检索结果-内蒙古大学图书馆

Csp-Net: Common Spatial Pattern Empowered Neural Networks for Eeg-Based Motor imagery Classification

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Jiang, Xue Meng, Lubin Chen, Xinru Xu, Yifan Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518063 China

Electroencephalogram-based motor imagery (MI) classification is an important paradigm of non-invasive brain-computer interfaces. Common spatial pattern (CSP), which exploits different energy distributions on the scalp while performing different MI tasks, is very popular in MI classification. Convolutional neural networks (CNNs) have also achieved great success, due to their powerful learning capabilities. This paper proposes two CSP-empowered neural networks (CSP-Nets), which integrate knowledge-driven CSP filters with data-driven CNNs to enhance the performance in MI classification. CSP-Net-1 directly adds a CSP layer before a CNN to improve the input discriminability. CSP-Net-2 replaces a convolutional layer in CNN with a CSP layer. The CSP layer parameters in both CSP-Nets are initialized with CSP filters designed from the training data. During training, they can either be kept fixed or optimized using gradient descent. Experiments on four public MI datasets demonstrated that the two CSP-Nets consistently improved over their CNN backbones, in both within-subject and cross-subject classifications. They are particularly useful when the number of training samples is very small. Our work demonstrates the advantage of integrating knowledge-driven traditional machine learning with data-driven deep learning in EEG-based brain-computer interfaces. © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB image

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang, Changlong Xiao, Yang Wu, Cunlin Zhang, Mingyang Zheng, Jinghong Cao, Zhiguo Zhou, Joey Tianyi Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Alibaba Group China Singapore Singapore

3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition. Our key idea is to equip A2J with strong local-global aware ability to well capture interacting hands’ local fine details and global articulated clues among joints jointly. To this end, A2J is evolved under Transformer’s non-local encoding-decoding framework to build A2J-Transformer. It holds 3 main advantages over A2J. First, self-attention across local anchor points is built to make them global spatial context aware to better capture joints’ articulation clues for resisting occlusion. Secondly, each anchor point is regarded as learnable query with adaptive feature learning for facilitating pattern fitting capacity, instead of having the same local representation with the others. Last but not least, anchor point locates in 3D space instead of 2D as in A2J, to leverage 3D pose prediction. Experiments on challenging InterHand 2.6M demonstrate that, A2J-Transformer can achieve state-of-the-art model-free performance (3.38mm MPJPE advancement in 2-hand case) and can also be applied to depth domain with strong generalization. The code is avaliable at https://***/ChanglongJiangGit/A2J-Transformer. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Revisiting Euclidean Alignment for Transfer Learning in EEG-Based Brain-Computer Interfaces

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China

Due to the non-stationarity and large individual differences of EEG signals, EEG-based brain-computer interfaces (BCIs) usually need subject-specific calibration to tailor the decoding algorithm for each new subject, which is time-consuming and user-unfriendly, hindering their real-world applications. Transfer learning (TL) has been extensively used to expedite the calibration, by making use of EEG data from other subjects/sessions. An important consideration in TL for EEG-based BCIs is to reduce the data distribution discrepancies among different subjects/session, to avoid negative transfer. Euclidean alignment (EA) was proposed in 2020 to address this challenge. Numerous experiments from 10 different BCI paradigms demonstrated its effectiveness and efficiency. This paper revisits the EA, explaining its procedure and correct usage, introducing its applications and extensions, and pointing out potential new research directions. It should be very helpful to BCI researchers, especially those who are working on EEG signal decoding. © 2025, CC BY.

关键词： Calibration

MULTI-SCALE RESNET INTEGRATED WITH ATTENTION MECHANISM FOR ENHANCED WHEAT FRESHNESS DIAGNOSIS BASED ON BIOPHOTONICS

学校读者我要写书评

暂无评论

Acta Scientiarum Polonorum, Technologia Alimentaria 2024年第4期23卷 525-535页

作者： Shi, Weiya Chen, Liang Key Laboratory of Grain Information Processing and Control Ministry of Education Henan 450001 China Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan 450001 China College of Artificial Intelligence and Big Data Henan University of Technology Henan 450001 China

Background. Accurate detection of wheat freshness is important for ensuring the quality and safety of wheat products, thereby protecting the health and interests of consumers. Material and methods. This study integrates biophoton emission technology with advanced deep learning frameworks to transform the process of wheat freshness assessment. Leveraging the powerful feature extraction capabilities of the ResNet architecture, we employ a multi-scale framework integrated with the Gaussian Context Transformer (GCT) attention mechanism. The MS-GCT-ResNet method presents a groundbreaking approach that not only enhances the accuracy and efficiency of wheat freshness discrimination but also demonstrates the potential for combining biophysical phenomena with cutting-edge Artificial intelligence (AI) technologies for precision agriculture and food quality control. Results. This model enhances detection accuracy and adaptability, offering a powerful technique for the rapid and precise evaluation of wheat freshness. Its effectiveness is validated using years of wheat sample data. Based on the experimental results, MS-GCT-ResNet achieves a recognition accuracy of 93.6%. Compared with traditional CNN and ResNet models, the recognition accuracy increases by 1.9% and 1.1%, respectively. Conclusion. MS-GCT-ResNet is a highly promising, non-invasive, and efficient technological advancement capable of quickly and accurately assessing wheat freshness. This method holds immense potential to revolutionize the agriculture and food processing industries. © (2024), (Wydawnictwo Uniwersytetu Przyrodniczego w Poznaniu). All rights reserved.

