检索结果-内蒙古大学图书馆

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Liu, Ziyu Gui, Kang Ge, Junfeng Ye, Lin National Key Laboratory of Science & Technology on Multispectral Information Processing Huazhong University of Science & Technology Wuhan430074 China School of Artificial Intelligence & Automation Huazhong University of Science & Technology Wuhan430074 China

ISBN: (数字)9781510674929

ISBN: (纸本)9781510674912

Aircraft icing is a severe threat to safe flight. The conditions and efficiency of current ice area and 3D ice shape measurement methods do not meet the research requirements for ice wind tunnel experiments. To address these issues, we propose a method for measuring ice area and 3D ice shape based on polarized light imaging for non-contact measurement. In this paper, we obtain p-polarized light image and s-polarized light image of the experimental area under the linearly polarized light environment. And we use the Otsu algorithm and the SAM (Segment Anything Model) algorithm to measure the ice area under different substrate conditions. On this basis, we extract the linearly polarized light reflected from the ice surface, and reconstruct the 3D ice surface shape by combining the linearly polarized laser scanning method based on polarized light imaging. The experimental results indicate that our method can detect the ice area in real time and the average measurement error of the ice area is less than 1.6%, which achieves superior measurement performance with different ice types at a low cost. For different ice shapes of highly transparent ice, the measurement results agree well with the design data, where the RMSE (Root Mean Square Error) of ice frustum measurement is 0.76 and the RMSE of three cross-sections of different ice shapes are 0.23, 0.27 and 0.45. The results verify the validity of ice area measurement based on polarized light imaging, and demonstrate the effect of complex ice shape measurement based on polarized light imaging, laying a foundation for the real-time measurement research in the ice wind tunnel. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Ice

来源：评论

学校读者我要写书评

暂无评论

Depth from focus with electrowetting liquid lens 12

Depth from focus with electrowetting liquid lens

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Zhang, Chunyu Hu, Jiaqi Zhang, Xinyu National Key Laboratory of Science & Technology on Multispectral Information Processing Huazhong University of Science & Technology Wuhan430074 China School of Artificial Intelligence & Automation Huazhong University of Science & Technology Wuhan430074 China

ISBN: (数字)9781510674929

ISBN: (纸本)9781510674912

Depth from focus and defocus is an effective technique to extract depth information from a set of images, which is called focal stack. In prior studies, this technology was commonly operated on complex laboratory imaging equipment. In this paper, a new imaging system based on electrowetting liquid lens is proposed. Electrowetting liquid lens is one of the adaptive lens which has adjustable focal length controlled by voltage signal. The focal stack can be easily got by sweeping the applied voltage without mechanical moving part. To eliminate the field of view (FOV) variations during the process of capturing focal stack, which is called focal breathing, we proposed an algorithm based on conventional flow concatenation to align focal stack images. We test the proposed imaging system on both laboratory scene and mobile phones, and the experiments demonstrate this imaging system can capture high quality images and shows excellent performance in extracting depth information without complex mechanical structure. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Imaging systems

来源：评论

学校读者我要写书评

暂无评论

Fully electrically controlled light-field camera via electrowetting liquid lens and liquid-crystal microlens array 12

Fully electrically controlled light-field camera via electro...

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Hu, Jiaqi Zhang, Chunyu Zhang, Xinyu National Key Laboratory of Science & Technology on Multispectral Information Processing Huazhong University of Science & Technology Wuhan430074 China School of Artificial Intelligence & Automation Huazhong University of Science & Technology Wuhan430074 China

ISBN: (数字)9781510674929

ISBN: (纸本)9781510674912

Light-field imaging is an effective and straightforward way to image with three-dimensional information. In this paper, a new type of the fully electrically controlled light-field camera based on electrowetting liquid lens and liquid crystal microlens array (EW-LCMLA) is proposed. In the proposed camera, a liquid-crystal microlens array (LCMLA) is placed on the CMOS sensor to get the raw light-field images. Unlike conventional light-field camera using LCMLA, the proposed camera can rapidly adjust the compound-eye degree of light-field image by inserting a liquid lens between main lens and LCMLA, and by switching the external voltage on the liquid lens, the camera can work on multiple imaging modes, such as light-field imaging, conventional two-dimensional imaging and focal-stack imaging. For further improve the. In this study, an algorithm based on focal stack theory is also proposed to extract the depth information from the raw light-field image and merge the image focus on different distances to get all-in-focus image. We test the different imaging mode of the camera in indoor environments, and the experiments demonstrate that the proposed camera can capture high quality image on different mode, and shows excellent focal length adjustment ability without complex mechanical structure. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Microlenses

来源：评论

学校读者我要写书评

暂无评论

Metal-insulator-metal metasurface for strongly absorbing incident radiation in a wide wavelength range of 5-14μm 12

Metal-insulator-metal metasurface for strongly absorbing inc...

