Driver-Gaze Camera Switching for Occlusion-Free Rearview Monitoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Camera monitor systems (CMS) face issues where subjects captured by multiple cameras with different viewpoints may disappear in composite images due to occlusion, leading to incomplete rearview monitoring, potentially causing accidents as drivers overlook critical objects behind larger vehicles.

Innovation Solution

An image processing apparatus that switches and displays images captured by multiple cameras based on driver behavior, such as head movements, to ensure continuous and seamless observation of the rearview, using a data processing unit to input driver information and switch between individual camera images or virtual composite images accordingly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a composite image is generated from multiple camera images with different viewpoints, then a unified rearview display is achieved, but subjects may disappear due to occlusion from the single viewpoint

Engineering Contradiction:
Improverearview monitoring completenessVSAvoidsubject visibility
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The system dynamically switches between multiple camera viewpoints based on detected driver head movement direction. When the driver looks left, the left camera image is displayed; when looking right, the right camera image is displayed. This dynamic adaptation ensures subjects remain visible by selecting the appropriate viewpoint, resolving the contradiction between unified display and subject visibility.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The rearview monitoring system is segmented into multiple independent camera viewpoints (left camera, right camera, rear camera) rather than relying on a single composite image. Each camera captures subjects from its specific viewpoint, and the system selectively displays the appropriate segment based on driver behavior, preventing occlusion-related subject disappearance.

Inventive Principle:
Principle #1Segmentation

2Loss of information

If multiple camera images are sequentially switched based on driver behavior, then subject visibility is improved, but display continuity may be affected

Engineering Contradiction:
Improvesubject visibilityVSAvoiddisplay continuity
Core Design Contradiction:
Loss of informationVSStability of the object's composition

Solution Approach 1:

The system employs periodic action by switching between different camera images at regular intervals or in response to periodic driver head movements. The display alternates between left, right, and rear camera images based on detected head movement patterns, maintaining subject visibility while creating a rhythmic display pattern that adapts to natural driver behavior.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system maintains continuity of useful action by continuously monitoring driver head movement and immediately switching to the appropriate camera image to keep subjects visible. The transition between different camera viewpoints is seamless and continuous, ensuring that the rearview monitoring function remains effective without interruption or loss of subject visibility.

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentEP3793191B1Image processing device, moving machine, and method, and program
Publication Date: 2024.09.04 SONY SEMICON SOLUTIONS CORP
  • EP3793191B1 patent drawingFigure 1
  • EP3793191B1 patent drawingFigure 2
  • EP3793191B1 patent drawingFigure 3

AI summary

Configuration, in which images output to a display unit are switched and displayed in accordance with the behavior of a driver, such as movements of the head of the driver, is achieved. Driver information indicating the behavior of the driver of a moving apparatus and images captured by a plurality of cameras that images a situation around the moving apparatus from different viewpoints are input. The images output to the display unit are switched in accordance with the driver information. The plurality of cameras is, for example, a plurality of rear cameras installed in the rear of the moving apparatus. For example, a direction of the face or line-of-sight of the driver is detected. An image in a direction corresponding to the detected direction of the face or line-of-sight of the driver is selected as an output image, and displayed on the display unit. Alternatively, an image in a direction indicated by a gesture of the driver is selected, and displayed on the display unit.