Foreground Analysis Using Tracking Information

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing video surveillance systems rely on edge energy methods for detecting abandoned or removed objects, which are sensitive to background clutter and result in high false alarm rates, especially in complex environments with varying lighting and cluttered backgrounds.

Innovation Solution

Implementing a method that uses tracking information to analyze static foreground objects, combining edge energy and region growing techniques with object tracking statistics to accurately classify objects as abandoned or removed, and trigger alerts only when user-defined criteria are met, thereby reducing false alarms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If edge energy methods are used for detecting abandoned or removed objects, then detection capability is provided, but false alarm rate increases due to sensitivity to background clutter

Engineering Contradiction:

Improvedetection capabilityVSAvoidfalse alarm rate

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent introduces tracking information as an intermediary element between background subtraction and final object classification. By incorporating object trajectories and motion patterns from tracking data, the system mediates the detection process to distinguish true abandoned objects from false alarms caused by background clutter, thereby improving measurement precision while maintaining detection capability

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback by using tracking information to verify and refine initial detections from background subtraction. The tracking module provides feedback about object motion patterns and trajectories, allowing the system to correct false alarms and improve the accuracy of abandoned object detection, thus reducing false alarm rates

Inventive Principle:

Principle #23Feedback

2Ease of operation

If background subtraction is used to detect candidate foreground objects, then static objects can be identified, but detection accuracy decreases in complex environments with varying lighting and cluttered backgrounds

Engineering Contradiction:

Improvestatic object identificationVSAvoiddetection accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent merges multiple detection approaches by combining background subtraction with tracking-based verification. The system integrates the simplicity of background subtraction for initial static object identification with the accuracy of tracking information to verify detections, thereby maintaining ease of operation while improving detection accuracy in complex environments

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system performs preliminary action by using background subtraction to quickly identify candidate foreground objects before applying more complex tracking verification. This preliminary identification step maintains ease of operation, while the subsequent tracking-based verification ensures detection accuracy, allowing the system to handle complex environments effectively

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS9460361B2Foreground analysis based on tracking information

Publication Date: 2016.10.04 NEC CORP

AI summary

Techniques for performing foreground analysis are provided. The techniques include identifying a region of interest in a video scene; detecting a static foreground object in the region of interest; and performing a foreground analysis based on tracking information to determine whether the static foreground object is abandoned or removed.