CN112200092B - Intelligent smoking detection method based on zoom movement of dome camera - Google Patents
Intelligent smoking detection method based on zoom movement of dome camera Download PDFInfo
- Publication number
- CN112200092B CN112200092B CN202011089599.2A CN202011089599A CN112200092B CN 112200092 B CN112200092 B CN 112200092B CN 202011089599 A CN202011089599 A CN 202011089599A CN 112200092 B CN112200092 B CN 112200092B
- Authority
- CN
- China
- Prior art keywords
- face
- camera
- image
- detection
- calculating
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/242—Aligning, centring, orientation detection or correction of the image by image rotation, e.g. by 90 degrees
-
- 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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/67—Focus control based on electronic image sensor signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
An intelligent smoking detection method based on zoom movement of a dome camera comprises the following steps: initializing, carrying out inspection on a ball machine, carrying out face detection, carrying out face position calculation, carrying out face occupation ratio calculation, carrying out camera direction adjustment, carrying out camera focal length adjustment, carrying out step eight, obtaining a face area diagram, carrying out smoking detection, carrying out face recognition, carrying out step eleven and warning record; the invention improves the traditional mode of manually adjusting the focal length and the direction of the dome camera, changes the traditional mode into the mode of automatically adjusting the focal length and the direction by matching with an intelligent algorithm, improves the efficiency of the dome camera, expands the application field of the dome camera, can be used for training and detecting the face, and improves the accuracy of detecting smoking.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to an intelligent smoking detection method based on zoom movement of a dome camera.
Background
The dome camera is a dome camera and is a monitoring camera integrating a camera system, a variable focal length lens and an electronic cradle head. The ball machine can realize 360-degree rotation through the electronic cradle head system, and can realize full coverage of a monitoring area. The zoom lens of the dome camera can realize clear monitoring of near-far targets by changing the focal length. The ball type monitoring is mainly applied to home monitoring, public transportation safety monitoring and factory production safety monitoring.
Face detection and face recognition technology are widely applied to various industries, face recognition is a means for performing biological identity verification by using face information, and face detection is a key step in face recognition and is to effectively detect a face image through characteristic attributes of a face. The invention uses human face detection to locate human face, and detects whether cigarette exists in the face image, and uses human face recognition technology to identify and record the facial features and identity of smokers, so as to record the detection.
According to statistics, most of the fire disasters in the current park are caused by smoking, and laws and regulations for prohibiting smoking in public places are formulated in large cities, but the smoking behaviors are difficult to monitor, and difficult penalties are always difficult for managers, so that smoking and smoke alarm are usually carried out by using a smoke sensor in the past, but the sensitivity of the smoke sensor is low, false alarm is easy to leak, and the smoke sensor cannot play an effective role especially in an outdoor environment. The invention can effectively reduce the management difficulty of smoking detection in specific occasions by utilizing a visual detection technology, so that the smoking behavior can be detected in real time and recorded. The invention mainly focuses on gas stations, bus stations, train stations, parks and other indoor and outdoor smoke-free areas.
Disclosure of Invention
The invention aims to provide an intelligent smoking detection method based on zoom movement of a dome camera, which can realize real-time movement detection of smoking behaviors.
The intelligent smoking detection method based on the variable-focus movement of the spherical camera adopts a learning training mode of a deep neural network, and designs an algorithm capable of detecting smoking behaviors from different angle distances according to the variable-focus movement characteristic of the spherical camera. The device can realize the detection and identification of smoking behaviors in specific occasions in all directions, multiple angles and long distances. And carrying out face recognition on smokers in specific occasions, and establishing a blacklist library.
The method can utilize the deep neural network to train and recognize the smoking photo, and simultaneously, utilizes the characteristic that the spherical camera can move, rotate and zoom, designs a smoking detection system capable of carrying out omnibearing multi-angle, and greatly expands the detectable range and precision. Finally, the face recognition technology is utilized to recognize and record the smokers, so that the functions of the system are perfected, and the deterrent of the system is improved.
