检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2025年第1期10卷 112-129页

作者： Jiang, Bo Li, Hong-Bin Xu, Yue-Lin Ding, Kai Zhao, Xu-Dong Science and Technology on Near-Surface Detection Laboratory Wuxi214035 China Jiangsu Puxu Software Information Technology Co. Ltd Nanjing210001 China

Vehicle sound-based classification is essential for preserving the natural environment and intelligent transportation, helping monitor device operation, maintain environmental safety, and regulate vehicle traffic. Nevertheless, the intricate nature of outdoor situations, combined with elements like wind noise, brings substantial extraneous or disruptive information into the data, which has a detrimental impact on classification performance. To tackle this issue, this study introduces a vehicle classification network called the Time-Frequency Hybrid Attention Mechanism Classification Network(TFANet). Firstly this network is built on the mature ResNet18 architecture and utilizes Mel Frequency Cepstral Coefficients (MFCC) features to analyze sound signals, significantly improving the accuracy and robustness of the classification model. In addition, it designs a time-frequency hybrid attention mechanism to assign more importance to the semantic relevant time frames and key frequency bands within the MFCCs spectrogram, helping to minimize the impact of irrelevant information and ensure the accuracy of vehicle classification. Finally, we collected and organized the Field Vehicle Sound Dataset (FVSD), and conducted relevant experiments on this dataset, demonstrating that the approach achieved an F1 score of 0.950. Meanwhile, additional experiments were performed using the IDMT-Traffic open-access dataset. The TFANet showed an improved F1 score in each category compared to the baseline model of this dataset. Notably, the Truck category, which had the poorest classification performance, significantly improved by 0.16 in the F1 score. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Hybrid vehicles

来源：评论

学校读者我要写书评

暂无评论

An adaptive formation path following flight control method for fixed-wing UAV based on dynamic target point 3

An adaptive formation path following flight control method f...

引用

2024 3rd International Conference on Aerospace and Control Engineering, ICoACE 2024

作者： Yang, Huitao Wen, Qiuqiu Peng, Fei School of Aerospace Engineering Beijing Institute of Technology Beijing100081 China Science and Technology on Near-Surface Detection Laboratory Jiangsu214035 China

Aiming at the shortcomings of the current fixed-wing UAV formation path tracking control method, which is complicated in design, poorly adapted to variable curvature paths, and low in accuracy, this paper proposes an adaptive formation path-following flight control method based on dynamic target points. First, based on the leader-follower architecture, this paper designs a generalized lateral control method for fixed-wing UAVs to realize the tracking of dynamic target points. Then, the leader UAV realizes independent path-following by selecting dynamic target points on the path. At the same time, the follower calculates the target points according to the formation parameters and the leader's state and additionally introduces a target distance control strategy to realize adaptive 2D formation keeping. Finally, mathematical simulations are carried out in this paper for verification. The simulation results show that this method can simultaneously take care of stable formation keeping and accurate path-following for fixed-wing UAV clusters. Compared with the existing methods, it can reduce the design difficulty, significantly improve the accuracy of complex path-following with variable curvature, and has good adaptive characteristics. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Flight paths

来源：评论

学校读者我要写书评

暂无评论

Evaluation of occlusion immunities of free-space orbital angular momentum shift keying

引用

Optics Express 2025年第6期33卷 13494-13505页

作者： Yang, Jinyu Zhang, Shurui Li, Lang Gao, Mingwei Gao, Chunqing Fu, Shiyao School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Key Laboratory of Information Photonics Technology Ministry of Industry and Information Technology of the People’s Republic of China Beijing100081 China Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education of the People’s Republic of China Beijing100081 China National Key Laboratory on Near-Surface Detection Beijing100072 China

Orbital angular momentum (OAM) provides a new high-dimensional degree-of-freedom for lasers enabling high-dimensional shift keying, thus showing huge potential in free-space optical data-transmissions. Ensuring the accuracy of data transmission is of concern in any communication system. However, in the free-space OAM shift keying link, interferences from environmental occlusions will broaden the OAM spectrum and thus affect the correctness of information received. In this paper, the occlusion immunities of two commonly used OAM shift keying strategies—OAM-encoding-symbols and OAM-encoding-bits—are evaluated under different occlusion scenarios. We introduce radial, azimuthal, and random occlusions into the link and then analyze the bit error rate (BER) of various OAM shift keying strategies. The results illustrate that the strategy of OAM-encoding-symbols exhibits stronger occlusion immunity with zero BER than OAM-encoding-bits. Moreover, proof-of-concept experiments are done to transmit grayscale images under occlusions. The final decoding results show identical data-transmission performance with simulations. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Selective formation of generalized optical skyrmions

引用

Optics Letters 2025年第9期50卷 2840-2843页

作者： Zhang, Haojun Gao, Chunqing Fu, Shiyao School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Key Laboratory of Information Photonics Technology Ministry of Industry and Information Technology of the People’s Republic of China Beijing100081 China Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education of the People’s Republic of China Beijing100081 China National Key Laboratory on Near-Surface Detection Beijing100072 China

