- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2018
- metal object detection (MOD)
- wireless power transfer (WPT)
- auxiliary detection coil
- Chest X-ray (CXR)
- Computer-aided Diagnosis (CADx)
- Early detection of tuberculosis
- Electrical Engineering and Automation
- Optoelectronic Information Science and Engineering
- Shanghai Jiao Tong University
- Bandung Institute of Technology (ITB)
-
[IEEE 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP) - Shenzhen, China (2018.7.13-2018.7.15)] 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP) - Spacecraft Detection Based on Deep Convolutional Neural Network
摘要： Spacecraft detection is one of essential issues on aerospace information processing and control, and can provide reliable dynamic state of target, so as to support decisions made on target recognition, classification, catalogue, et al. Although numerous spacecraft detection methods exist, most of them cannot achieve real-time detection, and are still lack of better accuracy and fault-tolerance for different scenes. Recently, deep learning algorithms have achieved fantastic detection performance in computer vision community, especially the regression-based convolutional neural network YOLOv2, which has good accuracy and speed, and outperforming other state-of-the-art detection methods. This paper for the first time applies CNN to the detection of spacecraft and sets up a dataset for target detection in space. Our method starts with image annotation and data augmentation, and then uses our improved regression-based convolutional neural network YOLOv2 to detect spacecraft in an image. The experimental results have shown that our algorithm achieves 97.8% detection rate in the test set, and the average detection time of each image is about 0.018s, which has lower time overhead and better robustness to rotation and illumination changes of spacecraft.
关键词： Spacecraft,CNN,Target detection,YOLOv2
更新于2025-09-23 15:23:52
-
Constellation-Optimal Beamformers For Multiuser MISO Broadcast Visible Light Communications
摘要： In this paper, we design energy-efficient space constellations for multiuser multi-input single-output (MISO) visible light communication broadcast systems with channel state information (CSI) at the receiver in the three scenarios: 1) with CSI at the transmitter (CSIT), 2) with statistical CSIT and 3) without CSIT. By utilizing the cooperation of multiuser interference, optimal multidimensional additively uniquely decomposable constellation groups are designed to optimize the received worst-case performance metrics of all users subject to two commonly used power constraints, i.e., average and peak optical power constraints. The resulting optimal designs are proved to be pulse amplitude modulation with an optimal beamformer, which can be efficiently attained by numerical search for Scenarios 1 and 2 and be given in a closed-form for Scenario 3. One of the common significant advantages of these designs is fast demodulation of the sum signal from a noisy received signal, since these optimal designs result in an equivalent ideal scalar AWGN channel. Comprehensive computer simulations demonstrate that our designs significantly outperform traditional zero-forcing, minimum mean square error and time-division methods.
关键词： Additively uniquely decomposable constellation group,multi-input single-output,maximum likelihood detection,optimal multidimensional constellation,visible light communications,broadcast channels
更新于2025-09-23 15:23:52
-
Regenerable Bead-Based Microfluidic Device with integrated THIN-Film Photodiodes for Real Time Monitoring of DNA Detection
摘要： Nanoporous microbead-based microfluidic systems for biosensing applications allow enhanced sensitivities, while being low cost and amenable for miniaturization. The regeneration of the microfluidic biosensing system results in a further decrease in costs while the integration of on-chip signal transduction enhances portability. Here, we present a regenerable bead-based microfluidic device, with integrated thin-film photodiodes, for real-time monitoring of molecular recognition between a target DNA and complementary DNA (cDNA). High-sensitivity assay cycles could be performed without significant loss of probe DNA density and activity, demonstrating the potential for reusability, portability and reproducibility of the system.
关键词： microfluidics,regenerable biosensor,DNA detection,a-Si:H photodiodes,fluorescence
更新于2025-09-23 15:23:52
-
Detection probability for moving ground target of normal distribution using infrared satellite
摘要： In this article, we discuss the detection probability for a moving ground target such as vehicles using an infrared imaging satellite. In the ?rst part, we discuss a basic detection model for a regional ground target using a satellite. The probability of detection is calculated. In the second part, a basic model for the recognition of a ground target using an infrared imaging satellite is developed based on the model in the ?rst part. Based above two parts,we discuss a basic model of the detection probability for a moving ground target using an infrared imaging satellite in the third part. As the normal distribution has the maximum entropy, we analyze the normal distribution of a moving ground target such as some vehicles, and based on our conclusions, we develop a basic probability model for the detection of a moving ground target using an infrared imaging satellite. Finally, the simulation was carried on by STK software.