The initial state of the spherical camera is long focal length, the spherical camera is inspected at a certain rotating speed, the human face is continuously recognized in the inspection process, and the neural network algorithm is utilized to recognize the human face. After the face is identified, the angle of the face is adjusted to center the face picture, and then the focal length of the camera is adjusted to amplify the face until the face proportion reaches one half of the picture. The mode of amplifying the face is to calculate the distance to the face by using the face duty ratio of the current focal length. Face size.
The cigarette has smaller target and single characteristic, and a good recognition result is difficult to achieve by using the traditional method. In the past, optimization of algorithms has been focused on, and recognition methods combining hardware and algorithms have been ignored. For the target with limited recognition distance which is difficult to overcome by the algorithm, the use efficiency of resources is increased, and the recognition range is improved. By adopting the cradle head inspection method, the cost can be effectively saved, and the efficiency can be improved.
The technical scheme provided by the invention is as follows: an intelligent smoking detection method based on zoom movement of a dome camera comprises the following steps:
step one, initializing: the method comprises the steps that firstly, initializing the ball machine, setting a routing inspection mode of the ball machine from left to right, setting the focal length of the ball machine to be minimum, and starting to detect a scene;
step two, inspecting by a ball machine; in the process of inspection, face detection is carried out, and as the minimum focal length is set, the detection range is the widest, so that more faces can be detected;
step three, face detection: detecting a human face by using a human face detection technology;
step four, calculating the face position: calculating the position of a human face center point in an image, and converting the position of the human face on the image into the position under a camera coordinate system;
step five, calculating the face ratio: calculating the size of the duty ratio of the face in the image to judge the size of the face;
step six, adjusting the camera direction: and adjusting the up-down and left-right positions of the camera according to the position of the center point of the face in the image, so that the face is positioned at the center position of the image.
Step seven, adjusting the focal length of the camera: and adjusting the focal length of the camera of the dome camera according to the position of the face in the figure and the duty ratio of the face, so that the image of the face is centered and occupies half of the image size.
Step eight, acquiring a face region diagram: after the ball machine is adjusted in place, the face image is scratched, and 20 pixels are respectively extended to four directions of the face image during the scratching process, so that preparation is made for subsequent detection.
Step nine, smoking detection: after the face image is scratched out, the presence or absence of smoking behavior in the image is detected by using a trained smoking detection algorithm.
Step ten, face recognition: when smoking behavior is detected, face recognition is carried out on the face, and records are recorded.
Step eleven, warning record: warning or penalizing the identified smoker.
The intelligent smoking detection method based on the zoom movement of the dome camera has the following beneficial effects:
1. the invention adopts an advanced intelligent means to detect whether people smoke in a specific occasion or not, and changes the traditional mode of detecting smoking by using smoke feeling by using a video detection mode. The smoking behavior is detected by utilizing a video mode, so that the detection range is enlarged, the detection efficiency is improved, and the detection cost is reduced.
2. The invention adopts the zoom movable spherical camera to cooperate with an intelligent detection means, improves the traditional mode of manually adjusting the focal length and direction of the spherical camera in the past, changes the traditional mode into the mode of automatically adjusting the focal length and direction by cooperating with an intelligent algorithm, improves the efficiency of the spherical camera and expands the application field of the spherical camera.
3. The invention designs a real-time light detection network which can be used for training and detecting human faces and detecting smoke, has simple structure and higher speed, can achieve the real-time detection effect on the edge side of android equipment and the like, has higher accuracy, and has fewer network layers and higher speed than the prior network layers.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of an embodiment of the present invention.
In the figure, 1 is a spherical monitoring camera; and 2, a cloud server platform.