Optical skyrmions, a type of topologically protected quasiparticle, have undergone various deformations in recent years. In this Letter, we present a scheme that can achieve the selective formation of generalized optical skyrmions. In our proposal, a liquid-crystal spatial light modulator and a variable liquid-crystal retarder, both of which are commonly programmable devices, are employed, allowing for the on-demand precise manipulation of topological textures of various quasiparticles including but not limited to skyrmions, antiskyrmions, and bimerons. The proof-of-concept experiments illustrate that generalized optical skyrmions whose skyrmion number up to 5 can be well generated with on-demand tailored topological textures. While maintaining a simple setup, the system demonstrates a notable capacity for the manipulation of intricate high-order textures, signifying its considerable potential for extensive and sophisticated applications in the generation and manipulation of skyrmions. © 2025 Optica Publishing Group.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Temporal multiplexing coding strategy for spatiotemporal compressed imaging 4

Temporal multiplexing coding strategy for spatiotemporal com...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Hao, Xiaowen Ke, Jun School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Key Laboratory of Photo-electronic Imaging Technology and System Ministry of Education of China Beijing100081 China National Key Laboratory on Near-surface Detection Beijing100072 China

ISBN: (纸本)9781510688834

Spatiotemporal compressed imaging(STCI) aims to improve the spatial and temporal resolution of an imaging system simultaneously, which can effectively alleviate the mutual constraints between the two imaging resolutions. However, the development of STCI is limited by the effectively modulate target scenes in dual-domain, and by the back-end reconstruction process which doesn't work well for high compression ratio(CR). In this paper, we propose a temporal multiplexing coding strategy for STCI, which can effectively help the reconstruction algorithm for a large CR. Simulated experiments are implemented to demonstrate our idea. The proposed method can achieve nice spatiotemporal reconstructions with CR equal to 128:1, in which the spatial CR is 16:1 and the temporal CR is 8:1. © 2025 SPIE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Optimizing object classification with single-pixel imaging and transformer networks 4

Optimizing object classification with single-pixel imaging a...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Cheng, Yin Liao, Yusen Sun, Xin Ke, Jun School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Key Laboratory of Photo-electronic Imaging Technology and System Ministry of Education of China Beijing100081 China National Key Laboratory on Near-surface Detection Beijing100072 China

ISBN: (纸本)9781510688834

Traditional computer vision tasks rely on high-quality images for classification, but single-pixel imaging (SPI) uses compressive sensing with a bucket detector to simplify hardware and reduce costs. However, factors like atmospheric turbulence can degrade SPI image quality, lowering classification accuracy. To address this, a block-based single-pixel image-free transformer classification framework is proposed. It uses a learnable binary sampling matrix for flexible sampling during SPI and divides the measurements into blocks, which are processed by a transformer network. Each block is treated as a sequence element, allowing the transformer to capture spatial and contextual relationships. Experiments show strong robustness to atmospheric turbulence, achieving 87% classification accuracy even at a 1% sampling rate, making this method suitable for challenging environments. © 2025 SPIE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Research on multi-layer lobster eye detection technology 10

Research on multi-layer lobster eye detection technology

引用

10th Symposium on Novel Optoelectronic detection technology and Applications

作者： Ji, Fan Wang, JunYa Chang, Jun Zhang, YunQiang Key Laboratory of Photoelectronic Lmaging Technology and System of Ministry of Education of China School of Optics and Photonics Beijng Institute of Technology Beijng100081 China National Key Laboratory on Near-surface Detection Beijing100072 China National Key Laboratory of Air-based Information Perception and Fusion Luoyang471009 China

ISBN: (数字)9781510688155

ISBN: (纸本)9781510688148

This paper focuses on the imaging technology of multi-layer lobster vision system based on infrared band, aiming to develop a multi-layer lobster eye coordination optical system that can improve the energy concentration. By designing the structure of the lobster eye lens and using the ray tracing software for simulation analysis, the energy concentration of the center of the cross focal spot generated by the lens is analyzed in detail. The optical system of multi-layer lobster eye lens is also designed to achieve the goal of increasing the energy concentration of the system. The whole study not only optimizes the performance of the optical system, but also provides an important theoretical and practical basis for the future application of bionic optical systems. © 2025 SPIE.

关键词： Ray tracing

来源：评论

学校读者我要写书评

暂无评论

Depth map stitching using compound eye cameras for wide FOV imaging 10

Depth map stitching using compound eye cameras for wide FOV ...

