期刊文献+
共找到498篇文章
< 1 2 25 >
每页显示 20 50 100
Improved Weighted Local Contrast Method for Infrared Small Target Detection
1
作者 Pengge Ma Jiangnan Wang +3 位作者 Dongdong Pang Tao Shan Junling Sun Qiuchun Jin 《Journal of Beijing Institute of Technology》 EI CAS 2024年第1期19-27,共9页
In order to address the problem of high false alarm rate and low probabilities of infrared small target detection in complex low-altitude background,an infrared small target detection method based on improved weighted... In order to address the problem of high false alarm rate and low probabilities of infrared small target detection in complex low-altitude background,an infrared small target detection method based on improved weighted local contrast is proposed in this paper.First,the ratio information between the target and local background is utilized as an enhancement factor.The local contrast is calculated by incorporating the heterogeneity between the target and local background.Then,a local product weighted method is designed based on the spatial dissimilarity between target and background to further enhance target while suppressing background.Finally,the location of target is obtained by adaptive threshold segmentation.As experimental results demonstrate,the method shows superior performance in several evaluation metrics compared with six existing algorithms on different datasets containing targets such as unmanned aerial vehicles(UAV). 展开更多
关键词 infrared small target unmanned aerial vehicles(UAV) local contrast target detection
下载PDF
Infrared Small Target Detection Algorithm Based on ISTD-CenterNet
2
作者 Ning Li Shucai Huang Daozhi Wei 《Computers, Materials & Continua》 SCIE EI 2023年第12期3511-3531,共21页
This paper proposes a real-time detection method to improve the Infrared small target detection CenterNet(ISTD-CenterNet)network for detecting small infrared targets in complex environments.The method eliminates the n... This paper proposes a real-time detection method to improve the Infrared small target detection CenterNet(ISTD-CenterNet)network for detecting small infrared targets in complex environments.The method eliminates the need for an anchor frame,addressing the issues of low accuracy and slow speed.HRNet is used as the framework for feature extraction,and an ECBAM attention module is added to each stage branch for intelligent identification of the positions of small targets and significant objects.A scale enhancement module is also added to obtain a high-level semantic representation and fine-resolution prediction map for the entire infrared image.Besides,an improved sensory field enhancement module is designed to leverage semantic information in low-resolution feature maps,and a convolutional attention mechanism module is used to increase network stability and convergence speed.Comparison experiments conducted on the infrared small target data set ESIRST.The experiments show that compared to the benchmark network CenterNet-HRNet,the proposed ISTD-CenterNet improves the recall by 22.85%and the detection accuracy by 13.36%.Compared to the state-of-the-art YOLOv5small,the ISTD-CenterNet recall is improved by 5.88%,the detection precision is improved by 2.33%,and the detection frame rate is 48.94 frames/sec,which realizes the accurate real-time detection of small infrared targets. 展开更多
关键词 infrared small target detection CenterNet data enhancement feature enhancement attention mechanism
下载PDF
CAFUNeT:A small infrared target detection method in complex backgrounds
3
作者 孙海蓉 康莉 HUANG Jianjun 《中国体视学与图像分析》 2023年第4期332-348,共17页
Small infrared target detection has widespread applications in various fields including military,aviation,and medicine.However,detecting small infrared targets in complex backgrounds remains challenging.To detect smal... Small infrared target detection has widespread applications in various fields including military,aviation,and medicine.However,detecting small infrared targets in complex backgrounds remains challenging.To detect small infrared targets,we propose a variable-structure U-shaped network referred as CAFUNet.A central differential convolution-based encoder,ASPP,an Attention Fusion module,and a decoder module are the critical components of the CAFUNet.The encoder module based on central difference convolution effectively extracts shallow detail information from infrared images,complemented by rich contextual information obtained from the deep features in the decoder module.However,the direct fusion of the shallow detail features with semantic features may lead to feature mismatch.To address this,we incorporate an Attention Fusion(AF)module to enhance the network performance further.We performed ablation studies on each module to evaluate its effectiveness.The results show that our proposed algorithm outperforms the state-of-the-art methods on publicly available datasets. 展开更多
关键词 small infrared target detection central difference convolution ASPP AF
下载PDF
Novel detection method for infrared small targets using weighted information entropy 被引量:13
4
作者 Xiujie Qu He Chen Guihua Peng 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2012年第6期838-842,共5页
This paper presents a method for detecting the small infrared target under complex background. An algorithm, named local mutation weighted information entropy (LMWIE), is proposed to suppress background. Then, the g... This paper presents a method for detecting the small infrared target under complex background. An algorithm, named local mutation weighted information entropy (LMWIE), is proposed to suppress background. Then, the grey value of targets is enhanced by calculating the local energy. Image segmentation based on the adaptive threshold is used to solve the problems that the grey value of noise is enhanced with the grey value improvement of targets. Experimental results show that compared with the adaptive Butterworth high-pass filter method, the proposed algorithm is more effective and faster for the infrared small target detection. 展开更多
关键词 infrared small target detection local mutation weight-ed information entropy (LMWIE) grey value of target adaptivethreshold.
