2021
2021
-
Record 145 of
Title:A real-time ultra-low light color imaging system based on FPGA
Author(s):Hua, Wang(1,2); He, Bian(2); Lei, Yang(1,2); Hui, Zhang(1,2); Zhong, CaoJian(2)Source: Journal of Physics: Conference Series Volume: 2033 Issue: 1 DOI: 10.1088/1742-6596/2033/1/012010 Published: October 5, 2021Abstract:This article shows a low light color image acquisition system, The core components of the system are the Fairchild’s SCMOS image sensor CIS1910F1111 and XILINX’s Artix-7 XC7A100T-2CSG324I FPGA, the remarkable advantage of the system is that it can obtain better color imaging effect under lower illumination environment, and the image noise is much less than other similar products. Based on the excellent imaging performance of the image detector, a high performance real-time low-light level color imaging system is developed. This imaging system can obtain the characteristic information of the targets under ultra-low illuminance environment, including the details, colors and so on. The hardware of the low light level imaging system mainly contains a color SCMOS image sensor and a FPGA, a driving circuit of a combination of DDR3, the ultra-low noise power conversion circuit and a Camera-Link and a 3G-SDI interface circuits. The SCMOS chip is used for photoelectric conversion of the shot scene and the FPGA is used for the control of the whole imaging system, image acquisition and image processing, etc, The FPGA software system consists of SCMOS initialize configuration and timing control module, automatic exposure control module, real-time color image processing module, imaging tone mapping module, image denoising module and image enhancement module. The automatic exposure control (AEC) module adaptively adjusts the average gray value of the region of interest. The module automatically calculates the exposure time and gain value of the next frame according to the current frame image data value. The real-time color image processing module includes color restoration, automatic white balance and color spaces conversion, etc. The image denoising module uses the advanced real-time guide-filter algorithm. The image tone mapping module and enhancement module are proposed based on an improved automatic threshold logarithmic and enhancement algorithm. Combining the hardware and FPGA soft algorithm with excellent performance, the imaging results show that the system can get good color image effect of the ultra-low light level about 10-2lx. ? 2021 Institute of Physics Publishing. All rights reserved.Accession Number: 20214311059011 -
Record 146 of
Title:Deep Category-Level and Regularized Hashing with Global Semantic Similarity Learning
Author(s):Chen, Yaxiong(1); Lu, Xiaoqiang(1)Source: IEEE Transactions on Cybernetics Volume: 51 Issue: 12 DOI: 10.1109/TCYB.2020.2964993 Published: December 1, 2021Abstract:The hashing technique has been extensively used in large-scale image retrieval applications due to its low storage and fast computing speed. Most existing deep hashing approaches cannot fully consider the global semantic similarity and category-level semantic information, which result in the insufficient utilization of the global semantic similarity for hash codes learning and the semantic information loss of hash codes. To tackle these issues, we propose a novel deep hashing approach with triplet labels, namely, deep category-level and regularized hashing (DCRH), to leverage the global semantic similarity of deep feature and category-level semantic information to enhance the semantic similarity of hash codes. There are four contributions in this article. First, we design a novel global semantic similarity constraint about the deep feature to make the anchor deep feature more similar to the positive deep feature than to the negative deep feature. Second, we leverage label information to enhance category-level semantics of hash codes for hash codes learning. Third, we develop a new triplet construction module to select good image triplets for effective hash functions learning. Finally, we propose a new triplet regularized loss (Reg-L) term, which can force binary-like codes to approximate binary codes and eventually minimize the information loss between binary-like codes and binary codes. Extensive experimental results in three image retrieval benchmark datasets show that the proposed DCRH approach achieves superior performance over other state-of-the-art hashing approaches. ? 2013 IEEE.Accession Number: 20220111430045 -
Record 147 of
Title:Job Recommendation System Based on Analytic Hierarchy Process and K-means Clustering
