QQ客服 官方微博 反馈留言

浏览/检索结果: 共4条，第1-4条 帮助 限定条件 内容类型：会议论文    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 Using bidirectional binary particle swarm optimization for feature selection in feature-level fusion recognition system (EI CONFERENCE) 会议论文 2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009, May 25, 2009 - May 27, 2009, Xi'an, China Wang D.; Ge W.; Wang Y. 收藏  |  浏览/下载：16/0  |  提交时间：2013/03/25 In feature-level fusion recognition system  the other is optimizing system sensor design to get outstanding cost performance. So feature selection become usually necessary to reduce dimensionality of the combination of multi-sensor features and improve system performance in system design. In general  there are two main missions. One is improving the recognition correct rate as soon as possible  the optimization is usually applied to feature selection because of its computational feasibility and validity. For further improving recognition accuracy and reducing selected feature dimensions  this paper presents a more rational and accurate optimization  Bidirectional Binary Particle Swarm Optimization (BBPSO) algorithm for feature selection in feature-level fusion target recognition system. In addition  we introduce a new evaluating function as criterion function in BBPSO feature selection method. At the last  we utilized Leave-One-Out method to validate the proposed method. The experiment results show that the proposed algorithm improves classification accuracy by two percentage points  while the selected feature dimensions are less one dimension than original Particle Swarm Optimization approach with 16 original feature dimensions. 2009 IEEE.   Using Bidirectional Binary Particle Swarm Optimization for Feature Selection in Feature-level Fusion Recognition System 会议论文 2009 Wang D. W.; Ge W.; Wang Y. J.; Ieee 收藏  |  浏览/下载：11/0  |  提交时间：2013/03/28 Application of multi-sensors parallel fusion system in photoelectric tracing (EI CONFERENCE) 会议论文 2008 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Applications, November 16, 2008 - November 19, 2008, Beijing, China Cheng G.-Y.; Cai S.; Gao H.-B.; Zhang S.-M.; Qiao Y.-F. 收藏  |  浏览/下载：15/0  |  提交时间：2013/03/25 To solve the real-time and reliability problem of tracking servo-control system in optoelectronic theodolite  a multisensors parallel processing system was proposed. Misdistances of three different wavebands were imported into system  and then prediction was done in DSP1 to get the actual position information. Data fusion was accomplished in PPGA imported by multi channel buffer serial port. The compound position information was used to control the theodolite. The results were compared with external guide data in DSP2 to implement correction of above calculation  and then were imported to epistemic machine through PXI interface. The simulation experiment of each calculation unit showed that this system could solve the real-time problem of feature level data fusion. The simulation result showed that the system can satisfy the real-time requirement with 1.25ms in theodolite with three imaging systems  while sampling frequency of photoelectric encoder was 800 Hz. 2009 SPIE.   Multiwavelet based multispectral image fusion for corona detection (EI CONFERENCE) 会议论文 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China Wang X.; Yan F.; Sui Y.-X.; Yang H.-J.; Pang Y.-J. 收藏  |  浏览/下载：14/0  |  提交时间：2013/03/25 Image fusion refers to the integration of complementary information provided by various sensors such that the new images are more useful for human or machine perception. Multiwavelet transform has simultaneous orthogonality  symmetry  compact support  and vanishing moment  which are not possible with scalar wavelet transform. Multiwavelet analysis can offer more precise image analysis than wavelet multiresolution analysis. In this paper  a new image fusion algorithm based on discrete multiwavelet transform (DMWT) to fuse the dual-spectral images generated from the corona detection system is presented. The dual-spectrum detection system is used to detect the corona and indicate its exact location. The system combines a solar-blind UV ICCD with a visible camera  where the UV image is useful for detecting UV emission from corona and the visible image shows the position of the corona. The developed fusion algorithm is proposed considering the feature of the UV and visible images adequately. The source images are performed at the pixel level. First  a decomposition step is taken with the DMWT. After the decomposition step  a pyramid for each source image in each level can be obtained. Then  an optimized coefficient fusion rule consisting of activity level measurement  coefficient combining and consistency verification is used to acquire the fused coefficients. This process reduces the impulse noise of UV image. Finally  a new fused image is obtained by reconstructing the fused coefficients using inverse DMWT. This image fusion algorithm has been applied to process the multispectral UV/visible images. Experimental results show that the proposed method outperforms the discrete wavelet transform based approach.