关键词： Moving ground target,Normal distribution,Detection probability,Regional ground target,Infrared light imaging satellite
更新于2025-09-23 15:23:52
-
Low-rank and sparse matrix decomposition with background position estimation for hyperspectral anomaly detection
摘要： Hyperspectral anomaly detection (AD) has attracted much attention over the last 20 years. It distinguishes pixels with significant spectral differences from the background without any prior knowledge. The low-rank and sparse matrix decomposition (LRaSMD)-based detector has been applied to AD, where the anomaly value is measured by Euclidean distance based on the sparse component. However, the background interference in sparse component seriously increases the false alarm rate and influences the detection of real anomalies. In this paper, a novel AD method based on LRaSMD and background position estimation is proposed, which aims to suppress background interference in the sparse component for a better separation between background and anomalies. Firstly, the original sparse matrix is obtained using the traditional LRaSMD method. Secondly, the abundance maps are constructed by the sequential maximum angel convex cone (SMACC) endmember extraction model. Thirdly, considering that the anomalies occupy only a few pixels with a low probability, the coordinate positions of background pixels are estimated through these abundance maps. Finally, the spectra corresponding to these positions in the original sparse matrix are replaced with zero vectors, and the final anomaly value is calculated based on the improved sparse matrix. The proposed method achieves an outstanding performance by considering both the spectral and spatial characteristics of anomalies. Experimental results on synthetic and real-world hyperspectral datasets demonstrate the superiority of the proposed method compared with several state-of-the-art AD detectors.
关键词： Anomaly detection,Background estimation,Low-rank and sparse matrix decomposition,Hyperspectral imagery,Endmember extraction
更新于2025-09-23 15:23:52
-
A stacked autoencoders-based adaptive subspace model for hyperspectral anomaly detection
摘要： In recent years, some adaptive subspace models perform well for hyperspectral anomaly detection (AD). In this paper, a stacked autoencoders-based adaptive subspace model (SAEASM) is proposed. First, three windows, namely, inner, outer and dictionary window, centered at the test point are used to obtain the local background pixel points and dictionary in the hyperspectral image (HSI). Second, the deep features of differences between the test point and the local dictionary pixels are first acquired by the use of SAE architectures. Then, the deep features of differences between the local background pixels and the local dictionary pixels are also acquired by the use of SAE architectures. Finally, the detection result is obtained by the stacked autoencoders-based adaptive subspace model that is based on the 2-norm of the above two deep features. The experimental results carried out on real and synthetic HSI demonstrate that the proposed SAEASM generally performs better than the comparison algorithms.
关键词： Hyperspectral image,Stacked autoencoders,Adaptive subspace,Anomaly detection
更新于2025-09-23 15:23:52
-
Ship detection in spaceborne infrared images based on Convolutional Neural Networks and synthetic targets
摘要： Automatic detection of ships in spaceborne infrared images is important for both military and civil applications due to its all-weather detection capability. While deep learning methods have made great success in many image processing fields recently, training deep learning models still relies on large amount of labeled data, which may limit its application performance for infrared images target detection tasks. Considering that, we propose a new infrared ship detection method based on Convolutional Neural Networks (CNN) which is trained only with synthetic targets. For the problem of limited infrared training data, we design a Transfer Network (T-Net) to generate large amount of synthetic infrared-style ship targets from Google Earth images. The experiments are conducted on a near infrared band image (0:845μm s 0:885μm), a short wavelength infrared band image (1:560μm s 1:66μm) and a long wavelength infrared band image (2:1μm s 2:3μm) of Landsat-8 satellite. The results demonstrate the effectiveness of the target generation ability of T-Net. With only synthetic training samples, our detection method achieves a higher accuracy than other classical ship detection methods.
