期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到448篇文章
< 1 2 … 23 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Pedestrian detection of infrared images based on an improved FCOS algorithm 认领 引用
1
作者 Fuzhen ZHU Hao HAN +1 位作者 Hengfei JIA Bing ZHU 《Optoelectronics Letters》 EI 2026年第2期105-110,共6页
The current infrared image pedestrian detectors have problems with high rates of false positives and false negatives. To solve these problems, we proposed an improved anchor-free fully convolutional one-stage object d... The current infrared image pedestrian detectors have problems with high rates of false positives and false negatives. To solve these problems, we proposed an improved anchor-free fully convolutional one-stage object detection(FCOS) algorithm. Firstly, we introduced the channel attention module squeeze excitation(SE)-Block in the FCOS backbone network, which was used to learn how to model the relative importance between different feature channels, and to achieve the weight recalibration of the features extracted from the convolution neural network, and improve the weight values that are more important for pedestrian target detection. Secondly, soft non-maximum suppression(Soft-NMS) replaced the conventional NMS within the algorithm's post-processing phase, which was used to reduce the probability of missed detection for occluded pedestrians. The experimental results show that our improved FCOS algorithm improves the average precision(AP) by 6.71% on the original dataset and 7.97% on the augmented KAIST pedestrian dataset compared with the original FCOS algorithm. Our improvements effectively meet the real-time requirements and there is no significant decrease in speed compared with the original FCOS algorithm, and decreased the false positives and false negatives for infrared image pedestrian detection. 展开更多
关键词 weight recalibration pedestrian detection infrared image pedestrian detectors channel attention module learn how model relative importance different feature channels improved FCOS algorithm infrared images Squeeze Excitation SE block
暂未订购 下载PDF
Unfolding analysis of LaBr3:Ce gamma spectrum with a detector response matrix constructing algorithm based on energy resolution calibration 认领 引用 被引量：19
2
作者 Rui Shi Xian-Guo Tuo +4 位作者 Huai-Liang Li Yang-Yang Xu Fan-Rong Shi Jian-Bo Yang Yong Luo 《Nuclear Science and Techniques》 SCIE EI CAS CSCD 2018年第1期23-31,共9页
With respect to the gamma spectrum, the energy resolution improves with increase in energy. The counts of full energy peak change with energy, and this approximately complies with the Gaussian distribution. This study... With respect to the gamma spectrum, the energy resolution improves with increase in energy. The counts of full energy peak change with energy, and this approximately complies with the Gaussian distribution. This study mainly examines a method to deconvolve the LaBr_3:Ce gamma spectrum with a detector response matrix constructing algorithm based on energy resolution calibration.In the