Incident Scene Image Augmentation with Linked Audio Descriptions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Public safety professionals face challenges in efficiently identifying relevant physical spaces or objects at incident scenes during investigations due to the lack of effective tools for augmenting images with relevant object descriptions.

Innovation Solution

A method and system that uses an electronic computing device to detect objects of interest in images, link them to audio streams associated with incident identifiers, and generate visual or audio prompts based on audio descriptions from these streams, enhancing the ability to identify and understand objects within the incident scene.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If public safety professionals manually identify and document objects at incident scenes, then they can collect evidence, but the process is time-consuming and inefficient

Engineering Contradiction:
Improveincident investigation efficiencyVSAvoidtime to identify and document objects
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical identification and documentation processes with an automated computer vision system using machine learning models to detect, classify, and document objects at incident scenes, significantly improving efficiency and reducing time loss

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automatically capturing images, identifying objects, linking them to audio streams, and generating documentation without requiring continuous manual intervention from public safety professionals

Inventive Principle:
Principle #25Self-service

2Ease of operation

If no object description augmentation is provided, then the investigation process is simpler, but professionals cannot efficiently identify relevant objects

Engineering Contradiction:
Improveability to identify relevant objectsVSAvoidobject description information
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The patent introduces an intermediary system that processes images and audio streams to extract and link object descriptions, serving as a bridge between raw incident data and actionable intelligence for public safety professionals

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary analysis by pre-processing images and audio streams to identify and document objects before the professional arrives or while they are at the scene, preparing information in advance to aid their investigation

Inventive Principle:
Principle #10Preliminary action

3Reliability

If audio streams are analyzed for every object, then complete documentation is achieved, but processing time and computational resources increase

Engineering Contradiction:
Improvecompleteness of object documentationVSAvoidprocessing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies partial action by analyzing audio streams selectively - only for objects detected in images rather than processing all possible objects, achieving sufficient documentation completeness while reducing unnecessary computational overhead

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS11922689B2Device and method for augmenting images of an incident scene with object description
Publication Date: 2024.03.05 MOTOROLA SOLUTIONS INC
  • US11922689B2 patent drawing
  • US11922689B2 patent drawing
  • US11922689B2 patent drawing

AI summary

A process of augmenting images of incident scenes with object descriptions retrieved from an audio stream. In operation, an electronic computing device detects an object of interest in an image captured corresponding to an incident scene and identifies an audio stream linked to an incident identifier of an incident that occurred at the incident scene. The electronic computing device then determines whether the audio stream contains an audio description of the detected object of interest. When it is determined that the audio stream contains the audio description of the detected object of interest, the electronic computing device generates a visual or audio prompt corresponding to the audio description of the detected object of interest and plays back the visual or audio prompt via a corresponding display or audio-output component communicatively coupled to the electronic computing device.