- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Deep Residual Network with Subclass Discriminant Analysis for Crowd Behavior Recognition
摘要： In this work, we extract rich representations of crowd behavior from video using a fine-tuned deep convolutional neural residual network. Using spatial partitioning trees we create subclasses within the feature maps from each of the crowd behavior attributes (classes). Features from these subclasses are then regularized using an eigenmodeling scheme. This enables to model the variance appearing from the intra-subclass information. Low dimensional discriminative features are extracted after using the total subclass scatter information. Dynamic time warping is used on the cosine distance measure to find the similarity measure between videos. A 1-nearest neighbor (NN) classifier is used to find the respective crowd behavior attribute classes from the normal videos. Experimental results on large crowd behavior video database show the superior performance of our proposed framework as compared to the baseline and current state-of-the-art methodologies for the crowd behavior recognition task.
关键词： Crowd behavior recognition,discriminant analysis,residual network,feature extraction
更新于2025-09-23 15:21:21
-
[Springer Theses] Electrical Properties of Indium Arsenide Nanowires and Their Field-Effect Transistors || Fabrication, Characterization and Parameter?Extraction of InAs Nanowire-Based Device
摘要： Nanofabrication, low noise electrical measurement and various nanoscale characterization methods are frequently used in the study. This chapter will give as introduction on the growth method, fabrication techniques, characterization methods of materials and devices, measurement systems, and way to extract the electrical parameters of InAs nanowires FET devices.
关键词： Parameter extraction,Fabrication of nanowire devices,Electrical measurement,Structural characterization
更新于2025-09-23 15:21:21
-
[IEEE 2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS) - Beijing (2018.8.19-2018.8.20)] 2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS) - Road Map Update from Satellite Images by Object Segmentation and Change Analysis
摘要： This paper studies to detect the change of road network from remote sensing images. Our purpose is to apply the method for practical usages, such as navigation map updating, road construction supervision, disaster survey, and so on. The proposed approach assumes that there is an outdated road map and the updating job is performed by detecting new road network and comparing the changes. The deep convolution network is utilized for precisely segmenting road areas. An image registration and correction procedure is performed to unify the spatial coordinate reference between the old map and the new road detection results. Then, we modify and standardize the extracted road segments, and apply it to determine the road variation of different periods. Experiments show that, the proposed method successfully identifies road changes, which is useful for fast map update in remote areas.
关键词： road change detection,road region extraction,image segmentation,deep convolutional networks
更新于2025-09-23 15:21:21
-
BAT algorithm inspired retinal blood vessel segmentation
摘要： The automated extraction of retinal blood vessels is the course of action in the medical analysis of retinal diseases. The proposed methodology for the retinal vessel segmentation is based on BAT algorithm and random forest classifier. A feature vector of 40-dimensional including local, phase and morphological features is extracted and the feature set which minimises the classifier error is identified by BAT algorithm. The selected features are also identified as the dominant features in the classification. Performance of the proposed method is analysed by the publicly available databases such as digital retinal images for vessel extraction and structured analysis of the retina. The authors’ proposed method is highly sensitive to identify the blood vessels, in view of the fact that it corresponds to the ability of the method to identify the blood vessels correctly. BAT algorithm-based proposed method achieves very high sensitivity and accuracy of about 82.85 and 95.34%, respectively.
关键词： digital retinal images,retinal blood vessel segmentation,structured analysis of the retina,feature extraction,BAT algorithm,random forest classifier
更新于2025-09-23 15:21:21
-
Online Third-Order Liquid Chromatographic Data with Native and Photoinduced Fluorescence Detection for the Quantitation of Organic Pollutants in Environmental Water
摘要： Third-order liquid chromatographic data were generated online for the simultaneous quantitation of six organic environmental pollutants. The employed strategy consists in reducing the linear flow rate at the column outlet. A postcolumn UV reactor and a fluorimetric detector allowed to properly record both photoinduced and native excitation?emission fluorescence matrices (EEPIFMs and EEFMs, respectively). The obtained third-order liquid chromatography data were chemometrically processed with the multivariate curve resolution?alternating least-squares model. The sensitivity of the overall analytical method was enhanced by a very simple solid-phase extraction with C18 membranes, to be able to successfully apply it to natural water samples tested as real matrices. Favorable detection limits for the investigated pollutants, ranging from 0.02 to 0.27 ng mL?1, were attained, with relative prediction errors between 2 and 7%. Since the studied samples contain uncalibrated interferents, the applied strategy achieves the second-order advantage. Implications regarding the potential achievement of the third-order advantage are discussed.
关键词： multivariate curve resolution?alternating least-squares,solid-phase extraction,second-order advantage,third-order advantage,third-order liquid chromatographic data,photoinduced fluorescence detection,organic environmental pollutants
更新于2025-09-23 15:21:21
-
[Communications in Computer and Information Science] Advances in Computing and Data Sciences Volume 905 (Second International Conference, ICACDS 2018, Dehradun, India, April 20-21, 2018, Revised Selected Papers, Part I) || Optical Character Recognition (OCR) of Marathi Printed Documents Using Statistical Approach
摘要： Optical Character Recognition (OCR) of local languages is an important research area as the techniques developed for one language cannot apply directly to other languages. The paper presents the development of a new statistical method based on template matching and modified template matching used for recognition of a local language of the State of Maharashtra Marathi. It is noted that proposed method not only gives good recognition rate but also have offered good CPU and memory efficiency. Along with system accuracy, average CPU consumption and memory utilization is also analyses and found the acceptable minimum. The proposed algorithm for Marathi OCR is optimized for speed compared with the existing algorithm and hence permits porting on handheld devices with low processing power like Mobile phones. The algorithm is robust in terms of characters size and style of writing.
