How Artificial Intelligence Is Changing Video Security Today

by Avigilon
Oct 3, 2018

Share
Avigilon Identity Search Results UI2

Avigilon recently contributed an article to Security Informed that discusses how artificial intelligence (AI) is changing video security today. The article outlines the need for AI in video security systems, how it can enable faster video search, and how it can help focus operators’ attention on key events and insights to reduce hours of work to minutes.

Below is the full article, modified from its original version to fit this blog post, which can also be found on SecurityInformed.com.


There’s a lot of excitement around artificial intelligence (AI) today — and rightly so. AI is shifting the modern landscape of security and dramatically changing the way users interact with their security systems. But with all the talk of AI’s potential, you might be wondering: what problems does AI help solve today?

The Need for AI

The fact is, today there are too many cameras and too much recorded video for security operators to keep pace with. On top of that, people have short attention spans. AI is a technology that doesn’t get bored and can analyze more video data than humans ever possibly could.

It is designed to bring the most important events and insight to users’ attention, freeing them to do what they do best: make critical decisions. There are two areas where AI can have a significant impact on video security today: search and focus of attention.

更快搜索

Imagine using the internet today without a search engine. You would have to search through one webpage at a time, combing through all its contents, line-by-line, to hopefully find what you’re looking for. That is what most video security search is like today: security operators scan hours of video from one camera at a time in the hope that they’ll find the critical event they need to investigate further. That’s where artificial intelligence comes in.

With AI, companies such as Avigilon are developing technologies that are designed to make video search as easy as searching the internet. Tools like Avigilon Appearance Search™ technology — a sophisticated deep learning AI video search engine — help operators quickly locate a specific person or vehicle of interest across all cameras within a site.

When a security operator is provided with physical descriptions of a person involved in an event, this technology allows them to initiate a search by simply selecting certain descriptors, such as gender or clothing color. During critical investigations, such as in the case of a missing or suspicious person, this technology is particularly helpful as it can use those descriptions to search for a person and, within seconds, find them across an entire site.

Focused Attention

The ability of AI to reduce hours of work to mere minutes is especially significant when we think about the gradual decline in human attention spans. Consider all the information a person is presented with on a given day. They don’t necessarily pay attention to everything because most of that information is irrelevant. Instead, they prioritise what is and is not important, often focusing only on information or events that are surprising or unusual.

Now, consider how much information a security operator who watches tens, if not hundreds or thousands of video cameras, is presented with daily. After just twenty minutes, their attention span significantly decreases, meaning most of that video is never watched and critical information may go undetected. By taking over the task of "watching" security video, AI technology can help focus operators’ attention on events that may need further investigation.

For instance, technology like Avigilon Unusual Motion (UMD) uses AI to continuously learn what typical activity in a scene looks like and then detect and flag unusual events, adding a new level of automation to video security.

This helps save time during an investigation by allowing operators to quickly search through large amounts of recorded video faster, automatically focusing their attention on the atypical events that may need further investigation, enabling them to more effectively answer the critical questions of who, what, where and when.

As AI technology evolves, the rich metadata captured in security video — like clothing color, age or gender — will add even more relevance to what operators are seeing. This means that in addition to detecting unusual activities based on motion, this technology has the potential to guide operators’ attention to other “unusual” data that will help them more accurately verify and respond to a security event.

The Key to Advanced Security

There’s no denying it, the role of AI in security today is transformative. AI-powered video management software is helping to reduce the amount of time spent on monitoring, making security operators more efficient and effective at their jobs. By removing the need to constantly watch video screens and automating the “detection” function of security, AI technology allows operators to focus on what they do best: verifying and acting on critical events.

This not only expedites forensic investigations but enables real-time event response, as well. When integrated throughout a security system, AI technology has the potential to dramatically change security operations. Just as high-definition imaging has become a quintessential feature of today’s video security cameras, the tremendous value of AI technology has positioned it as a core component of security systems today, and in the future.

© 2018, Avigilon Corporation. All rights reserved. AVIGILON, the AVIGILON logo, and AVIGILON APPEARANCE SEARCH are trademarks of Avigilon Corporation. Other names or logos mentioned herein may be the trademarks of their respective owners.

Keep current on Avigilon

Sign up to receive our blogs.

Follow us on Twitter, Facebook, LinkedIn, and view Avigilon videos on YouTube.

Category: Security

Tags:


For Media Relations

Please email media@avigilon.com or call 604-629-5182


词汇表

ACC 版本 经过摄像机测试的最新版 ACC。通常也支持更新版本的 ACC(除非具体列出)。
音频输入 接收来自摄像机的音频源。
音频输出 将音频发送到与摄像机相连的扬声器。
自动发现 在 LAN 环境中连接时,会自动发现摄像机 IP 地址。
压缩类型 描述摄像机支持的编码类型。
连接类型 描述所使用的设备驱动程序的类型。原生是指制造商指定的设备驱动程序。
去弯曲 在客户端内去除鱼眼或全景摄像机的图像弯曲现象。
数字输入 接收来自摄像头的数字或中继输入。
数字输出 触发物理连接到摄像机的数字或继电器输出。
运动 快速显示摄像机上的运动录制是否可用。
运动配置 在 ACC 客户端内配置运动检测。
运动录制 支持基于运动的录制。
PTZ 快速显示摄像机上的 PTZ 功能是否可用。
PTZ 控制 基本 PTZ 移动。
PTZ 模式/巡视 创建并触发 PTZ 模式或 PTZ 巡视的能力,具体取决于摄像机是否支持。
PTZ 预设 创建并触发 PTZ 预设位置。
单位类型 摄像机的类型。
验证方 测试摄像机并给出评测报告的组织。
已认证的固件 Specific firmware version tested.
制造商 Blah
型号 DS-2DE2103
连接类型 ONVIF
单位类型 IP PTZ 摄像机
Compression Types H.264

  • ACC 版本
  • 型号 DS-2DE2103
  • 连接类型 ONVIF
  • 制造商 Blah
  • 制造商 Blah
  • 制造商 Blah
  • 制造商 Blah
  • 制造商 Blah
  • 制造商 Blah
  • 制造商 Blah
  • 制造商 Blah
  • 制造商 Blah

验证人员:

Vendor
下载测试报告