1、 I n t e r n a t i o n a l T e l e c o m m u n i c a t i o n U n i o n ITU-T F.743.1 TELECOMMUNICATION STANDARDIZATION SECTOR OF ITU (04/2015) SERIES F: NON-TELEPHONE TELECOMMUNICATION SERVICES Audiovisual services Requirements for intelligent visual surveillance Recommendation ITU-T F.743.1 ITU-T F
2、-SERIES RECOMMENDATIONS NON-TELEPHONE TELECOMMUNICATION SERVICES TELEGRAPH SERVICE Operating methods for the international public telegram service F.1F.19 The gentex network F.20F.29 Message switching F.30F.39 The international telemessage service F.40F.58 The international telex service F.59F.89 St
3、atistics and publications on international telegraph services F.90F.99 Scheduled and leased communication services F.100F.104 Phototelegraph service F.105F.109 MOBILE SERVICE Mobile services and multidestination satellite services F.110F.159 TELEMATIC SERVICES Public facsimile service F.160F.199 Tel
4、etex service F.200F.299 Videotex service F.300F.349 General provisions for telematic services F.350F.399 MESSAGE HANDLING SERVICES F.400F.499 DIRECTORY SERVICES F.500F.549 DOCUMENT COMMUNICATION Document communication F.550F.579 Programming communication interfaces F.580F.599 DATA TRANSMISSION SERVI
5、CES F.600F.699 AUDIOVISUAL SERVICES F.700F.799 ISDN SERVICES F.800F.849 UNIVERSAL PERSONAL TELECOMMUNICATION F.850F.899 HUMAN FACTORS F.900F.999 For further details, please refer to the list of ITU-T Recommendations. Rec. ITU-T F.743.1 (04/2015) i Recommendation ITU-T F.743.1 Requirements for intell
6、igent visual surveillance Summary Recommendation ITU-T F.743.1 defines requirements for intelligent visual surveillance (IVS). The requirements are based on identifying specific objects, behaviours or attributes in video signals. The IVS system transforms the video signals into structured data, whic
7、h can be transmitted or archived so that the video surveillance system can act accordingly. This Recommendation defines the scenarios, the reference architecture and the requirements for IVS. History Edition Recommendation Approval Study Group Unique ID* 1.0 ITU-T F.743.1 2015-04-29 16 11.1002/1000/
8、12450 Keywords Intelligent visual surveillance, IVS requirement, IVS scenarios. _ * To access the Recommendation, type the URL http:/handle.itu.int/ in the address field of your web browser, followed by the Recommendations unique ID. For example, http:/handle.itu.int/11.1002/1000/11830-en. ii Rec. I
9、TU-T F.743.1 (04/2015) FOREWORD The International Telecommunication Union (ITU) is the United Nations specialized agency in the field of telecommunications, information and communication technologies (ICTs). The ITU Telecommunication Standardization Sector (ITU-T) is a permanent organ of ITU. ITU-T
10、is responsible for studying technical, operating and tariff questions and issuing Recommendations on them with a view to standardizing telecommunications on a worldwide basis. The World Telecommunication Standardization Assembly (WTSA), which meets every four years, establishes the topics for study
11、by the ITU-T study groups which, in turn, produce Recommendations on these topics. The approval of ITU-T Recommendations is covered by the procedure laid down in WTSA Resolution 1. In some areas of information technology which fall within ITU-Ts purview, the necessary standards are prepared on a col
12、laborative basis with ISO and IEC. NOTE In this Recommendation, the expression “Administration“ is used for conciseness to indicate both a telecommunication administration and a recognized operating agency. Compliance with this Recommendation is voluntary. However, the Recommendation may contain cer
13、tain mandatory provisions (to ensure, e.g., interoperability or applicability) and compliance with the Recommendation is achieved when all of these mandatory provisions are met. The words “shall“ or some other obligatory language such as “must“ and the negative equivalents are used to express requir
14、ements. The use of such words does not suggest that compliance with the Recommendation is required of any party. INTELLECTUAL PROPERTY RIGHTSITU draws attention to the possibility that the practice or implementation of this Recommendation may involve the use of a claimed Intellectual Property Right.
15、 ITU takes no position concerning the evidence, validity or applicability of claimed Intellectual Property Rights, whether asserted by ITU members or others outside of the Recommendation development process. As of the date of approval of this Recommendation, ITU had not received notice of intellectu
16、al property, protected by patents, which may be required to implement this Recommendation. However, implementers are cautioned that this may not represent the latest information and are therefore strongly urged to consult the TSB patent database at http:/www.itu.int/ITU-T/ipr/. ITU 2015 All rights r
17、eserved. No part of this publication may be reproduced, by any means whatsoever, without the prior written permission of ITU. Rec. ITU-T F.743.1 (04/2015) iii Table of Contents Page 1 Scope . 1 2 References . 1 3 Definitions 1 3.1 Terms defined elsewhere 1 3.2 Terms defined in this Recommendation .