algorithm, the full width at half maximum(FWHM)of full energy peak was calculated by the cubic spline interpolation algorithm and calibrated by a square root of a quadratic function that changes with the energy. Additionally, the detector response matrix was constructed to deconvolve the gamma spectrum. Furthermore, an improved SNIP algorithm was proposed to eliminate the background. In the experiment, several independent peaks of 152Eu,137Cs, and 60Co sources were detected by a LaBr_3:Ce scintillator that were selected to calibrate the energy resolution. The Boosted Gold algorithm was applied to deconvolve the gamma spectrum. The results showed that the peak position difference between the experiment and the deconvolution was within ± 2 channels and the relative error of peak area was approximately within 0.96–6.74%. Finally, a 133 Ba spectrum was deconvolved to verify the efficiency and accuracy of the algorithm in unfolding the overlapped peaks. 展开更多
关键词 Detector response matrix Energy resolution calibration LaBr3:Ce scintillator SNIP background elimination Boosted Gold deconvolution algorithm
暂未订购 下载PDF
A Novel Radius Adaptive Based on Center-Optimized Hybrid Detector Generation Algorithm 认领 引用 被引量：1
3
作者 Jinyin Chen 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2020年第6期1627-1637,共11页
Negative selection algorithm(NSA)is one of the classic artificial immune algorithm widely used in anomaly detection.However,there are still unsolved shortcomings of NSA that limit its further applications.For example,... Negative selection algorithm(NSA)is one of the classic artificial immune algorithm widely used in anomaly detection.However,there are still unsolved shortcomings of NSA that limit its further applications.For example,the nonselfdetector generation efficiency is low;a large number of nonselfdetector is needed for precise detection;low detection rate with various application data sets.Aiming at those problems,a novel radius adaptive based on center-optimized hybrid detector generation algorithm(RACO-HDG)is put forward.To our best knowledge,radius adaptive based on center optimization is first time analyzed and proposed as an efficient mechanism to improve both detector generation and detection rate without significant computation complexity.RACO-HDG works efficiently in three phases.At first,a small number of self-detectors are generated,different from typical NSAs with a large number of self-sample are generated.Nonself-detectors will be generated from those initial small number of self-detectors to make hybrid detection of self-detectors and nonself-detectors possible.Secondly,without any prior knowledge of the data sets or manual setting,the nonself-detector radius threshold is self-adaptive by optimizing the nonself-detector center and the generation mechanism.In this way,the number of abnormal detectors is decreased sharply,while the coverage area of the nonself-detector is increased otherwise,leading to higher detection performances of RACOHDG.Finally,hybrid detection algorithm is proposed with both self-detectors and nonself-detectors work together to increase detection rate as expected.Abundant simulations and application results show that the proposed RACO-HDG has higher detection rate,lower false alarm rate and higher detection efficiency compared with other excellent algorithms. 展开更多
