These days, a massive amount video is being recorded, but never watched or reviewed, due to lack of time. As a result, events and activities are missed, and suspicious behavior is not noticed in time to prevent incidents. This has led to the development of Intelligent Video (IV).
Intelligent video comprises any solution where the video surveillance system automatically performs an analysis of the captured video. Applications range from analytics such as video motion detection and audio detection, to more advanced systems including camera tampering detection, people counting, virtual fences, and vehicle license plate recognition. The applications performing these analyses are also referred to as Video Content Analysis (VCA) or Video Analytics (VA).
What is intelligent video?
Axis and Intelligent video
Download white paper
Intelligent Video is about reducing the vast amount of information contained in video, making it more manageable for systems and persons. Building this sort of analytics into network cameras has major advantages such as a more reliable and versatile video surveillance system, and drastically reduced workload for the staff.
The intelligent network camera is never idle and supports the operator 24 hours a day, seven days a week. It is constantly on guard, waiting for an impulse to start recording or sending an alarm to the operator.
Additionally, intelligent video systems can extract video and data from surveillance video streams and integrate that information with other applications, such as retail management systems or access control systems, creating new benefits and opening up new business possibilities.
The "intelligence" in intelligent video applications describes the analysis of video images and the automated use of the resulting data. The benefits from intelligent video systems are numerous, and include:
More efficient use of manpower
Large-scale video surveillance systems are limited in their effectiveness because it is difficult for operators to watch numerous monitors and keep track of every incident. With intelligent video solutions, fewer operators can monitor even very large installations, since staff will not be required to attentively watch many monitors for hours to notice undesired activity. Instead, the intelligent video system supports and informs operators about, for example, people moving about in restricted areas, cars driving the wrong way, or attempts to tamper with the video surveillance cameras.
Faster retrieval of stored video
Finding incidents in stored video is extremely time-consuming since the operator has to watch the recorded video. Given the difficulty of searching through stored video, most of it is simply archived and deleted. Video analytics – such as video motion detection – ensures that only relevant video footage is stored, so that when the need arises to search through old recordings, only video that could potentially include the event in question is retrieved. In addition, intelligent video systems that, for example, have tagged the video stream with appropriate labels during recording, can automatically search through days of stored video to find the right video footage in a matter of seconds.
Reduced network load and storage needs
Intelligent video systems that include video motion detection and audio detection minimize the need for storage space by recording only video that contains activity. Furthermore, by placing intelligent video ‘at the edge’, that is, processing as much as possible of the video in the network cameras themselves, the load on the network is significantly reduced as only relevant video is streamed from the cameras. Intelligent video applications help build video surveillance systems that are more cost-effective.
New business opportunities
Intelligent video also makes it possible to use video for applications outside of security. For example, in retail stores it can be used for analyzing consumer behavior, such as the number of people stopping by a particular merchandising shelf, or the popular routes through the shop. In airports, an intelligent video system could measure the queue time between entering and exiting a check-in point, helping direct staff and minimizing waiting time for travelers. In these and other ways, intelligent video makes it possible to extract greater benefit out of the video surveillance infrastructure, enabling a higher return-on-investment.
There are two broad categories of systems for implementing intelligent video: centralized and distributed. In centralized architectures, video and other information is collected by cameras and sensors and brought to a centralized server for analysis.
In distributed architectures, the edge devices (network cameras and video encoders) are ‘intelligent’ and are capable of processing the video and extracting relevant information. A further consideration is whether the system should allow for integration of applications from different vendors.
- Reliability and system availability – minimizing the risk of system failure and associated down-time
- Scalability and flexibility – the ability to effortlessly scale the system from a few to many cameras, as well as intelligently distribute processing across the network
- Interoperability – the ability to use system components from different vendors
- Security – making sure that only authorized personnel are allowed to access the system
- Total cost of ownership (TCO) – this includes capital costs for the system components and operational expenses
DVRs and centralized intelligence
To enable central monitoring of traditional CCTV systems surveillance video can be fed directly from the analog cameras into an intelligent video-enabled DVR. The DVR will perform the video analytics (people counting or car license plate extraction for example) before taking the remaining data, digitizing, compressing, and recording it; and distributing the resulting alarms and video output to authorized operators.
In this architecture, each analog camera is connected by a coax cable to the DVR. While this approach works adequately for small installations with a limited number of cameras, it is not scalable or flexible. Each DVR comes with a specific number of inputs and adding even one additional camera entails the addition of another DVR, which is a costly proposition. Also, since DVRs are proprietary embedded devices, they cannot be easily networked, or use intelligent video applications from different vendors, and do not support general network utilities, such as for security.
Network video systems and distributed intelligence
Network video allows for completely different strategy - distributed intelligence. Distributed architectures are designed to overcome the limitations of centralized architectures by distributing the processing to different elements in the network. The most scalable, cost-effective and flexible architecture is based on ‘intelligence at the edge’, that is, processing as much of the video as possible in the network cameras, or video encoders themselves. This architecture entails the least amount of bandwidth usage since the cameras can send out data and intelligently figure out what video needs to be sent. This significantly reduces the cost and complexity of the network centric processing model, and completely eliminates the drawbacks of centralized architectures.
