Automated Radar-Cued Camera Scheduling for Target Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current surveillance systems with radar and camera combinations are manual and inefficient, allowing only a subset of radar hits to be visually examined, leading to potential misses of moving targets and increased complexity and cost with additional cameras.
Innovation Solution
An automated scheduling system for a radar-cued camera that calculates a Track Value metric for each radar hit, combining Track Life, Slew, and Coverage values to optimize camera slew and zoom, enabling the camera to focus on the most valuable targets and maximize visual inspection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple cameras are added to improve visual detection coverage, then the ability to visually detect more targets is improved, but system complexity and cost increase
Solution Approach 1:
The system performs preliminary actions by calculating slew metrics and coverage metrics for all potential camera positions before actual camera movement. This allows the system to pre-determine the optimal camera configuration for detecting multiple radar targets, eliminating the need for additional cameras while maintaining comprehensive visual detection coverage.
Solution Approach 2:
The patent transitions from a spatial solution (adding more cameras) to a computational solution (adding calculation dimensions). By introducing multiple metric calculations (slew metric, coverage metric, combined metric) and using processor-based scheduling, the system achieves multi-target visual detection capability without increasing physical camera count, thus reducing system complexity.
2Ease of operation
If manual operation is used to examine radar hits, then operator control flexibility is maintained, but only a subset of radar hits can be visually examined leading to target misses
Solution Approach 1:
The system implements feedback by continuously monitoring radar target data, calculating updated metrics for each new radar hit, and dynamically adjusting camera slew commands based on the combined metric values. This closed-loop feedback enables the camera to automatically prioritize and track multiple targets in real-time, significantly increasing visual inspection throughput while maintaining operational effectiveness.
Solution Approach 2:
The system enables self-service by allowing the automated scheduling algorithm to independently determine camera positioning and timing without requiring manual operator intervention for each radar hit. The processor automatically calculates optimal camera positions based on slew metrics and coverage metrics, and executes camera movements autonomously, thereby increasing productivity while preserving operator flexibility for oversight and intervention when needed.
3Speed
If camera slew time is reduced to capture moving targets, then target detection responsiveness is improved, but the number of radar hits that can be examined decreases
Solution Approach 1:
The system performs preliminary calculations of slew metrics and coverage metrics for all potential camera positions before executing camera movements. This advance preparation allows the system to optimize camera slew timing and sequencing, enabling faster camera response to moving targets while coordinating multiple slew operations to maximize the number of radar hits examined within available time.
Solution Approach 2:
The system implements dynamic scheduling by continuously recalculating metrics for each new radar hit and adjusting camera slew commands in real-time. The combined metric dynamically balances slew time requirements against the number of examinable radar hits, allowing the system to adapt camera speed and timing based on current scene conditions, target urgency, and camera position, thereby optimizing both responsiveness and productivity.
Data Source
AI summary
Described is system for optimizing visual inspection of radar targets. The system detects radar hits with a radar system comprising radar and a radar-cued camera. The camera has a current state comprising a current slew position and a current zoom level. The radar hits are stored, and a set of metrics are determined for each radar hit. A track value (TV) metric is determined that combines the set of metrics for each zoom level of the camera. The camera sends a set of commands based on the TV metric, such that the camera slews from the current state to a new state. The new state is a position of a radar hit with the largest TV metric and a corresponding zoom level. Given the new state, an image is captured and processed to generate captured tracks. The current state of the camera is updated to reflect the new state.