Safety and Security Begins with Situational Awareness Provided by Intelligent Video
Keeping a safe, watchful eye on people in public spaces is challenging, especially in a healthcare setting where staff must interact with people during their most pained and stressful moments. Beyond the tense situations that can occur in an Emergency Department, healthcare facilities must balance safety with the desire to provide an open and inviting atmosphere to the community they serve.
Patient outcomes are improved when family, friends, and clergy visit frequently to offer encouragement. Access Control systems can help prevent unauthorized access to areas that must be secure, but vast areas of a hospital have to be open to the public.
Hospitals and healthcare facilities were early adopters of security camera technology to help maintain the safety of their staff and the public. The advancements in security camera technology have been profound. The grainy video from low-resolution analog cameras has been replaced with megapixel IP cameras storing HD quality video onto terabytes of inexpensive hard drives. Video Management Software (VMS) with sophisticated search tools has made forensic review of stored video much quicker than the cumbersome process of scrolling through hours of videotape.
There will always be a need to review recorded video to obtain a clear understanding of events, but the new challenge is to use video and access control technology to anticipate trouble and provide insight to respond to events as they are happening.
The proliferation of cost-effective security cameras that can capture and record events with great clarity has created a new problem – how do you watch dozens, if not hundreds of cameras and respond to events occurring in real-time?
Most smaller hospitals don’t have a dedicated security staff member watching live video in a security office. Security departments in larger hospitals have deployed hundreds of surveillance cameras covering broad areas indoors and out, 24 hours a day – 7 days a week. While video data is increasing, one person can only watch a limited amount of activity. People quickly lose their ability to concentrate, and suspicious movements on the screen are frequently overlooked. The solution? Intelligent Video.
How Intelligent Video Works
Intelligent Video (IV) is also referred to as Video Content Analysis (VCA) and Video Analytics (VA). Intelligent Video automatically analyzes the video stream and extracts useful information from images such as detecting intruders or unattended packages. Typical IV applications include Video Motion Detection, Video Pattern Matching, Auto Tracking and linkage to Access Control events. Intelligent Video works behind the scenes 24 hours a day without stopping, improving surveillance accuracy and effectiveness. When combined with an IP based Video Management System (VMS), Intelligent Video alerts can be sent real-time to PCs and smart phones so action can be taken the moment the event is taking place.
Video Motion Detection (VMD)
Motion Detection is the basic and prevalent technology in the security industry. VMD compares a series of images in the video stream, identifying the static background and moving foreground objects. VMD catches all motion, which is the difference between images, but this simultaneously presents a weakness. VMD detects wind-whipped flags and reflected light as moving objects, creating false alerts that demand attention and distract operators. Intelligent Video technology has made significant progress in extracting information such as position, size, motion direction, and staying time of detected objects, and analyzing their behavior. Intelligent Video Motion Detection (i-VMD) can now distinguish loitering from ordinary activities.
Where Video Motion Detection focuses on motion and does not care what the object is, Image Recognition identifies the target by using its shape characteristics. Facial Recognition is an example of an Image Recognition application that focuses on features of the human face such as the eyes, nose, and mouth. Intelligent Video searches for face-shaped parts on a captured image and identifies the person by estimating the similarity between the captured face and pictures in databases.
Advanced Auto Tracking
Advanced Auto Tracking is an Intelligent Video feature combined with conventional video motion detection and PTZ control, using indoor and outdoor PTZ network cameras. When a network camera finds a moving object in its view, the camera automatically starts panning, tilting and zooming, and keeps the moving object displayed in the center of the monitor screen. The network camera tracks the moving object until the target passes from its view. When the target leaves its view, another PTZ camera uses a proprietary inter-camera notification protocol to resume the tracking.
Intelligent Video System Configuration
There are three Intelligent Video system configurations:
- Camera-based systems where the Intelligent Video analytics are embedded into the camera
- Server-based systems which process on a centralized processing server
- Hybrid systems combining camera-based and server-based systems
Torrence represents the leading developers of all three types of Intelligent Video systems.
Network cameras analyze images and send alarms to operators based on pre-configured alert rules. Camera-based systems do not require high-performance central servers, making the systems more scalable, reliable, and cost-effective. Intelligent Video Motion Detection (i-VMD), Face Detection and Auto Tracking can all be done using camera-based system configurations.
Server-based systems enable more complex analysis. All images captured by cameras are sent to a central server that analyzes them with stronger processing power, more memory, higher-speed database access, and more sophisticated software.
Hybrid systems combine camera-based systems with server-based systems, substantially reducing server and network overloads. A hybrid system enables a smaller system to run Intelligent Video applications.
Examples of Intelligent Video Analytics to Improve Situational Awareness
Video Motion Detection
Intruder Detection, Loitering Detection, Direction Detection, Scene Change Detection, Object Detection and Cross Line Detection. The i-VMD extracts information such as position, size, moving direction, and staying time from the detected moving object and analyzes its behavior. For example, the i-VMD determines if the moving object is loitering or walking normally and sends an alarm to the operators. High-performance network cameras can simultaneously detect and track up to eight moving objects.
