Geo-Registered Video Analysis Rules for Multi-Sensor Tripwire Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional video analytics systems require users to manually define tripwires and features in pixel-based images from multiple sensors, leading to inefficiencies and inaccuracies due to human error and the difficulty in transferring these definitions across different camera frames of reference.
Innovation Solution
The system generates video analysis rules based on geo-registered map data, allowing users to define tripwires and features on a map interface independent of individual camera views, enabling efficient and accurate rule creation and application across multiple sensors using latitude and longitude coordinates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users manually define tripwires in pixel-based images from each sensor, then the detection rules can be established for each individual sensor view, but the process becomes inefficient and error-prone when multiple sensors monitor the same physical area
Solution Approach 1:
The patent introduces map data as an intermediary layer between the physical area and the pixel-based sensor views. Users define tripwires on the map in a common geographic coordinate system, and the system automatically transforms these definitions to each sensor's pixel space. This intermediary map representation eliminates the need for manual tripwire definition in each sensor view while maintaining placement accuracy.
Solution Approach 2:
The patent creates a digital copy of the physical monitored area using map data with geographic coordinates. This map copy serves as a master reference that can be replicated and transformed to generate tripwire definitions for multiple sensors simultaneously, rather than manually creating separate definitions for each sensor.
2Adaptability or versatility
If tripwires are manually drawn on each sensor's pixel-based view, then each sensor can have customized detection rules, but human error causes tripwires to not coincide exactly across different sensors
Solution Approach 1:
The map data with geographic coordinates serves as an intermediary that provides a common reference frame for all sensors. Tripwires defined on the map are transformed to each sensor's pixel space using the sensor's location and orientation data, ensuring consistent alignment across all sensors while allowing customization through the map interface.
Solution Approach 2:
The patent changes the coordinate system parameter from pixel-based (sensor-specific) to geographic coordinate-based (common reference). By defining tripwires in geographic coordinates on the map and then transforming to pixel coordinates for each sensor, the system maintains reliability across sensors while preserving adaptability through map-based customization.
3Productivity
If pixel-defined tripwires are transferred between cameras, then the same detection rules can be applied across multiple sensors, but the technical difficulty increases because pixels of different cameras do not share a common frame of reference
Solution Approach 1:
The patent introduces map data with geographic coordinates as an intermediary that simplifies the transfer process. Instead of directly transforming pixel coordinates between cameras (which is complex), the system defines tripwires on the map in geographic coordinates and uses the known location and orientation of each camera to automatically generate the appropriate pixel-based rules for each sensor.
Solution Approach 2:
The patent inverts the traditional approach by not starting with pixel-based tripwire definitions and trying to transfer them between cameras. Instead, it starts with map-based geographic coordinate definitions and derives the pixel-based rules for each camera, reversing the transformation direction to simplify the process.
Data Source
AI summary
Systems, methods and computer-readable media for creating and using video analysis rules that are based on map data are disclosed. A sensor(s), such as a video camera, can track and monitor a geographic location, such as a road, pipeline, or other location or installation. A video analytics engine can receive video streams from the sensor, and identify a location of the imaged view in a geo-registered map space, such as a latitude-longitude defined map space. A user can operate a graphical user interface to draw, enter, select, and/or otherwise input on a map a set of rules for detection of events in the monitored scene, such as tripwires and areas of interest. When tripwires, areas of interest, and/or other features are approached or crossed, the engine can perform responsive actions, such as generating an alert and sending it to a user.