检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Junkun Hong Yitian Long Yueyi Luo Liujie Hua Jun Long Qianqian Qi School of Computer Science and Engineering Central South University Changsha China Data Science Institute Vanderbilt University Nashville Tennessee United States School of Mathematics and Statistics Central South University Changsha China Big Data Institution Central South University Changsha China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The past few years have witnessed the immense development of small object detection, which is aimed at detecting size-limited targets in high-resolution images. The prevailing methods focus on extracting fine-grained information by expanding the receptive fields and then generating the potential small object region. However, these solutions inevitably add sophisticated detectors and extra learning components, which incur time-consuming and computation-costing. Meanwhile, we observe that it’s suboptimal to extract fine features in such a generic way. To alleviate the issues, we propose a multi-branch small object detection framework with a regular-scale detection branch and a small-scale detection branch. Specifically, we design and pre-train a reinforcement learning agent to control feature extractors in both branches according to the results of small object areas. Moreover, we present a region clipping algorithm to rebuild the small object to regular size, which can be input into a mature detector directly. The extensive experiments on COCO, VisDrone, SODA-D, and our collecting TVDS datasets demonstrate our method outperforms the state-of-the-art methods in several metrics.

关键词： Measurement Pipelines signal processing algorithms Object detection Reinforcement learning Detectors signal processing Feature extraction data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

A small Target Detection Method in Sea Clutter Based on Feature Manifold

A Small Target Detection Method in Sea Clutter Based on Feat...

引用

signal, Information and data processing (ICSIDP), IEEE International Conference on

作者： Jian Guan Xingyu Jiang Baoxin Chen Hao Ding Yunlong Dong Ningbo Liu Information Fusion Institute Naval Aviation University Yantai China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Target detection methods based on multidimensional features are often applied to the detection of small targets in sea clutter. However, existing algorithms do not fully utilize the correlation information between features, which to some extent limits their performance. To address this issue, this paper proposes a small target detection method in sea clutter using feature manifolds. By establishing a high-dimensional manifold representation of radar echo feature data, the radar target detection problem is transformed into a discrimination problem between two geometric points on a feature matrix manifold. This method integrates the use of multidimensional features and their correlation information, thereby effectively improving target detection performance. Experimental results on the SDRDSP dataset demonstrate that the proposed detection approach outperforms existing feature-based methods in terms of detection accuracy.

关键词： Manifolds Correlation Radar clutter Radar detection Object detection Feature extraction data processing Radar signal processing Clutter Testing

来源：评论

学校读者我要写书评

暂无评论

A multi-layer simulation technique for modeling large and small-scale scattering in radar sounder data 28

A multi-layer simulation technique for modeling large and sm...

引用

Conference on Image and signal processing for Remote Sensing XXVIII

作者： Cortellazzi, Marco Thakur, Sanchari Sbalchiero, Elisa Bruzzone, Lorenzo Univ Trento Dept Informat Engn & Comp Sci Sommarive 5 I-38123 Trento Italy

ISBN: (纸本)9781510655386;9781510655379

Radar sounders (RS) provide information on subsurface targets for planetary investigations. Several simulation techniques have been developed to support the RS design and the data interpretation. Each technique has different properties and modeling capabilities, achieving different trade-offs between accuracy and computational requirements. The state-of-the-art RS simulation techniques include: i) numerical methods, such as the Finite-Difference Time-Domain (FDTD) technique, which allows the modelling of small-scale scattering phenomena at the cost of high computational requirements;ii) facet modeling and ray-tracing based methods, such as the multi-layered coherent RS (MCS) technique, which requires less computational resources than FDTD, allowing the modeling of large-scale scattering phenomena. Recently an integrated simulation methodology has been presented, for simulating small-scale scattering phenomena in large scenarios. However, this methodology was designed for modeling only surface scattering. In this paper, we propose a method that extends the capabilities of the integrated methodology to model both large and small-scale roughness in a multi-layer scenario. The proposed method uses the FDTD technique to evaluate the effects associated with small-scale roughness in terms of i) scattering phenomena associated with the layers and ii) power losses associated with the signal transmitted through a rough layer. To recursively apply scattering and transmission to multiple layers of the subsurface, a coherent ray-tracing method is used. We experimentally assessed the effectiveness of the proposed methodology on three-layer models by integrating the effect of roughness imposed on the layers and in transmission through them.

关键词： Radar sounder planetary exploration simulations FDTD ray-tracing coherent simulator RIME SRS

来源：评论

学校读者我要写书评

暂无评论

Subspace Projection Algorithm based on Code Agile Waveform for Folded Clutter Suppression

Subspace Projection Algorithm based on Code Agile Waveform f...

