2017
2017
-
Record 49 of
Title:PMSM servo control system design based on fuzzy PID
Author(s):Qiang, Guo(1); Junfeng, Han(2); Wei, Peng(2)Source: Proceedings - 2017 2nd International Conference on Cybernetics, Robotics and Control, CRC 2017 Volume: 2018-January Issue: DOI: 10.1109/CRC.2017.28 Published: July 2, 2017Abstract:This paper firstly introduces the cascaded controller structure of PMSM (permanent magnet synchronous motor) servo system, and then designs a fuzzy adaptive PID position controller. Then builds the simulation model of PMSM cascaded controller in MATLAB /Simulink environment, which position loop adopts fuzzy PID control. Finally, the comparison between the fuzzy PID and the traditional PID simulation results shows that the fuzzy PID is more superior than the traditional PID. ? 2017 IEEE.Accession Number: 20182205249404 -
Record 50 of
Title:A deep learning approach to real-Time recovery for compressive hyper spectral imaging
Author(s):Li, Ruimin(1,2); Zheng, Yang(1,2); Wen, Desheng(1); Song, Zongxi(1)Source: Proceedings of 2017 IEEE 3rd Information Technology and Mechatronics Engineering Conference, ITOEC 2017 Volume: 2017-January Issue: DOI: 10.1109/ITOEC.2017.8122510 Published: November 27, 2017Abstract:Compressive coded hyper spectral (HS) imaging actualizes compressed sampling and snapshot acquisition of HS data, whereas current recovery algorithms take too long time to make real-Time HS imaging satisfactory. This paper proposes a deep learning approach for compressive HS imaging to shorten the recovery time. A fully-connected network is designed to train a block-based non-linear reconstruction operator. There is a mergence after obtaining the recovery 3D blocks, followed with a block edge mean filter. The contribution of this approach is that it uses deep neural network to do the reconstruction of the HS data for the first time and it has low-complexity and needs less memory because of operating on local patches. The proposed method was validated on a public available HS dataset and the experimental results show that this approach is superior to the state-of-The-Art in the recovery accuracy, and dramatically improves the reconstruction speed by 400 ~ 760 times. ? 2017 IEEE.Accession Number: 20181104895468 -
Record 51 of
Title:Integrated generation of complex optical quantum states and their coherent control
Author(s):Roztocki, Piotr(1); Kues, Michael(1,2); Reimer, Christian(1); Romero Cortés, Luis(1); Sciara, Stefania(1,3); Wetzel, Benjamin(1,4); Zhang, Yanbing(1); Cino, Alfonso(3); Chu, Sai T.(5); Little, Brent E.(6); Moss, David J.(7); Caspani, Lucia(8,9); Aza?a, José(1); Morandotti, Roberto(1,10,11)Source: Proceedings of SPIE - The International Society for Optical Engineering Volume: 10456 Issue: DOI: 10.1117/12.2286435 Published: 2017Abstract:Complex optical quantum states based on entangled photons are essential for investigations of fundamental physics and are the heart of applications in quantum information science. Recently, integrated photonics has become a leading platform for the compact, cost-efficient, and stable generation and processing of optical quantum states. However, onchip sources are currently limited to basic two-dimensional (qubit) two-photon states, whereas scaling the state complexity requires access to states composed of several ( ? COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.Accession Number: 20180404671595 -
Record 52 of
Title:CCD imagers MTF enhanced filter design
Author(s):Jian, Zhang(1,2); Yangyu, Fan(1); Zhe, Xu(2)Source: International Conference on Communication Technology Proceedings, ICCT Volume: 2017-October Issue: DOI: 10.1109/ICCT.2017.8359924 Published: July 2, 2017Abstract:In order to improve the imaging quality of the optical imagers, the modulation transfer function enhanced CCD signal filter circuit is designed. Firstly, the imager MTF transfer chain is discussed, and the impact to MTF causing by each part of imaging chain is introduced. Secondly, from frequency domain and time domain respectively the MTF enhanced filter principle and implementation method are analyzed, the filter minimum bandwidth is confirmed. By comparing the step response of the filter and the response of the camera to the Nyquist spatial frequency fringe imaging in simulation experiment, the optimum quality factor of the MTF enhancement filter is determined. Lastly, the camera MTF test was carried out using black and white stripe target, and the SNR of the camera was measured by integrating sphere. The test results show that MTF enhanced filter can improve the system MTF 30% when the quality factor is 1, and the noise suppression capability is comparable to that of the maximally flat filter in the pass-band. MTF enhancement filter can effectively improve the imaging performance of CCD camera. ? 2017 IEEE.Accession Number: 20182305271468 -
Record 53 of
Title:Optimization on stereo correspondence based on local feature algorithm
