VIVOTEK

AI-Powered Video Analytics on Edge

Advanced AI engine for people detection, dramatically reduces the adverse effects of distraction by small animals, light rain, lighting changes, etc.
Higher accuracy and fewer false alarms.
Multiple event rules for different application scenarios.
Video Content Analysis (VCA) detectors for Intrusion, Loitering, Missing Objects, Unattended Objects, Line Crossing, and Face Detection.
VIVOTEK Smart VCA is the next-generation video analytics suite running on VIVOTEK cameras for security applications. The on-board Smart VCA suite includes Intrusion Detection, Loitering Detection, Missing Object Detection, Unattended Object Detection, Line Crossing Detection, and Face Detection.

Deep Learning Technology

The core of VIVOTEK’s Smart VCA is a deep learning AI engine offering advanced accuracy in people detection compared with traditional rule-based designs. VIVOTEK took advantage of its extensive experience in the surveillance field and resulting vast image databases to develop a neural-network powered detection engine for the human form. Based on a database of human silhouettes and rapid responses via a pre-trained deep learning model, the smart engine instantly recognizes the appearance of human forms in the surveillance area. As humans are the objects of interest in the majority of video surveillance, the people-detection feature enables users to quickly configure their installation. With people-detection, only human activities will serve as event triggers, while swaying vegetation, vehicles passing by, or animal activities in the scene will be ignored. This helps reduce both false alarms as well as the time and effort taken for camera configuration.

Multiple Event Rules

Above the AI core, multiple event rules are provided to detect intrusion, persons loitering or running in a zone or crossing a line, objects missing and abandoned, or to detect faces from a crowd within the zone. These rules cover most of the typical security application requirements, and multiple rules can be applied to a single camera view.

Intrusion Detection

VIVOTEK Intrusion Detection can be used to detect persons entering or leaving a virtual area within the camera’s field of view.

Example Application Scenarios:

• Detect when a person enters a bank vault or school after hours.
• Detect when a person leaves an emergency exit hallway and fire escape.

Loitering Detection

VIVOTEK Loitering Detection is used to detect a person or a group of people lingering in one area longer than a preset time threshold.

Example Application Scenarios:

• Detect a person loitering at a walk-up or drive-up ATM lane.
• Detect a person loitering in a high-theft area of a store.

Line Crossing Detection

VIVOTEK Line Crossing Detection detects a person or a group of people crossing a virtual trip-wire.

Example Application Scenarios:

• Detect someone who enters a driveway, an entrance or an exit.
• At a fenced boundary, detect when:
• Someone is close to the perimeter
• Someone has crossed the perimeter

Unattended Object Detection

VIVOTEK Unattended Object Detection detects unattended objects or objects left behind.

Example Application Scenarios:

• Detect boxes placed in front of an emergency exit.
• Detect objects left on subway tracks or platforms, on a bridge, or in a bank lobby.

Missing Object Detection

VIVOTEK Missing Object Detection detects the removal of a predefined asset from a scene.

Example Application Scenarios:

• In a campus setting, the Missing Object feature can be used to monitor high-risk areas, such as the administrative offices, computer labs, or science laboratories, for theft.

Face Detection

VIVOTEK Face Detection detects and tracks faces in the camera’s field of view.

Example Application Scenarios:

• Detected and captured faces can be used for monitoring and evidence purposes.

Crowd Detection

VIVOTEK Crowd Detection can be used to identify how many people there are in a given area. Stores and business’ can then effortlessly manage social distances between customers, intelligently helping to alleviate the stress of managing customer congestion.

Example Application Scenarios:

• Detect congestion when the number of people in a region is more than a set number and trigger an alarm.
• Monitor a special area within which at most one person is allowed at any given time.

Running Detection

VIVOTEK Running Detection can be used to detect the moving speed of a person in a scene. In surveillance applications, person(s) running at high speed in places such as campus, hospital, factory, shopping mall, or bank could potentially be an abnormal situation.

Example Application Scenarios:

• A theft is running away in a shopping mall when people found and are chasing him. Running Detection can detect the running persons in the scene.
• When a robbery has happened in a parking lot, Running Detection can detect a person is running after the robber.