Author(s):Feng, Peini(1); Jiahao Jiang, Charles(1); Wang, Jiale(1); Yeung, Sunny(1); Li, Xijie(2)Source: ACM International Conference Proceeding Series Volume: Issue: DOI: 10.1145/3474963.3474978 Published: June 25, 2021Abstract:Many students search for summer jobs during the vacation, but there are always too many choices. We need to find a way to help people choose a best summer job. We constructed a three-tier system to comprehensively illustrate the factors that high school students need to consider when looking for a summer job from the criteria of comfort, salary, personal gain, and matching degree. Under each criterion lie several sub-criteria (which are discussed later in detail). We also investigated students' opinions toward each factor to get the judgement matrices for our AHP model. To reduce the subjectivity of the AHP model and reduce the correlation of various indexes in model construction, the AHP model and principal component analysis model were combined to construct the optimal weight model to obtain the optimal weight. And we utilized K-means clustering model to classify the work, adopted elbow method to determine the K value of the number of categories divided according to SSE (Sum of the squared errors) from the perspective of the data itself, and selected the class with the highest clustering center as the selection range of students. Finally we created ten fictional persons based on the samples we chose. The relevant questionnaires tested the students' character ability, and we used the GRNN neural network model to map the questionnaire to the weight. In this way, our model can conveniently get the weight result and calculate to help students find the optimal jobs collection by filling in the questionnaire. ? 2021 ACM.Accession Number: 20214411086118 -
Record 148 of
Title:A Novel Negative-Transfer-Resistant Fuzzy Clustering Model with a Shared Cross-Domain Transfer Latent Space and its Application to Brain CT Image Segmentation
Author(s):Jiang, Yizhang(1,2); Gu, Xiaoqing(3); Wu, Dongrui(4); Hang, Wenlong(5); Xue, Jing(6); Qiu, Shi(7); Lin, Chin-Teng(8)Source: IEEE/ACM Transactions on Computational Biology and Bioinformatics Volume: 18 Issue: 1 DOI: 10.1109/TCBB.2019.2963873 Published: January-February 2021Abstract:Traditional clustering algorithms for medical image segmentation can only achieve satisfactory clustering performance under relatively ideal conditions, in which there is adequate data from the same distribution, and the data is rarely disturbed by noise or outliers. However, a sufficient amount of medical images with representative manual labels are often not available, because medical images are frequently acquired with different scanners (or different scan protocols) or polluted by various noises. Transfer learning improves learning in the target domain by leveraging knowledge from related domains. Given some target data, the performance of transfer learning is determined by the degree of relevance between the source and target domains. To achieve positive transfer and avoid negative transfer, a negative-transfer-resistant mechanism is proposed by computing the weight of transferred knowledge. Extracting a negative-transfer-resistant fuzzy clustering model with a shared cross-domain transfer latent space (called NTR-FC-SCT) is proposed by integrating negative-transfer-resistant and maximum mean discrepancy (MMD) into the framework of fuzzy c-means clustering. Experimental results show that the proposed NTR-FC-SCT model outperformed several traditional non-transfer and related transfer clustering algorithms. ? 2004-2012 IEEE.Accession Number: 20210609904074 -
Record 149 of
Title:Efficient two-step focal length calibration of space zoom camera without targets
Author(s):Wang, Hao(1); Peng, Jianwei(1); Zeng, Hong(2); Zhang, Gaopeng(1); Wang, Feng(1); Liao, Jiawen(1)Source: Optical Engineering Volume: 60 Issue: 11 DOI: 10.1117/1.OE.60.11.114104 Published: November 1, 2021Abstract:Computer vision plays a key role in measuring the relative posture and position between spacecrafts, especially in various close-range space tasks. As one of the essential steps for computer vision, camera calibration is important for obtaining precise three-dimensional contours of a space target. The focal length of on-orbit zoom cameras constantly changes. Thus, it is practical to calibrate the focal length rather than other intrinsic camera parameters. However, traditional calibration targets, such as checkerboards, cannot be used to calibrate a space camera in orbit. To address this problem, we propose a two-step process for focal length calibration. In the first step, the initial estimate of the camera focal length was generated with vanishing points obtained from the solar panels of satellites. In the second step, the initial solution was optimized by the particle swarm optimization algorithm. The results of the simulations and laboratory experiments confirmed the accuracy, flexibility, and good antinoise interference performance of the proposed method. Thus, the proposed method has practical significance for space tasks, such as space rendezvous-docking and on-orbit maintenance. ? 2021 Society of Photo-Optical Instrumentation Engineers (SPIE).Accession Number: 20215011323793 -
Record 150 of
Title:A comparison of neural networks algorithms for EEG and sEMG features based gait phases recognition