下载PDF
Dim Moving Small Target Detection by Local and Global Variance Filtering on Temporal Profiles in Infrared Sequences
5
作者 Chen Hao Liu Delian 《航空兵器》 CSCD 北大核心 2019年第6期43-49,共7页
In this paper, the temporal different characteristics between the target and background pixels are used to detect dim moving targets in the slow-evolving complex background. A local and global variance filter on tempo... In this paper, the temporal different characteristics between the target and background pixels are used to detect dim moving targets in the slow-evolving complex background. A local and global variance filter on temporal profiles is presented that addresses the temporal characteristics of the target and background pixels to eliminate the large variation of background temporal profiles. Firstly, the temporal behaviors of different types of image pixels of practical infrared scenes are analyzed.Then, the new local and global variance filter is proposed. The baseline of the fluctuation level of background temporal profiles is obtained by using the local and global variance filter. The height of the target pulse signal is extracted by subtracting the baseline from the original temporal profiles. Finally, a new target detection criterion is designed. The proposed method is applied to detect dim and small targets in practical infrared sequence images. The experimental results show that the proposed algorithm has good detection performance for dim moving small targets in the complex background. 展开更多
关键词 small target detection infrared image sequences complex background temporal profile variance filtering
下载PDF
Infrared Image Small Target Detection Based on Bi-orthogonal Wavelet and Morphology
6
作者 迟健男 张朝晖 +1 位作者 王东署 郝彦爽 《Defence Technology(防务技术)》 SCIE EI CAS 2007年第3期203-208,共6页
An image multi-scale edge detection method based on anti-symmetrical bi-orthogonal wavelet is given in theory. Convolution operation property and function as a differential operator are analyzed,which anti-symmetrical... An image multi-scale edge detection method based on anti-symmetrical bi-orthogonal wavelet is given in theory. Convolution operation property and function as a differential operator are analyzed,which anti-symmetrical bi-orthogonal wavelet transform have. An algorithm for wavelet reconstruction in which multi-scale edge can be detected is put forward. Based on it, a detection method for small target in infrared image with sea or sky background based on the anti-symmetrical bi-orthogonal wavelet and morphology is proposed. The small target detection is considered as a process in which structural background is removed, correlative background is suppressed, and noise is restrained. In this approach, the multi-scale edge is extracted by means of the anti-symmetrical bi-orthogonal wavelet decomposition. Then, module maximum chains formed by complicated background of clouds, sea wave and sea-sky-line are removed, and the image background becomes smoother. Finally, the morphology based edge detection method is used to get small target and restrain undulate background and noise. Experiment results show that the approach can suppress clutter background and detect the small target effectively. 展开更多