18、1 4 Abbreviations 2 5 Scenarios for intelligent visual surveillance . 3 5.1 Target recognition 3 5.2 Event recognition and intelligent alarm . 4 5.3 Data analysis . 7 5.4 Intelligent video diagnosis 10 5.5 Intelligent video retrieval . 11 5.6 Intelligent video synopsis . 12 6 Reference architecture
19、12 7 Requirements for an IVS 14 7.1 User requirements . 14 7.2 Service requirements 16 Bibliography. 17 Rec. ITU-T F.743.1 (04/2015) 1 Recommendation ITU-T F.743.1 Requirements for intelligent visual surveillance 1 Scope This Recommendation defines requirements for intelligent visual surveillance (I
20、VS), which are based on identifying specific objects, behaviours or attribute in video signals. The visual surveillance service (see b-ITU-T F.743) is a telecommunication service focusing on audiovisual application technology that is used to capture remote multimedia information (such as audio signa
21、ls, video signals, images and various alarm signals) and to present it to end users in friendly manner, based on managed broadband networks with ensured quality, security and reliability. IVS systems can automatically identify specific objects, behaviours or attributes in video signals. They extract
22、 data from the video signals, which are then transmitted or archived so that the visual surveillance system can act accordingly. 2 References The following ITU-T Recommendations and other references contain provisions which, through reference in this text, constitute provisions of this Recommendatio
23、n. At the time of publication, the editions indicated were valid. All Recommendations and other references are subject to revision; users of this Recommendation are therefore encouraged to investigate the possibility of applying the most recent edition of the Recommendations and other references lis
24、ted below. A list of the currently valid ITU-T Recommendations is regularly published. The reference to a document within this Recommendation does not give it, as a stand-alone document, the status of a Recommendation. ITU-T H.626 Recommendation ITU-T H.626 (2011), Architectural requirements for vis
25、ual surveillance. 3 Definitions 3.1 Terms defined elsewhere This Recommendation uses the following term defined elsewhere: 3.1.1 visual surveillance ITU-T H.626: A telecommunication service focusing on video (but including audio) application technology, which is used to remotely capture multimedia (
26、such as audio, video, image, alarm signal, etc.) and present them to the end user in a user-friendly manner, based on a managed broadband network with ensured quality, security and reliability. 3.2 Terms defined in this Recommendation This Recommendation defines the following terms: 3.2.1 boundary d
27、etection: see perimeter prevention. 3.2.2 directed tripwire intrusion: Alarm output that is based on a polygonal region defined by the user. An alarm can be triggered when an object enters or leaves the polygon. 3.2.3 event recognition: Method that recognizes and analyses the events in the scene, an
28、d describes them using natural language. 3.2.4 facial recognition: Detection of the human face in video and extraction of its characteristics. The extracted information and/or image are compared with other images or a database of individuals images, generating comparison results. Facial recognition
29、can be used in airports, ports, railway stations, coach stations and other public places. 2 Rec. ITU-T F.743.1 (04/2015) 3.2.5 intelligent video diagnosis: Automatic recognition of video images failures, such as snowflakes, scrolling or fuzzy video, partial colour, picture freeze, gain imbalance, pa
30、n/tilt/zoom (PTZ) control problems and video signal loss. 3.2.6 intelligent video retrieval: Identification of useful or required information from videos. The search criteria can include target category, colour and velocity. 3.2.7 intelligent video synopsis: A simple summary of video content that ca
31、n be generated in an automatic or semi-automatic way. First, the target motion is analysed and moving targets are extracted. Then, the different targets are spliced to the same background scenes, and combined in some way. 3.2.8 perimeter prevention; boundary detection: An intelligent surveillance sc
32、enario where target objects, such as persons or transportation, can be identified in key areas. Through a virtual cordon or virtual warning region, it can also identify the direction of a target. 3.2.9 region detection: Alarm output that is based on the polygonal regions defined by the user and that
33、 is triggered when an object enters or leaves the region. 3.2.10 region stranded: Alarm output that is based on the polygonal regions defined by the user and that is triggered when the retention time of an object exceeds a prescribed threshold. 3.2.11 target recognition: A method that separates an i