Author(s):Li, Xiaohan(1); Zongxi, Song(1)Source: 2017 2nd International Conference on Image, Vision and Computing, ICIVC 2017 Volume: Issue: DOI: 10.1109/ICIVC.2017.7984529 Published: July 18, 2017Abstract:Stereo correspondence is one of the most important steps in binocular stereovision. It consists feature point extraction and image matching. In order to solve the problems of bad anti-noise performance and low accuracy of image matching in Scale Invariant Feature Transform (SIFT) algorithm, an optimized matching method based on local feature algorithm with Speeded-up Robust Feature (SURF) is proposed in this paper. In terms of feature extraction, SURF feature descriptor has a good anti-noise performance, which is extended from 64 dimensions to 128 dimensions makes the descriptor more specific, and the matching method is improved. The average value of the feature distance is used to replace the second neatest distance of the original matching algorithm, and Random Sample Consensus (RANSAC) algorithm is used to eliminate the wrong matching pairs. Test results indicate that the change of SURF feature points numbers in Gaussian noise is no more than positive or negative 15%, while the change of SIFT is more than 50%. In addition, the matching accuracy of the proposed method is increased by 20.5% compared to the original method of the shortest Euclidean distance between two feature vectors. Based on such result analysis, SURF algorithm with optimization matching method makes the matching accuracy more effective and has a practical value. ? 2017 IEEE.Accession Number: 20173804169386 -
Record 54 of
Title:Bird species recognition based on SVM classifier and decision tree
Author(s):Qiao, Baowen(1,2); Zhou, Zuofeng(2); Yang, Hongtao(2); Cao, Jianzhong(2)Source: 1st International Conference on Electronics Instrumentation and Information Systems, EIIS 2017 Volume: 2018-January Issue: DOI: 10.1109/EIIS.2017.8298548 Published: July 2, 2017Abstract:Bird species recognition is a challenging problem due to the variant illumination and different view point of camera. In this paper, a new feature which is the ratio between the distance of the eye to the root of beak and the distance of the width of the beak is used to distinguish the different bird species. Integrated the new feature into the multi-scale decision tree and the SVM framework, a new bird species recognition algorithm is proposed to get the final recognition result. The Experiment results show that the proposed new feature can improve the correct classification rate about nine percent. ? 2017 IEEE.Accession Number: 20182605362750 -
Record 55 of
Title:Hierarchical recurrent neural network for video summarization
Author(s):Zhao, Bin(1); Li, Xuelong(2); Lu, Xiaoqiang(2)Source: MM 2017 - Proceedings of the 2017 ACM Multimedia Conference Volume: Issue: DOI: 10.1145/3123266.3123328 Published: October 23, 2017Abstract:Exploiting the temporal dependency among video frames or subshots is very important for the task of video summarization. Practically, RNN is good at temporal dependency modeling, and has achieved overwhelming performance in many video-based tasks, such as video captioning and classification. However, RNN is not capable enough to handle the video summarization task, since traditional RNNs, including LSTM, can only deal with short videos, while the videos in the summarization task are usually in longer duration. To address this problem, we propose a hierarchical recurrent neural network for video summarization, called H-RNN in this paper. Specifically, it has two layers, where the first layer is utilized to encode short video subshots cut from the original video, and the final hidden state of each subshot is input to the second layer for calculating its confidence to be a key subshot. Compared to traditional RNNs, H-RNN is more suitable to video summarization, since it can exploit long temporal dependency among frames, meanwhile, the computation operations are significantly lessened. The results on two popular datasets, including the Combined dataset and VTW dataset, have demonstrated that the proposed H-RNN outperforms the state-of-the-arts. ? 2017 ACM.Accession Number: 20174804481824 -
Record 56 of
Title:A multi-task framework for weather recognition
Author(s):Li, Xuelong(1); Wang, Zhigang(2); Lu, Xiaoqiang(1)Source: MM 2017 - Proceedings of the 2017 ACM Multimedia Conference Volume: Issue: DOI: 10.1145/3123266.3123382 Published: October 23, 2017Abstract:Weather recognition is important in practice, while this task has not been thoroughly explored so far. The current trend of dealing with this task is treating it as a single classification problem, i.e., determining whether a given image belongs to a certain weather category or not. However, weather recognition differs significantly from traditional image classification, since several weather features may appear simultaneously. In this case, a simple classification result is insufficient to describe the weather condition. To address this issue, we propose to provide auxiliary weather related information for comprehensive weather description. Specifically, semantic segmentation of weather-cues, such as blue sky and white clouds, is exploited as an auxiliary task in this paper. Moreover, a convolutional neural network (CNN) based multi-task framework is developed which aims to concurrently tackle weather category classification task and weather-cues segmentation task. Due to the intrinsic relationships between these two tasks, exploring auxiliary semantic segmentation of weather-cues can also help to learn discriminative features for the classification task, and thus obtain superior accuracy. To verify the effectiveness of the proposed approach, extra segmentation masks of weather-cues are generated manually on an existing weather image dataset. Experimental results have demonstrated the superior performance of our approach. The enhanced dataset, source codes and pre-trained models are available at https://github.com/wzgwzg/Multitask-Weather. ? 2017 ACM.Accession Number: 20174804481697 -