关键词 控制导航系统 航天器 边缘方向 红外线图像 小目标探测
下载PDF
Using deep learning to detect small targets in infrared oversampling images 被引量:15
7
作者 LIN Liangkui WANG Shaoyou TANG Zhongxing 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2018年第5期947-952,共6页
According to the oversampling imaging characteristics, an infrared small target detection method based on deep learning is proposed. A 7-layer deep convolutional neural network(CNN) is designed to automatically extrac... According to the oversampling imaging characteristics, an infrared small target detection method based on deep learning is proposed. A 7-layer deep convolutional neural network(CNN) is designed to automatically extract small target features and suppress clutters in an end-to-end manner. The input of CNN is an original oversampling image while the output is a cluttersuppressed feature map. The CNN contains only convolution and non-linear operations, and the resolution of the output feature map is the same as that of the input image. The L1-norm loss function is used, and a mass of training data is generated to train the network effectively. Results show that compared with several baseline methods, the proposed method improves the signal clutter ratio gain and background suppression factor by 3–4 orders of magnitude, and has more powerful target detection performance. 展开更多
关键词 infrared small target detection OVERSAMPLING deep learning convolutional neural network(CNN)
下载PDF
Small tracking error correction for moving targets of intelligent electro-optical detection systems
8
作者 Cheng SHEN Zhijie WEN +2 位作者 Wenliang ZHU Dapeng FAN Mingyuan LING 《Frontiers of Mechanical Engineering》 SCIE CSCD 2024年第2期29-44,共16页
Small tracking error correction for electro-optical systems is essential to improve the tracking precision of future mechanical and defense technology.Aerial threats,such as“low,slow,and small(LSS)”moving targets,po... Small tracking error correction for electro-optical systems is essential to improve the tracking precision of future mechanical and defense technology.Aerial threats,such as“low,slow,and small(LSS)”moving targets,pose increasing challenges to society.The core goal of this work is to address the issues,such as small tracking error correction and aiming control,of electro-optical detection systems by using mechatronics drive modeling,composite velocity–image stability control,and improved interpolation filter design.A tracking controller delay prediction method for moving targets is proposed based on the Euler transformation model of