Author(s):Wei, Pengna(1); Zhang, Jinhua(1); Tian, Feifei(2,3); Hong, Jun(1)Source: Biomedical Signal Processing and Control Volume: 68 Issue: DOI: 10.1016/j.bspc.2021.102587 Published: July 2021Abstract:Surface electromyography (sEMG) and electroencephalogram (EEG) can be utilized to discriminate gait phases. However, the classification performance of various combination methods of the features extracted from sEMG and EEG channels for seven gait phase recognition has yet to be discussed. This study investigates the effectiveness of various dimensions of feature sets with different neural network algorithms in multiclass discrimination of gait phases. There are thirty-seven feature sets (slope sign change (SSC) of eight sEMG and twenty-one EEG channels, mean absolute value (MAV) of eight sEMG channels) and three classifiers (Linear Discriminant Analysis (LDA), K-nearest neighbor (KNN), Kernel Support Vector Machine (KSVM)) were utilized. The thirty-seven one-dimensional and six two-dimensional feature sets were applied to LDA and KNN, twenty-one-dimensional and thirty-seven-dimensional feature sets were applied to three optimized KSVM for gait phase recognition. We found that thirty-seven-dimensional feature sets with grid search KSVM achieved the highest classification accuracy (98.56 ± 1.34 %) and the time consumption was 26.37 s. The average time consumption of two-dimensional feature sets with KNN was the shortest (0.33 s). The SSC of sEMG with wider values distributions than others obtained a high performance. This indicates the wider the value distribution of features, the better accuracy of gait recognition. The findings suggest that a multi-dimensional feature set composed of EEG and sEMG features with KSVM achieved good performance. Considering execution time and recognition rate, two-dimensional feature sets with KNN are suitable for online gait recognition, thirty-seven-dimensional feature sets with KSVM are more likely to be used for off-line gait analysis. ? 2021 Elsevier LtdAccession Number: 20211610220311 -
Record 151 of
Title:High-index doped silica glass planar lightwave circuits
Author(s):Chu, Sai T.(1); Little, Brent E.(2)Source: Optics InfoBase Conference Papers Volume: Issue: DOI: null Published: 2021Abstract:We provide a review of the recent progress of the high-index doped silica glass planar lightwave circuits with a focus on the emerging applications in nonlinear optics and RF photonics. ? OSA 2021.Accession Number: 20214811221866 -
Record 152 of
Title:Phase retrieval based on difference map and deep neural networks
Author(s):Li, Baopeng(1,2,3,4); Ersoy, Okan K.(4); Ma, Caiwen(1); Pan, Zhibin(2); Wen, Wansha(1,3); Song, Zongxi(1); Gao, Wei(1)Source: Journal of Modern Optics Volume: 68 Issue: 20 DOI: 10.1080/09500340.2021.1977860 Published: 2021Abstract:Phase retrieval occurs in many research areas. There are some classical phase retrieval methods such as hybrid input-output (HIO) and difference map (DM). However, phase retrieval results are sensitive to noise, and the reconstructed images always include artefacts. In this paper, we use the DM algorithm together with DNN to get better phase retrieval results. We train one deep neural network using amplitude images and phase images, respectively. First, using DM, we get initial reconstructed amplitude and phase results. Then, using DNN improves both amplitude and phase results. Finally, using the DM algorithm again improves the DNN results further. The numerical experimental results show that using DM gives better results than HIO, and using DNN improves phase information better than just using DNN to train for amplitude information alone. Compared with only using DNN improves amplitude methods, our method using DM plus DNN plus DM yields a better reconstruction performance for both amplitude and phase. ? 2021 Informa UK Limited, trading as Taylor & Francis Group.Accession Number: 20213810923757 -
Record 153 of
Title:Target classification algorithms based on multispectral imaging: A review
Author(s):Zeng, Zimu(1,2); Wang, Weifeng(1); Zhang, Wenbo(1)Source: ACM International Conference Proceeding Series Volume: Issue: DOI: 10.1145/3449388.3449393 Published: January 8, 2021Abstract:Multispectral imaging extracts rich spectral information from targets, which greatly expands the function of traditional imaging technology. Multispectral imaging is widely used in agriculture, military, medicine, industry, and meteorology. Because of the information redundancy in multispectral images, it is necessary to reduce the dimension by pre-processing. In recent years, most of the researchers have adopted the methods of pre-processing before classification. Based on the principles of feature selection, feature transformation, and feature extraction, common dimensionality reduction methods are introduced, and the advantages and disadvantages of them are discussed. Afterwards, classification methods are divided into traditional methods and deep learning methods, and their characteristics and application prospect are discussed. Through comparison, the former are cost-effective and have the mature theories, while the latter have strong adaptability and high classification accuracy. At present, methods could be optimized from the perspective of saving computing resources and using spectral information efficiently. In the future, traditional methods will be improved and comprehensively used, while new methods with stronger adaptability and precision will be developed. ? 2021 ACM.Accession Number: 20212510533305 -