关键词 Artificial immunity center optimized hybrid detect negative detector negative selection algorithm(NSA) radius adaptive
暂未订购 下载PDF
A Cuckoo Search Detector Generation-based Negative Selection Algorithm 认领 引用
4
作者 Ayodele Lasisi Ali M.Aseere 《Computer Systems Science & Engineering》 SCIE EI 2021年第8期183-195,共13页
The negative selection algorithm(NSA)is an adaptive technique inspired by how the biological immune system discriminates the self from nonself.It asserts itself as one of the most important algorithms of the artificia... The negative selection algorithm(NSA)is an adaptive technique inspired by how the biological immune system discriminates the self from nonself.It asserts itself as one of the most important algorithms of the artificial immune system.A key element of the NSA is its great dependency on the random detectors in monitoring for any abnormalities.However,these detectors have limited performance.Redundant detectors are generated,leading to difficulties for detectors to effectively occupy the non-self space.To alleviate this problem,we propose the nature-inspired metaheuristic cuckoo search(CS),a stochastic global search algorithm,which improves the random generation of detectors in the NSA.Inbuilt characteristics such as mutation,crossover,and selection operators make the CS attain global convergence.With the use of Lévy flight and a distance measure,efficient detectors are produced.Experimental results show that integrating CS into the negative selection algorithm elevated the detection performance of the NSA,with an average increase of 3.52%detection rate on the tested datasets.The proposed method shows superiority over other models,and detection rates of 98%and 99.29%on Fisher’s IRIS and Breast Cancer datasets,respectively.Thus,the generation of highest detection rates and lowest false alarm rates can be achieved. 展开更多
关键词 Negative selection algorithm detector generation cuckoo search optimization
暂未订购 下载PDF
Readout electronics for the gamma detector of the HIRFL-CSR external target facility 认领 引用
5
作者 Xian-Qin Li Hai-Bo Yang +10 位作者 Xiao-Meng Ma Chao-Jie Zou Tao Liu Xian-Cai Zhou Duo Yan Yang-Zhou Su Shu-Wen Tang Shi-Tao Wang Yu-Hong Yu Zhi-Yu Sun Cheng-Xin Zhao 《Nuclear Science and Techniques》 SCIE EI CAS CSCD 2025年第2期71-81,共11页