a two-axis,two-gimbal cantilever beam coaxial configuration.Small tracking error formation is analyzed in detail to reveal the scientific mechanism of composite control between the tracking controller’s feedback and the motor’s velocity–stability loop.An improved segmental interpolation filtering algorithm is established by combining line of sight(LOS)position correction and multivariable typical tracking fault diagnosis.Then,a platform with 2 degrees of freedom is used to test the system.An LSS moving target shooting object with a tracking distance of S=100 m,target board area of A=1 m^(2),and target linear velocity of v=5 m/s is simulated.Results show that the optimal method’s distribution probability of the tracking error in a circle with a radius of 1 mrad is 66.7%,and that of the traditional method is 41.6%.Compared with the LOS shooting accuracy of the traditional method,the LOS shooting accuracy of the optimized method is improved by 37.6%. 展开更多
关键词 electro-optical detection system small tracking error moving target visual servo aiming contro
原文传递
A Novel Filtering-Based Detection Method for Small Targets in Infrared Images
9
作者 Sanxia Shi Yinglei Song 《Computers, Materials & Continua》 SCIE EI 2024年第11期2911-2934,共24页
Infrared small target detection technology plays a pivotal role in critical military applications,including early warning systems and precision guidance for missiles and other defense mechanisms.Nevertheless,existing ... Infrared small target detection technology plays a pivotal role in critical military applications,including early warning systems and precision guidance for missiles and other defense mechanisms.Nevertheless,existing traditional methods face several significant challenges,including low background suppression ability,low detection rates,and high false alarm rates when identifying infrared small targets in complex environments.This paper proposes a novel infrared small target detection method based on a transformed Gaussian filter kernel and clustering approach.The method provides improved background suppression and detection accuracy compared to traditional techniques while maintaining simplicity and lower computational costs.In the first step,the infrared image is filtered by a new filter kernel and the results of filtering are normalized.In the second step,an adaptive thresholding method is utilized to determine the pixels in small targets.In the final step,a fuzzy C-mean clustering algorithm is employed to group pixels in the same target,thus yielding the detection results.The results obtained from various real infrared image datasets demonstrate the superiority of the proposed method over traditional approaches.Compared with the traditional method of state of the arts detection method,the detection accuracy of the four sequences is increased by 2.06%,0.95%,1.03%,and 1.01%,respectively,and the false alarm rate is reduced,thus providing a more effective and robust solution. 展开更多
