Proceedings ArticleDOI
TOF Camera Array for Package Volume Measurement
TLDR
In this paper, a vision system with a 4 by 2 time-of-flight (TOF) camera array was proposed to measure package volume automatically, and a splicing algorithm was developed so that low resolution TOF sensors can be used without sacrificing measurement accuracy.Abstract:
Package volume is critical for logistics companies to manage transportation cost. A vision system with a 4 by 2 time of flight (TOF) camera array was proposed to measure package volume automatically. Timing control was implemented to avoid interference between different TOF sensors. A splicing algorithm was developed so that low resolution TOF sensors can be used without sacrificing measurement accuracy. The vision system is able to cover 1.6 m by 3.7 m area and to process a video stream with a frame rate greater than 22 fps. The point cloud spacing ranges between 4.1 mm and 5.8 mm. The average measurement error in volume is less than 4.7%.read more
Citations
More filters
Proceedings ArticleDOI
A Real-time Object Volume Measurement Method Based on Line Laser Scanning
TL;DR: In this paper , a real-time object volume measurement system based on line laser scanning is proposed, where the volume of the object is calculated in the process of obtaining the ordered point cloud in a point-by-point, line-byline integration way.
References
More filters
Journal ArticleDOI
Double three-step phase-shifting algorithm.
TL;DR: In this article, a double three-step phase shifting algorithm was proposed to reduce the measurement error of a 3D shape-measurement system, which is based on digital fringe projection and phase shifting techniques.
Journal ArticleDOI
Phase error compensation for three-dimensional shape measurement with projector defocusing
TL;DR: This research experimentally studied a large depth range of defocused fringe patterns, from near-binary to near-sinusoidal, and analyzed the associated phase errors and established a mathematical phase error function in terms of the wrapped phase and the depth z.
Proceedings ArticleDOI
Linear stereo matching
TL;DR: A novel cost aggregation step with complexity independent of the window size that outperforms state-of-the-art O(1) methods and does not rely on integral histograms enabling aggregation using colour images instead of grayscale ones is proposed.
Journal ArticleDOI
Real-time high-quality stereo vision system in FPGA
TL;DR: This is the first complete real-time hardware system that supports both cost aggregation on cross-based regions and semi-global optimization on FPGA, and can adjust image resolution, parallelism degree, and support region size to achieve maximum efficiency flexibly during the implementation.
Proceedings ArticleDOI
Depth from Defocus in the Wild
TL;DR: This work considers the problem of two-frame depth from defocus in conditions unsuitable for existing methods yet typical of everyday photography: a handheld cellphone camera, a small aperture, a non-stationary scene and sparse surface texture, and combines a global analysis of image content with local estimation of joint depth-flow likelihoods in tiny patches.