The Cooling Storage Ring of the Heavy Ion Research Facility in Lanzhou(HIRFL-CSR)was constructed to study nuclear physics,atomic physics,interdisciplinary science,and related applications.The External Target Facility(... The Cooling Storage Ring of the Heavy Ion Research Facility in Lanzhou(HIRFL-CSR)was constructed to study nuclear physics,atomic physics,interdisciplinary science,and related applications.The External Target Facility(ETF)is located in the main ring of the HIRFL-CSR.The gamma detector of the ETF is built to measure emitted gamma rays with energies below 5 MeV in the center-of-mass frame and is planned to measure light fragments with energies up to 300 MeV.The readout electronics for the gamma detector were designed and commissioned.The readout electronics consist of thirty-two front-end cards,thirty-two readout control units(RCUs),one common readout unit,one synchronization&clock unit,and one sub-trigger unit.By using the real-time peak-detection algorithm implemented in the RCU,the data volume can be significantly reduced.In addition,trigger logic selection algorithms are implemented to improve the selection of useful events and reduce the data size.The test results show that the integral nonlinearity of the readout electronics is less than 1%,and the energy resolution for measuring the 60 Co source is better than 5.5%.This study discusses the design and performance of the readout electronics. 展开更多
关键词 HIRFL-CSR Gamma detector External target facility Readout electronics Readout control unit Common readout unit Peak-detection algorithm
暂未订购 下载PDF
Collusion detector based on G-N algorithm for trust model 认领 引用
6
作者 Lin Zhang Na Yin +1 位作者 Jingwen Liu Ruchuan Wang 《Journal of Systems Engineering and Electronics》 SCIE CSCD 2016年第4期926-935,共10页
In the open network environment, malicious attacks to the trust model have become increasingly serious. Compared with single node attacks, collusion attacks do more harm to the trust model. To solve this problem, a co... In the open network environment, malicious attacks to the trust model have become increasingly serious. Compared with single node attacks, collusion attacks do more harm to the trust model. To solve this problem, a collusion detector based on the GN algorithm for the trust evaluation model is proposed in the open Internet environment. By analyzing the behavioral characteristics of collusion groups, the concept of flatting is defined and the G-N community mining algorithm is used to divide suspicious communities. On this basis, a collusion community detector method is proposed based on the breaking strength of suspicious communities. Simulation results show that the model has high recognition accuracy in identifying collusion nodes, so as to effectively defend against malicious attacks of collusion nodes. 展开更多
关键词 trust model collusion detector G-N algorithm
暂未订购 下载PDF
Design and FPGA-Implementation of Minimum PED Based K-Best Algorithm in MIMO Detector 认领 引用
7
作者 Poornima Ramasamy Mahabub Basha Ahmedkhan Mounika Rangasamy 《Circuits and Systems》 2016年第6期612-621,共10页