Detailed Description
The invention will be further illustrated by the following examples, with reference to the accompanying drawings. Fig. 1 is up>A block diagram of up>A flow chart of the invention, and as shown in the drawing, in the intelligent smoking detection method based on the zoom movement of the dome camerup>A, the invention selects up>A 2DC6420IW-A dome camerup>A of the Haikang Wei view as an adaptive dome camerup>A of the invention, and the adaptive dome camerup>A is provided with up>A cloud platform, and can adjust the position direction of the dome camerup>A by commanding and adjusting the steering torque of up>A motor of the cloud platform. The method comprises the following steps:
step one, initializing S1: when the method is started, the cloud algorithm is deployed to perform initialization setting on the dome camera through an API of the dome camera, the inspection mode of the dome camera is set to be from left to right, the focal length of the dome camera is set to be minimum, after the setting is completed, the algorithm sets the dome camera to start inspection on a scene, and at the moment, the dome camera starts to rotate from left to right;
in the implementation process, a method for deploying on a cloud platform is adopted, an algorithm is firstly deployed on the cloud platform, the cloud platform and the dome camera are connected together through a network, the cloud platform can acquire an image shot by the dome camera in real time, and meanwhile, the cloud platform detects the current state of the dome camera in real time, and the method comprises the following steps: the current angle of the dome camera and the focal distance of the dome camera. The image and the state of the dome camera are input into an algorithm, a new position of the dome camera is obtained through algorithm calculation, then image information after the dome camera is adjusted is obtained, the face of the image information obtained after the adjustment is clearer, the information of cigarettes with important smoking characteristics is amplified, and the smoking behavior can be easily detected by a smoking detection network. The deployment diagram is shown in fig. 2.
Step two, inspecting by a ball machine S2; in the process of inspection, continuously taking photos by the ball machine, wherein the shooting frequency is every second, taking ten photos and transmitting the taken photos to the cloud;
step three, face detection S3: the face detection algorithm of the cloud is utilized to detect the face, and the face detection is carried out on each picture in the cloud, and as the minimum focal length is set, the detection range is the widest, so that more faces can be detected, and the detected face image is a minimum rectangular frame containing all faces;
the invention provides a deep neural network-light detection network for training face detection and smoking detection, which consists of a six-layer convolutional network and further comprises a classification layer and a positioning layer. The input of the picture is set to 300X300, and the human face and smoking image can be effectively detected by using the input of the size. In order to enable the neural network to effectively identify targets with different sizes, the invention specifically clusters the sizes of faces and smoking pictures effectively, obtains effective sampling sizes and improves the accuracy of the model.
Step four, calculating a face position S4: calculating the position of the center point of each detected face in the image, namely calculating the position (X, Y) of the center position of the rectangular frame in the whole image, calculating the actual position (X, Y, Z) of the face through the position of the face on the image, and transmitting the actual position of the face to the step six;
the specific calculation process is that firstly, the vector distance from the center point of the face to the center point of the image, namely the distance containing the angular position relation, is calculated. And then, the vector is projected to a three-dimensional coordinate system space of the camera through the conversion of a coordinate system, wherein the space relation of a third dimension can be calculated through the ratio of the face in the image under different focal lengths, and the distance between the camera and the target can be calculated. The distance and angle required by the movement of the visual center of the camera to the alignment target center can be obtained through the conversion of the coordinate system, so that the position of the camera is adjusted. The image we rely on pixel locations in the image to calculate the true position of the target is as follows:
D＝(J×N)÷T (1)
wherein J is the focal length of the camera obtained by reading camera parameters, T is the pixel distance occupied in the image, N is the empirical coefficient obtained through experiments, different cameras are different coefficients, and D is the actual distance of the target. Wherein (X, Y, Z) can be obtained by the formula (1);
step five, calculating the face duty ratio S5: calculating the ratio of the face in the image through the face, namely calculating the proportion of the pixels occupied by each rectangular frame containing the face to the pixels of the whole image, so as to judge the ratio N of the face, and transmitting the data of the face ratio to the step six;
step six, adjusting the camera direction S6: according to the face positions (X, Y, Z) and the face duty ratio image size N obtained in the step four and the step five, positions D1 and D2, which are needed to be moved up and down and left and right, of the camera are obtained through calculation with the current position of the camera, and the face is located at the center of the image.