34、mage region from the image background and uses some image feature value to classify the target types. 3.2.12 traffic/pedestrian flow analysis: Motion analysis and feature classification of the video of moving target(s) within the specified single or multiple video monitoring area. The pedestrian flo
35、w data can be detected accurately. 3.2.13 tripwire intrusion: The setting off of an alarm when an object crosses a line drawn within the surveillance area. 4 Abbreviations This Recommendation uses the following abbreviations and acronyms: APP Application CIV Client Intelligent Video CMS Centre Manag
36、ement System CMU Centre Management Unit CU Client Unit ICU Intelligent Customer Unit IPU Intelligent Premises Unit IVM Intelligent Video Management IVS Intelligent Visual Surveillance IVU Intelligent Video Unit MDU Media Distribution Unit MSU Media Storage Unit NTP Network Time Protocol PIV Premises
37、 Intelligent Video PTZ Pan/Tilt/Zoom Rec. ITU-T F.743.1 (04/2015) 3 PU Premises Unit SCU Service Control Unit SMS Short Message Service 5 Scenarios for intelligent visual surveillance This clause describes various scenarios for intelligent visual surveillance (IVS). 5.1 Target recognition Target rec
38、ognition separates the image region from the image background, using some image feature value to achieve the classification of the target type; the characteristics of target classification include space and time attributes. The space attribute comprises target contour, target size and target texture
39、. The time attribute includes the change of target size and velocity. Accordingly, all targets are classified as follows: persons, vehicles or miscellaneous objects. 5.1.1 Person identification The person identification system identifies human characteristics, which are different from those of vehic
40、les and miscellaneous objects. 5.1.2 Vehicle (car, ship, aircraft) recognition Vehicle recognition can identify the attributes of a vehicle, such as the type and colour. The type can be recognized using rules about the size of the vehicle. A vehicle smaller than a certain size might be a car and som
41、ething larger might be a truck. In addition, the colour of the vehicle can be used for recognition, but it might be influenced by the ambient light. See Figure 5-1. Figure 5-1 Target recognition (vehicle) 5.1.3 Miscellaneous objects As shown in Figures 5-2 and 5-3, miscellaneous objects include movi
42、ng objects that are not persons or vehicles; e.g., animals, smoke, fire and pollutants. Specifically, smoke and fire recognition can be used in forests, tunnels, oil, petrol and gas stations. As shown in Figure 5-3, this system can distinguish between smoke and other objects that are moving in the v
43、ideo. 4 Rec. ITU-T F.743.1 (04/2015) Figure 5-2 Target recognition (miscellaneous object) F I R EFigure 5-3 Target recognition (miscellaneous object) 5.2 Event recognition and intelligent alarm 5.2.1 Perimeter prevention Perimeter prevention (also known as boundary detection) identifies target objec
44、ts (such as persons or vehicles) in key areas defined by a virtual cordon or virtual warning region. Perimeter prevention can also identify the direction of the target. 1) Region detection: Alarm output must be based on the polygonal regions defined by the user. When an object enters or leaves a reg
45、ion, an alarm can be triggered. See Figure 5-4. Figure 5-4 Region detection Rec. ITU-T F.743.1 (04/2015) 5 2) Region stranded: Alarm output must be based on the polygonal regions defined by the user. When the retention time of an object exceeds a prescribed threshold, an alarm can be triggered. See
46、Figure 5-5. Figure 5-5 Region stranded 3) Tripwire intrusion: A line that is drawn within the surveillance area. When an object crosses that line, an alarm is triggered. See Figure 5-6. T r i p w i r eFigure 5-6 Tripwire intrusion 4) Directed tripwire intrusion: A line is drawn within the surveillan
47、ce area. When an object travelling in a specified direction crosses the line, an alarm can be triggered. A virtual cordon is drawn within the video image. When a target crosses the line in the specified direction, an alarm can be triggered. As shown in Figure 5-7, the direction of the virtual cordon
48、 can be unidirectional or bidirectional. 6 Rec. ITU-T F.743.1 (04/2015) (a) Intruder detection (b) Wrong direction detection Figure 5-7 Directed tripwire intrusion 5.2.2 Region security alarm and linkage Step 1: Bob is a security clerk. His job is to find suspicious persons and abnormal behaviour by
49、 watching real-time video from residential areas of interest using a surveillance system. Step 2: Bob uses an IVS system, where an electronic fence is defined based on a virtual line or a polygon in the video images and that is linked to an alarm. When objects cross the electronic fence and their direction of movement is consistent with the setting, the system generates sound and light alarms to alert related personnel, who then deal with the situation. Step 3: Leonard lives in this residential area. He enters
