(searched for: doi:10.13176/11.512)
Computer Vision pp 367-379; https://doi.org/10.1007/978-3-030-14085-4_29
Remote Sensing, Volume 10; https://doi.org/10.3390/rs10121902
Laminated rubber bearings are widely used for the mitigation of seismic damage of large-scale structures and equipment. However, owing to the flexibility in horizontal direction, the traditional contacted transducer is difficult to acquire the displacement data accurately in the three directions, respectively. In this paper, three-dimensional displacement measurement of laminated rubber bearing based on the large-scale shaking table is achieved by the use of a tri-camera high-speed videogrammetric system consisting of three complementary-metal-oxide-semiconductor (CMOS) cameras, one synchronous controller, and one pair of 1000 watt light sources, which are used to simultaneously acquire the tri-camera image sequences of laminated rubber bearing at a speed of 300 frames per second (fps). Firstly, this paper proposes a fast image block technique for detecting and tracking targets in tri-camera image sequences by integration of techniques morphological edge detection, attribute based ellipse extraction and least-squares-based fitting adjustment. Secondly, this paper presents an integrated bundle adjustment approach, which brings continuous tracking points into one collinearity condition equation, to reconstruct the three dimensional coordinates of continuous tracking points, for the purpose of improving the accuracy of three-dimensional coordinates of tracking points based on tri-camera image sequences. At last, an empirical experiment was conducted to measure the three-dimensional displacement of laminated rubber bearings on the shaking table by the use of the proposed method. The experimental results showed that the proposed method could obtain three-dimensional displacement of laminated rubber bearings with an accuracy of more than 0.5 mm.
Biosensors, Volume 8; https://doi.org/10.3390/bios8030085
An automatic spot identification method is developed for high throughput surface plasmon resonance imaging (SPRi) analysis. As a combination of video accessing, image enhancement, image processing and parallel processing techniques, the method can identify the spots in SPRi images of the microarray from SPRi video data. In demonstrations of the method, SPRi video data of different protein microarrays were processed by the method. Results show that our method can locate spots in the microarray accurately regardless of the microarray pattern, spot-background contrast, light nonuniformity and spotting defects, but also can provide address information of the spots.
Published: 12 August 2018
Communications in Computer and Information Science pp 180-191; https://doi.org/10.1007/978-981-13-1702-6_18
The publisher has not yet granted permission to display this abstract.
Remote Sensing, Volume 9; https://doi.org/10.3390/rs9060590
Road detection plays key roles for remote sensing image analytics. Hough transform (HT) is one very typical method for road detection, especially for straight line road detection. Although many variants of Hough transform have been reported, it is still a great challenge to develop a low computational complexity and time-saving Hough transform algorithm. In this paper, we propose a generalized Hough transform (i.e., Radon transform) implementation for road detection in remote sensing images. Specifically, we present a dictionary learning method to approximate the Radon transform. The proposed approximation method treats a Radon transform as a linear transform, which then facilitates parallel implementation of the Radon transform for multiple images. To evaluate the proposed algorithm, we conduct extensive experiments on the popular RSSCN7 database for straight road detection. The experimental results demonstrate that our method is superior to the traditional algorithms in terms of accuracy and computing complexity.
Published: 1 December 2015
IET Computer Vision, Volume 9, pp 914-925; https://doi.org/10.1049/iet-cvi.2014.0347
A robust ellipse detector is proposed. The detector preprocesses the edge map by removing all the isolated points and conjunction points, and exploits polygonal curve to extract the elliptical arcs. A non-iterative geometric distance computation method is presented to serve a criterion which identifies the elliptical arcs belonging to the same ellipse by likelihood ratio test and fit ellipses to those merged arcs. The authors test their algorithm on both synthetic and real images, and the experimental results show a good performance of their algorithm.