Step seven, adjusting the focal length S7 of the camera: when the camera is adjusted in position, the focusing distance of the camera of the spherical camera is controlled by the cloud end to be adjusted according to the occupation ratio D of the face after the face is positioned in the center, so that the image of the face is centered and at least occupies half of the image size, namely N > =0.5.
Step eight, acquiring a face area diagram S8: after the ball machine is adjusted in place, the face image is scratched, namely, the rectangular frame is scratched out of the image, and 20 pixels are respectively extended to the rectangular frame containing the face in four directions during the scratching process, so that preparation is made for subsequent detection.
Step nine, smoking detection S9: after the face image is scratched, the scratched image blocks are sent into a smoking detection algorithm, the trained smoking detection algorithm is utilized to detect the smoking behavior in the image, and the detection results are divided into two types: smoking and non-smoking behaviour.
Step ten, face recognition S10: when smoking behavior is detected, the identity of the person detecting the smoking behavior is authenticated, and the person can be relied on to recognize or utilize a mature face recognition method to recognize the person at the moment, and the person is recorded.
Step eleven, warning record S11: alerting or penalizing identified smokers
Fig. 2 is a schematic diagram of the implementation of the present invention, and as shown in fig. 2, the dome-type surveillance camera 1 is mainly used for acquiring an image and feeding back the current state in real time: comprising the following steps: the cloud server 2 is mainly used for deploying algorithms, controlling the dome camera by the algorithms after receiving information from the dome camera, and detecting images by the algorithms.
In order to verify the technical effect of the invention, the inventor performs detection simultaneously by using the zoom movement method of the ball machine and the monitor camera without using the method of the invention respectively through simulating actual conditions and testing the accuracy calculated 1000 times by artificially simulating the actual conditions, namely, performing smoking behaviors by a person at a distance of 5 to 10m from the ball machine and the common monitor camera, and obtaining the following data. The specific values are shown in Table 1: the obtained beneficial effects are shown.
Table 1: the obtained beneficial effect table
| Smoking identification network identificationAccuracy rate of | |
| Detection without matching with ball machine | 85％ |
| Detection after matching with ball machine | 98％ |
According to the intelligent smoking detection method based on the zoom movement of the spherical camera, as the target can be automatically zoomed and amplified, a far-distance clearer target graph can be obtained, even though the background uses the same detection algorithm, the result shows that under the same condition, the recognition accuracy of a smoking recognition network after the detection by matching of the spherical camera is 98%, and the recognition accuracy of the smoking recognition network after the detection by matching of the spherical camera is 85%, compared with the detection accuracy of the detection by the non-use method, the detection method has the advantages that the actual effect is obvious.
The above examples are only specific embodiments of the present invention for illustrating the technical solution of the present invention, but not for limiting the scope of the present invention, and although the present invention has been described in detail with reference to the foregoing examples, it will be understood by those skilled in the art that the present invention is not limited thereto: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (4)
1. An intelligent smoking detection method based on zoom movement of a dome camera comprises the following steps:
step one, initializing: the method comprises the steps that firstly, initializing the ball machine, setting a routing inspection mode of the ball machine from left to right, setting the focal length of the ball machine to be minimum, and starting to detect a scene;
step two, inspecting by a ball machine; in the process of inspection, face detection is carried out, and as the minimum focal length is set, the detection range is the widest, so that more faces are detected;
step three, face detection: detecting a human face by using a human face detection technology;
step four, calculating the face position: the position of the center point of the human face in the image is calculated, and the position of the human face on the image is converted into the position of the camera under the three-dimensional coordinate system, specifically: calculating the position of the center point of each detected face in the image, namely calculating the position (X, Y) of the center position of a rectangular frame containing the face in the whole image, calculating the actual position (X, Y, Z) of the face through the position of the face on the image, and transmitting the actual position of the face to the step six;
