In-Vehicle Hand Detection via Inter-Frame Luminance Difference

Solution Overview

Problem

In-vehicle gesture recognition systems face erroneous hand detection due to objects other than the user's hand appearing in the hand detection region between the driver's and passenger seats, leading to inaccurate gesture recognition and potential device malfunction.

Innovation Solution

A hand detection device that captures images of the hand detection region, calculates inter-frame luminance differences, and determines whether detected hands are erroneous based on these differences, ensuring accurate hand detection by distinguishing between user inputs and background objects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the hand detection region is set to the area between the driver's seat and the passenger seat, then the detection area covers the main user's hand, but objects other than the hand (passengers in backseat, luggage) may appear and be erroneously detected

Engineering Contradiction:

Improvehand detection accuracyVSAvoiderroneous detection of non-hand objects

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary action by calculating the luminance difference between the current frame and the preceding frame before hand detection. This preliminary luminance difference calculation allows the system to predict whether a detected hand is likely to be a real hand or a false detection of background objects, enabling premature filtering of erroneous detections.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback by comparing the luminance difference between consecutive frames to validate hand detections. The erroneous detection determination unit receives the hand detection result and the luminance difference information, then provides feedback to filter out false detections while maintaining accurate hand detection results.

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If the hand detection region is expanded to capture more area, then more user gestures can be detected, but the probability of detecting background objects as hands increases

Engineering Contradiction:

Improvedetection coverageVSAvoiddetection reliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary action by calculating the luminance difference between the current frame and the preceding frame before hand detection. This preliminary luminance difference calculation allows the system to predict whether a detected hand is likely to be a real hand or a false detection of background objects, enabling premature filtering of erroneous detections.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback by comparing the luminance difference between consecutive frames to validate hand detections. The erroneous detection determination unit receives the hand detection result and the luminance difference information, then provides feedback to filter out false detections while maintaining accurate hand detection results.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20230401898A1Hand detection device, gesture recognition device, and hand detection method

Publication Date: 2023.12.14 MITSUBISHI ELECTRIC CORP

AI summary

In the hand detection device, an image acquisition unit acquires an image for hand detection, which is an image obtained by capturing a hand detection region in a vehicle. A luminance difference calculation unit calculates an inter-frame luminance difference of the image for hand detection. A hand detection unit detects a hand of a user from the image for hand detection. An erroneous detection determination unit determines whether or not the detected hand has been erroneously detected on the basis of the luminance difference between the frame in which the hand has been detected and the frame immediately preceding thereof in the hand detection area.