Structural analysis of a 3D scene from 2D image pixel positions is an important and unresolved issue in image processing and patternrecognition. Current algorithms for 3D structural analysis do not explicitly use geo...
详细信息
Structural analysis of a 3D scene from 2D image pixel positions is an important and unresolved issue in image processing and patternrecognition. Current algorithms for 3D structural analysis do not explicitly use geometrical properties of distance between feature points and angle information as constraints to calibrate transformation parameters. We propose a novel two-stage approach to analyse the structure of a 3D scene based on the explicit expressions of distance and angle measurement. In the first stage, we transform the 3D-2D problem into a linear problem and propose a robust algorithm based on the total least squares method to estimate the rotation matrix and translation vector. In the second stage, we propose a coarse-to-fine geometric algorithm to refine the estimation. The proposed two-stage approach provides the closed form solutions to structural parameters through the analysis of image correspondence vectors synthesised into a single coordinate frame. For a comparative study of performance, we also extended a well known 2D-2D epipolar geometry algorithm proposed by R.Y. Tsai and T.S. Huang (1984) to solve 3D-2D problems. Experimental results show that the proposed approach and geometric algorithms are in general more accurate, stable, and efficient than the extended Tsai and Xuang algorithm.
The research described is concerned with establishing innovative methods for quality control for manually intensive production lines. Our industrial partner is a European leader in the manufacturing of caravans. A sys...
The research described is concerned with establishing innovative methods for quality control for manually intensive production lines. Our industrial partner is a European leader in the manufacturing of caravans. A systematic approach to tackling manufacturing defects requires information about the frequency and cause of defects as well as the cost of ignoring, repairing and eliminating them. Unfortunately, this information is very difficult to acquire for the type of production line we are tackling. In the absence of the information necessary to plan a conventional quality improvement strategy, we are using computer simulation in the attempt to understand how changes to designs and manufacturing practices will affect quality.
Presents a method with preliminary results on collecting and analysing dynamic data describing some foot motions in 3D space. The overall aim of the research is to represent and compare such data for normal and club-f...
详细信息
Presents a method with preliminary results on collecting and analysing dynamic data describing some foot motions in 3D space. The overall aim of the research is to represent and compare such data for normal and club-foot patients and to investigate ways in which motion pattern data can effectively be analysed by a computer-based system. The method comprises three steps: first, sensor readings from an electromagnetic device are filtered, interpolated and transformed; second, motion parameters described as roll, pitch and yaw are evaluated from sensor data and projected on to 2D space from selected viewpoints; third, a convex hull analysis based on shape geometry is developed and performed on the projected parameters. Finally, a discussion on the suitability of the method for motion pattern analysis of the foot is presented.
暂无评论