Neurotechnology announces the release of SentiVeillance Cluster, an off-the-shelf software for monitoring systems with cluster architecture implementation for smart city-scale projects
The highly scalable solution enables surveillance systems to automatically analyze video feeds, observe vehicles and pedestrians in real time – from small single-machine setups to surveillance centers with hundreds of camera feeds
VILNIUS, Lithuania, November 18, 2022 /PRNewswire/ — Neurotechnology, a provider of deep learning-based solutions and high-accuracy biometric identification technologies, today announced the launch of SentiVeillance Cluster for real-time biometric face identification, people and vehicle tracking and automatic vehicle license plate recognition. The solution was designed for large surveillance systems supporting continuous video streams from multiple servers. It provides operators with structured and sorted live data, enabling faster decision-making in a variety of scenarios, including law enforcement, security and smart city surveillance applications.
The technology can be used in applications ranging from small surveillance setups to full smart city surveillance systems.
“We are delighted to present the SentiVeillance Cluster, as it will open up new opportunities for our
customers,” said Vytautas Pranckėnas, SentiVeillance Product Manager at Neurotechnology. “Equipped with a scalable architecture and award-winning biometric algorithms, this solution offers flexible applications and reliable results. We see immense potential for this technology to be used in a variety of applications – from small surveillance setups to entire smart city surveillance systems.”
SentiVeillance Cluster software is designed to analyze many video streams at once and combine multiple servers into a cluster network. Key system features include:
- Identification and biometric tracking of people
- Tracking and classification of pedestrians and vehicles
- Integration with Milestone VMS video management system
- Real-time custom watchlist verification with automatic event triggering and logging
- Multiple video streams that can be analyzed on a cluster of machines
- Support for multiple GPUs
Terms of SentiVeillance:
The SentiVeillance Cluster software supports biometric facial recognition, a vehicle-to-human modality, and Automated License Plate Recognition (ALPR) modalities for surveillance systems.
- Biometric facial recognition
In addition to continuous face tracking and person recognition, the face algorithm provides gender classification, age determination and attribute detection capabilities. Watchlists can be generated using face image data and additional metadata (e.g. biographical fields, custom fields) to quickly populate watchlists. No additional registration is required for face coverings (e.g. masks).
In access control applications, facial recognition ensures a high degree of confidence that only authorized persons can access public and private sector premises. SentiVeillance monitoring for safety and security decreases the likelihood of theft, abuse, gang violence and other illegal activities.
The accuracy and performance of the algorithm has been tested in the most reliable series of large-scale independent evaluations for facial recognition algorithms at NIST Facial Recognition Vendor Test (FRVT).
- Vehicle-human modality
Vehicle and pedestrian detection can be performed on moving or static objects, allowing system users to perform operations directly from live video feeds. The algorithm can distinguish vehicles such as bicycles, trucks, buses, cars and pedestrians. Additionally, color, vehicle brand information and motion vector estimates can be made.
In electronic toll systems, SentiVeillance algorithms can be used for fast and accurate vehicle recognition to automatically collect usage fees or toll charged to the vehicle owner for the use of toll roads, tunnels, etc
- Automatic License Plate Recognition (ALPR) mode
The ALPR algorithm provides reliable detection even in difficult recognition scenarios, allowing high tolerance to camera position and license plate orientation. By using the ALPR and VH modalities together, it is possible to check if a license plate is on the correct type of vehicle and alert the authorities if it is not.
The system can simultaneously analyze multiple traffic camera videos and read license plates of many moving vehicles in real time. This feature provides parking security by using an automated monitoring system to reduce and prevent theft and damage. Surveillance systems with the ALPR modality installed at the entrances to the car parks guarantee access control for registered vehicles.
Parking monitoring application
SentiVeillance customer uniPark implements parking solutions throughout the Baltic and Polandwith more than 160 projects in Lithuania, including airports, shopping and business centers and downtown parking areas. uniPark collaborated with the SentiVeillance team to create parking surveillance, without conventional barriers or check-in terminals, based on automated license plate recognition and video feed from conventional surveillance cameras.
“We have been using the SentiVeillance solution in uniPark car parks for over a year, and we are absolutely impressed with the benefits of this technology,” said Justinas Doviltis, IT Director at uniPark. “The ability to record cars from different camera angles and in totally uncontrolled scenarios, without barriers or close-up cameras, gives us new opportunities to provide flexible and cost-effective solutions to the market.”
SentiVeillance Cluster is based on the SentiVeillance SDK which has been designed for easy integration of real-time biometric face identification, person and vehicle tracking and automatic license number recognition into surveillance systems. When using the SentiVeillance SDK, separate modalities may be used alone or in combination, subject to monitoring system design.
Depending on the needs of the surveillance project, several pricing options are available for SDK users that provide flexibility and scalability with no recurring fees. Try all SentiVeillance products on your system by downloading a free 30-day trial or explore the possibilities at www.sentiVeillance.com.
Neurotechnology is a developer of high-precision algorithms and software based on deep neural networks and other AI-related technologies. The company was launched in 1990 in Vilnius, Lithuania, with the key idea of using neural networks for various applications, such as biometric identification of people, computer vision, robotics and artificial intelligence. Neurotechnology’s algorithms have achieved top results in independent technology assessments, including NIST MINEX, PFT, FRVT, and IREX. The company’s solutions and products have been used in more than 140 countries around the world and in nationwide projects such as general elections in Ghana, voter deduplication in the Democratic Republic of Congo and other projects. which collectively process the data of more than 200 million citizens. Recently, Neurotechnology, together with consortium partner Tata Consultancy Services (TCS), was selected as one of the biometric service providers for the world’s largest biometric identification system, india Aadhaar, which already has 1.3 billion people registered in its database and is expected to grow to more than 2 billion over the next seven years. https://www.neurotechnology.com.
View original content for multimedia download: https://www.prnewswire.com/news-releases/neurotechnology-announces-the-release-of-sentiveillance-cluster-ready-to-use-software-for-surveillance-systems -with-cluster-architecture-implementation-for-smart-city-scale-projects-301682934.html