Search Assistance for Occluded Target Detection in Captured Video

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies struggle to detect search target objects hidden by peripheral objects due to limitations in camera placement, leading to missed detections.

Innovation Solution

A search assistance device and method that utilizes a captured video acquisition unit, object information acquisition, and a determination unit to identify hidden search targets, creating comparison videos to reveal obscured objects using peripheral object information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If images are captured using a limited number of cameras in specific directions, then device complexity is reduced, but detection reliability deteriorates when search targets are hidden by peripheral objects

Engineering Contradiction:
Improvenumber of camerasVSAvoiddetection reliability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent transitions from two-dimensional image analysis to three-dimensional spatial reasoning by constructing a 3D model of the search area using depth information from multiple images. This 3D model enables the system to determine whether search targets are hidden behind peripheral objects by analyzing spatial relationships in three dimensions, thereby improving detection reliability without requiring additional cameras.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent introduces a 3D model as an intermediary representation between the captured images and the detection result. This 3D model serves as a mediator that integrates information from multiple 2D images and provides a comprehensive spatial understanding, allowing the system to infer the presence of hidden search targets even when they are occluded in any single 2D view.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Device complexity

If only images from specific directions are acquired due to camera limitations, then device complexity is reduced, but measurement precision deteriorates for hidden objects

Engineering Contradiction:
Improvecamera configurationVSAvoidtarget detection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

By constructing a 3D model from 2D images, the system adds a depth dimension to the analysis. This enables precise determination of spatial relationships and occlusion states, improving measurement precision for detecting whether search targets are hidden behind peripheral objects without requiring additional cameras or changing the camera configuration.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The system performs preliminary construction of a 3D model before conducting the actual detection process. This pre-processing step creates a comprehensive spatial representation that enables accurate detection of hidden objects during the search, improving measurement precision without requiring real-time changes to the camera system.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If multiple images from different points are used to extract targets, then detection reliability improves, but device complexity increases

Engineering Contradiction:
Improvetarget detection reliabilityVSAvoidnumber of cameras
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent makes a single camera system perform multiple functions by using it to capture images from different positions and angles. The same camera is utilized to gather diverse spatial information that would traditionally require multiple dedicated cameras, thereby improving detection reliability without increasing the number of camera devices.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system employs dynamic image acquisition by capturing images at different positions and angles rather than relying on a fixed multi-camera setup. This dynamic approach allows a single camera to effectively perform the role of multiple static cameras, improving detection reliability while maintaining simple device configuration.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4529155B1Search assistance device, search assistance system, search assistance method, and program
Publication Date: 2026.04.22 MITSUBISHI ELECTRIC CORP
  • EP4529155B1 patent drawingFigure 1
  • EP4529155B1 patent drawingFigure 2
  • EP4529155B1 patent drawingFigure 3

AI summary

A search assistance device according to a first aspect includes: a captured video acquisition unit that acquires a captured video; an object information acquisition unit that acquires object information indicating an object included in the captured video; a setting unit that sets a search target image including a search target object; a determination unit that determines whether or not part of a search target candidate is hidden by a peripheral object using the search target image or the object information; and a video creation unit that creates a comparison video to be compared to search for the search target object using an image that shows the peripheral object in the captured video in a case where it is determined that part of the search target candidate is hidden by the peripheral object.