Intruder Detection detects people or cars trespassing in restricted areas. When a network camera detects moving objects in its view, it starts tracking each one of them. Once they step into a pre-defined detection area (the yellow box drawn into the camera view), the camera sends an alarm to the operators and highlights them with frames on the screen. This helps operators quickly identify what the camera is tracking.
Direction Detection detects people, cars, or moving objects going in the wrong direction, such as a vehicle entering a parking lot from the exit. When a network camera detects moving objects in its view, the camera starts tracking the movement and estimates the direction objects are going. When an object is moving in an unauthorized direction, the camera sends an alarm to the operators and highlights the object with a frame.
Scene Change Detection
Scene Change Detection detects tampering with the camera view. When a network camera detects interference or tampering, such as spraying on a camera dome, changing a camera direction, or covering a camera with a cloth, the camera sends an alarm to the operators. People pay little attention to motionless pictures. If a camera is intentionally obscured, a long time may pass before an operator becomes aware of it. Intelligent Video identifies tampering immediately.
Object detection detects objects disappearing that should be present or something left behind that shouldn’t be there. An IV network camera keeps a constant watch on a pre-defined area, comparing current footage with the past footage. When a left or removed object is detected, the camera sends an alarm to the operators and highlights the object or empty place with a frame. This helps operators easily identify what is left or removed.
Cross Line Detection
Cross Line Detection detects people or objects trespassing in restricted areas. When a network camera detects moving objects in its view, the camera starts tracking each one of them. Once the object crosses an imaginary line in a pre-defined direction, the camera sends an alarm to the operator and highlights the object in a frame. This helps the operator quickly identify what crossed the line.
Advanced Auto Tracking
Advanced Auto Tracking is an Intelligent Video feature combined with conventional video motion detection and PTZ control, and can be used on indoor or outdoor PTZ network cameras. When a network camera detects a moving object in its view, the camera automatically starts panning, tilting and zooming, and keeps the moving object displayed in the center of the monitor screen. The network camera tracks the moving object until the target passes from its view. When the target leaves its view, another camera uses a proprietary inter-camera notification protocol to resume the tracking.
Face Recognition System
Based on the Hybrid IV system architecture, a Facial Recognition Analytics Platform provides a high-performance, flexible and scalable Intelligent Video system. The system identifies a target person using both live and recorded video. IV cameras send clipped face images to the server. The Facial Recognition Analytics software extracts the face characteristics, compares them with the target facial photos in a linked database, and scores the similarity of the features. When the system finds a person similar to the target, it sends an alarm to the operator. The operator can then trace the subject with a glance at the History Table that shows when and where other cameras captured them on the campus.
Considerations for Deploying Camera-Based i-VMD
Camera-based i-VMD enables security officials to add Intelligent Video analytics to their surveillance systems at an affordable cost. Installing the cameras properly to maximize the desired detection performance is essential.
There are some basic steps to properly deploy and run i-VMD cameras:
The purpose, targets, zones, operating times, and environmental restrictions should be clarified during the planning stage. Based on these requirements, the system can be designed using the proper cameras and options.
The detection performance is affected by factors such as the captured target size, shooting angle, light, weather, and background. Typical camera settings may not be ideal for your requirements. Torrence recommends requesting an on-site survey to confirm if the cameras can detect targets as planned. If necessary, the design and/or settings can be revised before dollars are spent on a solution that will not function as expected.
Good detection performance requires steady, clear input into the camera. Cameras must be securely installed. Poor mounting and other installation issues negatively affect image quality through swinging from poles or vibration of walls or the ground.
Improper maintenance can lead to increase failure detections. Environment changing with the seasons may affect detection performance. Proper maintenance keeps i-VMD efficient.
Event Driven Video
Integration of Access Control and Video Management for a Complete Security Solution
Linking Video Management Systems (VMS) and Access Control provides substantial benefits for both real-time Situational Awareness and after-the-fact investigations. Access control events like card swipes and doors opening can be used to trigger security monitor alerts so security personnel can react to an unfolding situation or automatically archive the video tagged with the location and time. Prominent examples are med rooms and supply closets where the loss may not be immediately apparent. LDRP entrances, pharmacies, patient record rooms, employee entrances, and loading docks are other areas to consider. In typically unoccupied areas like Med Rooms, camera recording based on entry saves bandwidth and storage space instead of recording 24/7/365. Access control events can also trigger a PTZ camera to swing into place to ensure the camera sends a live stream to security and records a view of where the alarm occurred.
Torrence can help you choose the right components to build a comprehensive video security solution. Our Bicsi and CTS certified design engineers and NiCet certified installation and service teams provide a full-service experience for our healthcare clients. Contact us for a free on-site evaluation and solution proposal.