Visilytics
Luceats’s AI and Convolutional Neural network powered video analytics solutions delivers actionable, tailored and trusted intelligence from any camera* source.
It can be deployed on-premises for real-time analysis and in the cloud for post-event investigations
Any Video Source
Our next-gen algorithms work on video from any digital video source, including any type of mobile camera*
Near Real Time
Analyze an unlimited number of camera* in near real time for a wide array of multi-class detections and events. VISILYTICS delivers total-environment intelligence
Post-Event
Execute video investigations at 20x speed, save thousands of man hours, and collect videos from staff or the public with a click of the button
Customized Analytics
Luceats cutting-edge deep learning platform supports customizable analytics aligned to your business requirement
Beyond Face Recognition
Industry-leading face recognition and 80+ object detection search is just a drop in the bucket of our capabilities. We deliver world-class multi-class detection powered by deep learning to the end user
Robust Rules Engine
Create real-time alerts and alarms around multi-class detections, zones of interests, face recognition, object detection and more
Visilytics Core Components
Object Detection
Form of computer vision that recognizes objects in an image or video and finds them. Currently model has been trained to detect over 80 objects from video feeds
Object Tracking
Object Tracking is a discipline that seeks to track objects as they travel through a sequence of video frames in computer vision.
Object Recognition
Recognition of objects is a form of computer vision for recognizing objects in pictures or recordings. The main consequence of deep learning and machine learning algorithms is object recognition.
Near Real-Time Video Analytics
Video cameras produce overwhelming amounts of data, so surveillance teams sometimes can’t manually review the stored footage to perform a post-incident report.
Triggering Real-Time Alerts
1. Anomaly Alerting
Based on deviation from standard and trained video model, anomalies are identified and alerted in real time.
2. Appearance Similarity Alerting
Based on entity appearance resemblance requirements, video surveillance operators may customize a warning.
3. Object Recognition Alerting
Intelligence services may use it to quickly identify faces, 80+ objects in real-time, based on digital images extracted from video or images
4. Count Based Alerting
Alerts can be activated when, within a given period, a certain number of objects (vehicles or people) are observed in a pre-defined location.
