CN109040693B - Intelligent alarm system and method - Google Patents
Intelligent alarm system and method Download PDFInfo
- Publication number
- CN109040693B CN109040693B CN201811014170.XA CN201811014170A CN109040693B CN 109040693 B CN109040693 B CN 109040693B CN 201811014170 A CN201811014170 A CN 201811014170A CN 109040693 B CN109040693 B CN 109040693B
- Authority
- CN
- China
- Prior art keywords
- video
- image
- semantic segmentation
- intelligent
- preset condition
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an intelligent alarm system and a method, wherein the system comprises a video acquisition module, an intelligent analysis module, an interaction module and an alarm module. By adopting the intelligent warning system and the intelligent warning method, the video images are detected and analyzed based on the deep neural network model, the fishing behaviors around the pond close to the power line can be accurately detected, the system operation performance can meet the requirement of real-time detection on dozens of paths of videos under the condition of configuring one general GPU server, and the influence of other interferents can be avoided.
Description
Technical Field
The invention relates to the technical field of automation, in particular to the technical field of scheduling, and specifically relates to an intelligent alarm system and method.
Background
Although a warning board for prohibiting fishing is usually hung near a power line on a pond, an electric shock accident due to fishing may occur. The occurrence of accidents can be reduced by increasing the manual patrol frequency, but the manual patrol has the characteristics of high cost and poor timeliness. At present, video monitoring equipment is also installed at the side of a pond close to a power line by a power supply department door, monitoring pictures around the pond are transmitted to a monitoring center for remote viewing, but due to the fact that monitoring points are numerous, a video monitoring attendant stares at a screen to watch, and visual fatigue is easily caused, so that missed detection is caused. Therefore, manual patrol or remote staring on-duty watchmen are not an efficient solution.
Because in the video monitoring system near the pond of the power line, the monitoring depth of field, the illumination condition and the monitoring visual angle of the camera are not fixed, the detection precision of the intelligent video analysis system based on the general video image processing technology to the fishing behavior under the monitoring condition is not high.
Because the fishing rod is slender, when the target marking is carried out by using the target detection method based on the deep neural network, the sounding Box usually occupies most of the whole image, and therefore, the detection precision of the fishing rod is not very high.
Therefore, whether a general video image processing technology or a target detection technology based on a deep neural network is utilized, intelligent and automatic alarm for preventing electric shock in fishing is very difficult, the existing fishing electric shock prevention method and system are low in detection precision, a lot of misjudgments or missed judgments can be generated, and the method and system do not play a good alarm and prevention role in electric shock accidents possibly caused by fishing behaviors close to a power line.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an intelligent alarm system and an intelligent alarm method capable of preventing in time.
In order to achieve the purpose, the intelligent warning system and the method of the invention are as follows:
the intelligent warning system is mainly characterized in that the system comprises:
the video acquisition module is used for acquiring real-time video images;
the intelligent analysis module is connected with the video acquisition module through a wireless network and is used for analyzing whether the video image meets a system preset condition;
and the warning module is connected with the intelligent analysis module through an interaction module and is used for sending a warning signal when the video image meets the preset condition of the system.
This intelligent warning system's intelligent analysis module includes:
the classification unit is connected with the video acquisition module and is used for classifying the video images and storing first video images meeting a first preset condition;
the detection unit is connected with the classification unit and used for detecting whether the first video image meets a second preset condition or not;
and the semantic segmentation unit is connected with the detection unit and used for performing semantic segmentation on the first video image when the first video image meets a second preset condition and detecting whether the first video image after the semantic segmentation meets a third preset condition.
The interaction module of the intelligent warning system is also connected with the video acquisition module and used for configuring the acquisition parameters of the video acquisition module.
This intelligent warning system still includes:
and the charging unit is connected with the video acquisition module and is used for charging operation.
The intelligent warning system is applied to the field of preventing fishing electric shock.
The intelligent warning method based on the intelligent warning system is mainly characterized by comprising the following steps:
(1) the video acquisition module acquires video images in real time;
(2) the intelligent analysis module analyzes whether the video image meets a system preset condition, and continues the step (3) after meeting the system preset condition, otherwise, returns to the step (1);
(3) the alarm module sends out an alarm signal.
In the intelligent warning method, the intelligent analysis module comprises a classification unit, a detection unit and a semantic segmentation unit, and the step (2) comprises the following steps:
(2.1) the classification unit classifies the video images and stores a first video image which meets a first preset condition;
(2.2) the detection unit detects whether the first video image meets a second preset condition, if so, the step (2.3) is carried out, otherwise, the step (1) is returned to;
and (2.3) the semantic segmentation unit performs semantic segmentation on the first video image, detects whether the first video image after the semantic segmentation meets a third preset condition, if so, enters the step (3), otherwise, returns to the step (1).