Minimum Partial Euclidean Distance (MPED) based K-best algorithm is proposed to detect the best signal for MIMO (Multiple Input Multiple Output) detector. It is based on Breadth-first search method. The proposed algor... Minimum Partial Euclidean Distance (MPED) based K-best algorithm is proposed to detect the best signal for MIMO (Multiple Input Multiple Output) detector. It is based on Breadth-first search method. The proposed algorithm is independent of the number of transmittingeceiving antennas and constellation size. It provides a high throughput and reduced Bit Error Rate (BER) with the performance close to Maximum Likelihood Detection (MLD) method. The main innovations are the nodes that are expanded and visited based on MPED algorithm and it keeps track of finally selecting the best candidates at each cycle. It allows its complexity to scale linearly with the modulation order. Using Quadrature Amplitude Modulation (QAM) the complex domain input signals are modulated and are converted into wavelet packets and these packets are transmitted using Additive White Gaussian Noise (AWGN) channel. Then from the number of received signals the best signal is detected using MPED based K-best algorithm. It provides the exact best node solution with reduced complexity. The pipelined VLSI architecture is the best suited for implementation because the expansion and sorting cores are data driven. The proposed method is implemented targeting Xilinx Virtex 5 device for a 4 × 4, 64-QAM system and it achieves throughput of 1.1 Gbps. The results of resource utilization are tabulated and compared with the existing algorithms. 展开更多
关键词 Multiple Input Multiple Output Detector K-Best Algorithm Partial Euclidean Distance Quadrature Amplitude Modulation Field Programmable Gate Array
暂未订购 下载PDF
多模型迭代重建算法在宽体探测器CT中行双低剂量头颈CTA联合全脑CTP一站式检查的可行性 认领 引用 被引量：1
8
作者 祁冬 李娟 +2 位作者 司峥 杨米雪 崔悦 《医学影像学杂志》 2026年第3期137-142,共6页
目的探讨多模型迭代重建(ASiR-V)算法在宽体探测器CT中行双低剂量头颈CT血管成像(CTA)联合全脑CT灌注成像(CTP)一站式检查的可行性。方法选取疑似急性缺血性脑卒中(AIS)患者84例,按照随机数字表法随机分为A、B、C三组,每组28例。在双低... 目的探讨多模型迭代重建(ASiR-V)算法在宽体探测器CT中行双低剂量头颈CT血管成像(CTA)联合全脑CT灌注成像(CTP)一站式检查的可行性。方法选取疑似急性缺血性脑卒中(AIS)患者84例,按照随机数字表法随机分为A、B、C三组,每组28例。在双低剂量头颈CTA联合全脑CTP一站式检查中,A组管电压100 kV、对比剂碘海醇(碘浓度350 mg/mL)、图像重建FBP算法,B组管电压80 kV、对比剂碘克沙醇(碘浓度320 mg/mL)、图像重建FBP算法,C组管电压80 kV、对比剂碘克沙醇(碘浓度320 mg/mL)、图像重建ASiR-V算法。比较三组头颈CTA和全脑CTP扫描参数、图像质量主观评分,分析三组图像质量主观评价和客观评价一致性,并比较三组辐射剂量和碘摄入量。结果与A组比较,B组同部位CT值标准差(SD)升高(P均<0.05),同部位信噪比(SNR)、对比噪声比(CNR)降低(P均<0.05);与B组比较,C组同部位SD降低,同部位SNR、CNR升高(P均<0.05)。与A组比较,B组同部位脑血流量(CBF)、脑血容量(CBV)、达峰反应时间(Tmax)降低(P均<0.05);与B组比较,C组同部位CBF、CBV、Tmax升高(P均<0.05)。B组头颈CTA、全脑CTP图像质量主观评分均低于A、C组(P均<0.05)。2位医师对三组头颈CTA和全脑CTP图像质量主观评价的一致性很好(Kappa分别为0.812、0.809)。医师内ICC分析显示,SNR、CBF、Tmax的一致性好(ICC分别为0.782、0.805、0.812);医师间ICC分析显示,CNR、CBV、Tmax的一致性好(ICC分别为0.831、0.791、0.855)。与A组比较,B、C组容积CT剂量指数、CT剂量长度乘积、有效辐射剂量及碘摄入量均降低(P均<0.05)。结论ASiR-V算法在宽体探测器CT中行双低剂量头颈CTA联合全脑CTP一站式检查具有可行性,不仅能获得满意的图像质量,还能降低辐射剂量和碘摄入量。 展开更多
关键词 体层摄影术,X线计算机 血管成像 灌注成像 急性缺血性脑卒中 宽体探测器 多模型迭代重建算法
暂未订购 下载PDF
双神经网络深度学习算法对不同低剂量上腹部CT图像质量的评估 认领 引用
9
作者 李彩霞 王建平 +3 位作者 齐宏亮 黄美燕 李典育 周建伟 《中国医学物理学杂志》 CSCD 2026年第7期905-909,共5页
