Contact us:  0820896374

eMail us info@WeDoSecurity.co.za

Video Analytics

As CCTV software has evolved, we’ve come to understand video analytics as crunching the visual data streamed from network cameras and performing real-time event detection and post-event analysis. 

Specifically, when it comes to video surveillance, the term video analytics refers to catching visual data streams from network cameras and performing real-time event detection and post-event analysis. However, there are some major differences to keep in mind:

Standard Video Analytics

“Video Motion Detection” (VMD), is a video analytic function based on the analysis of pixel variation. The cameras with VMD can detect changes that occur in their field of view, and generate alarms regardless of the object type.

Functions include;

  • Camera Tampering
  • Line Crossing
  • Sterile Area

Pixel Based video analytics

Pixel-based video analytics is known as “Video Motion Detection” (VMD). VMD cameras automatically detect pixel variations in their field of view and generate alarms regardless of the object type. 

The downside of using VMD is that the images can vary throughout the day due to varying lighting conditions, noise in the images, or tree movement. Because of these factors, VMD technology is recommended for indoor installation only.

Advanced Video Analytics

Artificial intelligence is based on a series of algorithms that process data by comparing the object seen with hundreds of thousands of stored reference images of objects in different angles, positions, and motions.

By combining all of the values from the various questions, an overall ranking is created which tells the A.I. whether the object is a human, a vehicle, or an object.

The ability to distinguish the type of “object”, false alarms caused by rain, shadows, light changes, shacking trees, and animals are significantly reduced with a smart camera.

Functions include;

    • DDA Analytics
    • Face Detection
    • Face Recognition
    • License Plate Recognition ( LPR )
pixel based video analytics

Smart Cameras

Wikipedia defines a Smart Camera as;

A smart camera (sensor) or intelligent camera (sensor) or (smart) vision sensor or intelligent vision sensor or smart optical sensor or intelligent optical sensor or smart visual sensor or intelligent visual sensor is a machine vision system which, in addition to image capture circuitry, is capable of extracting application-specific information from the captured images, along with generating event descriptions or making decisions that are used in an intelligent and automated system

The ProvisionISR Smart Cameras are ideal for streaming high-quality video and performing smart video analytics over a network.

The brand-new SMART-SIGHT SERIES includes high-performance AI cameras, which are designed to perform specific tasks such as face recognition, license plate recognition, and perimeter security.

Each component of the system, from the sensor, to the optics, through the CPU, and even the lighting, was specifically chosen to provide the most accurate AI result.

DDA Analytics

Detect. Distinguish. Alert.

DDA VIDEO ANALYTICS is one of the Artificial Intelligence features built by Provision-ISR. With DDA VIDEO ANALYTICS, the system uses smart objects recognition to distinguish between:

DDA VIDEO ANALYTICS distinguishes between humans, 4 wheel vehicles, and 2 wheel vehicles using smart object recognition technology. By using this technology, the system triggers alarms or sends push notifications only when the desired object is detected, reducing false alarms caused by shadows, light changes, shaking trees, animals, etc.

The AI technology in DDA Analytics is based on a series of algorithms that operate as questions comparing the scene object with thousands of stored reference images of objects at different angles, positions, and movements.

The AI asks itself whether the observed object moves like the reference images. If it has the characteristic of having two arms and two legs, moves with similar speed, and if it is vertical instead of horizontal.

The system derived an overall ranking by combining the values from the questions, which indicates the probability that the object is or isn’t a human, a vehicle, a vehicle, or an object.

DDA Video Analytics Options

The user draws a line in the scene and sets both the crossing direction and crossing permissions.


Example:
If vehicles are not allowed to cross the line (but humans are) the system will generate an alarm only to the passage of a vehicle. No alarm will be generated if a person cross the line.

The user draws a area in the scene and sets access permissions.

 

Example:
If vehicles are not allowed to access the area (but people are) the system will generate an alarm only when a vehicle enter the limited area.In addition, the user can configure if entering/exiting the area will trigger an alarm

The user positions the camera at a gate entrance/exit to get a real-time entrance and exit monitoring.

 

Example:
If the observed vehicle counting area is set at the entrance of a parking the system will allow to monitor when the parking reach the maximum number of vehicles allowed.

DDA ANALYTICS APPLICATIONS

NO PARKING AREA - STERILE AREA

HUMANS ALLOWED

The system determines whether the object is a human by detecting and distinguishing its characteristics. The event is registered, but no alarm is triggered.  

VEHICLES NOT ALLOWED

A warning will be generated when a car that is not allowed to enter the restricted area is detected and recognized by the system.

PERIMETER PROTECTION

VEHICLES ALLOWED

The car outside the gate enters the area drawn by the user. When the system detects and identifies the car as one that is allowed to enter the restricted area, no alarm is triggered  

HUMANS NOT ALLOWED

A person enters the area drawn by the user. The system generates an alarm when it detects and distinguishes a human attempting to climb over the fence.

DISTINCTION BETWEEN HUMANS / VEHICLES / OBJECTS

VEHICLES AND HUMANS NOT ALLOWED

When an object is left within the limited area, no alarm is generated (no vehicles or people are detected by the system) When the shadow of a person enters the limited area, no alarm is generated.

HUMANS NOT ALLOWED

When the system recognizes a person entering a restricted area as a human, it generates an alarm.

Get in touch with us Today and get your FREE Quote to upgrade your security system
wedosecurity_favicon.png

082 089 6374

WhatsApp or Call us

Please note our  Installations & Repairs are limited to Gauteng and George to Knysna in the Western Cape.

We do   sell and deliver throughout South Africa

Email info@wedosecurity.co.za

Would you like an installation quote
Please advise how we may assist