引用

signal, Information and data processing (ICSIDP), IEEE International Conference on

作者： Zihao Liu Huayu Fan Zhaopeng Cao Lixiang Ren Quanhua Liu Erke Mao Radar Research Lab Beijing Institute of Technology Beijing China Key Laboratory of Electronic and Information Technology in Satellite Navigation Beijing Institute of Technology Beijing China Yangtze Delta Region Academy of Beijing Institute of Technology Beijing China Chongqing Innovation Center of Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

The Internal Clutter Motion (ICM) results in an expansion of the clutter Doppler spectrum. With conventional waveforms, the presence of range ambiguity causes short-range strong clutter with ICM to be folded into the long-range interval. The folded clutter, along with Doppler expansion, submerges low-speed small targets, significantly affecting the target detection performance of ground-based early warning radar. Agile waveforms improve the distinguishability of echoes from different range intervals by varying the waveform parameters between pulses, enhancing the degree of signal processing. Therefore, this paper proposes a subspace projection algorithm based on code agile waveform to suppress the folded clutter with ICM. First, the clutter subspace is constructed using the echo model of the code agile waveform and the distribution characteristics of clutter in the range-Doppler domain. Next, subspace projection is applied to each range interval, with iterative processing between intervals to achieve folded clutter suppression. Finally, the joint mismatch filtering and Pulse Doppler (PD) processing is performed to realize coherent accumulation in each range interval. The simulations and processing results of real measured data demonstrate the effectiveness of the proposed algorithm in suppressing folded clutter and improving the detection performance of small targets at long-ranges and low-speeds.

关键词： Codes Filtering Radar clutter signal processing algorithms Radar detection signal processing data models Doppler effect Clutter Projection algorithms

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Low signal-to-Noise-Ratio Target Detection Enhancement

引用

SENSORS 2023年第6期23卷 3314页

作者： Ma, Tian J. Anderson, Robert J. Sandia Natl Labs POB 5800 Albuquerque NM 87185 USA

In real-time remote sensing application, frames of data are continuously flowing into the processing system. The capability of detecting objects of interest and tracking them as they move is crucial to many critical surveillance and monitoring missions. Detecting small objects using remote sensors is an ongoing, challenging problem. Since object(s) are located far away from the sensor, the target's signal-to-Noise-Ratio (SNR) is low. The Limit of Detection (LOD) for remote sensors is bounded by what is observable on each image frame. In this paper, we present a new method, a "Multi-frame Moving Object Detection System (MMODS)", to detect small, low SNR objects that are beyond what a human can observe in a single video frame. This is demonstrated by using simulated data where our technology-detected objects are as small as one pixel with a targeted SNR, close to 1:1. We also demonstrate a similar improvement using live data collected with a remote camera. The MMODS technology fills a major technology gap in remote sensing surveillance applications for small target detection. Our method does not require prior knowledge about the environment, pre-labeled targets, or training data to effectively detect and track slow- and fast-moving targets, regardless of the size or the distance.

关键词： remote sensing remote sensing detection target detection low SNR target detection low signal-to-noise ratio target detection low SNR target tracking low signal-to-noise-ratio target tracking multi-frame moving object detection system MMODS

来源：评论

学校读者我要写书评

暂无评论

Localized Target Detection Algorithms in Low Illumination Wide-Field of View High-Resolution Environments 24

Localized Target Detection Algorithms in Low Illumination Wi...

引用

4th International Conference on Artificial Intelligence, Big data and Algorithms, CAIBDA 2024

作者： Xie, Chengyou Huang, Xiaohui Jia, Zhenhong Song, Sensen Wang, Jiajia Zhou, Gang Shi, Fei Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi Xinjiang China

ISBN: (纸本)9798400710247

To solve the problem of difficult detection of small targets in wide-field videos captured by eagle-eye equipment in low-illumination environments. we propose a local moving target detection algorithm based on sample consistency. First, the initial background model is established using the first ten frames of the video. The contrast and texture features between the current and background frames are calculated, and the S component in the HSV space is extracted and fused to obtain the final features. Finally, The target area is located through the global segmentation map and the local tracking detection module is activated. Experimental results demonstrate that Compared to other algorithms, the proposed algorithm reduces the running time by implementing local detection. It effectively minimizes the interference caused by light sources and dark spot noise in low-light environments, thereby enhancing the accuracy of the algorithm. © 2024 Copyright held by the owner/author(s).

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Infrared small target detection based on long-short term frame difference algorithm(LSTFD)

Infrared small target detection based on long-short term fra...