目的:探讨国产宽体超高分辨率CT结合双神经网络深度学习重建技术(DLIR-CI)对上腹部不同辐射剂量方案CT图像质量的优化作用。方法:纳入33例行上腹部CT平扫的患者,采用2025年3月上市的320排宽体探测器CT进行扫描,根据扫描剂量的不同分为... 目的:探讨国产宽体超高分辨率CT结合双神经网络深度学习重建技术(DLIR-CI)对上腹部不同辐射剂量方案CT图像质量的优化作用。方法:纳入33例行上腹部CT平扫的患者,采用2025年3月上市的320排宽体探测器CT进行扫描,根据扫描剂量的不同分为常规剂量(RD)组(120 kV,350 mA)、低剂量1(LD1)组(120 kV,175 mA)和低剂量2(LD2)组(120 kV,70 mA)。所有RD组采用迭代重建算法(CV40%)重建,LD1组和LD2组均采用CV40%和深度学习重建算法(CI)(强度系数为20%/40%/60%/80%)重建,总共对99层图像进行质量评估,测量不同算法肝脏和肾脏的CT值及标准差(SD),并计算信噪比(SNR)。同时采用5分评价法评价所有图像的噪声等级和锐利度,客观评价采用SPSS软件的线性混合模型分析,事后两两比较采用Bonferroni法校正。结果:(1)与RD组的CTDIvol相比,LD1组和LD2组的剂量分别降低50%和80%;(2)与RD_CV40%相比,LD1_CV40%和LD2_CV40%的SD值分别增加24%和71%,SNR值分别降低21%和43%;(3)在LD1组和LD2组的组内比较中,CI40%、CI60%、CI80%的SD值和SNR值分别与CV40%相比,肝脏和肾脏的SD值均逐渐降低,SNR值均显著提高(P0.05);(5)LD1组和LD2组的CI60%和CI80%分别与RD_CV40%相比,肝脏和肾脏的SD值更低,SNR值更高,差异均有统计学意义(P<0.05);(6)主观评价中,LD1组和LD2组的CI40%、CI60%和CI80%的噪声等级评分和锐利度评分均明显优于RD_CV40%的评分,差异有统计学意义(P<0.05)。结论:上腹部CT扫描剂量较常规剂量降低50%、80%时,结合深度学习重建算法(强度系数≥40%)的图像可以达到常规剂量迭代重建CV40%的效果,甚至更优的图像质量,在临床应用中明显降低辐射风险。 展开更多
关键词 CT 宽体探测器 深度学习重建算法 低剂量 图像质量
暂未订购 下载PDF
融合Retinex及多尺度滤波的红外图像增强算法 认领 引用
10
作者 程瑶 唐清涛 +3 位作者 石肖伊 龚奥 吴哲滔 冉茂明 《红外技术》 CSCD 北大核心 2026年第7期801-807,共7页
针对传统红外探测器所采集的红外图像存在对比度低、高斯白噪声降低图像质量以及细节信息丢失等问题,提出了一种集多尺度滤波、图像细节增强的红外图像目标增强算法。该算法通过改进传统Retinex算法中的模糊方式,即用双边模糊代替高斯模... 针对传统红外探测器所采集的红外图像存在对比度低、高斯白噪声降低图像质量以及细节信息丢失等问题,提出了一种集多尺度滤波、图像细节增强的红外图像目标增强算法。该算法通过改进传统Retinex算法中的模糊方式,即用双边模糊代替高斯模糊,解决了传统Retinex算法中由高斯模糊引起的红外图像细节和边缘信息丢失的问题,同时实现红外图像对比度的增强。在此基础上通过三维块匹配滤波、非局部均值滤波等多尺度滤波及去噪处理后,消除了红外图像对比度过度增强而出现的光晕伪影。通过实验验证了本算法的可行性并由对比实验可知,相较于高斯滤波、均值滤波等传统空域去噪算法,本文算法更能有效去除红外图像存在的高斯白噪声。实验结果表明,本文算法处理得到的红外目标图像细节信息增强、清晰度好、对比度高,且优于其他空域图像增强算法如直方图均衡化、对数变换等。 展开更多
关键词 红外图像增强 红外探测器 三维块匹配滤波 Retinex算法 非局部均值滤波
暂未订购 下载PDF
相位级次编码的虚拟结构光3D点云压缩 认领 引用
11
作者 宁爱平 齐慧敏 +1 位作者 武迎春 刘丽 《太原科技大学学报》 2026年第2期77-83,共7页
为了提高虚拟结构光3D点云数据的压缩率,提出相位级次编码的3D点云压缩方法。该方法对B通道相位级次图进行游程编码,得到其索引值和次数值,对R、G通道的正余弦条纹图用中值边缘预测算法得到其预测条纹图,通过计算差值得到标签映射,根据... 为了提高虚拟结构光3D点云数据的压缩率,提出相位级次编码的3D点云压缩方法。该方法对B通道相位级次图进行游程编码,得到其索引值和次数值,对R、G通道的正余弦条纹图用中值边缘预测算法得到其预测条纹图,通过计算差值得到标签映射,根据标签值将相位级次的索引值和次数值分别隐藏在R、G通道条纹图像中,以实现数据压缩。实验结果表明在解码精度不变的条件下,数据压缩率平均提高46.54%,验证了所提算法的有效性。 展开更多
关键词 3D点云 虚拟结构光 相位级次编码 中值边缘预测
暂未订购 下载PDF
基于改进LSD直线检测算法的钢轨表面边界提取 认领 引用 被引量：10
12
作者 曹义亲 何恬 刘龙标 《华东交通大学学报》 2021年第3期95-101,共7页
针对传统LSD直线检测算法容易丢失图像细节,造成提取直线不连续等不足,提出一种基于双边滤波改进Canny提取边缘图像的LSD直线检测算法。利用Canny算法提取边缘图像,基于边缘图像采用LSD直线检测算法进行直线提取;考虑到Canny边缘检测中... 针对传统LSD直线检测算法容易丢失图像细节,造成提取直线不连续等不足,提出一种基于双边滤波改进Canny提取边缘图像的LSD直线检测算法。利用Canny算法提取边缘图像,基于边缘图像采用LSD直线检测算法进行直线提取;考虑到Canny边缘检测中使用高斯滤波,在降噪的同时会模糊图像边缘,而双边滤波对于图像边缘有较好的保护作用,采用双边滤波代替Canny边缘检测中的高斯滤波进行边缘图像提取。同时,将基于双边滤波改进Canny提取边缘图像的LSD直线检测算法应用到钢轨表面边界提取中。实验结果表明,改进LSD直线检测算法对钢轨表面边界直线提取效果较佳,相关评价指标得到较大提升,正常钢轨图像和锈迹钢轨图像的峰值信噪比分别提升6.49%和13.58%,为后续钢轨表面缺陷识别奠定了基础,具有一定的实用价值。 展开更多
关键词 钢轨边界提取 Canny算法 双边滤波 直线检测 LSD算法
暂未订购 下载PDF
基于蒙卡模拟能量响应的CLYC探测器γ能谱解析方法 认领 引用
13
作者 李宇浩 郑洪龙 +7 位作者 庹先国 贺平 魏世平 杨剑波 王朝林 李宇航 余佳佳 邓淇元 《强激光与粒子束》 CAS CSCD 北大核心 2026年第9期10-17,共8页
对于能量分辨能力不足的探测器,能谱解析工作能够提高核素识别和活度计算的准确度。CLYC探测器以其能够同时探测中子和γ光子的优点被广泛应用于中子-光子双模探测领域中,其能量分辨能力与高纯锗、碲锌镉等半导体探测器相比相对较差,在... 对于能量分辨能力不足的探测器,能谱解析工作能够提高核素识别和活度计算的准确度。CLYC探测器以其能够同时探测中子和γ光子的优点被广泛应用于中子-光子双模探测领域中,其能量分辨能力与高纯锗、碲锌镉等半导体探测器相比相对较差,在复杂的辐射环境中难以保证对γ能谱的分析精度。采用蒙特卡罗方法计算CLYC探测器的γ能量响应函数,并通过插值法构建探测器的能量响应矩阵,利用极大似然期望最大化算法(MLEM)进行γ能谱解析。选取0~3 MeV的能量区间,每间隔0.05 MeV计算一个响应函数,利用插值算法构建了CLYC探测器对γ射线的高精度响应矩阵,并结合MLEM算法对226Ra能谱、60Co-137Cs混合能谱及152Eu复杂能谱进行解谱验证,对特征峰面积进行了定量计算。结果表明:该方法能够有效克服探测器能量分辨率的限制,解谱后特征峰位清晰,复杂能谱中的重峰区域实现了有效分离,特征峰面积计算结果稳定,清晰反映了入射γ射线的能量和强度信息,提高了能谱分析的精度。 展开更多