The intelligent warning method comprises the following steps (2.2) specifically:
the detection unit detects whether the first video image meets a second preset condition or not based on the deep neural network model.
The step (2.3) of the intelligent alarm system comprises the following steps:
(2.3.1) the semantic segmentation unit performs semantic segmentation on the first video image based on a deep neural network model and outputs a binary image, wherein the binary image is the first video image after the semantic segmentation;
(2.3.2) carrying out univariate linear regression analysis on the binary image to judge whether a third preset condition is met, if so, entering the step (3), and if not, returning to the step (1).
By adopting the intelligent warning system and the intelligent warning method, the video images are detected and analyzed based on the deep neural network model, the fishing behaviors around the pond close to the power line can be accurately detected, the system operation performance can meet the requirement of real-time detection on dozens of paths of videos under the condition of configuring one general GPU server, and the influence of other interferents can be avoided.
Drawings
Fig. 1 is a schematic diagram of a connection structure of the intelligent warning system of the present invention.
Fig. 2 shows an embodiment of an intelligent warning system according to the present invention.
Detailed Description
In order to more clearly describe the technical contents of the present invention, the following further description is given in conjunction with specific embodiments.
The invention relates to an intelligent alarm system (please refer to fig. 1), comprising:
the video acquisition module is used for acquiring real-time video images;
the intelligent analysis module is connected with the video acquisition module through a wireless network and is used for analyzing whether the video image meets a system preset condition;
and the warning module is connected with the intelligent analysis module through an interaction module and is used for sending a warning signal when the video image meets the preset condition of the system.
This intelligent warning system's intelligent analysis module includes:
the classification unit is connected with the video acquisition module and is used for classifying the video images and storing first video images meeting a first preset condition;
the detection unit is connected with the classification unit and used for detecting whether the first video image meets a second preset condition or not;
and the semantic segmentation unit is connected with the detection unit and used for performing semantic segmentation on the first video image when the first video image meets a second preset condition and detecting whether the first video image after the semantic segmentation meets a third preset condition.
The interaction module of the intelligent warning system is also connected with the video acquisition module and used for configuring the acquisition parameters of the video acquisition module.
The invention also relates to an intelligent warning method based on the intelligent warning system, which comprises the following steps:
(1) the video acquisition module acquires video images in real time;
(2) the intelligent analysis module analyzes whether the video image meets a system preset condition, and continues the step (3) after meeting the system preset condition, otherwise, returns to the step (1);
(3) the alarm module sends out an alarm signal.
In the intelligent warning method, the intelligent analysis module comprises a classification unit, a detection unit and a semantic segmentation unit, and the step (2) comprises the following steps:
(2.1) the classification unit classifies the video images and stores a first video image which meets a first preset condition;
(2.2) the detection unit detects whether the first video image meets a second preset condition, if so, the step (2.3) is carried out, otherwise, the step (1) is returned to;
and (2.3) the semantic segmentation unit performs semantic segmentation on the first video image, detects whether the first video image after the semantic segmentation meets a third preset condition, if so, enters the step (3), otherwise, returns to the step (1).
The intelligent warning method comprises the following steps (2.2) specifically:
the detection unit detects whether the first video image meets a second preset condition or not based on the deep neural network model.
The step (2.3) of the intelligent alarm system comprises the following steps:
(2.3.1) the semantic segmentation unit performs semantic segmentation on the first video image based on a deep neural network model and outputs a binary image, wherein the binary image is the first video image after the semantic segmentation;
(2.3.2) carrying out univariate linear regression analysis on the binary image to judge whether a third preset condition is met, if so, entering the step (3), and if not, returning to the step (1).
In a specific embodiment, the video capture module of the present invention may include a high-definition dome camera, which captures video images at 360 degrees, and in particular, in order to capture video images at night, the video capture module is further equipped with an infrared night vision unit.
In one embodiment, the warning module of the present invention includes a power amplifier and a tweeter, and is controlled by the interaction module, and when the warning signal is sent, the warning signal is amplified by the power amplifier and then output to the tweeter for broadcasting.
In a specific embodiment, the intelligent analysis module of the present invention is implemented remotely and controlled by the interaction module, the interaction module sets parameters such as the start and stop of the intelligent analysis module and the number of analysis video paths and analysis frequency, and the analysis result of the intelligent analysis module can also be transmitted to the interaction module for real-time display.