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Gao, Zecheng Chen, Cheng Ye, Mao Yang, Guang Duan, Shenghua Zhang, Chunyu Zhu, Wenjie Hu, Jiaqi Ji, Wuyang Zhang, Xinyu National Key Laboratory of Science & Technology on Multispectral Information Processing Huazhong University of Science & Technology Wuhan430074 China School of Artificial Intelligence & Automation Huazhong University of Science & Technology Wuhan430074 China

ISBN: (数字)9781510674929

ISBN: (纸本)9781510674912

Optical stealth technology is very significant in coping with high-sensitivity infrared image detectors and various guided detectors. In recent years, great efforts have been made developing absorbers in the infrared regime. Although these approaches promise distinct advantages in performance enhancement, there are still some problems, such as limitations on sample size and bandwidth. Thus, we proposed an ultra-broadband absorber with metal-insulator-metal three-layer construction by using periodic array of ultra-thin metallic ribbons on top of the silicon oxide layer placed on a metallic reflector. The simulation results demonstrate that the average absorption rate of near 90% is realized by the proposed absorbing structure in 5μm-14μm. Meanwhile, the proposed ultra-broadband absorber is low cost, compact, and large-area processing, which can be flexibly and easily scaled up for mass production via plasma enhanced chemical vapor deposition, magnetron-sputtering deposition, and electron-beam-evaporation deposition. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Plasmonics

来源：评论

学校读者我要写书评

暂无评论

Study on transmission and nanofocusing characteristics of surface array micronano metasurface 12

Study on transmission and nanofocusing characteristics of su...

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Ji, Wuyang Duan, Shenghua Liu, Taige Zhang, Xinyu National Key Laboratory of Science & Technology on Multispectral Information Processing Huazhong University of Science & Technology Wuhan430074 China School of Artificial Intelligence & Automation Huazhong University of Science & Technology Wuhan430074 China

ISBN: (数字)9781510674929

ISBN: (纸本)9781510674912

The optical metasurface formed by the periodic arrangement of micro-nano structures with sub-wavelength size can efficiently sense and control the polarization, amplitude and phase of electromagnetic waves. When the light incident on the metasurface, the resonance response based on the plasmon will be generated at the position of wave vector matching in the periodic micro-nano structure, which will change the surface charge distribution characteristics. The properties of light reflection, light transmission, light absorption and local enhancement of the metasurface in infrared band can be effectively improved by setting the size, shape, material composition and period spacing of the surface micro -nano structure reasonably. Based on the characteristics of plasmon on solid surface, the metasurface composed of metal excitation layer of titanium array is designed. The local enhanced metasurface with low reflection characteristics is obtained by reasonable configuration of titanium structure parameters such as size and period. In order to further improve its optical transmittance in infrared band, a variety of substrate materials, such as silicon, silicon dioxide and zinc selenide, were simulated and verified. Finally, a zinc-selenide titanium array metasurface with an average transmittance of 68% in 1-14μm band was obtained. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： II-VI semiconductors

来源：评论

学校读者我要写书评

暂无评论

Robust Ascent Trajectory Optimization for Hypersonic Vehicles Based on IGS-UMPSP

Robust Ascent Trajectory Optimization for Hypersonic Vehicl...

引用

Chinese Intelligent Automation Conference, CIAC 2023

作者： Qi, Yuting Wang, Bo Liu, Lei Fan, Huijin Wang, Yongji National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789819961863

This paper proposes a new approach for solving trajectory optimization problems with uncertain system parameters, which is the generalized quasi-spectral version of unscented model predictive static programming. The proposed method combines two existing techniques, the generalized quasi-spectral model predictive static programming and the unscented optimal control, to generate control solutions that can meet multiple constraints, while minimizing the covariance of the terminal output. The technique has shown good robustness in simulations and has been demonstrated to be effective in solving ascent trajectory optimization problems of hypersonic vehicles, providing a reference trajectory for guidance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Fixed-Time Cooperative Guidance law with Impact time Constraints

Three-Dimensional Fixed-Time Cooperative Guidance law with I...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Yajun Liu, Lei Fan, Huijin Wang, Bo School of Artificial Intelligence and Automation Huazhong University of Science and Technology National Key Laboratory of Multispectral Information Intelligent Processing Technology Wuhan430074 China

ISBN: (纸本)9798350303759

In this article, we propose fixed-time cooperative guidance laws for achieving simultaneous attacks on a maneuvering target by multiple missiles at desired terminal angles. The 3-D guidance commands encompass radial acceleration along the line-of-sight (LOS) direction to enable coordinated attacks, as well as normal acceleration perpendicular to the LOS direction to ensure interception with terminal angle constraints. Firstly, the radial acceleration is designed from a nonlinear fixed-time cooperative protocol to achieve the fixed-time consensus of impact times for multiple missiles. Secondly, based on the fixed-time sliding manifold and fixed-time reaching law, the normal acceleration is designed for each missile to converge the LOS angle to the desired value within a fixed time. Furthermore, the unknown target acceleration is treated as a system disturbance, estimated by fixed-time observers, and compensated in the guidance commands, ensuring effective handling of uncertainties introduced by the target's acceleration. Finally, simulations are conducted to demonstrate the performance of the guidance law in the 3-D guidance scenario. © 2023 IEEE.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Cross-video Identity Correlating for Person Re-identification Pre-training 38