the calculation process of the actual position (X, Y, Z) of the face is calculated through the position of the face on the image, namely, the vector distance from the center point of the face to the center point of the image, namely, the distance containing the position relation of angles is calculated firstly, then the vector is projected to the three-dimensional coordinate system space of the camera through the conversion of a coordinate system, wherein in the three-dimensional spatial relation, the distance between the camera and a target is calculated through the occupation ratio of the face in the image under different focal lengths;
the distance and angle required by the movement of the camera visual center to the target center are obtained through the conversion of the coordinate system, so that the camera position is adjusted, and the formula for calculating the real position of the target by relying on the pixel position in the image is as follows:
wherein J is the focal length of the camera obtained by reading camera parameters, T is the pixel distance occupied in the image, N is the empirical coefficient obtained through experiments, different cameras are different coefficients, and D is the actual distance of the target obtained through calculation, wherein (X, Y, Z) are obtained through a formula (1);
step five, calculating the face ratio: calculating the size of the duty ratio of the face in the image to judge the size of the face;
step six, adjusting the camera direction: according to the position of the center point of the human face in the image, adjusting the up-down and left-right positions of the camera to enable the human face to be positioned at the center position of the image;
step seven, adjusting the focal length of the camera: according to the position of the face in the figure and the duty ratio of the face, the focal length of the camera of the dome camera is adjusted, so that the image of the face is centered and occupies half of the image size;
step eight, acquiring a face region diagram: after the ball machine is adjusted in place, the face image is scratched, and 20 pixels are respectively extended to four directions of the face image during the scratching process, so that preparation is made for subsequent detection;
step nine, smoking detection: after the face image is scratched out, detecting whether smoking behaviors exist in the image by using a trained smoking detection algorithm;
step ten, face recognition: when smoking behavior is detected, face recognition is carried out, and records are recorded;
step eleven, warning record: warning or penalizing the identified smoker.
2. The intelligent smoking detection method based on the zoom movement of the dome camera according to claim 1, wherein: and step five, calculating the face duty ratio, namely calculating the duty ratio of the face in the image, namely calculating the proportion of the pixels occupied by each rectangular frame containing the face and the pixels of the whole image, so as to judge the duty ratio S of the face, and transmitting the data of the face duty ratio to step six.
3. The intelligent smoking detection method based on the zoom movement of the dome camera according to claim 1, wherein: and step six, adjusting the camera direction, namely according to the face positions (X, Y, Z) and the face duty ratio image size S obtained in the step four and the step five, calculating the current position of the camera to obtain positions D1 and D2 which are required to be moved up and down and left and right of the camera, so that the face is positioned at the center of the image.
4. The intelligent smoking detection method based on the zoom movement of the dome camera according to claim 1, wherein: and seventhly, adjusting the focal length of the camera, namely adjusting the position of the camera, namely enabling the face to be at the center position, and controlling the focusing distance of the camera of the dome camera by the cloud end according to the occupation ratio S of the face, so that the image of the face is centered and at least occupies half of the image size, namely S > =0.5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011089599.2A CN112200092B (en) | 2020-10-13 | 2020-10-13 | Intelligent smoking detection method based on zoom movement of dome camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011089599.2A CN112200092B (en) | 2020-10-13 | 2020-10-13 | Intelligent smoking detection method based on zoom movement of dome camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112200092A CN112200092A (en) | 2021-01-08 |
| CN112200092B true CN112200092B (en) | 2023-06-23 |
Family
ID=74010003