In a specific embodiment, the interaction module of the present invention is implemented in a user terminal, and interacts through a computer WEB interface or a mobile phone APP to implement functions of on-demand viewing of a live video, control of an intelligent analysis module, confirmation of an analysis result, output of an alarm prompt voice message, statistical analysis of alarm information at each monitoring point and each time period, and the like.
In an embodiment, please refer to fig. 2, which is an application of the intelligent warning system of the present invention in the technical field of preventing fishing electric shock, specifically including the following steps:
(1) the images of the monitoring points are collected by the video collection module at regular intervals in turn, the time interval can be configured in the interaction module, for example, the time interval can be 1 second, and the collected images are transmitted to the background fishing behavior intelligent analysis system through a 4G network;
(2) inputting the collected image into a pedestrian detection depth neural network for pedestrian detection, judging whether a person exists in the image, and continuing the following steps if the person is detected in the image; otherwise, returning to the step (1) to continue to acquire a new image;
(3) through a target detection and semantic segmentation deep neural network model and a network thereof, model parameters are also obtained through training field sample image learning, the network can simultaneously carry out target detection of a person holding a fishing rod and semantic segmentation of the fishing rod, and a Mask RCNN network architecture can be selected for the target detection and semantic segmentation deep neural network;
(4) inputting the 'image of the person' into a detection unit for detection, and if the 'person holding the fishing rod' is detected, continuing the following steps; otherwise, returning to the step (1) to continue to acquire a new image;
(5) performing semantic segmentation on a fishing rod in a Bounding Box through a semantic segmentation deep neural network, and outputting a binary image of the fishing rod;
(6) fitting the binary image of the fishing rod into a linear equation through a univariate linear regression module, and calculating the slope of the linear equation;
(7) comparing the slope of the fishing rod linear equation fitted by the current image with the slope of the fishing rod linear equation fitted by the same path of image at a certain interval (configurable), if the difference is greater than a threshold value, judging that the fishing rod moves, and continuing the following steps; otherwise, returning to the step (1) to continue to acquire a new image. For example, the time interval may be configured to be 10 seconds, and the threshold value for the slope difference may be set to 0.05;
(8) and sending a buzzing sound in the interaction module, popping up and displaying the monitoring video, reminding a monitoring attendant to process, confirming after the monitoring attendant checks, storing an alarm picture once the confirmation is confirmed, and automatically sending an alarm broadcast to a field alarm device, wherein if the alarm broadcast is a false alarm, the alarm broadcast is cancelled.
In a specific embodiment, the intelligent warning system and the intelligent warning method can be applied to the field of preventing fishing electric shock, and particularly, firstly, a target detection technology based on a deep neural network is utilized to carry out high-precision detection on people in a video image, and images without people are filtered out, so that the system operation performance can be greatly improved, and false detection can be reduced. Then, the target detection and semantic segmentation technology based on the deep neural network is utilized to detect 'people holding the fishing rod' on the filtered image, and meanwhile, the semantic segmentation is carried out on the fishing rod target in a Bounding Box, then a straight line equation is fitted to the divided fishing rod by applying a univariate linear regression algorithm to calculate the slope of the fishing rod, comparing with the slope of the fitted linear equation of the fishing rod detected by the same path of video image after a certain time, if the difference of the slopes is more than a threshold value, the fishing rod is considered to be in motion, since 3 kinds of fishing behavior elements of "person", "person holding the fishing rod having moved" have been detected at this time, and then can judge accurately as the fishing action, and carry out the analysis to the 3D video data of certain period of time, further avoided with branch or other interference object false retrieval for the fishing rod.
By adopting the intelligent warning system and the intelligent warning method, the video images are detected and analyzed based on the deep neural network model, the fishing behaviors around the pond close to the power line can be accurately detected, the system operation performance can meet the requirement of real-time detection on dozens of paths of videos under the condition of configuring one general GPU server, and the influence of other interferents can be avoided.