Cross-video Identity Correlating for Person Re-identificatio...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Zuo, Jialong Nie, Ying Zhou, Hanyu Zhang, Huaxin Wang, Haoyu Guo, Tianyu Sang, Nong Gao, Changxin National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Huawei Noah's Ark Lab Canada

Recent researches have proven that pre-training on large-scale person images extracted from internet videos is an effective way in learning better representations for person re-identification. However, these researches are mostly confined to pre-training at the instance-level or single-video tracklet-level. They ignore the identity-invariance in images of the same person across different videos, which is a key focus in person re-identification. To address this issue, we propose a Cross-video Identity-cOrrelating pre-traiNing (CION) framework. Defining a noise concept that comprehensively considers both intra-identity consistency and inter-identity discrimination, CION seeks the identity correlation from cross-video images by modeling it as a progressive multi-level denoising problem. Furthermore, an identity-guided self-distillation loss is proposed to implement better large-scale pre-training by mining the identity-invariance within person images. We conduct extensive experiments to verify the superiority of our CION in terms of efficiency and performance. CION achieves significantly leading performance with even fewer training samples. For example, compared with the previous state-of-the-art [9], CION with the same ResNet50-IBN achieves higher mAP of 93.3% and 74.3% on Market1501 and MSMT17, while only utilizing 8% training samples. Finally, with CION demonstrating superior model-agnostic ability, we contribute a model zoo named ReIDZoo to meet diverse research and application needs in this field. It contains a series of CION pre-trained models with spanning structures and parameters, totaling 32 models with 10 different structures, including GhostNet, ConvNext, RepViT, FastViT and so on. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Attitude Control for Flying-Wing UAV Using Modified Incremental Nonlinear Dynamic Inversion

Robust Attitude Control for Flying-Wing UAV Using Modified I...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Wangmian Xue, Chenlong Wang, Bo Liu, Lei Fan, Huijin Yang, Jiahao School of Artificial Intelligence and Automation Huazhong University of Science and Technology National Key Laboratory of Multispectral Information Intelligent Processing Technology Wuhan430074 China

ISBN: (纸本)9798350303759

This paper proposes a modified incremental nonlinear dynamic inversion (MINDI) control scheme for attitude tracking control of flying-wing unmanned aerial vehicles (UAV). Based on the incremental dynamic inversion formulation, the angular rate controller is designed to alleviate the nonlinearity and coupling characteristics of the flying-wing configuration. Then, in order to address the impact of factors such as angular acceleration measurement errors and actuator faults on the control performance, a super-twisting-like fixed-time convergence algorithm is introduced to replace the linear control law in the nominal INDI method, ensuring rapid convergence of tracking errors. The simulation results demonstrate that the proposed method effectively mitigates the impact of such errors and faults. Compared to the nominal INDI, the modified method exhibits stronger fault tolerance and robustness in the attitude tracking control of the flying-wing UAV. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

ORT: Occlusion-robust for multi-object tracking

引用

Fundamental Research 2023年第3期5卷 1214-1220页

作者： Han, Shoudong Wang, Hongwei Yu, En Hu, Zhuo National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan 430074 China School of Automation Wuhan University of Technology Wuhan 430070 China

Although the joint-detection-and-tracking paradigm has promoted the development of multi-object tracking (MOT) significantly, the long-term occlusion problem is still unsolved. After a period of trajectory inactivation due to occlusion, it is difficult to achieve trajectory reconnection with appearance features because they are no longer reliable. Although using motion cues does not suffer from occlusion, the commonly used Kalman Filter is also ineffective in its long-term inertia prediction in cases of no observation updates or wrong updates. Besides, occlusion is prone to cause multiple track-detection pairs to have close similarity scores during the data association phase. The direct use of the Hungarian algorithm to give the global optimal solution may generate the identity switching problem. In this paper, we propose the Long-term Spatio-Temporal Prediction (LSTP) module and the Ordered Association (OA) module to alleviate the occlusion problem in terms of motion prediction and data association, respectively. The LSTP module estimates the states of all tracked objects over time using a combination of spatial and temporal Transformers. The spatial Transformer models crowd interaction and learns the influence of neighbors, while the temporal Transformer models the temporal continuity of historical trajectories. Besides, the LSTP module also predicts the visibilities of the motion prediction boxes, which denote the occlusion attributes of trajectories. Based on the occlusion attribute and active state, the association priority is defined in the OA module to associate trajectories in order, which helps to alleviate the identity switching problem. Comprehensive experiments on the MOT17 and MOT20 benchmarks indicate the superiority of the proposed MOT framework, namely Occlusion-Robust Tracker (ORT). Without using any appearance information, our ORT can achieve competitive performance beyond other state-of-the-art trackers in terms of trajectory accuracy and purity.

关键词： Data association Motion-based prediction Multi-object tracking Trajectory reconnection

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：