CN105117693A - Video detection method based on optical identification - Google Patents
Video detection method based on optical identification Download PDFInfo
- Publication number
- CN105117693A CN105117693A CN201510493425.5A CN201510493425A CN105117693A CN 105117693 A CN105117693 A CN 105117693A CN 201510493425 A CN201510493425 A CN 201510493425A CN 105117693 A CN105117693 A CN 105117693A
- Authority
- CN
- China
- Prior art keywords
- blocked
- region
- image information
- target
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention provides a video detection method based on optical identification. The method comprises the steps of placing an optical identification into an application environment to constitute an identification area, shooting the identification area through a video device to obtain video image information, determining a blocked area which comprises the optical identification according to the video image information, analyzing the video image information and detecting whether the blocked area exists or not, and obtaining a result that an object exists if the blocked area can not be detected. According to the method, the influence of ambient light change and video device imaging quality can be overcome, and the robustness is good.
Description
Technical field
The present invention relates to digital image processing techniques, particularly relate to a kind of video detecting method based on optical indicia.
Background technology
In video monitoring, often need to detect a certain class specific objective and whether occur, as people, animal, parts, automobile, aircraft etc.Common methods has the physical features by detecting this specific objective, as passed through specific range of temperatures human body and animal; The automobile passed through is detected by the ferromagnetic characteristic of ground induction coil; By reflection of electromagnetic wave Characteristics Detection aircraft; Come count of zero parts and tablet etc. by hyperacoustic reflection characteristic, these ways and meanses, accuracy is good, stability is high, but all needs special device to carry out.
In recent years, along with the fast development of optical image technology and computer technology, occurring that video detects the method for specific objective, by detecting the presence or absence of the optical signature of target in video frame image, having judged whether target occurs.But video detects order calibration method to be affected with being subject to various factor, thus causes poor stability.After background wipes out extraction prospect, then target is detected according to the estimation size of target and resemblance, it is the method relatively commonly used, but the method is limited by the quality of Background Reconstruction, when target and background gray scale close to time, easily miss target, and when ambient lighting variation characteristic is uncertain, the methods and strategies of Background Reconstruction itself is difficult to adjustment in time.Frame difference method detect target also often used, but when target slowly move or stop motion time, then can't detect.
In recent years, there is a lot of method based on pattern-recognition, namely first extracting such clarification of objective, by whether there is the image block with this feature in detected image, differentiating whether such target occurs, appear at which position, the method requires that target itself has comparatively specific profile and architectural feature, need to select suitable sample set to train, otherwise often training is unsuccessful, when target itself has larger attitudes vibration or is at least partially obscured, often can't detect.Above video object detection method, usually can be subject to ambient lighting change and the impact of video camera imaging quality, how overcome above problem, is a huge challenge.
Summary of the invention
Video detecting method based on optical indicia provided by the invention, can overcome the impact of ambient lighting change and video-unit image quality, have good robustness.
According to an aspect of the present invention, a kind of video detecting method based on optical indicia is provided, comprises:
Optical indicia is inserted in applied environment and forms identified areas; By video-unit, shooting is carried out to described identified areas and obtain video image information; Determine according to described video image information the region that is blocked, described in the region that is blocked comprise described optical indicia; If be blocked region described in can't detect, then there is target.
The video detecting method based on optical indicia that the embodiment of the present invention provides, identified areas is formed by being inserted in applied environment by optical indicia, video-unit carries out shooting to identified areas and obtains video image information, the region that is blocked is determined according to video image information, when can't detect be blocked region when, then there is target, thus the impact of ambient lighting change and video-unit image quality can be overcome, there is good robustness.
Accompanying drawing explanation
The video detecting method process flow diagram based on optical indicia that Fig. 1 provides for the embodiment of the present invention;
Another video detecting method process flow diagram based on optical indicia that Fig. 2 provides for the embodiment of the present invention;
The optical indicia schematic diagram that Fig. 3 provides for the embodiment of the present invention;
The vehicle detection application scenarios schematic diagram that Fig. 4 provides for the embodiment of the present invention;
Fig. 5 detects application scenarios schematic diagram for the gate inhibition that the embodiment of the present invention provides.
Embodiment
Below in conjunction with accompanying drawing, the video detecting method based on optical indicia that the embodiment of the present invention provides is described in detail.
The video detecting method process flow diagram based on optical indicia that Fig. 1 provides for the embodiment of the present invention.
With reference to Fig. 1, in step S101, optical indicia is inserted in applied environment and forms identified areas.
Here, applied environment comprises gate inhibition, indoor channel, traffic route, production line, work station and parking lot.