In this specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
Claims (8)
1. An intelligent warning system, characterized in that, the system includes:
the video acquisition module is used for acquiring real-time video images;
the intelligent analysis module is connected with the video acquisition module through a wireless network and is used for analyzing whether the video image meets a system preset condition;
the alarm module is connected with the intelligent analysis module through an interaction module and is used for sending an alarm signal when the video image meets the preset condition of the system;
the intelligent analysis module comprises:
the classification unit is connected with the video acquisition module and is used for classifying the video images and storing first video images meeting a first preset condition;
the detection unit is connected with the classification unit and used for detecting whether the first video image meets a second preset condition or not;
the semantic segmentation unit is connected with the detection unit and used for performing semantic segmentation on the first video image when the first video image meets a second preset condition and detecting whether the first video image after the semantic segmentation meets a third preset condition;
the intelligent analysis module realizes the alarm of the fishing behavior through the following steps:
a. inputting the collected image into a pedestrian detection depth neural network for pedestrian detection, judging whether a person exists in the image, and continuing the following steps if the person is detected in the image; otherwise, continuing to acquire a new image;
b. through a target detection and semantic segmentation deep neural network model and a network thereof, model parameters are also obtained through training field sample image learning, the network can simultaneously carry out target detection of a person holding a fishing rod and semantic segmentation of the fishing rod, and a Mask RCNN network architecture can be selected for the target detection and semantic segmentation deep neural network;
c. inputting the 'image of the person' into a detection unit for detection, and if the 'person holding the fishing rod' is detected, continuing the following steps; otherwise, continuing to acquire a new image;
d. performing semantic segmentation on a fishing rod in a Bounding Box through a semantic segmentation deep neural network, and outputting a binary image of the fishing rod;
e. fitting the binary image of the fishing rod into a linear equation through a univariate linear regression module, and calculating the slope of the linear equation;
f. comparing the slope of the fishing rod linear equation fitted by the current image with the slope of the fishing rod linear equation fitted by the same path of image at a certain interval, if the difference is greater than a threshold value, judging that the fishing rod moves, and continuing the following steps; otherwise, continuing to acquire a new image.
2. The intelligent warning system of claim 1 wherein the interactive module is further connected to the video capture module for configuring capture parameters of the video capture module.
3. The intelligent warning system of claim 1, wherein said system further comprises:
and the charging unit is connected with the video acquisition module and is used for charging operation.
4. The intelligent warning system of any one of claims 1 to 3, wherein the system is applied to the field of preventing fishing electric shock.
5. An intelligent alarm method implemented based on the intelligent alarm system of claim 1, wherein the method comprises the following steps:
(1) the video acquisition module acquires video images in real time;
(2) the intelligent analysis module analyzes whether the video image meets a system preset condition, and continues the step (3) after meeting the system preset condition, otherwise, returns to the step (1);
(3) the alarm module sends out an alarm signal.
6. The intelligent warning method according to claim 5, wherein the intelligent analysis module comprises a classification unit, a detection unit and a semantic segmentation unit, and the step (2) comprises the steps of:
(2.1) the classification unit classifies the video images and stores a first video image which meets a first preset condition;
(2.2) the detection unit detects whether the first video image meets a second preset condition, if so, the step (2.3) is carried out, otherwise, the step (1) is returned to;
and (2.3) the semantic segmentation unit performs semantic segmentation on the first video image, detects whether the first video image after the semantic segmentation meets a third preset condition, if so, enters the step (3), otherwise, returns to the step (1).
7. The intelligent warning method according to claim 6, wherein the step (2.2) is specifically:
the detection unit detects whether the first video image meets a second preset condition or not based on the deep neural network model.
8. The intelligent warning method according to claim 6, characterized in that said step (2.3) comprises the steps of:
(2.3.1) the semantic segmentation unit performs semantic segmentation on the first video image based on a deep neural network model and outputs a binary image, wherein the binary image is the first video image after the semantic segmentation;
(2.3.2) carrying out univariate linear regression analysis on the binary image to judge whether a third preset condition is met, if so, entering the step (3), and if not, returning to the step (1).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811014170.XA CN109040693B (en) | 2018-08-31 | 2018-08-31 | Intelligent alarm system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811014170.XA CN109040693B (en) | 2018-08-31 | 2018-08-31 | Intelligent alarm system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109040693A CN109040693A (en) | 2018-12-18 |