关键词 Gaussian filtering infrared small target detection fuzzy C-means clustering robustness
下载PDF
Multi-Channel Based on Attention Network for Infrared Small Target Detection
10
作者 张彦军 王碧云 蔡云泽 《Journal of Shanghai Jiaotong university(Science)》 EI 2024年第3期414-427,共14页
Infrared detection technology has the advantages of all-weather detection and good concealment,which is widely used in long-distance target detection and tracking systems.However,the complex background,the strong nois... Infrared detection technology has the advantages of all-weather detection and good concealment,which is widely used in long-distance target detection and tracking systems.However,the complex background,the strong noise,and the characteristics of small scale and weak intensity of targets bring great difficulties to the detection of infrared small targets.A multi-channel based on attention network is proposed in this paper,aimed at the problem of high missed detection rate and false alarm rate of traditional algorithms and the problem of large model,high complexity and poor detection performance of deep learning algorithms.First,given the difficulty in extracting the features of infrared multiscale and small dim targets,the multiple channels are designed based on dilated convolution to capture multiscale target features.Second,the coordinate attention block is incorporated in each channel to suppress background clutters adaptively and enhance target features.In addition,the fusion of shallow detail features and deep abstract semantic features is realized by synthesizing the contextual attention fusion block.Finally,it is verified that,compared with other state-of-the-art methods based on the datasets SIRST and MDFA,the proposed algorithm further improves the detection effect,and the model size and computational complexity are smaller. 展开更多
关键词 infrared image small target detection deep learning attention mechanism feature fusion
原文传递
基于YOLOv5s的改进实时红外小目标检测 被引量:1
11
作者 谷雨 张宏宇 彭冬亮 《激光与红外》 CAS CSCD 北大核心 2024年第2期281-288,共8页
针对红外图像分辨率低、背景复杂、目标细节特征缺失等问题,提出了一种基于YOLOv5s的改进实时红外小目标检测模型Infrared-YOLOv5s。在特征提取阶段,采用SPD-Conv进行下采样,将特征图切分为特征子图并按通道拼接,避免了多尺度特征提取... 针对红外图像分辨率低、背景复杂、目标细节特征缺失等问题,提出了一种基于YOLOv5s的改进实时红外小目标检测模型Infrared-YOLOv5s。在特征提取阶段,采用SPD-Conv进行下采样,将特征图切分为特征子图并按通道拼接,避免了多尺度特征提取过程中下采样导致的特征丢失情况,设计了一种基于空洞卷积的改进空间金字塔池化模块,通过对具有不同感受野的特征进行融合来提高特征提取能力;在特征融合阶段,引入由深到浅的注意力模块,将深层特征语义特征嵌入到浅层空间特征中,增强浅层特征的表达能力;在预测阶段,裁减了网络中针对大目标检测的特征提取层、融合层及预测层,降低模型大小的同时提高了实时性。首先通过消融实验验证了提出各模块的有效性,实验结果表明,改进模型在SIRST数据集上平均精度均值达到了95.4%,较原始YOLOv5s提高了2.3%,且模型大小降低了72.9%,仅为4.5 M,在Nvidia Xavier上推理速度达到28 f/s,利于实际的部署和应用。在Infrared-PV数据集上的迁移实验进一步验证了改进算法的有效性。提出的改进模型在提高红外图像小目标检测性能的同时,能够满足实时性要求,因而适用于红外图像小目标实时检测任务。 展开更多
关键词 红外小目标检测 YOLOv5s 注意力机制 特征融合
下载PDF
基于跨越连接与融合注意力机制的红外弱小目标检测方法
12
作者 李慧 李正周 +2 位作者 杨雨昕 郝聪宇 刘海涛 《光子学报》 EI CAS CSCD 北大核心 2024年第9期218-229,共12页