If cameras for example have motion detection, then rather than streaming all the video, only interesting video that has motion in it can be sent to the monitoring station for further action and analysis. The load on the infrastructure and people involved falls dramatically. For specialized video analytics, where only the data is needed and not the video, such as, people counting, or automatic number plate recognition – running the applications in the camera has a dramatic impact since the cameras can extract the required data and send just that information, with perhaps a few snapshots.Furthermore, processing video at the edge – or partly at the edge – significantly reduces the cost of the servers needed to run the intelligent video applications. Servers that typically process only a few video streams when doing the entire video processing, can handle hundreds of video streams if some of the processing is done in the cameras.
By integrating intelligent edge devices with video management systems, and dividing the load between the different parts of the network, intelligent video solutions can be created that scale effortlessly, are more flexible, and cost-effective than centralized solutions.
Integrating intelligent video from different vendors
Many manufacturers of video surveillance equipment supply intelligent video applications with their products. Often these are applications that enhance camera functionality with video motion detection. Occasionally equipment manufacturers provide other, more advanced video applications with functionality such as tamper detection, and people counting.
However, building robust and commercially viable applications for video analytics requires expertise in image analysis and, sometimes, specialized knowledge in a certain application area, such as retail or transportation. For this reason, a number of software vendors have chosen to focus on supplying intelligent video applications that solve specific needs. To support this development Axis has introduced the AXIS Camera Application Platform. This open platform enables third-party suppliers to develop compatible applications that readily can be downloaded to designated Axis cameras and encoders. Together with network cameras, video encoders and/or video management software systems, these intelligent video applications form complete solutions, tailored to specific market requirements.
While this creates great freedom of choice for the end user, it also allows easy integration between the cameras/encoders, video management software, and the intelligent video applications. In order to be commercially attractive and to optimize compatibility, devices, software, and intelligent video applications need to be built on open interfaces (APIs) and platforms. This generates a much sought flexibility for users and enables them to design intelligent video surveillance systems that fit their needs perfectly.
Browse the list of available applications at http://www.axis.com/applications.
Active Tampering Alarm
Active Tampering Alarm is an intelligent video analytics application available in selected Axis network cameras. The Active Tampering Alarm functionality enables security staff to detect disrupted camera operation, by automatically alerting the operator when a camera is manipulated in any way.
The product is especially useful in applications where there is potential for vandalism – such as in schools, prisons, public transportation, and in harsh environments where weather, vibration, or dirt can disturb the camera’s performance. Active Tampering Alarm detects incidents such as accidental redirection, blocking or defocusing of cameras, and reacts when the camera is attacked, spray-painted, or intentionally covered.
Without Active Tampering Alarm, it can take a long time before tampering is noticed. This is especially true for applications where one operator monitors multiple cameras. If not detected right away, significant incidents may go undetected and completely unusable video is stored. However with Active Tampering Alarm, there is an immediate notification when normal camera operation is disturbed.
Many network video cameras include audio support, though, just as in video surveillance, local legislation or codes of practice sometimes limits the use of this feature. When possible, using audio can be a powerful complement to video. Audio detection is based on the same principles as video motion detection. The application detects noise – such as the breaking of a window or voices – and uses this as a trigger to transmit and record video, or to alert operators of suspicious activities.
Audio detection can supplement video motion detection, since it can react to events in areas too dark for the video motion detection to function properly, or detect activity that is hidden from the view of the cameras.
For audio detection to work, the camera needs to at least include audio support, and either have a built-in microphone or have an external microphone attached. The audio detection is configured to react to a certain volume of sound and send an alarm or initiate recording of the video stream and the audio, if so desired. Axis offers audio detection in all network video products that contain audio support.
Video motion detection
Video motion detection is the original, basic, and prevalent intelligent video application within video surveillance. It is primarily used to reduce the amount of video that is stored, by flagging video that has changes and eliminating video in which nothing changes.
By only storing video in which changes occur, security personnel can store video for a greater time period on a given storage capacity. It is also used to flag events to operators – such as persons entering locked areas – for immediate action.
Video motion detection is the foundation for a large number of more advanced video analytics, such as people counting, digital fences, and object tracking. Axis has offered video motion detection in its network video products since 2000 and today, all Axis network video products – are delivered out of the box with video motion detection.
其难点在于，确保在事件发生时，以足够高的图像质量录制了场景的正确部分，以便进行辨识。成本问题通常妨碍着大量摄像机的安装，或者难以专门聘请操作人员来手动控制水平转动/垂直转动/变焦 (PTZ) 摄像机。安讯士的自动追踪功能解决了这个问题，它让 PTZ 半球摄像机能够自动跟踪场景中的移动目标。
AXIS Cross Line Detection
AXIS Cross Line Detection是一款绊线入侵检测应用程序，可安装到支持安讯士摄像机应用平台的安讯士网络摄像机和编码器上。这款应用程序适用于大多数的室内外安装以及各种光线条件。
AXIS Cross Line Detection 尤其适用于人/车流量小的区域的进出监控，用于侦测超过预定义虚拟线的人、车等对象。这款应用程序非常适合监控建筑物的入口、码头、停车场以及区域周界。更多有关 AXIS Cross Line Detection的信息。
安讯士网络视频产品包括应用程序编程接口 (API)——AXIS VAPIX®，其促进了定制软件解决方案的开发。这使合作伙伴能够开发应用程序——包括智能视频应用程序，这些应用程序能够兼容安讯士网络摄像机和视频编码器。