QQ客服 官方微博 反馈留言

浏览/检索结果: 共5条，第1-5条 帮助 限定条件 专题：长春光学精密机械与物理研究所    第一署名单位    第一作者单位    通讯作者单位     已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 Ship Detection in Optical Satellite Images Using Haar-like Features and Periphery-Cropped Neural Networks 期刊论文 Ieee Access, 2018, 卷号: 6, 页码: 71122-71131 作者:  Yu, Y.;  Ai, H.;  He, X. J.;  Yu, S. H.;  Zhong, X. 收藏  |  浏览/下载：2/0  |  提交时间：2019/09/17 Object detection  feature extraction  CNN  AdaBoost classifier  object detection  tracks  shape  Computer Science  Engineering  Telecommunications   Efficient human action recognition using accumulated motion image and support vector machines (EI CONFERENCE) 会议论文 International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2011, November 19, 2011 - November 23, 2011, Suzhou, China Cao W.; Zhang X.; Cao S.; Zhang J.; Wang M.; Han G. 收藏  |  浏览/下载：66/0  |  提交时间：2013/03/25 Vision-based human action recognition provides an advanced interface  and research in this field of human action recognition has been actively carried out. This paper describes a scheme for recognizing human actions from a video sequences. The proposed method is an extension of the Motion History Image(MHI) method based on the ordinal measure of accumulated motion  which is robust to variations of appearances. We define the accumulated motion image(AMI) using image differences firstly. Then the AMI of the video sequencesis resized to a MN regulation following the standard of training phases. Finally  we employ Support Vector Machine(SVM) as a classifier to distinguish the current activity in target video sequences. In a word  our proposed algorithm not only outperforms the state of art on public available KTH data set and Weizmann data set  but also proves practical to some real world applications  in addition  this method is computationally simple and able to achieve a satisfactory accuracy.   Design for target classifier based on semi-supervised learning (EI CONFERENCE) 会议论文 2011 International Conference on Electric Information and Control Engineering, ICEICE 2011, April 15, 2011 - April 17, 2011, Wuhan, China Jiangrui K. 收藏  |  浏览/下载：18/0  |  提交时间：2013/03/25 The target classifier is an ingredient of the target recognition system. In order to achieve the automation and computerization of target recognition  a method for training target classifier based on semi-supervised learning is provided. It adopts CFS algorithm for dada feature selection  and uses semi-supervised learning algorithm  Co-training to construct the target classifiers. The final classifier was produced through integration learning method. Experimental results show that the performance of the target classifier based on semi-supervised learning trained is superior to the traditional target classifier. 2011 IEEE.   A new method of target recognition based on rough set and support vector machine (EI CONFERENCE) 会议论文 2nd International Conference on Image Analysis and Signal Processing, IASP'2010, April 12, 2010 - April 14, 2010, Xiamen, China Guo Z.-J.; He X.; Wei Z.-H.; Liang G.-L. 收藏  |  浏览/下载：12/0  |  提交时间：2013/03/25 Automatic target recognition (ATR) is an important task in image application. This paper concentrates on two key subroutines of ATR system: Pre-treatment and design of classifier. In the pre-treatment subroutine  a new method based on Rough Set (RS) is proposed to partition the original sample set into some subsets and calculate their class membership  so that some samples can be chosen by class membership to be trained. After pre-treatment  an iterative algorithm based on Rough Set and Support Vector Machines (IRSSVM) is introduced to design a classifier for recognizing two types of targets. The experiment results show that IRSSVM needs less training time and the classifier is simpler and has more generalization and higher recognition rate. 2010 IEEE.   A method of aircraft image target recognition based on modified PCA features and SVM (EI CONFERENCE) 会议论文 9th International Conference on Electronic Measurement and Instruments, ICEMI 2009, August 16, 2009 - August 19, 2009, Beijing, China Donghe W.; Xin H.; Wei Z.; Huilong Y. 收藏  |  浏览/下载：21/0  |  提交时间：2013/03/25 Automatic target recognition(ATR) is an important task in image application. This paper concentrates on two key subroutines of ATR system: Dimensionality reduction and Classifier. After pretreatment on original features a self-organizing neural network trained with the Hebbian rule is used to extract the principal component features. Then a classifier based on Directed Acyclic Graph Support Vector Machines(DAGSVM) is adopted to recognize more than two types of aircraft targets. The experiment results show the proposed method achieves better subset features and higher recognition rate. 2009 IEEE.