Record 154 of
Title:Multiple Reliable Structured Patches for Object Tracking
Author(s):Wu, Siyuan(1); Huang, Ju(1); Feng, Yachuang(1); Sun, Bangyong(1)Source: Cognitive Computation Volume: 13 Issue: 6 DOI: 10.1007/s12559-020-09741-5 Published: November 2021Abstract:It is essential to build the effective appearance model for object tracking in computer vision. Most object trackers can be roughly divided into two categories according to the appearance model: the bounding box model and the patch model. The bounding box model cannot handle shape deformation and occlusion of the non-rigid moving object effectively. The patch model is prone to be disturbed by complex backgrounds. In this paper, we propose a robust multi-structured-patch appearance model to represent the target for object tracking. The proposed appearance model is aimed to exploit and identify reliable patches that can be tracked effectively through the whole tracking process. According to attention mechanism in biological vision system, a coarse-to-fine strategy is usually used to search the target. Therefore, the proposed appearance model is represented by robust patches in different sizes, in which the bigger patches search the rough region of the target and the smaller patches estimate the accurate location. Experimental results on OTB100 dataset show that the proposed method outperforms state-of-the-art trackers. ? 2020, Springer Science+Business Media, LLC, part of Springer Nature.Accession Number: 20203209009012 -
Record 155 of
Title:Coherent synthetic aperture imaging for visible remote sensing via reflective Fourier ptychography
Author(s):Xiang, Meng(1,2); Pan, An(1,2); Zhao, Yiyi(1); Fan, Xuewu(1); Zhao, Hui(1); Li, Chuang(1); Yao, Baoli(1)Source: Optics Letters Volume: 46 Issue: 1 DOI: 10.1364/OL.409258 Published: January 1, 2021Abstract:Synthetic aperture radar can measure the phase of a microwave with an antenna, which cannot be directly extended to visible light imaging due to phase lost. In this Letter, we report an active remote sensing with visible light via reflective Fourier ptychography, termed coherent synthetic aperture imaging (CSAI), achieving high resolution, a wide field-of-view (FOV), and phase recovery. A proof-of-concept experiment is reported with laser scanning and a collimator for the infinite object. Both smooth and rough objects are tested, and the spatial resolution increased from 15.6 to 3.48 μm with a factor of 4.5. The speckle noise can be suppressed obviously, which is important for coherent imaging. Meanwhile, the CSAI method can tackle the aberration induced from the optical system by one-step deconvolution and shows the potential to replace the adaptive optics for aberration removal of atmospheric turbulence. ? 2020 Optical Society of AmericaAccession Number: 20211310131721 -
Record 156 of
Title:Multi-scale joint network based on Retinex theory for low-light enhancement
Author(s):Song, Xijuan(1,2); Huang, Jijiang(1); Cao, Jianzhong(1); Song, Dawei(1,2)Source: Signal, Image and Video Processing Volume: 15 Issue: 6 DOI: 10.1007/s11760-021-01856-y Published: September 2021Abstract:Due to the limitations of devices, images taken in low-light environments are of low contrast and high noise without any manual intervention. Such images will affect the visual experience and hinder further visual processing tasks, such as target detection and target tracking. To alleviate this issue, we propose a multi-scale joint low-light enhancement network based on the Retinex theory. The network consists of a decomposition part and an enhancement part. As a joint network, the decomposition and enhancement parts are mutually constrained, and the parameters are updated at the same time so that the image processing results are more excellent in detail. Our algorithm avoids the separation and recombination of decomposition and enhancement. Therefore, less information is lost in the processing of low-light images, and the enhancement result of the proposed algorithm is very close to the ground truth. In addition, in the enhancement part, we adopt a multi-scale network to fully extract image features. The multi-scale network maintains a balance between the global and local luminance of the illumination image. Retinex theory can effectively solve the problem of noise amplification and color distortion. At the same time, we have added color loss to solve the problem of color distortion, so that the enhancement result is closer to the normal-light image in color. The enhancement results are intuitively excellent, and the peak signal-to-noise ratio and structural similarity index results also reflect the reliability of the algorithm. ? 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature.Accession Number: 20210609884621