| CN109040693B true CN109040693B (en) | 2020-11-10 |
Family
ID=64622681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811014170.XA Active CN109040693B (en) | 2018-08-31 | 2018-08-31 | Intelligent alarm system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040693B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110503812A (en) * | 2019-08-23 | 2019-11-26 | 陈�峰 | A kind of flammability hazard source behavior monitoring system and method based on convolutional neural networks |
| CN111583265A (en) * | 2020-05-07 | 2020-08-25 | 赛特斯信息科技股份有限公司 | Method for realizing phishing behavior detection processing based on codec structure and corresponding semantic segmentation network system |
| CN111695492A (en) * | 2020-06-10 | 2020-09-22 | 国网山东省电力公司电力科学研究院 | Method and system for detecting fishing hidden danger of power transmission line |
| CN112233353A (en) * | 2020-09-24 | 2021-01-15 | 国网浙江兰溪市供电有限公司 | Artificial intelligence-based anti-fishing monitoring system and monitoring method thereof |
| CN113305858B (en) * | 2021-06-07 | 2022-05-03 | 仲恺农业工程学院 | Visual robot method and device for removing shellfish in raw water pipeline |
| CN114124653A (en) * | 2021-10-20 | 2022-03-01 | 北京电子工程总体研究所 | Real-time alarm method, device and system for command control system |
| CN114241717A (en) * | 2021-12-17 | 2022-03-25 | 广州西麦科技股份有限公司 | Electric shock prevention safety early warning method and system |
| CN115240278B (en) * | 2022-09-23 | 2023-01-06 | 东莞先知大数据有限公司 | Fishing behavior detection method |
| CN115331386B (en) * | 2022-10-13 | 2022-12-27 | 合肥中科类脑智能技术有限公司 | Prevent fishing detection alarm system based on computer vision |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484666A (en) * | 2014-12-17 | 2015-04-01 | 中山大学 | Advanced image semantic parsing method based on human-computer interaction |
| CN206710819U (en) * | 2017-03-22 | 2017-12-05 | 国网山东省电力公司莱芜供电公司 | The supervisory systems and stringing tower of power transmission and transformation line |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090118582A (en) * | 2008-05-14 | 2009-11-18 | 주식회사 토페스 | Unexpcted accident monitoring system |
| CN106845396B (en) * | 2017-01-18 | 2020-05-22 | 南京理工大学 | Illegal fishing behavior identification method based on automatic image identification |
| CN107220604A (en) * | 2017-05-18 | 2017-09-29 | 清华大学深圳研究生院 | A kind of fall detection method based on video |
| CN107169468A (en) * | 2017-05-31 | 2017-09-15 | 北京京东尚科信息技术有限公司 | Method for controlling a vehicle and device |
| CN107341446A (en) * | 2017-06-07 | 2017-11-10 | 武汉大千信息技术有限公司 | Specific pedestrian's method for tracing and system based on inquiry self-adaptive component combinations of features |
-
2018
- 2018-08-31 CN CN201811014170.XA patent/CN109040693B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484666A (en) * | 2014-12-17 | 2015-04-01 | 中山大学 | Advanced image semantic parsing method based on human-computer interaction |
| CN206710819U (en) * | 2017-03-22 | 2017-12-05 | 国网山东省电力公司莱芜供电公司 | The supervisory systems and stringing tower of power transmission and transformation line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109040693A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109040693B (en) | Intelligent alarm system and method | |
| KR101942808B1 (en) | Apparatus for CCTV Video Analytics Based on Object-Image Recognition DCNN | |
| TWI749113B (en) | Methods, systems and computer program products for generating alerts in a video surveillance system | |
| CN107229894A (en) | Intelligent video monitoring method and system based on computer vision analysis technology | |
| US20080136934A1 (en) | Flame Detecting Method And Device | |
| CN107679471B (en) | Indoor personnel air post detection method based on video monitoring platform | |
| CN108073577A (en) | A kind of alarm method and system based on recognition of face | |
| KR20070116715A (en) | Home security applications for television with digital video cameras | |
| CN102915638A (en) | Surveillance video-based intelligent parking lot management system | |
| CN111047824B (en) | Indoor child nursing linkage control early warning method and system | |
| CN110852147A (en) | Security alarm method, security alarm device, server and computer readable storage medium | |
| CN113191252A (en) | Visual identification system for production control and production control method | |
| CN104519351A (en) | Automatic test method for set top boxes | |
| CN101411190B (en) | Spurious motion filter | |
| CN113971868A (en) | Alarm method and system based on infant behavior statistics | |
| CN111402096A (en) | Online teaching quality management method, system, equipment and medium | |
| CN115205581A (en) | Fishing detection method, fishing detection device and computer readable storage medium | |
| CN110895663B (en) | Two-wheel vehicle identification method and device, electronic equipment and monitoring system | |
| WO2018076508A1 (en) | Method and apparatus for security monitoring of greenhouse | |
| CN113392706A (en) | Device and method for detecting smoking and using mobile phone behaviors | |
| CN113361469A (en) | Method, device and equipment for identifying coverage state and storage medium | |
| KR20200056879A (en) | apparatus and method for automatically detecting bird's cast | |
| CN110928305B (en) | Patrol method and system for patrol robot of railway passenger station | |
| CN104392201A (en) | Human fall identification method based on omnidirectional visual sense | |
| CN115331386B (en) | Prevent fishing detection alarm system based on computer vision |
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 |