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011089599.2A Active CN112200092B (en) | 2020-10-13 | 2020-10-13 | Intelligent smoking detection method based on zoom movement of dome camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200092B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113392706A (en) * | 2021-05-13 | 2021-09-14 | 上海湃道智能科技有限公司 | Device and method for detecting smoking and using mobile phone behaviors |
| CN113392710A (en) * | 2021-05-19 | 2021-09-14 | 上海可深信息科技有限公司 | Intelligent recognition method and system for smoking behavior |
| CN113343859A (en) * | 2021-06-10 | 2021-09-03 | 浙江大华技术股份有限公司 | Smoking behavior detection method and device, storage medium and electronic device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110569771A (en) * | 2019-08-30 | 2019-12-13 | 重庆博拉智略科技有限公司 | smoking identification method and device, storage medium and electronic equipment |
| CN110852275A (en) * | 2019-11-12 | 2020-02-28 | 成都新舟锐视科技有限公司 | Face detection re-amplification tracking method in dome camera tracking process |
| CN111639546A (en) * | 2020-05-07 | 2020-09-08 | 金钱猫科技股份有限公司 | Small-scale target cloud computing identification method and device based on neural network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100568262C (en) * | 2007-12-29 | 2009-12-09 | 浙江工业大学 | Human face recognition detection device based on the multi-video camera information fusion |
| CN107590461B (en) * | 2017-09-12 | 2021-04-02 | Oppo广东移动通信有限公司 | Face recognition method and related product |
| CN108419014B (en) * | 2018-03-20 | 2020-02-21 | 北京天睿空间科技股份有限公司 | Method for capturing human face by linkage of panoramic camera and multiple capturing cameras |
| CN109711307A (en) * | 2018-12-19 | 2019-05-03 | 中科天网（广东）科技有限公司 | A kind of smoking evidence collecting method based on recognition of face |
-
2020
- 2020-10-13 CN CN202011089599.2A patent/CN112200092B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110569771A (en) * | 2019-08-30 | 2019-12-13 | 重庆博拉智略科技有限公司 | smoking identification method and device, storage medium and electronic equipment |
| CN110852275A (en) * | 2019-11-12 | 2020-02-28 | 成都新舟锐视科技有限公司 | Face detection re-amplification tracking method in dome camera tracking process |
| CN111639546A (en) * | 2020-05-07 | 2020-09-08 | 金钱猫科技股份有限公司 | Small-scale target cloud computing identification method and device based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112200092A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112200092B (en) | Intelligent smoking detection method based on zoom movement of dome camera | |
| CN108615321B (en) | Security pre-warning system and method based on radar detecting and video image behavioural analysis | |
| CN101123722B (en) | Panorama video intelligent monitoring method and system | |
| CN101119482B (en) | Overall view monitoring method and apparatus | |
| CN107093171B (en) | Image processing method, device and system | |
| WO2021047306A1 (en) | Abnormal behavior determination method and apparatus, terminal, and readable storage medium | |
| CN110675592B (en) | High-altitude parabolic early warning protection system based on target identification and control method | |
| US7065232B2 (en) | Three-dimensional ear biometrics system and method | |
| WO2018101247A1 (en) | Image recognition imaging apparatus | |
| CN109376601B (en) | Object tracking method based on high-speed ball, monitoring server and video monitoring system | |
| KR101948569B1 (en) | Flying object identification system using lidar sensors and pan/tilt zoom cameras and method for controlling the same | |
| US11232689B2 (en) | Smoke detection method with visual depth | |
| CN108353148A (en) | Nolo flight quality testing examining system and nolo flight object detecting method | |
| CN111985365A (en) | Straw burning monitoring method and system based on target detection technology | |
| CN111062234A (en) | Monitoring method, intelligent terminal and computer readable storage medium | |
| US20110157360A1 (en) | Surveillance system and method | |
| CN114120171A (en) | Fire smoke detection method, device and equipment based on video frame and storage medium | |
| CN107547865A (en) | Trans-regional human body video frequency object tracking intelligent control method | |
| JP7035272B2 (en) | Shooting system | |
| CN116310678A (en) | Fire source identification and positioning method by combining solid-state laser radar with thermal imaging vision | |
| JP2017058831A (en) | Information specification system, information specification method, and program thereof | |
| CN107622248A (en) | One kind watches identification and interactive approach and device attentively | |
| CN111612815A (en) | Infrared thermal imaging behavior intention analysis method and system | |
| CN114639172B (en) | High-altitude parabolic early warning method and system, electronic equipment and storage medium | |
| CN113076797B (en) | Charging station electric vehicle fire alarm method and system based on intelligent video identification |
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 |