针对复杂背景红外小弱目标信号弱、特征不明显、干扰虚警多等检测性能低问题,提出基于跨越连接与融合注意力机制的单阶段红外弱小目标检测算法。该方法融合注意力机制与残差网络提取小目标多特征,减少复杂背景干扰;双向跨越连接结构融... 针对复杂背景红外小弱目标信号弱、特征不明显、干扰虚警多等检测性能低问题,提出基于跨越连接与融合注意力机制的单阶段红外弱小目标检测算法。该方法融合注意力机制与残差网络提取小目标多特征,减少复杂背景干扰;双向跨越连接结构融合低层与高层各自的特征信息,凸显小弱目标特征表达能力;增加一个高分辨率检测层,重新聚类弱小目标先验框,增强目标与背景的特征差别学习能力;最后,建立真实目标和预测目标框的高斯分布模型,计算两者相似性,解决因IoU度量造成的目标损失回归偏差敏感问题,提升损失回归准确性。在公开红外小目标数据集上进行对比测试,实验结果表明该算法对多种复杂背景下红外小弱目标检测均取得了最佳性能,在平均精度和速度等方面都得到显著提升,模型最小,方便部署。 展开更多
关键词 红外小目标 目标检测 跨越连接 注意力机制 多尺度融合
下载PDF
HRformer:基于多级回归Transformer网络的红外小目标检测
13
作者 杜妮妮 单凯东 王建超 《红外技术》 CSCD 北大核心 2024年第2期199-207,共9页
红外小目标检测是指从低信噪比、复杂背景的红外图像中对小目标进行检测,在海上救援、交通管理等应用中具有重要实际意义。然而,由于图像分辨率低、目标尺寸小以及特征不突出等因素,导致红外目标很容易淹没在包含噪声和杂波的背景中,如... 红外小目标检测是指从低信噪比、复杂背景的红外图像中对小目标进行检测,在海上救援、交通管理等应用中具有重要实际意义。然而,由于图像分辨率低、目标尺寸小以及特征不突出等因素,导致红外目标很容易淹没在包含噪声和杂波的背景中,如何精确检测红外小目标的外形信息仍然是一个挑战。针对上述问题,构建了一种基于多级回归Transformer(HRformer)网络的红外小目标检测算法。具体来说,首先为了在获得多尺度信息的同时尽可能避免原始图像信息的损失,采用像素逆重组(PixelUnShuffle)操作对原始图像下采样来获取不同层级网络的输入,同时采用一种可学习的像素重组(PixelShuffle)操作对每一层级的输出特征图进行上采样,提升了网络的灵活性;接着,为实现网络中不同层级特征之间的信息交互,本文设计了一种包含空间注意力计算分支以及通道注意力计算分支在内的交叉注意力融合(cross attention fusion,CAF)模块实现特征高效融合以及信息互补;最后,为进一步提升网络的检测性能,结合普通Transformer结构具有较大感受野以及基于窗口的Transformer结构具有较少计算复杂度的优势,提出了一种局部-全局Transformer(LGT)结构,能够在提取局部上下文信息的同时对全局依赖关系进行建模,计算成本也得到节省。实验结果表明,与目前较为先进的一些红外小目标检测算法相比,本文所提出的算法具有更高的检测精度,同时具有较少的参数量,在解决实际问题中更有意义。 展开更多
关键词 红外图像 弱小目标检测 TRANSFORMER 图像分割
下载PDF
多尺度注意力特征增强融合的红外小目标检测新网络
14
作者 贾桂敏 程羽 齐孟飞 《中国安全科学学报》 CAS CSCD 北大核心 2024年第6期90-98,共9页
为提高红外成像中小目标检测的性能,提高低空空域监管能力,提出一种基于多尺度注意力特征增强融合的红外小目标检测新网络。首先,使用Resnet34提取红外图像的多尺度特征;其次,使用多尺度空间注意力特征增强模块(MFEM)来提高特征提取能力... 为提高红外成像中小目标检测的性能,提高低空空域监管能力,提出一种基于多尺度注意力特征增强融合的红外小目标检测新网络。首先,使用Resnet34提取红外图像的多尺度特征;其次,使用多尺度空间注意力特征增强模块(MFEM)来提高特征提取能力;然后,在逐级上采样过程中使用双通道注意力特征融合模块(DFFM),融合语义信息和细节信息,以更好地保护红外小目标的特征;最后,与其他方法对比,并以地/空红外弱小飞机目标视频序列检测为例测试真实场景。结果表明:新方法与现有方法相比,交互比(IoU)、F值和漏检率(FNR)的评分均获得改进;通过多尺度注意力特征增强融合可准确地定位到目标并生成精细的分割结果;MFEM能够同时利用多尺度上下文信息和空间注意力机制来突出红外小目标;DFFM通过给不同通道特征的集合赋予权重,得到最合适的特征图进行特征融合,从而提高检测性能。 展开更多
关键词 红外图像 小目标检测 特征增强 特征融合 注意力机制
下载PDF
基于视觉Transformer和双解码器的红外小目标检测方法
15
作者 代少升 刘科生 +3 位作者 黄炼 贺自强 毛兴华 任汶皓 《红外技术》 CSCD 北大核心 2024年第9期1070-1080,共11页
当前基于卷积神经网络的红外小目标检测方法在编码器阶段受限于感受野,且解码器在多尺度特征融合中缺乏有效的特征交互。本文提出了一种基于编码器-解码器结构的新方法,针对现有红外小目标检测方法中的问题进行改进。该方法使用视觉Tran... 当前基于卷积神经网络的红外小目标检测方法在编码器阶段受限于感受野,且解码器在多尺度特征融合中缺乏有效的特征交互。本文提出了一种基于编码器-解码器结构的新方法,针对现有红外小目标检测方法中的问题进行改进。该方法使用视觉Transformer作为编码器,能够有效地提取红外小目标图像的多尺度特征。视觉Transformer是一种新兴的深度学习架构,其通过自注意力机制捕捉图像中像素之间的全局关系,以处理长程依赖性和上下文信息。此外,本文还设计了一个由交互式解码器和辅助解码器组成的双解码器模块,旨在提高解码器对红外小目标的重构能力。该双解码器模块能够充分利用不同特征之间的互补信息,促进深层特征和浅层特征之间的交互,并通过将两个解码器的结果进行叠加,以更好地重构红外小目标。在广泛使用的公共数据集上的实验结果表明,本文提出的方法在F1和mIoU两个评价指标上的性能优于其他对比方法。 展开更多
关键词 红外小目标检测 视觉Transformer 多尺度特征融合 编解码结构
下载PDF
改进非凸估计与非对称时空正则化的红外小目标检测方法
16
作者 胡亮 杨德贵 +1 位作者 赵党军 张俊超 《国防科技大学学报》 EI CAS CSCD 北大核心 2024年第3期180-194,共15页