引用

10th Symposium on Novel Optoelectronic detection technology and Applications

作者： Qiao, Zhibo Hao, Qun Li, Shibiao Cheng, Yang School of Optics and Photonics Beijing Institute of Technology Beijing100081 China National Key Laboratory on Near-Surface Detection Beijing100072 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314003 China

ISBN: (数字)9781510688155

ISBN: (纸本)9781510688148

Depth information is an important tool in the computer vision field for object detection, recognition, and 3D modeling. Conventional depth sensors have a limited field of view(FOV) and provide limited depth information. Depth map stitching has been proposed to construct a large FOV image by combining depth maps from different perspectives. Due to the sparsity of features and susceptibility to lighting conditions in the depth images, stitching faces a challenge as it often relies on feature matching for obtaining mapping matrices. To overcome this issue, this paper proposes an algorithm that utilizes color image features to guide depth map stitching. Initially, the LightGlue algorithm based on SuperPoint features is employed for precise feature matching to obtain accurate homography matrices. Depth maps are then generated using stereo vision and aligned with color images, effectively transforming the depth map stitching challenge into a color image stitching task. Additionally, we designed a bionic compound eye imaging system that captures images in real time using multiple cameras. This system consists of eight cameras arranged in pairs at specific angles with a circular configuration, achieving an expanded FOV. Experimental results demonstrate that the system effectively captures depth maps with an FOV of 110°×90° and can display real-time video with 8 frames at 640 ×480 resolution. The maximum relative depth error is 5.7% @ 0.55m. In the future, this technology is expected to be applied in panoramic 3D reconstruction, underwater mapping, and autonomous driving. © 2025 SPIE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Optical simulation and imaging performance evaluation on the influencing parameters of the Alvarez lenses 10

Optical simulation and imaging performance evaluation on the...

引用

10th Symposium on Novel Optoelectronic detection technology and Applications

作者： Li, Chaohui Hao, Qun Liu, Lin Cheng, Yang School of Optics and Photonics Beijing Institute of Technology Beijing100081 China National Key Laboratory on Near-Surface Detection Beijing100072 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314003 China

ISBN: (数字)9781510688155

ISBN: (纸本)9781510688148

Optical varifocal systems have extensive applications such as consumer electronics, defense equipment, industrial monitoring, and medical devices. Traditional varifocal methods typically involve multiple lenses and mechanical components. The lenses often move along the optical axis using motors to achieve the varifocal ability. This configuration introduces some limitations, such as more structural complexity, larger size, slower varifocal speed, and higher production cost. Different from the traditional varifocal lenses, Alvarez lenses comprise two symmetrically arranged freeform surface phase plates moving perpendicular to the optical axis. The Alvarez lenses achieve a wide varifocal range through small lateral displacement offering a compact design and a large varifocal range. Besides the parameter of lateral displacement, the varifocal range and the imaging performance of the Alvarez lenses are influenced by other parameters. This paper aims to explore and analyze how different parameters impact the imaging performance of Alvarez lenses. The analysis focuses on the two parameters, i.e., the vector height modulation coefficient(A), the tilt of the freeform surface (D), air gaps, and installation errors. Parameter A controls the height difference between peaks and valleys of the freeform surface and directly affects the varifocal capability of the Alvarez lenses. Through the optical simulation of the Alvarez lens via OpticStudio software, we found that a decrease in the value of parameter A helps to reduce the rate of performance degradation. However, the smaller value of the parameter A necessitates a larger lateral displacement to achieve equivalent changes in focal length. The increase in displacement results in higher power consumption and a slower response time. Thus, selecting an optimal A value and refining D are crucial to enhancing the Alvarez lenses's overall performance. To identify the optimized parameters, we simulated five different sets of the param

关键词： Ray tracing

来源：评论

学校读者我要写书评

暂无评论

Resolution-Adaptive 3D Point Cloud Processing Inspired by Biomimetic Vision 10

Resolution-Adaptive 3D Point Cloud Processing Inspired by Bi...

引用

10th Symposium on Novel Optoelectronic detection technology and Applications

作者： Jie, Cao Chenyu, Xu Sirui, Guo Bin, Han Qun, Hao School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Zhejiang Jiaxing314003 China National Key Laboratory on Near-Surface Detection Beijing100072 China Changchun University of Science and Technology Jilin Changchun130022 China

ISBN: (数字)9781510688155

ISBN: (纸本)9781510688148

With the widespread application of 3D point clouds in various fields such as remote sensing reconnaissance and intelligent driving, the demand for efficient point cloud processing technology is increasingly growing. This paper introduces a resolution-adaptive processing method inspired by bionic vision, which simulates the human visual system's ability to focus on regions of interest (ROI) while maintaining high resolution in the ROI areas and reducing the resolution of surrounding areas. First, deep learning technology is utilized to construct an ROI detection network capable of identifying key targets within the point cloud. Subsequently, a bionic dynamic resolution processing based on the region of interest is applied to reconcile the contradiction between resolution and data volume. Finally, we propose a bionic retinal mechanism for 3D target recognition, and the results demonstrate that this method significantly improves the processing speed and target recognition accuracy in the field of 3D point cloud target identification. This study provides a new technical approach for 3D point cloud data processing, offering favorable support for technological advancements and application expansion in related fields of 3D point clouds. © 2025 SPIE.

关键词： 3D point cloud 3D target recognition Intelligent driving Resolution-adaptive processing

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：