引用

Intelligent Control, Measurement and signal processing and Intelligent Oil Field (ICMSP), International Conference on

作者： Bing Zhu Jiahui Shi Ruixing Yu Weixin Gao Siyu Wang School of Electronic Engineering Xi'an Shiyou University Xi'an China School of Astronautics Northwestern Polytechnical University Xi'an China

ISBN: (数字)9798331516550

ISBN: (纸本)9798331516567

According to the characteristic that the position change of small infrared target in sequence images is more obvious than background and noise, an infrared small target detection algorithm based on multi-frame time domain information is proposed, called the Long-Short Term Frame Difference (LSTFD) algorithm. The algorithm first adopts the SURF (Speeded Up Robust Feature) alignment strategy to eliminate the relative motion of background pixels caused by camera shake and achieve global motion compensation. Then, the image sequence is constructed based on the current frame, and the computational results of long-interval difference and short-interval difference are combined to detect the infrared small targets. The experimental results show that the LSTFD algorithm can accurately detect moving targets with high detection accuracy and low false alarm rate under the condition of low signal-to-noise ratio. And the average detection rate can reach over 90% on five sets of experimental data.

关键词： Accuracy signal processing algorithms Object detection Cameras Motion compensation Trajectory Image sequences Motion measurement Time-domain analysis signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Underwater Multiple targets Tracking Using Multi-Bernoulli Filter and Improved data Association

Underwater Multiple Targets Tracking Using Multi-Bernoulli F...

引用

IEEE International Conference on Information Communication and signal processing (ICICSP)

作者： Jiawei Gou Xionghou Liu Yixin Yang Chao Sun Ruijie Zhang Qifeng Bao Shaanxi Key Laboratory of Underwater Information Technology School of Marine Science and Technology Northwestern Polytechnical University Shaanxi Xian China

ISBN: (数字)9798350355895

ISBN: (纸本)9798350355901

Traditional multi-target tracking methods using Random Finite Set (RFS) theory mainly generate trajectories by using label RFS or performing data association after RFS filtering. For the case of target trajectories intersect, the too small distance between adjacent targets (i.e. targets are in close proximity) can cause label confusion or association errors, making it challenging for these methods to generate accurate trajectories. To solve this problem, we propose a target tracking method that integrates the multi-target multi-Bernoulli (MeMBer) filter and the improved data association. The MeMBer filter is used to obtain the target state estimations before data association. To avoid association errors when targets are in close proximity, we make the following improvements based on the nearest-neighbor data association method. When multiple targets are far from each other, we directly use the existing nearest-neighbor method to generate trajectories; when multiple targets are in close proximity, we treat the trajectory predictions of the last time step as the current trajectories, therefore avoiding data association errors. The simulation results demonstrate that the proposed method effectively solves the problem of inaccurate trajectory estimation during the intersection of target trajectories.

关键词： Radio frequency Target tracking Monte Carlo methods Simulation signal processing Information filters Filtering theory Trajectory State estimation Clutter

来源：评论

学校读者我要写书评

暂无评论

Learning DCT Subband using Kolmogorov-Arnold Network for Infrared small Target Detection

Learning DCT Subband using Kolmogorov-Arnold Network for Inf...

引用

signal, Information and data processing (ICSIDP), IEEE International Conference on

作者： Zekai Zhang Yingrui Zhao Shichao Zhou Zihui Yang School of Information and Communication Engineering Beijing Information Science and Technology University Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Deep learning-based infrared small target detection (IRSTD) methods typically exploit spatial domain cues to infer dim and weak infrared targets. However, relying solely on spatial domain information is sub-optimal due to the lack of structure and texture details of the target. Alternatively, we learn frequency priors to enhance targets in frequency domain, and propose a Frequency Domain Enhanced Network (FDENet). It contains a frequency domain discrete cosine transform enhancement (FDE) module with KAN-inspired DCT learning mechanism. Specifically, the FDE module uses multiple univariate nonlinear functions to combine continuous multivariate functions to directly map frequency-aware cues without spatial features. It then aligns the frequency-aware cues and with the spatial features to capture dimly weak targets. Generalization experiments and comparative studies on two real-world infrared single-frame image datasets fully demonstrate the effectiveness of our method.

关键词： Learning systems Frequency-domain analysis Object detection Feature extraction data processing Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Research on data processing method for detection of small and weak targets in space

Research on data processing method for detection of small an...

引用

Conference on AOPC - Optical Sensing, Imaging, and Display Technology

作者： Sen, Tian Yan, Wen Chinese Acad Sci Xian Inst Opt & Precis Mech Xian Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9781510661905;9781510661912

Space debris identification and localization has been studied for a long time at home and abroad, but there are still shortcomings in the detection of very low SNR small targets, especially the detection and recognition of very low SNR faint small targets submerged in the dense galactic background Stars in order to effectively target detection, background removal is essential, in order to distinguish between the target and the stars, through the accumulation of judgement block number of star closely adjacent to judge, if the judgment of the block, star closely adjacent number more than set threshold, so that the point for stars, on the other hand, argue that point as the goal to be detected, then, to the star point of the block The results of the algorithm show that, according to different star map images, the size of matrix block and the threshold of star point can be modified to achieve better star removal effect.

关键词： the Milky Way's background low signal to noise ratio target detection multiframe superposition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：