Outdoor Intrusion Detection
According to a U.S. Department of Justice survey, a household member is present during approximately 28% of burglaries, and 7% of these victims experienced some type of violent crime.
There are multiple reasons for seniors to have a video surveillance system with automated intrusion detection and responder notification. The first is simply that surveillance systems deter crime - 60% of convicted burglars stated the presence of a security system influenced their decision to target another home (per the University of North Carolina at Charlotte’s Department of Criminal Justice and Criminology).
The second reason is automated intrusion detection can detect suspicious activity outside of a house or facility and generate an immediate deterrence (e.g. audio warning and turning on lights) and notify residents, caregivers, and responders.
Automated intrusion detection systems based upon traditional rules based technology are prone to false alarms resulting in responders not reacting. One of the significant challenges is that the target environment often changes, for example, a fence or tree sways from a wind gust, seasonal changes generate unexpected shadows to appear or a bird decides to perch on a fence - all require the analytics to be re-tuned. Conversely, analytics based upon machine learning continually update their data models to take into account environmental changes.
Today’s generation of video analytics are deep-learning based. They can learn from and make predictions on data. Over time, the system learns the scene and is able to prioritize important events based on user feedback. This increases sensitivity to conditions that are of concern while reducing false alarms to keep the focus on what matters.
There are multiple reasons for seniors to have a video surveillance system with automated intrusion detection and responder notification. The first is simply that surveillance systems deter crime - 60% of convicted burglars stated the presence of a security system influenced their decision to target another home (per the University of North Carolina at Charlotte’s Department of Criminal Justice and Criminology).
The second reason is automated intrusion detection can detect suspicious activity outside of a house or facility and generate an immediate deterrence (e.g. audio warning and turning on lights) and notify residents, caregivers, and responders.
Automated intrusion detection systems based upon traditional rules based technology are prone to false alarms resulting in responders not reacting. One of the significant challenges is that the target environment often changes, for example, a fence or tree sways from a wind gust, seasonal changes generate unexpected shadows to appear or a bird decides to perch on a fence - all require the analytics to be re-tuned. Conversely, analytics based upon machine learning continually update their data models to take into account environmental changes.
Today’s generation of video analytics are deep-learning based. They can learn from and make predictions on data. Over time, the system learns the scene and is able to prioritize important events based on user feedback. This increases sensitivity to conditions that are of concern while reducing false alarms to keep the focus on what matters.
Indoor monitoring
Smart systems also enable indoor monitoring. Some examples within assisted living institutions include...
- Room Entry/Exit Monitoring - room entry by a neighboring resident or a resident exiting during late evening hours
- Prolong Activities - residents entering an area, e.g., bathroom, and failing to exit within a specified time
- Agressive Behavior - often a senior’s behavior is an early warning to a detrimental event; a resident walking rapidly may indicate an incident or trigger an incident
- Post-Surgery Monitoring- bed bound residents attempting to get up and walk