针对复杂背景下的红外小目标检测,在非对称时空正则化约束的非凸张量低秩估计算法基础上,提出了一种新的核范数估计方法代替原算法中的估计方法。提出基于结构张量与多结构元顶帽(Top-Hat)滤波的自适应权重张量对目标张量进行约束,增强... 针对复杂背景下的红外小目标检测,在非对称时空正则化约束的非凸张量低秩估计算法基础上,提出了一种新的核范数估计方法代替原算法中的估计方法。提出基于结构张量与多结构元顶帽(Top-Hat)滤波的自适应权重张量对目标张量进行约束,增强目标张量稀疏性的同时抑制其中残存的强边缘结构。实验结果表明,所提改进算法能够更好地消除图像中强边缘结构对检测结果的影响,在保证检测率的情况下,较原算法具有更低的虚警率。 展开更多
关键词 红外小目标检测 张量恢复 张量核范数 多结构元Top-Hat滤波
下载PDF
基于改进顶帽变换的红外弱小目标检测 被引量:1
17
作者 张晶晶 曹思华 +1 位作者 崔文楠 张涛 《电子与信息学报》 EI CAS CSCD 北大核心 2024年第1期267-276,共10页
天空背景下的红外弱小目标检测技术较为成熟,但在近地复杂背景下,红外弱小目标的检测存在准确率不高、虚警目标多、实时性差的问题。针对以上问题,该文提出一种基于改进顶帽变换的红外弱小目标检测算法(OTHOLCM)。该算法采用基于改进顶... 天空背景下的红外弱小目标检测技术较为成熟,但在近地复杂背景下,红外弱小目标的检测存在准确率不高、虚警目标多、实时性差的问题。针对以上问题,该文提出一种基于改进顶帽变换的红外弱小目标检测算法(OTHOLCM)。该算法采用基于改进顶帽变换的图像预处理算法(OTH),通过对不同灰度值的图像采取不同的策略针对性地处理图像,达到目标增强、背景抑制的效果。并在此基础上,采用基于改进多尺度局部对比度的红外弱小目标检测算法(OLCM),通过针对目标尺寸特点进行尺度设计,使得在保证算法实时性的基础上扩大目标尺寸检测范围。实验证明:OTHOLCM算法可以保证实时性并明显提高目标检测准确率、减少虚警目标数量。与3层模板局部差异度量算法(TTLDM)、基于边角感知的时空张量模型(ECASTT)等先进算法相比,OTHOLCM算法可使真阳性率分别提高近79%,61%,假阳性率分别降低近77%,73%,目标检测速度达到每秒25帧。 展开更多
关键词 红外弱小目标 目标检测 顶帽变换 局部对比度 目标增强
下载PDF
一种多深度特征连接的红外弱小目标检测方法 被引量:1
18
作者 王维佳 熊文卓 +3 位作者 朱圣杰 宋策 孙翯 宋玉龙 《计算机科学》 CSCD 北大核心 2024年第1期175-183,共9页
针对红外弱小目标像元数量少、图像背景复杂、检测精度低且耗时较长的问题,文中提出了一种多深度特征连接的红外弱小目标检测模型(MFCNet)。首先,提出了多深度交叉连接主干形式以增加不同层间的特征传递,增强特征提取能力;其次,设计了... 针对红外弱小目标像元数量少、图像背景复杂、检测精度低且耗时较长的问题,文中提出了一种多深度特征连接的红外弱小目标检测模型(MFCNet)。首先,提出了多深度交叉连接主干形式以增加不同层间的特征传递,增强特征提取能力;其次,设计了注意力引导的金字塔结构对深层特征进行目标增强,分离背景与目标;提出非对称融合解码结构加强解码中纹理信息与位置信息保留;最后,引入点回归损失得到中心坐标。所提网络模型在SIRST公开数据集与自建长波红外弱小目标数据集上进行训练并测试,实验结果表明,与现有数据驱动和模型驱动算法相比,所提算法在复杂场景下具有更高的检测精度及更快的速度,模型的平均精度相比次优模型提升了5.41%,检测速度达到100.8 FPS。 展开更多
关键词 红外弱小目标 深度学习 目标检测 特征连接 注意力机制
下载PDF
基于孪生网络和Transformer的红外弱小目标跟踪方法 被引量:1
19
作者 崔晨辉 蔺素珍 +2 位作者 李大威 禄晓飞 武杰 《计算机应用》 CSCD 北大核心 2024年第2期563-571,共9页
针对红外弱小目标跟踪准确性较低这一问题,提出一种基于孪生网络和Transformer的红外弱小目标跟踪方法。首先,构建多特征提取级联模块分别提取红外弱小目标模板帧和搜索帧的深度特征,并将二者分别与其对应的HOG特征进行维度层面的串联;... 针对红外弱小目标跟踪准确性较低这一问题,提出一种基于孪生网络和Transformer的红外弱小目标跟踪方法。首先,构建多特征提取级联模块分别提取红外弱小目标模板帧和搜索帧的深度特征,并将二者分别与其对应的HOG特征进行维度层面的串联;其次,引入多头注意力机制Transformer进行模板特征图和搜索特征图的互相关操作,生成响应图;最后,通过响应图上采样网络和边界框预测网络,获得目标在图像的中心位置和回归边界框,完成对红外弱小目标的跟踪。在包含13655张红外图像数据集上的测试结果表明:与KeepTrack跟踪方法相比,成功率提高5.9个百分点,精确率提高1.8个百分点;与TransT(Transformer Tracking)方法相比,成功率提高14.2个百分点,精确率提高14.6个百分点,证明所提方法对复杂背景下的红外弱小目标跟踪准确性更高。 展开更多
关键词 目标跟踪 红外弱小目标 孪生网络 TRANSFORMER 多特征提取
下载PDF
改进YOLOv7+Bytetrack的小目标检测与追踪 被引量:2
20
作者 聂源 赖惠成 高古学 《计算机工程与应用》 CSCD 北大核心 2024年第12期189-202,共14页
近年来,目标检测技术已经相当成熟,但小目标检测一直是目标检测领域的一大挑战。为了解决这一问题,设计一种名为MFF-YOLOv7的小目标检测算法,该算法旨在提高小目标检测的准确率。设计级联双向特征金字塔KBiFPN,以及联合提出的多级感受... 近年来,目标检测技术已经相当成熟,但小目标检测一直是目标检测领域的一大挑战。为了解决这一问题,设计一种名为MFF-YOLOv7的小目标检测算法,该算法旨在提高小目标检测的准确率。设计级联双向特征金字塔KBiFPN,以及联合提出的多级感受野特征聚合模块MFA,来聚合浅层特征并增强特征的信息表达能力。为了解决小目标漏检问题,设计了新的解耦头和新的注意力机制。新的解耦头对小目标的检测能力更强,新的注意力机制可以重点关注感兴趣的小目标区域。引入了一种新的损失函数ECIOU,旨在加快模型的收敛速度。为了验证模型的性能,分别在三个小目标数据集上进行了实验。实验结果表明,MFF-YOLOv7算法提高了检测精度。同时,使用多目标追踪Bytetrack算法在MOT17和VisDrone2019-MOT两个多目标追踪数据集上对新模型进行了验证,进一步证明了其有效性。此外,MFF-YOLOv7算法在动态视频追踪中表现出了良好的性能。 展开更多
关键词 MFF-YOLOv7 小目标检测 多级感受野 多目标追踪 Bytetrack
下载PDF
上一页 1 2 25 下一页 到第
使用帮助 返回顶部