Lower-Limb Motion Measurement from Dummy Edge Contours
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately measure the motion of a driver's lower limbs in automobile collision tests due to skin occlusion, which hinders the assessment of injury risks and safety improvements in automobile design.
Innovation Solution
A method involving real-time capture and analysis of edge contours of the lower limbs using a deep convolutional neural network to track and calculate skeleton connection points, forming a two-dimensional dynamic model diagram for precise motion assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If skin occlusion method is used to measure lower limb motion, then the measurement process is simple, but the measurement precision deteriorates due to inability to directly measure skeleton connection points
Solution Approach 1:
The patent introduces an intermediary measurement approach by using external markers or sensors attached to the dummy's lower limb clothing, which serve as mediators to indirectly capture skeleton connection point positions. This allows measurement without direct skin contact while maintaining accuracy through the intermediary markers that track motion.
Solution Approach 2:
The patent creates a digital copy or model of the lower limb motion by capturing images and reconstructing the skeleton connection points through image processing algorithms. This virtual copy enables precise measurement of motion parameters without direct physical measurement, resolving the contradiction between measurement simplicity and accuracy.
2Reliability
If traditional collision tests are conducted to assess driver injury risks, then comprehensive safety data can be obtained, but the number of tests required increases time and resource consumption
Solution Approach 1:
The patent implements preliminary action by conducting detailed lower limb motion measurement and analysis during the collision test itself, rather than requiring separate follow-up studies. The image capture and skeleton reconstruction are performed in real-time during the test, allowing injury risk assessment to be obtained simultaneously with the collision data, thus reducing additional time requirements.
Solution Approach 2:
The patent ensures continuous useful action by capturing images at multiple time points throughout the collision process, maintaining continuous monitoring of lower limb motion. This continuous data collection enables comprehensive injury risk assessment without requiring multiple separate tests, as all necessary motion phases are captured in a single continuous measurement sequence.
Data Source
AI summary
A method for measuring motion postures of lower limbs of an automobile collision dummy continuously collects lower limb images of the automobile collision dummy during a collision in a real automobile collision test; identifies an edge contour in each lower limb image; samples a plurality of points from the edge contours for fitting to obtain a lateral thigh expression, a lower medial thigh expression, a lateral lower leg expression, and a lower medial leg expression respectively; determines various bone positions, various joint positions, and various bone angles of each lower limb; and associates the various bone positions, the various joint positions, and an included angle between two ends of each joint in the plurality of lower limb images in a chronological order to form a series of two-dimensional human rod-shaped model diagrams.