R
Rong Qu
Researcher at University of Nottingham
Publications - 294
Citations - 8834
Rong Qu is an academic researcher from University of Nottingham. The author has contributed to research in topics: Contextual image classification & Heuristics. The author has an hindex of 43, co-authored 282 publications receiving 7277 citations. Previous affiliations of Rong Qu include Queen's University Belfast & Information Technology University.
Papers
More filters
Patent
Polarized SAR classification method based on clustering refinement residual error model
Jiao Licheng,Li Lingling,Zhang Hui,Tang Xu,Guo Yuwei,Ding Jingyi,Zhang Mengxuan,Gu Jing,Chen Puhua,Yang Shuyuan,Hou Biao,Rong Qu +11 more
TL;DR: In this paper, a polarized SAR classification method based on a clustering refinement residual error model is proposed, which comprises the following steps of (1) constructing the clustering refining residual error (CRE) model, (2) preprocessing the polarized SAR image to be classified, (3) generating a training data set and a test data set, (4) carrying out information fusion processing on the deep and shallow layer of a network, (5) reclassified the small graph spot of an initial classification graph, and (6) classifying test data and acquiring a test
Patent
High-resolution SAR image change detection method based on global-local SPP Net
Jiao Licheng,Rong Qu,Yang Zhengyan,Ma Jingjing,Yang Shuyuan,Hou Biao,Ma Wenping,Liu Fang,Shang Ronghua,Zhang Xiangrong,Zhang Dan,Tang Xu +11 more
TL;DR: In this paper, a high-resolution SAR image change detection method based on a global-local SPP Net was proposed, which comprises the following steps of selecting partial label data from two registered SAR images with the different phases in the same region as a training sample; normalizing the training sample within [0, 1] and marking as X1; selecting m groups of image blocks with the larger scale from the X1 and putting the image blocks into a local large-scale SPP net to carry out area-of-interest detection training in order to obtain a trained area
Patent
SAR image classification method based on curvelet depth ladder network model
Jiao Licheng,Rong Qu,Li Xi,Zhang Dan,Yang Shuyuan,Hou Biao,Ma Wenping,Liu Fang,Tang Xu,Ma Jingjing,Gu Jing,Chen Puhua +11 more
TL;DR: In this paper, a curvelet depth ladder network model is employed to perform feature extraction of samples and fully utilizes multi-scale and multi-direction features of the samples, and therefore the sample dimension is reduced, robustness of feature extraction is improved, and training and classification speed of the network is improved.
Book ChapterDOI
Examination Timetabling Problems
Nelishia Pillay,Rong Qu +1 more
TL;DR: Examination timetabling represents one of the earliest and most studied problem domains in hyper-heuristics (HH) and progress has been made on designing simple and effective approaches across different benchmarks as well as real-world problems.
Patent
Three-dimensional point cloud classification method based on nested neural network and grid map
Jiao Licheng,Guo Yuwei,Lian Yanchao,Feng Tuo,Jinliu Zhou,Rong Qu,Ding Jingyi,Zhang Dan,Tang Xu,Li Lingling,Feng Zhixi +10 more
TL;DR: In this article, a 3D point cloud classification method based on a nested convolutional neural network and a grid map is proposed, and the point cloud which is wrongly classified is modified by combining the grid map method, so that the classification precision of satellite remote sensing three-dimensional point cloud data is greatly improved.