | Mouth model training method and apparatus, mouth recognition method and apparatus, device, and medium | |
| KR102357326B1 (en) | Method and apparatus for extracting face feature, method and apparatus for recognizing face | |
| CN103902977B (en) | Face identification method and device based on Gabor binary patterns | |
| CN111062429A (en) | Chef cap and mask wearing detection method based on deep learning | |
| CN101558431B (en) | Face authentication device | |
| KR20210100602A (en) | Face image-based risk recognition method, apparatus, computer device and storage medium | |
| CN112633144A (en) | Face occlusion detection method, system, device and storage medium | |
| CN105335722A (en) | Detection system and detection method based on depth image information | |
| CN110826370B (en) | Method and device for identifying identity of person in vehicle, vehicle and storage medium | |
| JP6351243B2 (en) | Image processing apparatus and image processing method | |
| CN111507134A (en) | Human-shaped posture detection method and device, computer equipment and storage medium | |
| CN112052746A (en) | Target detection method and device, electronic equipment and readable storage medium | |
| CN102842033A (en) | Human expression emotion semantic recognizing method based on face recognition | |
| CN116152863B (en) | Personnel information identification method and device, electronic equipment and storage medium | |
| CN112241667A (en) | Image detection method, device, equipment and storage medium | |
| CN106778574A (en) | For the detection method and device of facial image | |
| JP6947005B2 (en) | Attribute recognition device, attribute recognition method, and machine learning device | |
| Amosov et al. | Human localization in the video stream using the algorithm based on growing neural gas and fuzzy inference | |
| CN112541394A (en) | Black eye and rhinitis identification method, system and computer medium | |
| CN113436735A (en) | Body weight index prediction method, device and storage medium based on face structure 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 |