CN107358191B - Video alarm detection method and device - Google Patents
Video alarm detection method and device Download PDFInfo
- Publication number
- CN107358191B CN107358191B CN201710549612.XA CN201710549612A CN107358191B CN 107358191 B CN107358191 B CN 107358191B CN 201710549612 A CN201710549612 A CN 201710549612A CN 107358191 B CN107358191 B CN 107358191B
- Authority
- CN
- China
- Prior art keywords
- video data
- alarm
- video
- training
- unit
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Abstract
The invention provides a video alarm detection method and device. The method comprises the following steps: the intelligent video processing platform trains the training set to generate an alarm detector of the video data by utilizing a machine learning algorithm based on the training set of the video data, and carries out alarm detection processing on the video data to be processed by utilizing the alarm detector of the video data.
Description
Technical Field
The invention relates to the technical field of video detection, in particular to a video alarm detection method and device.
Background
Video monitoring is widely applied to many occasions due to intuition, accuracy, timeliness and rich information content. In recent years, with the rapid development of computers, networks, video processing and transmission technologies, video monitoring technologies have been developed. Video monitoring is an important component of a safety precaution system, and a traditional video monitoring system comprises a front-end camera, a transmission cable and a video monitoring platform.
The most important of video monitoring is video acquisition, and the very concerned information in a video picture mainly comprises the following steps: environment, people, vehicles, weather, intrusion, natural disasters, traffic accidents, and the like.
Video detection is to obtain effective information by analyzing video pictures, and at present, no method for effectively detecting video data and generating alarm information of the video data exists.
Disclosure of Invention
The embodiment of the invention provides a video alarm detection method and device, which are used for realizing effective alarm detection on video data.
In order to achieve the purpose, the invention adopts the following technical scheme.
One aspect of the present invention provides a video alarm detection method based on a video processing intelligent platform, comprising: the video processing intelligent platform utilizes a machine learning algorithm to train a training set of video data to generate an alarm detector of the video data; and performing alarm detection processing on the video data to be processed by using an alarm detector of the video data.
Further, the alarm detector for training the training set of video data by using a machine learning algorithm to obtain the video data comprises: collecting and storing video data in various video shooting scenes; setting various video classification factors and carrying out combined classification on the stored video data according to the classification factors; typical video data in the video data of each category is extracted, and the typical video data is used as a training set; extracting characteristic images of the training set to set alarm images corresponding to the characteristic images; and the alarm detector is used for training the characteristic images and the corresponding alarm images by utilizing a machine learning algorithm to generate video data, and comprises various characteristic images corresponding to each classified video data and alarm images corresponding to each characteristic image.
Further, the alarm detection processing is performed on the video data to be processed by using an alarm detector of the video data, and the alarm detection processing comprises the following steps: receiving video data to be processed, and carrying out classification processing on the video data to be processed to obtain the classification of the video data to be processed; decomposing a plurality of video pictures of video data to be processed according to a set time sequence; and synthesizing the alarm information corresponding to each video picture to obtain the alarm information corresponding to the video data to be detected.
Further, the video alarm detection method based on the video processing intelligent platform further comprises the following steps: and converting alarm information corresponding to the video data to be detected into an SVAC code stream, and sending the SVAC code stream to other equipment through a network.
Another aspect of the present invention provides a video alarm detection device based on an intelligent video processing platform, comprising: the learning training unit is used for training a training set of the video data by utilizing a machine learning algorithm to generate an alarm detector of the video data; and the alarm detection unit is used for carrying out alarm detection processing on the video data to be processed by utilizing the alarm detector of the video data.
Further, the learning training unit includes: the training data collection unit is used for collecting video data in various video shooting scenes; a storage unit for storing the collected video data; the video data classification unit is used for setting various video classification factors and carrying out combined classification on the video data stored in the storage unit according to the various classification factors; the video data extraction unit is used for extracting typical video data in each category of video data, and taking the typical video data as a training set; the characteristic image extraction unit is used for extracting characteristic images of the training set so as to set alarm images corresponding to the characteristic images; and the alarm detector generating unit is used for training the characteristic images and the alarm images corresponding to the characteristic images by utilizing a machine learning algorithm to generate the alarm detector of the video data, and the alarm detector comprises various characteristic images corresponding to each classified video data and the alarm image corresponding to each characteristic image.