关键词： OCR,Devanagari Marathi character recognition,Statistical feature extraction
更新于2025-09-23 15:21:21
-
Subwavelength-scale nanorods implemented hexagonal pyramids structure as efficient light-extraction in Light-emitting diodes
摘要： Subwavelength-scale nanorods were implemented on the hexagonal pyramid of photochemically etched light-emitting diodes (LEDs) to improve light extraction efficiency (LEE). Sequential processes of Ag deposition and inductively coupled plasma etching successfully produce nanorods on both locally unetched flat surface and sidewall of hexagonal pyramids. The subwavelength-scale structures on flat surface offer gradually changed refractive index, and the structures on side wall of hexagonal pyramid reduce backward reflection, thereby enhancing further enhancement of the light extraction efficiency. Consequently, the nanorods implemented LED shows a remarkable enhancement in the light output power by 14% compared with that of the photochemically etched LEDs which is known to exhibit the highest light output power. Theoretical calculations using a rigorous coupled wave analysis method reveal that the subwavelength-scale nanorods are very effective in the elimination of TIR as well as backward reflections, thereby further enhancing LEE of the LEDs.
关键词： subwavelength-scale nanorods,light-emitting diodes,light extraction efficiency,hexagonal pyramids,photochemical etching
更新于2025-09-23 15:21:01
-
Enhanced optical efficiency and color purity for organic light-emitting diodes by finely optimizing parameters of nanoscale low-refractive index grid
摘要： To extract the confined waveguided light in organic light-emitting diodes (OLEDs), inserting a low refractive index (RI) periodic structure between the anode and organic layer has been widely investigated as a promising technology. However, the periodic-structure-based light extraction applied inside devices has been shown to severely distort spectrum and affect EL characteristics. In this study, a simple light extraction technology using periodic low-RI nanodot array (NDA) as internal light extraction layer has been demonstrated. The NDA was fabricated simply via laser interference lithography (LIL). The structural parameters of periodic pattern, distance, and height were easily controlled by the LIL process. From computational analysis using finite-difference time-domain (FDTD) method, the NDA with 300 nm pitch and 0.3 coverage ratio per unit cell with 60 nm height showed the highest enhancement with spectral-distortion-minimized characteristics. Through both computational and experimental systematic analysis on the structural parameters of low-RI NDA-embedded OLEDs, highly efficient OLEDs have been fabricated. Finally, as representative indicators, hexagonal and rectangular positioned NDA-embedded OLEDs showed highly improved external quantum efficiencies of 2.44 (+29.55%) and 2.77 (+57.38%), respectively. Furthermore, the disadvantage originating from the nanoscale surface roughness on the transparent conductive oxide was minimized.
关键词： organic light-emitting diodes,nanodot array,FDTD simulation,laser interference lithography,light extraction,low refractive index
更新于2025-09-23 15:21:01
-
[IEEE 2019 International Conference on Numerical Simulation of Optoelectronic Devices (NUSOD) - Ottawa, ON, Canada (2019.7.8-2019.7.12)] 2019 International Conference on Numerical Simulation of Optoelectronic Devices (NUSOD) - Simulation of quantum light sources using the self-consistently coupled Schr??dinger-Poisson-Drift-Diffusion-Lindblad syste
摘要： A very-large-scale integration capable of extracting motion features from moving images in real time has been developed employing row-parallel and pixel-parallel architectures based on the digital pixel sensor technology. Directional edge filtering of input images is carried out in row-parallel processing to minimize the chip real estate. To achieve a real-time response of the system, a fully pixel-parallel architecture has been explored in adaptive binarization of filtered images for essential feature extraction as well as in their temporal integration and derivative operations. As a result, self-speed-adaptive motion feature extraction has been established. The chip was designed and fabricated in a 65-nm CMOS technology and used to build an object detection system. Motion-sensitive target image localization was demonstrated as an illustrative example.
关键词： parallel architecture,digital pixel sensor (DPS),Block-readout scheme,motion feature extraction (MFE),vision chip
更新于2025-09-23 15:21:01
-
[IEEE 2019 44th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz) - Paris, France (2019.9.1-2019.9.6)] 2019 44th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz) - THz Quantum Cascade Lasers with Optimized Beam Divergence
摘要： Huynen decomposition (HD) as the first formalized target decomposition has not been widely accepted. The preference for symmetry and regularity restricts not only its application but also its unification with other target dichotomies. The nonuniqueness issue then arises because we may have different dichotomies of radar targets, but we have no idea on how to select them. In this paper, a unified Huynen dichotomy is developed by extending HD for a full preference for symmetry and regularity, nonsymmetry, irregularity, and their couplings. It covers all of the existing dichotomies and provides a unified selection mechanism for them. Scattering preference is identified as a main feature of target dichotomy, and its concise description is devised by relating each dichotomy to a canonical scattering. A scattering degree of preference (SDoP) parameter is defined to measure the preference of each dichotomy. In virtue of an adaptive combination and permutation of SDoPs, a scattering pyramid description of the mixed scattering is developed, which has better discrimination of target than entropy/alpha. An SDoP/alpha classification is further proposed by statistical modeling of the unified dichotomy, which is a competent alternative to entropy/alpha. The excellent performance of unified dichotomy makes us believe that the existing concerns on HD are well treated and the Huynen–Cloude controversy, in a sense, may be ended.
关键词： target extraction,target decomposition,unsupervised classification,Huynen decomposition (HD),radar polarimetry
更新于2025-09-23 15:21:01