Stereo Monocular Camera Object State Determination

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional video image compression technologies, such as MPEG, face challenges in accurately distinguishing and extracting shapes of static and dynamic objects from video images captured by car-mounted cameras, especially due to the movement of vehicles, which complicates object recognition and automatic vehicle operation.

Innovation Solution

A system comprising a stereo camera and a monocular camera mounted on a moving object, utilizing stereo matching principles and moving speed data to estimate object locations over time, generates correction image data for accurate determination of static and dynamic objects by comparing expected and actual object positions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If video images are captured by car-mounted cameras and compressed using MPEG technology, then video compression is achieved, but accurate distinction and extraction of static and dynamic object shapes becomes difficult

Engineering Contradiction:
Improvevideo compression efficiencyVSAvoidobject shape extraction accuracy
Core Design Contradiction:
Loss of energyVSMeasurement precision

Solution Approach 1:

The patent segments objects into static and dynamic categories by comparing their positions across multiple frames. Static objects (road, signs) remain at consistent positions while dynamic objects (other vehicles, pedestrians) change positions. This segmentation enables accurate shape extraction for both object types despite video compression

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary action by capturing multiple frames before processing and compression. By acquiring a sequence of video frames at predetermined intervals, the system establishes temporal reference points that enable subsequent distinction between static and dynamic objects, improving shape extraction accuracy

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If multiple captured images are used to distinguish static and dynamic objects, then object recognition accuracy is improved, but processing complexity increases

Engineering Contradiction:
Improveobject recognition accuracyVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential information needed for distinction - object positions in each frame - rather than processing entire images. By focusing on position coordinates and comparing them across frames, the system achieves accurate static/dynamic object distinction while reducing processing complexity

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system uses a predetermined number of video frames (excessive action) to ensure accurate distinction, but only processes partial information (position coordinates) from each frame rather than analyzing complete image data, balancing accuracy with processing efficiency

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS10937177B2Non-transitory computer readable recording medium, method, and device for determining moving state
Publication Date: 2021.03.02 FUJITSU LTD
  • US10937177B2 patent drawing
  • US10937177B2 patent drawing
  • US10937177B2 patent drawing

AI summary

A determination device generates, based on a first captured image captured by a first image capturing device mounted on a moving object, a shape of a subject (one of subjects) included in the first captured image. The determination device estimates the location of the shape of the subject after specific time based on the location of the shape of the subject and a moving speed. The determination device extracts the shape of the subject from a second captured image captured by a second image capturing device mounted on the moving object; compares the location of the shape of the subject extracted from the second captured image with the location of the shape of the subject estimated from the first captured image; and performs determination related to a moving state of the subject.