Video Analytics & AI

Facial Recognition

Face recognition techniques are widely use at video surveillance industry. Once the extracted images have been categorized as faces, facial recognition can create positive IDs of individuals through the use of deep learning algorithms.

Such recognition techniques can be used:

• For access control granting access with using cards
• At crowded environments for minimizing criminal activity
• At forensic analysis for searching suspects at multiple scenes or videos
• For marketing purposes in order to extract information such as age gender, ethnicity etc.

Retail AI Analytics

Retail Analytics use state-of-the-art algorithms that enable the detection of faces and are also able to determine people’s key characteristics such as gender and age. Retail algorithms can also track customers’ journeys through stores and analyze their routes to detect walking patterns. Using this technology retailers can identify how long a customer spends on a shelf and answer crucial questions such as where is the best place to put items in order to maximize sales and improve customer experience.

Smart Traffic Control

Traffic control is now used at the majority of modern cities. Vehicle counting techniques, differentiations between cars, trucks, buses, taxis, and so on, can also generate high-value information that can be used to obtain insights about local traffic. Installing traffic control cameras allows for more precise traffic control and can support: Real-time parking spot detection - a smart parking system based on video analytics helps drivers find a vacant spot by analyzing images from security cameras.

Such traffic control systems can support also: Traffic Lights, Speed, U-turn, speed, wrong way, bus lane violations etc.

License Plate Recognition (LPR / ANPR)

Optical Character Recognition (OCR) has been used for decades to extract text from images. LPR systems collect license plate information and use it in order to authorize the pass of vehicle or motorbike in a certain area or a road. LPR systems can easily identify vehicles that are involved in illegal acts or spot a vehicle that has been stolen.

Security AI Analytics

With the use of AI we are able to provide security video analytics such us:

• Image classification: select the category of an image from among a set of predetermined categories (vehicle, person, object etc.).
• Object localization: locate an object in an image (drawing a bounding box around the object).
• Object detection: detect an object in an image, also detect object left behind or object removal
• Object identification: identify & categorize all of its instances in an image
• Object tracking: object that moves or stop moving, wrong direction, intrusion,
• Object behavior: analyze object reactions, moves, body positions, interactions
• Crowd management: count objects, directions of move, waiting time ...and move from the field of reaction to the field of proaction.