Record 57 of
Title:The influence of temperature and pressure on primary mirror surface figure and image quality of the 1.2m colorful schlieren system
Author(s):Xu, Songbo(1); Wang, Peng(1); Chen, Lei(2); Wang, Jing(1); Xie, Yong-Jun(1)Source: Proceedings of SPIE - The International Society for Optical Engineering Volume: 10256 Issue: DOI: 10.1117/12.2247935 Published: 2017Abstract:In this paper, a colorful schlieren system without any protecting windows was introduced which results in that the 1.2m primary mirror would directly be confronted with the pressure and temperature variation from the wind tunnel test. To achieve a good schlieren image under the wind tunnel test working condition of a wide temperature fluctuation range (-10°C to 50°C) as well as a pressure (2kPa), a new flexible support method of the primary mirror was strategically designed. A finite element model of the primary mirror combined with its supporting structures was built up to approach the surface figure of the primary mirror under the complex working conditions as gravity, temperature variation, and pressure. The schlieren images due to the change of the primary mirror surface figure were simulated by Light-tools software. It was found that the temperature changing and pressure would lead to the variation of the surface figure of the primary mirror surface figure and therefore, results in the changing of the quality of simulated schlieren images. ? 2017 SPIE.Accession Number: 20171703607490 -
Record 58 of
Title:A novel ACM for segmentation of medical image with intensity inhomogeneity
Author(s):Niu, Yuefeng(1,2); Cao, Jianzhong(1); Liu, Liqiang(1,2); Guo, Huinan(1)Source: 2017 2nd IEEE International Conference on Computational Intelligence and Applications, ICCIA 2017 Volume: 2017-January Issue: DOI: 10.1109/CIAPP.2017.8167228 Published: December 4, 2017Abstract:This paper presents a scheme of improvement on the Li's model in terms of intensity inhomogeneous images. By introducing local entropy to Li's model, our method is able to segment medical images with intensity inhomogeneity and estimate the bias field simultaneously. The level set energy function is redefined as a weighted energy integral, where the weight is local entropy deriving from a grey level distribution of image. The total energy functional is then incorporated into a level set formulation. Experimental results on test images show that our approach outperforms the existing locally statistical active contour model (LSACM) and Li's model in terms of accuracy and efficiency with less central processing unit (CPU) time. ? 2017 IEEE.Accession Number: 20181104902438 -
Record 59 of
Title:Noise reduction and analysis for Chang'E-1 Imaging Interferometer (IIM) data
Author(s):Zhu, Feng(1); Liu, Jiahang(1); Chen, Tieqiao(1)Source: Proceedings of 2017 International Conference on Progress in Informatics and Computing, PIC 2017 Volume: Issue: DOI: 10.1109/PIC.2017.8359532 Published: 2017Abstract:Imaging Interferometer (IIM) aboard Chang'E-1 is a Fourier transform imaging spectrometer, with goals to analyze the abundance and distribution of chemical elements on the lunar surface. IIM data suffer from various degradations, which will lead to misleading interpretations of IIM data and inaccuracy of subsequent applications. In this paper, we introduced a noise reduction method based on low-rank matrix decomposition theory. The restoration results are expected to have a better performance in image quality and spectral signatures according to visual and quantitative assessments. Meanwhile, we analyze the characteristic of the noise separated from IIM data using top spectral view of noise cube. The preliminary analysis of the noise characteristics contribute to optimize the data preprocessing of IIM data such as spectrum reconstruction and radiometric correction. ? 2017 IEEE.Accession Number: 20182405301283 -
Record 60 of
Title:Ground-based optical detection of low-dynamic vehicles in near-space
Author(s):Jing, Nan(1,2); Li, Chuang(1); Zhong, Peifeng(1,2)Source: Optical Engineering Volume: 56 Issue: 1 DOI: 10.1117/1.OE.56.1.014107 Published: January 1, 2017Abstract:Ground-based optical detection of low-dynamic vehicles in near-space is analyzed to detect, identify, and track high-altitude balloons and airships. The spectral irradiance of a representative vehicle on the entrance pupil plane of ground-based optoelectronic equipment was obtained by analyzing the influence of its geometry, surface material characteristics, infrared self-radiation, and the reflected background radiation. Spectral radiation characteristics of the target in both clear weather and complex meteorological weather were simulated. The simulation results show the potential feasibility of using visible-near-infrared (VNIR) equipment to detect objects in clear weather and long-wave infrared (LWIR) equipment to detect objects in complex meteorological weather. A ground-based VNIR and LWIR optoelectronic experimental setup is built to detect low-dynamic vehicles in different weather. A series of experiments in different weather are carried out. The experiment results validate the correctness of the simulation results. ? 2017 Society of Photo-Optical Instrumentation Engineers (SPIE).Accession Number: 20170803379718