关键词： Convolutional Neural Networks,Spaceborne infrared image,Synthetic targets,Ship detection
更新于2025-09-23 15:23:52
-
Tea Diseases Detection Based on Fast Infrared Thermal Image Processing Technology
摘要： The overall goal of this study is to develop an effective, simple, aptly computer vision algorithm to detect tea disease area using infrared thermal image processing techniques and to estimate tea disease. This paper finds that the area of tea disease has certain regularity with its infrared image gray distribution. Using this rule, we extracted two characteristic parameters into a classifier to help achieve rapid tea disease detection, which increase the accuracy of detection a small amount. Tea plant images were taken from Jiangsu Tea Expo Park, China during daylight and the tea disease detection algorithm were tested on 116 images collected from 57 trees. The tea disease detection algorithm consisted of the following steps: classify canopy infrared thermal image, convert red, green and blue (RGB) image to hue, saturation and value (HSV), thresholding, color identification, noise filtering, binarization, closed operation and counting. A correlation coefficient of 0.97 was obtained between the tea disease detection algorithm and counting performed through human observation, 2% higher than traditional algorithms without classifiers.
关键词： Color detection,Tea disease,Infrared thermal image,Fast classification,Image processing
更新于2025-09-23 15:23:52
-
Electrochemical surface plasmon resonance (EC-SPR) aptasensor for ampicillin detection
摘要： Surface plasmon resonance technique is highly sensitive to various processes taking place on a metal film and it has emerged as a powerful label-free method to study molecular binding processes taking place on a surface. Another important but less explored area of applications is the use of hybrid methods which combine electrochemistry with optical methods for better monitoring and understanding of biochemical processes. A detection method based on surface plasmon resonance was developed for ampicillin, applying electrochemical techniques for the elaboration and characterization of the aptasensing platform used in this study. Ampicillin is a broad-spectrum β-lactam antibiotic, used both in human and veterinary medicine for the treatment and prevention of primary respiratory, gastrointestinal, urogenital, and skin bacterial infections. It is widely used because of its broad spectrum and low cost. This widespread use can result in the presence of residues in the environment and in food leading to health problems for individuals who are hypersensitive to penicillins. The gold chip was functionalized through potential-assisted immobilization, using multipulse amperometry, first with a thiol-terminated aptamer, as a specific ligand and secondly, using the same procedure, with mercaptohexanol, used to cover the unoccupied binding sites on the gold surface in order to prevent the nonspecific adsorption of ampicillin molecules. After establishing the optimal conditions for the chip functionalization, different concentrations of ampicillin were detected in real time, in the range of 2.5–1000 μmol L?1, with a limit of detection of 1 μmol L?1, monitoring the surface plasmon resonance response. The selectivity of the aptasensor was proven in the presence of other antibiotics and drugs, and the method was successfully applied for the detection of ampicillin from river water.
关键词： Multipulse amperometry,Electrochemical surface plasmon resonance (EC-SPR),Ampicillin,QCM,Antibiotic detection,SPR aptasensor
更新于2025-09-23 15:23:52
-
Comparison of image quality and lesion detection between digital and analog PET/CT
摘要： Objective The purpose of this study was to compare image quality and lesion detection capability between a digital and an analog PET/CT system in oncological patients. Materials and methods One hundred oncological patients (62 men, 38 women; mean age of 65 ± 12 years) were prospectively included from January–June 2018. All patients, who accepted to be scanned by two systems, consecutively underwent a single day, dual imaging protocol (digital and analog PET/CT). Three nuclear medicine physicians evaluated image quality using a 4-point scale (?1, poor; 0, fair; 1, good; 2, excellent) and detection capability by counting the number of lesions with increased radiotracer uptake. Differences were considered significant for a p value <0.05. Results Improved image quality in the digital over the analog system was observed in 54% of the patients (p = 0.05, 95% CI, 44.2–63.5). The percentage of interrater concordance in lesion detection capability between the digital and analog systems was 97%, with an interrater measure agreement of κ = 0.901 (p < 0.0001). Although there was no significant difference in the total number of lesions detected by the two systems (digital: 5.03 ± 10.6 vs. analog: 4.53 ± 10.29; p = 0.7), the digital system detected more lesions in 22 of 83 of PET+ patients (26.5%) (p = 0.05, 95% CI, 17.9–36.7). In these 22 patients, all lesions detected by the digital PET/CT (and not by the analog PET/CT) were < 10 mm. Conclusion Digital PET/CT offers improved image quality and lesion detection capability over the analog PET/CT in oncological patients, and even better for sub-centimeter lesions.
关键词： Analog PET/CT,Digital PET/CT,Image quality,Lesion detection capability
更新于2025-09-23 15:23:52