关键词 能谱解析 MLEM算法 CLYC探测器 响应函数
暂未订购 下载PDF
基于多传感器融合的开关柜局部放电精准检测方法 认领 引用 被引量：1
14
作者 万如一 吉宝贤 +1 位作者 潘健 陆丽娟 《电动工具》 2026年第1期39-42,共4页
基于多传感器融合技术,提出一种适用于高压开关柜局部放电的精准检测方法。该方法整合超声、特高频(UHF)、暂态地电压(TEV)及红外等多类传感器数据,搭建高精度硬件采集与同步通信系统,同时构建实时处理与智能辨识平台。通过对支持向量... 基于多传感器融合技术,提出一种适用于高压开关柜局部放电的精准检测方法。该方法整合超声、特高频(UHF)、暂态地电压(TEV)及红外等多类传感器数据,搭建高精度硬件采集与同步通信系统,同时构建实时处理与智能辨识平台。通过对支持向量机、随机森林及深度学习模型的对比与优化,形成多源信息融合判别算法。多场景测试结果显示,所提方法在检测精度、响应速度与抗干扰能力上均具备显著优势。 展开更多
关键词 开关柜 多传感器融合 局部放电检测仪 深度学习 诊断 算法
暂未订购 下载PDF
LDA与LSD相结合的车道线分类检测算法 认领 引用 被引量：13
15
作者 郭克友 王艺伟 郭晓丽 《计算机工程与应用》 CSCD 北大核心 2017年第24期219-225,共7页
提出一种车道线分类检测算法。首先采用LDA对道路图像进行有针对性的灰度化,以便更好地区分车道线与道路。采用LSD算法检测灰度图像中的直线部分并确定车道线的方向。在此基础上,选取符合车道线灰度范围内的像素点。对远距离的像素点采... 提出一种车道线分类检测算法。首先采用LDA对道路图像进行有针对性的灰度化,以便更好地区分车道线与道路。采用LSD算法检测灰度图像中的直线部分并确定车道线的方向。在此基础上,选取符合车道线灰度范围内的像素点。对远距离的像素点采用抛物线拟合,近距离的像素点采用直线拟合。同时,将检测到的车道线进行虚线实线的分类标记。最后结合视频序列的连续性对检测结果进行反向验证。实验结果证明,提出的方法对直道弯道检测均有很好的效果。算法的处理速度为每秒10帧左右,采用的测试视频的帧率为每秒15帧,基本满足实时性的要求。 展开更多
关键词 线性判别分析(LDA) 线段检测器(LSD) 直线-抛物线模型 车道线分类 视频序列连续性
暂未订购 下载PDF
Parallel Distributed CFAR Detection Optimization Based on Genetic Algorithm with Interval Encoding 认领 引用 被引量：1
16
作者 于泽 周荫清 《Chinese Journal of Aeronautics》 SCIE EI CAS 2010年第3期351-358,共8页
Aiming at parallel distributed constant false alarm rate （CFAR） detection employing K/N fusion rule,an optimization algorithm based on the genetic algorithm with interval encoding is proposed. N-1 local probabilitie... Aiming at parallel distributed constant false alarm rate （CFAR） detection employing K/N fusion rule,an optimization algorithm based on the genetic algorithm with interval encoding is proposed. N-1 local probabilities of false alarm are selected as optimization variables. And the encoding intervals for local false alarm probabilities are sequentially designed by the person-by-person optimization technique according to the constraints. By turning constrained optimization to unconstrained optimization,the problem of increasing iteration times due to the punishment technique frequently adopted in the genetic algorithm is thus overcome. Then this optimization scheme is applied to spacebased synthetic aperture radar （SAR） multi-angle collaborative detection,in which the nominal factor for each local detector is determined. The scheme is verified with simulations of cases including two,three and four independent SAR systems. Besides,detection performances with varying K and N are compared and analyzed. 展开更多
关键词 parallel processing systems synthetic aperture radar detectors genetic algorithms optimization encoding
暂未订购 下载PDF
LSD井下视频图像线特征匹配算法改进 认领 引用 被引量：4
17
作者 毛昕蓉 杨兴林 +1 位作者 张小红 韩晓冰 《西安科技大学学报》 CAS 北大核心 2022年第6期1224-1231,共8页
图像特征提取匹配做为视觉SLAM(Simultaneous Localization and Mapping)的重要组成部分,在井下无人巡检机器人上应用广泛。针对井下环境复杂,光照不足,现有特征提取匹配算法存在匹配率低,进而导致视觉SLAM定位精度低的问题。通过对现有... 图像特征提取匹配做为视觉SLAM(Simultaneous Localization and Mapping)的重要组成部分,在井下无人巡检机器人上应用广泛。针对井下环境复杂,光照不足,现有特征提取匹配算法存在匹配率低,进而导致视觉SLAM定位精度低的问题。通过对现有LSD(Line Segment Detector)线特征匹配算法进行改进,采用对比度亮度和对数变换算法对采集的视频图像帧进行图像增强,利用Canny边缘提取算法对增强后的视频图像帧进行图像边缘信息提取后进行LSD线特征提取匹配,与原始算法进行平均匹配率对比分析。结果表明:在连续300帧井下视频图像匹配过程中,改进算法的平均匹配率为99.88%,原始算法的平均匹配率为88.42%,其平均匹配率提升11.46%。说明改进的LSD井下视频图像线特征提取匹配算法具有更高的匹配精度且更适用与井下无人巡检机器人进行无人巡检工作。 展开更多