Further, the alarm detection unit includes an alarm information synthesis unit, and the alarm information synthesis unit is used for: receiving video data to be processed, and carrying out classification processing on the video data to be processed to obtain the classification of the video data to be processed; decomposing video data to be processed into a plurality of video pictures according to a set time sequence; and synthesizing the alarm information corresponding to each video picture to obtain the alarm information corresponding to the video data to be detected.
Further, video alarm detection device based on video processing intelligent platform still includes: and the SVAC code stream conversion unit is used for converting the alarm information corresponding to the video data to be detected into an SVAC code stream and sending the SVAC code stream to other equipment through a communication network.
According to the technical scheme provided by the embodiment of the invention, the intelligent platform can be used for effectively and intelligently detecting the video data, automatically generating the alarm information of the video data and reducing the manual participation links. According to the coding specification of the SVAC, the alarm information can be converted into SVAC code streams, and the SVAC code streams are sent to other equipment, so that more applications can be realized.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a processing flow chart of a video alarm detection method based on a video processing intelligent platform according to an embodiment of the present invention;
fig. 2 is a structural diagram of a video alarm detection apparatus based on a video processing intelligent platform according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
Example one
Fig. 1 provides a processing flow of a video alarm detection method based on a video processing intelligent platform.
Step S110: and the video processing intelligent platform receives and stores the video data.
Step S120: and the video processing intelligent platform classifies and extracts the stored video data to generate a training set, and trains based on the training set of the video data by utilizing a machine learning algorithm to generate the alarm detector of the video data.
The video processing intelligent platform collects and stores a large amount of video data in various video shooting scenes, sets various video classification factors, and performs combination classification on the stored video data according to one or more of the various classification factors, wherein the classification factors can comprise shooting object types (moving or static), shooting time (day or night), shooting weather (various weather factors which can cause obvious video differences such as sunny days, rainy days, snowy days or foggy days), shooting equipment models, shooting lens directions and the like.
The video processing intelligent platform extracts typical video data in each category of video data, takes the typical video data as a training set, extracts characteristic images of the training set, sets alarm images corresponding to the characteristic images, trains the characteristic images and the corresponding alarm images by using a machine learning algorithm to generate an alarm detector of the video data, wherein the alarm detector comprises various characteristic images corresponding to each category of video data and the alarm images corresponding to the characteristic images. The various feature images corresponding to each category of video data may include: a person image, a person face image, a person motion image, a specific object image, a road image, a building image, various animal images, and the like.
Step S130: and performing alarm detection processing on the video data to be detected by using an alarm detector of the video data to generate alarm information of the video data to be detected.
The video processing intelligent platform receives video data to be processed, and carries out classification processing on the video data to be processed to obtain the classification of the video data to be processed.
Then, the video processing intelligent platform decomposes the video data to be processed into a plurality of video pictures according to a set time sequence (such as shooting time from first to last). And synthesizing the alarm information corresponding to all the video pictures to obtain the alarm information corresponding to the video data to be detected.
Step S140: and converting alarm information corresponding to the video data to be detected into an SVAC code stream.
SVAC (Survellance Video and Audio Coding, Surveillance Video and Audio Coding) is an Audio and Video Coding specification in the security field, is also a Coding standard in the monitoring field, and is rich in specification and can support realization of a plurality of application schemes.
The video processing intelligent platform converts the alarm information corresponding to the video data to be detected into an SVAC code stream, and sends the SVAC code stream to other equipment through a communication network, for example, sends an alarm message to a mobile phone gateway.
Example two
Fig. 2 shows a video alarm detection method and device based on a video processing intelligent platform. The intelligent platform-based video alarm detection device comprises a learning training unit 210 and an alarm detection unit 220. The learning training unit 210 is used to train a training set of video data with a machine learning algorithm to generate an alarm detector of the video data. The alarm detection unit 220 is configured to perform alarm detection processing on the video data to be processed by using the alarm detector for the video data.
