VIDEO SUMMARISATION SYSTEM
Hours of footage. Minutes to the answer
Our Video Summarisation System is built around an on-demand video import and search model rather than requiring continuous, always-on processing of every camera feed; it lets investigators import only the specific footage they need, exactly when they need it. When an incident occurs, operators simply pull the relevant time range and camera(s) from existing NVRs or recorded storage, and the system indexes that footage on demand, ready for search within minutes.
This approach transforms hours of recorded footage into actionable, searchable summaries without the overhead of running analytics continuously across an entire camera network. Using patented synopsis technology, the system layers objects and events from the imported clip onto a single background frame, each tagged with its original timestamp, enabling investigators to review a full day’s activity in minutes instead of hours, while preserving complete forensic integrity.
Once footage is imported, the platform’s advanced search engine becomes the core investigation tool, allowing teams to search within that clip using rich filters such as appearance, colour, clothing, vehicle type, speed, direction, dwell time, face, and licence plate. Whether tracking a suspect’s path through a facility or verifying an incident timeline, the system reduces investigation time from hours to minutes and produces exportable, court-ready reports — all without the cost, storage burden, or complexity of continuous background processing.
Key Features
On-Demand Import & Indexing
Import Only What’s Needed
Pull specific time ranges and camera feeds from existing NVRs, VMS, or recorded storage only when an investigation requires it.
Fast On-Demand Indexing
Imported footage is processed and made searchable within minutes, not hours, avoiding pre-processing of unused footage.
Lower Infrastructure Overhead
Since processing is triggered per case rather than running continuously, compute and storage resources scale with the actual investigative workload, not the total camera count.
Works with Existing Recordings
Compatible with footage already stored on NVRs, DVRs, or cloud archives, requiring no changes to existing recording infrastructure.
Patented Video Synopsis Technology
Condenses Hours into Minutes
Eliminates empty frames and overlays multiple events from the imported clip onto a single timeline view, preserving original timestamps for verification.
Maintains Forensic Integrity
Every object and event links back to the original footage with precise time metadata, ensuring admissibility in legal proceedings.
Multi-Camera Synchronization
Reviews activity across multiple imported camera feeds simultaneously, revealing movement patterns and cross-camera trajectories.
Advanced Search & Filtering
Appearance-Based Search
Locates people and vehicles within imported footage by clothing colour, object type, size, gender, and other visual attributes.
Appearance Similarity
Finds similar-looking objects across cameras without requiring a specific image match, ideal for tracking suspects who change appearance.
Face Recognition
Searches detect faces in imported clips against watchlists or uploaded reference images (this can be disabled for privacy compliance).
Licence Plate Recognition
Identifies vehicles in uncontrolled, real-world conditions within the imported footage set.
Movement-Based Filters
Filters by speed, direction, path, dwell time, and area entry/exit to isolate relevant events quickly.
Multi-Camera Search
Searches across all imported cameras at once, accelerating suspect tracking and incident verification.
Case Management & Collaboration
Case Building
Organises imported footage, bookmarks, and investigation findings into a single container for streamlined review and reporting.
Team Collaboration
Enables multiple users to work on the same imported case simultaneously, with role-based access controls.
Investigation Reports
Generates exportable, annotated reports with relevant clips, metadata, and summaries for prosecution or internal review.
Operational Intelligence (Optional)
Retrospective Trend Analysis
For organisations that need it, footage from a defined period can be imported and aggregated to identify patterns in footfall, vehicle flow, or hotspot activity.
Custom Zone Analysis
Defines custom zones and paths within imported footage for detailed area usage and movement analysis.
Third-Party Data Correlation
Cross-references imported video with point-of-sale, access control, or workforce data for enriched investigative context.
Deployment & Scalability
Flexible, Case-Driven Licensing
Scales with the number of concurrent investigations and imported cameras rather than requiring licensing for an entire live network.
GPU-Accelerated On-Demand Processing
Leverages hardware acceleration to index imported footage quickly, minimising turnaround time for urgent cases.
Privacy Controls
Face recognition and licence plate search can be disabled to meet local regulatory or organisational privacy policies.
Connects devices and systems from any manufacturer on one open platform, protecting existing investments and giving you the freedom to choose best-of-breed technology for every application with no vendor lock-in.
Cross-references data from multiple sources to catch complex events that individual systems would miss on their own, for example, linking a failed access card swipe, a motion sensor alert, and an unrecognised vehicle into a single confirmed security breach.
Walks every operator through a predefined, step-by-step response procedure when an incident occurs, ensuring consistent, auditable, and rapid handling regardless of who is on shift.
Triggers preconfigured responses the instant an event occurs, unlocking emergency exits, activating lighting, and notifying first responders the moment a fire alarm is raised, without waiting on a human decision.
Displays all security assets and active incidents on a live, interactive map. Operators click a camera icon to pull up live video or a door icon to lock or unlock it remotely, with full geospatial context for every event.
Logs every event, action, and operator response automatically, creating a complete audit trail for post-incident analysis, compliance reporting, and performance review.
Lets security managers monitor systems, receive alerts, and respond to incidents from a smartphone or tablet, keeping control in hand from anywhere, not just the control room.
Analyses historical event data to identify patterns and forecast emerging risks, helping teams move from reactive monitoring to proactive threat prevention.
Centralises visibility into available security personnel, vehicles, and equipment, so operators can dispatch the right response assets to the right location, every time.
Applies live changes to rules, thresholds, and device configurations across all connected subsystems without interrupting operations or requiring changes to each system individually.
Continuously checks the status of every connected device, flagging a faulty camera, offline sensor, or failed component before it creates a coverage gap, not just after a security event occurs.
Runs on redundant servers, gateways, and databases with automatic failover, so a subsystem failure never interrupts control room operations or compromises business continuity.