Optical indicia is the mark comprising shape, structure and color, specifically can refer to optical indicia schematic diagram as shown in Figure 3, in figure 3, grey is ground, white and black are mark color used in optical indicia, color in optical indicia is not limited to white and black, also can replace by other colors.
In step S102, by video-unit, shooting is carried out to identified areas and obtain video image information.
In step S103, determine according to video image information the region that is blocked, the region that is blocked comprises optical indicia.
In step S104, analyze described video image information, be blocked described in whether detection exists region.
In step S105, if can't detect the region that is blocked, then there is target.
Further, be blocked described in can't detect if described region, then there is target and comprise:
If described in be blocked the shape in region change or described in the region that is blocked be blocked, then there is target.
Further, described method also comprises:
If be blocked region described in detecting, then there is not target.
Further, be blocked described in detecting if described region, then there is not target and comprise:
If described in be blocked the shape in region do not change or described in the region that is blocked be not blocked, then there is not target.
Further, describedly to comprise according to described video image information region of determining to be blocked:
According to described video image information utilize Hough transformation or local binary patterns LBP algorithm determine described in be blocked region.
Here, Hough transformation is the method identifying geometric configuration from image, is mainly used for from image, isolate the geometric configuration with certain same characteristic features.
Local binary patterns (LocalBinaryPatterns, LBP) algorithm is a kind of texture analysis algorithm, extracts textural characteristics by certain image processing techniques, and obtains the processing procedure of the quantitative of texture or qualitative description by textural characteristics.
Another video detecting method process flow diagram based on optical indicia that Fig. 2 provides for the embodiment of the present invention.
With reference to Fig. 2, in step S201, optical indicia is inserted in applied environment and forms identified areas.
In step S202, by video-unit, shooting is carried out to identified areas and obtain video image information.
In step S203, determine according to video image information the region that is blocked.
In step S204, analyze video image information, be blocked described in whether detection exists region, if can't detect the region that is blocked, then performs step S205; If the region that is blocked detected, then continue to perform step S204.
In step S205, there is target.
The vehicle detection application scenarios schematic diagram that Fig. 4 provides for the embodiment of the present invention.
With reference to Fig. 4, Car license recognition is taken the photograph machine and is carried out shooting acquisition video image information to identified areas, the region that is blocked is determined by analyzing video image information, video image information is analyzed, whether the detection region that is blocked is blocked, if be blocked, then at vehicle through identified areas, thus complete the work of vehicle detection.Wherein, identified areas can be, but be not limited to, and is specially mosaic shape.
Fig. 5 detects application scenarios schematic diagram for the gate inhibition that the embodiment of the present invention provides.
With reference to Fig. 5, be contained in room by video camera, and optical indicia is placed in the inside line of door, video camera carries out shooting to the identified areas comprising optical indicia and obtains video image information, determines by analyzing video image information the region that is blocked.
When the region that is blocked exists, then, when nobody comes in, door is in closed condition.
Shape when the region that is blocked changes or is blocked by human body, then illustrating has people to come in.Now, alarm host machine starts to report to the police, and warning message is sent to owner, infrastructure management company or public security department, thus guarantees the safety of owner.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (6)
1. based on a video detecting method for optical indicia, it is characterized in that, described method comprises:
Optical indicia is inserted in applied environment and forms identified areas;
By video-unit, shooting is carried out to described identified areas and obtain video image information;
Determine according to described video image information the region that is blocked, described in the region that is blocked comprise described optical indicia;
Analyze described video image information, be blocked described in whether detection exists region;
If be blocked region described in can't detect, then there is target.
2. method according to claim 1, is characterized in that, be blocked described in can't detect if described region, then there is target and comprise:
If described in be blocked the shape in region change or described in the region that is blocked be blocked, then there is target.
3. method according to claim 2, is characterized in that, described method also comprises:
If be blocked region described in detecting, then there is not target.
4. method according to claim 3, is characterized in that, be blocked described in detecting if described region, then there is not target and comprise:
If described in be blocked the shape in region do not change or described in the region that is blocked be not blocked, then there is not target.
5. method according to claim 1, is characterized in that, describedly comprises according to described video image information region of determining to be blocked:
According to described video image information utilize Hough transformation or local binary patterns LBP algorithm determine described in be blocked region.