The learning training unit 210 includes a training data collection unit 211, a storage unit 212, a video data classification unit 213, a video data extraction unit 214, a feature image extraction unit 215, and an alarm detector generation unit 216.
Specifically, the training data collection unit 211 is configured to collect video data in various video shooting scenes. The storage unit 212 is used to store the collected video data. The video data classification unit 213 is configured to set various video classification factors and perform combined classification of the video data stored in the storage unit 225 according to one or more of the various classification factors. The video data extraction unit 214 is configured to extract typical video data from the video data of each category, and use the typical video data as a training set. The feature image extraction unit 215 performs feature image extraction on the training set to set an alarm image corresponding to each feature image. The alarm detector generation unit 216 is an alarm detector for training the feature images and the corresponding alarm images by using a machine learning algorithm to generate video data. The alarm detector comprises various characteristic images corresponding to each classified video data and an alarm image corresponding to each characteristic image.
The alarm detection unit 220 includes an alarm information synthesis unit 221. The alarm information synthesizing unit 221 is configured to receive video data to be processed, decompose the video data to be processed into a plurality of video pictures according to a set time sequence, and synthesize alarm information corresponding to all the video pictures to obtain alarm information corresponding to video data to be detected.
Further, this video alarm detection device based on intelligent platform still includes:
and the SVAC code stream converting unit 230 is configured to convert the alarm information corresponding to the video data to be detected into an SVAC code stream, and send the SVAC code stream to other devices through the communication network.
The specific process of using the device of the embodiment of the invention to carry out video alarm detection based on the intelligent platform is similar to the method embodiment, and is not repeated here.
In summary, the embodiment of the invention can effectively perform intelligent detection on the video data by using the intelligent platform, automatically generate the alarm information of the video data, and reduce the manual participation links. According to the coding specification of the SVAC, the alarm information can be converted into SVAC code streams, and the SVAC code streams are sent to other equipment, so that more applications can be realized.
The alarm information in the video processing intelligent platform can be mutually shared and iterated step by step.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (2)
1. A video alarm detection method, comprising:
the video processing intelligent platform utilizes a machine learning algorithm to train based on a training set of video data to generate an alarm detector of the video data;
performing alarm detection processing on the video data to be processed by using the alarm detector of the video data;
the alarm detector which utilizes a machine learning algorithm and trains based on a training set of video data to obtain the video data comprises:
collecting and storing video data in various video shooting scenes;
setting various video classification factors and carrying out combined classification on the stored video data according to the classification factors;
extracting typical video data in the video data of each classification, and taking the typical video data as a training set;
extracting characteristic images from the training set to set alarm images corresponding to the characteristic images;
and training the characteristic images and the corresponding alarm images by utilizing a machine learning algorithm to generate an alarm detector of the video data, wherein the alarm detector comprises various characteristic images corresponding to each classified video data and alarm images corresponding to each characteristic image.