关键词 LSD算法 Canny边缘提取 线特征匹配 井下视频图像 匹配率
暂未订购 下载PDF
深度学习重建算法联合超高分辨力探测器对眼眶CT图像质量的影响 认领 引用
18
作者 赵一昂 程雨荷 +2 位作者 马梓轩 张永县 刘丹丹 《CT理论与应用研究（中英文）》 2026年第1期80-85,共6页
目的:本研究旨在探索0.3125 mm超高分辨力探测器联合ClearInfinity(CI)深度学习重建算法对眼眶CT图像质量的影响。方法:采用NeuViz Epoch Elite CT机,对Catphan 600模体及3只7岁猕猴进行扫描,设置准直宽度64×0.625 mm与128×0.... 目的:本研究旨在探索0.3125 mm超高分辨力探测器联合ClearInfinity(CI)深度学习重建算法对眼眶CT图像质量的影响。方法:采用NeuViz Epoch Elite CT机,对Catphan 600模体及3只7岁猕猴进行扫描,设置准直宽度64×0.625 mm与128×0.3125 mm,分别采用滤波反投影(FBP)、60%自适应迭代重建算法ClearView(CV)及60%深度学习重建算法CI获取图像,通过调制传递函数(MTF)、对比噪声比(CNR)等客观指标及双盲法主观评分评估图像质量,并进行统计学分析。结果:模体实验中,标准算法与骨算法下,准直宽度128×0.3125 mm图像的MTF50%、MTF10%及CNR部分指标显著优于64×0.625 mm;CI算法图像的CNR显著优于FBP和CV算法。动物实验中,准直宽度128×0.3125 mm图像中内直肌的CNR显著高于64×0.625 mm,CI算法下内直肌与眼球的CNR及主观评分均最优,且两位医师主观评分一致性好(Kappa≥0.75)。结论:0.3125 mm超高分辨力探测器联合深度学习算法可显著提升眼眶CT图像的分辨力、对比度,减少噪声与伪影,具有良好的临床应用前景。 展开更多
关键词 超高分辨力探测器 深度学习重建算法 眼眶CT
暂未订购 下载PDF
西南高山峡谷区坡耕地空间分布特征及驱动因素分析 认领 引用
19
作者 张艾琳 秦伟 +3 位作者 丁琳 周金星 胡云华 黄婷婷 《农业工程学报》 EI CAS CSCD 北大核心 2026年第7期342-353,共12页
坡耕地是山区农业生产和水土流失防治的关键,揭示其空间分布及驱动机制对土地资源可持续利用与生态–经济协同发展至关重要。然而,现有坡度提取方法难以准确反映耕地地块的整体坡度特征,制约了坡耕地的精准识别及其不同尺度的分布特征... 坡耕地是山区农业生产和水土流失防治的关键,揭示其空间分布及驱动机制对土地资源可持续利用与生态–经济协同发展至关重要。然而,现有坡度提取方法难以准确反映耕地地块的整体坡度特征,制约了坡耕地的精准识别及其不同尺度的分布特征解析。为此,该研究提出一种基于DEM的耕地地块整体坡度自动批处理算法,以提升坡度计算精度,进而基于该算法提取坡耕地,并结合核密度、空间自相关与地理探测器等方法,系统揭示西南高山峡谷区坡耕地的存量特征、多尺度分布格局及其驱动因素与交互效应。结果表明:1)该研究坡度算法值与手工测量值吻合良好(R2=0.9,MAE=2.5°),可解决传统算法在缓坡大地块高估坡度、陡坡小地块低估坡度的不足;2)西南高山峡谷区共分布坡耕地91.8万块、总面积1.25万km2,占耕地的72.6%,总体呈“南聚北疏”分布格局,在人口较多、海拔较低的南部县域(占全区面积7.4%)和流域(占全区面积13.2%)高度聚集;3)坡耕地主要分布于亚热带气候区,土壤类型以红壤(25.9%)、棕壤(16.9%)、黄棕壤(15.7%)和黄壤(10.2%)为主,43.3%超过禁垦坡度、约1/3达30°以上,集中于2000~3500 m中山带(56.7%)和2000 m以下低山河谷带(33.2%);4)县域坡耕地分异主控于人口密度,其次为地形因子;流域则受多因子协同影响;各因子对坡耕地分布的影响均以交互增强为主,尤其人口密度与土壤、地形、水热等条件的协同解释力普遍提升。该研究可为西南高山峡谷区等山区坡耕地合理利用与科学整治提供支撑。 展开更多
关键词 坡耕地 空间分布 驱动因素 实际坡度算法 地理探测器 西南高山峡谷区
暂未订购 下载PDF
深度学习重建算法在超高分辨力颅脑CT中的图像质量改善与剂量降低研究 认领 引用
20
作者 杨佳硕 程雨荷 +2 位作者 马梓轩 刘丹丹 张永县 《CT理论与应用研究（中英文）》 2026年第1期74-79,共6页
目的:本研究旨在探讨超高分辨力探测器CT联合深度学习重建算法对颅脑CT图像质量的影响及剂量降低潜力。方法:采用NeuViz Epoch Elite CT机,对Catphan 600模体(设置容积CT剂量指数(CTDIvol)为50、37.5和25 mGy)及3只猕猴(CTDIvol为50 mGy... 目的:本研究旨在探讨超高分辨力探测器CT联合深度学习重建算法对颅脑CT图像质量的影响及剂量降低潜力。方法:采用NeuViz Epoch Elite CT机,对Catphan 600模体(设置容积CT剂量指数(CTDIvol)为50、37.5和25 mGy)及3只猕猴(CTDIvol为50 mGy)进行扫描,准直宽度为128×0.3125 mm,分别采用滤波反投影(FBP)、自适应迭代重建算法(如ClearView,CV30%、CV60%)及深度学习重建算法(如ClearInfinity,CI30%、CI60%)获取图像。通过调制传递函数(MTF)、对比噪声比(CNR)、伪影程度等客观指标及双盲法主观评分(5分制)评估图像质量,并进行统计学分析。结果:模体实验:所有剂量下,CNR随重建算法等级提升而显著提高,其中CI60%图像的CNR显著优于其他算法;25 mGy下CI60%的CNR与50 mGy下FBP接近,且MTF10%与MTF50%无显著下降。动物实验中,CI60%图像中的半卵圆层面的CNR显著高于其他算法,伪影随迭代等级升高呈降低趋势。两名医师对图像质量评价一致性好(Kappa值均≥0.75);主观评分整体随CV/CI等级的提高而提高,且均为CI60%最高。结论:超高分辨力探测器CT下深度学习重建算法可在不降低高对比分辨力的前提下,提升颅脑CT图像的对比度、减少噪声与伪影,具有显著的剂量降低潜力,临床应用价值良好。 展开更多
关键词 深度学习重建算法 超高分辨力探测器CT 颅脑CT
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 23 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