6. method according to claim 1, is characterized in that, described applied environment comprises doorway, indoor channel, traffic route, production line, work station and parking lot.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510493425.5A CN105117693A (en) | 2015-08-12 | 2015-08-12 | Video detection method based on optical identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510493425.5A CN105117693A (en) | 2015-08-12 | 2015-08-12 | Video detection method based on optical identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105117693A true CN105117693A (en) | 2015-12-02 |
Family
ID=54665676
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510493425.5A Pending CN105117693A (en) | 2015-08-12 | 2015-08-12 | Video detection method based on optical identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105117693A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109145839A (en) * | 2018-08-29 | 2019-01-04 | 福建超汇信息技术有限公司 | Pricing method and computer readable storage medium based on Machine Vision Recognition |
CN110008968A (en) * | 2019-04-09 | 2019-07-12 | 哈尔滨新中新电子股份有限公司 | A kind of robot clearing automatic trigger method based on image vision |
CN110796209A (en) * | 2018-08-03 | 2020-02-14 | 杭州海康机器人技术有限公司 | Trigger detection method, device and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102799862A (en) * | 2012-06-29 | 2012-11-28 | 陕西省交通规划设计研究院 | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image |
CN103366578A (en) * | 2013-06-27 | 2013-10-23 | 北京文通图像识别技术研究中心有限公司 | Image-based vehicle detection method |
CN103744120A (en) * | 2013-12-30 | 2014-04-23 | 中云智慧(北京)科技有限公司 | Method and device for assisting identification of contraband |
CN104349143A (en) * | 2014-11-11 | 2015-02-11 | 广东中星电子有限公司 | Video monitoring method, video monitoring device and video monitoring system |
-
2015
- 2015-08-12 CN CN201510493425.5A patent/CN105117693A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102799862A (en) * | 2012-06-29 | 2012-11-28 | 陕西省交通规划设计研究院 | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image |
CN103366578A (en) * | 2013-06-27 | 2013-10-23 | 北京文通图像识别技术研究中心有限公司 | Image-based vehicle detection method |
CN103744120A (en) * | 2013-12-30 | 2014-04-23 | 中云智慧(北京)科技有限公司 | Method and device for assisting identification of contraband |
CN104349143A (en) * | 2014-11-11 | 2015-02-11 | 广东中星电子有限公司 | Video monitoring method, video monitoring device and video monitoring system |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110796209A (en) * | 2018-08-03 | 2020-02-14 | 杭州海康机器人技术有限公司 | Trigger detection method, device and system |
CN109145839A (en) * | 2018-08-29 | 2019-01-04 | 福建超汇信息技术有限公司 | Pricing method and computer readable storage medium based on Machine Vision Recognition |
CN110008968A (en) * | 2019-04-09 | 2019-07-12 | 哈尔滨新中新电子股份有限公司 | A kind of robot clearing automatic trigger method based on image vision |
CN110008968B (en) * | 2019-04-09 | 2023-08-08 | 哈尔滨新中新电子股份有限公司 | Automatic triggering method for robot settlement based on image vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10055979B2 (en) | Roadway sensing systems | |
De Charette et al. | Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates | |
CN111325769B (en) | Target object detection method and device | |
CN103069796A (en) | Method for counting objects and apparatus using a plurality of sensors | |
CN103986906B (en) | Door opening and closing detection method based on monitoring videos | |
CN103971380A (en) | Pedestrian trailing detection method based on RGB-D | |
CN110619279A (en) | Road traffic sign instance segmentation method based on tracking | |
US11371851B2 (en) | Method and system for determining landmarks in an environment of a vehicle | |
WO2014160027A1 (en) | Roadway sensing systems | |
Shobayo et al. | Development of smart plate number recognition system for fast cars with web application | |
KR20150049529A (en) | Apparatus and method for estimating the location of the vehicle | |
CN102445453B (en) | Automatic detection device and identification method for integrality of guardrail of high-speed railway line | |
CN102902951A (en) | System and method for vehicle target location and event detection on basis of high-definition video monitoring images | |
CN105117693A (en) | Video detection method based on optical identification | |
CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
CN111783700B (en) | Automatic recognition and early warning method and system for pavement foreign matters | |
KR101686558B1 (en) | Multilane camera recognition system and method for analysing image to learning type thereof | |
CN113205690A (en) | Roadside parking departure event judgment method and system based on multiple dimensions | |
Wu et al. | Recognition of airport runways in FLIR images based on knowledge | |
Ryu et al. | Feature-based pothole detection in two-dimensional images | |
CN114332781A (en) | Intelligent license plate recognition method and system based on deep learning | |
CN103366578A (en) | Image-based vehicle detection method | |
CN112668478B (en) | Well lid monitoring method and device, electronic equipment and storage medium | |
CN107729811B (en) | Night flame detection method based on scene modeling | |
CN112104838B (en) | Image distinguishing method, monitoring camera and monitoring camera system thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151202 |