2. A video alarm detection device, comprising:
the learning training unit is used for generating an alarm detector of the video data based on training of a training set of the video data by utilizing a machine learning algorithm;
the alarm detection unit is used for carrying out alarm detection processing on the video data to be processed by utilizing the alarm detector of the video data;
wherein the learning training unit comprises:
the training data collection unit is used for collecting video data in various video shooting scenes;
a storage unit for storing the collected video data;
the video data classification unit is used for setting various video classification factors and carrying out combined classification on the video data stored in the storage unit according to the various classification factors;
the video data extraction unit is used for extracting typical video data in each category of video data, and the typical video data is used as a training set;
the characteristic image extraction unit is used for extracting characteristic images of the training set so as to set alarm images corresponding to the characteristic images;
and the alarm detector generating unit is used for training the characteristic images and the alarm images corresponding to the characteristic images by utilizing a machine learning algorithm to generate the alarm detector of the video data, and the alarm detector comprises various characteristic images corresponding to each classified video data and the alarm image corresponding to each characteristic image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710549612.XA CN107358191B (en) | 2017-07-07 | 2017-07-07 | Video alarm detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710549612.XA CN107358191B (en) | 2017-07-07 | 2017-07-07 | Video alarm detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107358191A CN107358191A (en) | 2017-11-17 |
| CN107358191B true CN107358191B (en) | 2020-12-22 |
Family
ID=60291780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710549612.XA Active CN107358191B (en) | 2017-07-07 | 2017-07-07 | Video alarm detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107358191B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108881708A (en) * | 2017-12-18 | 2018-11-23 | 南通使爱智能科技有限公司 | A kind of intelligent image processing unit |
| AT524306B1 (en) * | 2020-09-10 | 2022-09-15 | Pke Holding Ag | modeling a situation |
| CN112383756B (en) * | 2020-11-13 | 2021-08-17 | 珠海大横琴科技发展有限公司 | Video monitoring alarm processing method and device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102008039130A1 (en) * | 2008-08-21 | 2010-02-25 | Billy Hou | Automatic tracing and identification system for movable object e.g. human, in building, has safety monitoring sensor connected with safety monitoring system such that tracing camera receives desired data when sensor is operated |
| CN104253482A (en) * | 2014-08-08 | 2014-12-31 | 济南大学 | Image data base and inspection robot-based equipment trouble detection method |
| SG10201510337RA (en) * | 2015-12-16 | 2017-07-28 | Vi Dimensions Pte Ltd | Video analysis methods and apparatus |
| WO2017120375A1 (en) * | 2016-01-05 | 2017-07-13 | Wizr Llc | Video event detection and notification |
| CN106097346B (en) * | 2016-06-13 | 2019-08-27 | 中国科学技术大学 | A kind of video fire hazard detection method of self study |
| CN106781236A (en) * | 2016-12-29 | 2017-05-31 | 东南大学 | A kind of based on person detecting and again remote alarming device and long-distance monitoring method of recognition methods |
-
2017
- 2017-07-07 CN CN201710549612.XA patent/CN107358191B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107358191A (en) | 2017-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102752574B (en) | Video monitoring system and method | |
| CN107358191B (en) | Video alarm detection method and device | |
| CN107004271B (en) | Display method, display apparatus, electronic device, computer program product, and storage medium | |
| CN107205137A (en) | One kind monitoring recognition methods and device | |
| CN109460744B (en) | Video monitoring system based on deep learning | |
| CN106803936B (en) | Video snapshot method and device based on memory coding mechanism | |
| CN109740505B (en) | Training data generation method and device and computer equipment | |
| Dufour | Intelligent video surveillance systems | |
| KR20140039927A (en) | Method and apparatus for detecting event from multiple image | |
| CN109905423B (en) | Intelligent management system | |
| CN105357523A (en) | High-order singular value decomposition (HOSVD) algorithm based video compression system and method | |
| CN103369300A (en) | Nationwide video monitoring image unified coding and abnormal information automatic emergency system | |
| CN106778434A (en) | The method and its device of a kind of adjustment Quick Response Code of dynamic on the display region | |
| CN102857788A (en) | Video quality diagnostic system and video quality diagnostic method | |
| CN112309068B (en) | Forest fire early warning method based on deep learning | |
| CN111090773A (en) | Digital retina architecture and software architecture method and system | |
| CN109348140B (en) | Real-time video splicing method in monitoring scene | |
| CN107231547B (en) | Video monitoring system and method | |
| KR20130054705A (en) | Multi-purpose intelligent monitoring device using ubiquitous sensor network based on binary code division multiple access | |
| CN108073854A (en) | A kind of detection method and device of scene inspection | |
| CN109977891A (en) | A kind of object detection and recognition method neural network based | |
| CN110543825A (en) | Dangerous construction behavior identification method and device based on space-time characteristics | |
| WO2019135270A1 (en) | Motion video analysis device, motion video analysis system, motion video analysis method, and program | |
| CN215186950U (en) | Pedestrian red light running behavior evidence acquisition device based on face recognition technology | |
| CN115019462A (en) | Video processing method, device, storage medium and equipment |
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 |