关键词： attention mechanism biophoton emission detection multi-scale wheat freshness

Dynamic Neural Radiance Field From Defocused Monocular Video

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Luo, Xianrui Sun, Huiqiang Peng, Juewen Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of AIA Huazhong University of Science and Technology China College of Computing and Data Science Nanyang Technological University Singapore

Dynamic Neural Radiance Field (NeRF) from monocular videos has recently been explored for space-time novel view synthesis and achieved excellent results. However, defocus blur caused by depth variation often occurs in video capture, compromising the quality of dynamic reconstruction because the lack of sharp details interferes with modeling temporal consistency between input views. To tackle this issue, we propose D2RF, the first dynamic NeRF method designed to restore sharp novel views from defocused monocular videos. We introduce layered Depth-of-Field (DoF) volume rendering to model the defocus blur and reconstruct a sharp NeRF supervised by defocused views. The blur model is inspired by the connection between DoF rendering and volume rendering. The opacity in volume rendering aligns with the layer visibility in DoF rendering. To execute the blurring, we modify the layered blur kernel to the ray-based kernel and employ an optimized sparse kernel to gather the input rays efficiently and render the optimized rays with our layered DoF volume rendering. We synthesize a dataset with defocused dynamic scenes for our task, and extensive experiments on our dataset show that our method outperforms existing approaches in synthesizing all-in-focus novel views from defocus blur while maintaining spatial-temporal consistency in the scene. Copyright © 2024, The Authors. All rights reserved.

关键词： Volume rendering

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells

学校读者我要写书评

暂无评论

Constraining Depth Map Geometry for Multi-View Stereo: A Dua...

International Conference on Computer Vision (ICCV)

作者： Xinyi Ye Weiyue Zhao Tianqi Liu Zihao Huang Zhiguo Cao Xin Li Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Albany Albany NY

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods, DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS.

关键词：

Fast Full-frame Video Stabilization with Iterative Optimization

学校读者我要写书评

暂无评论

Fast Full-frame Video Stabilization with Iterative Optimizat...

International Conference on Computer Vision (ICCV)

作者： Weiyue Zhao Xin Li Zhan Peng Xianrui Luo Xinyi Ye Hao Lu Zhiguo Cao Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Albany Albany NY

Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one. The question of how to strike a good trade-off between visual quality and computational speed has remained one of the open challenges in video stabilization. Inspired by the analogy between wobbly frames and jigsaw puzzles, we propose an iterative optimization-based learning approach using synthetic datasets for video stabilization, which consists of two interacting submodules: motion trajectory smoothing and full-frame outpainting. First, we develop a two-level (coarse-to-fine) stabilizing algorithm based on the probabilistic flow field. The confidence map associated with the estimated optical flow is exploited to guide the search for shared regions through backpropagation. Second, we take a divide-and-conquer approach and propose a novel multi-frame fusion strategy to render full-frame stabilized views. An important new insight brought about by our iterative optimization approach is that the target video can be interpreted as the fixed point of nonlinear mapping for video stabilization. We formulate video stabilization as a problem of minimizing the amount of jerkiness in motion trajectories, which guarantees convergence with the help of fixed-point theory. Extensive experimental results are reported to demonstrate the superiority of the proposed approach in terms of computational speed and visual quality. The code will be available on GitHub.

关键词：

3D Cinemagraphy from a Single image

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Xingyi Cao, Zhiguo Sun, Huiqiang Zhang, Jianming Xian, Ke Lin, Guosheng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Adobe Research S-Lab Nanyang Technological University Singapore

We present 3D Cinemagraphy, a new technique that marries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and camera motion. We empirically find that naively combining existing 2D image animation and 3D photography methods leads to obvious artifacts or inconsistent animation. Our key insight is that representing and animating the scene in 3D space offers a natural solution to this task. To this end, we first convert the input image into feature-based layered depth images using predicted depth values, followed by unprojecting them to a feature point cloud. To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow. Finally, to resolve the problem of hole emergence as points move forward, we propose to bidirectionally displace the point cloud as per the scene flow and synthesize novel views by separately projecting them into target image planes and blending the results. Extensive experiments demonstrate the effectiveness of our method. A user study is also conducted to validate the compelling rendering results of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Animation

Real-Time Maritime Obstacle Detection Based on YOLOv5 for Autonomous Berthing 16th

学校读者我要写书评

暂无评论

Real-Time Maritime Obstacle Detection Based on YOLOv5 for Au...

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Chen, Guotong Qi, Jiangtao Dai, Zeyu Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China China Ship Scientific Research Center No. 222 Shanshui East Road Binhu District Wuxi214082 China

ISBN: (纸本)9789811912528

The shipping industry is developing towards intelligence, in which autonomous berthing and docking systems play an important role. Real-time maritime obstacle detection is essential for autonomous berthing, which can protect ships from collisions. In the field of real-time objection detection, YOLOv5s is one of the most effective networks. To solve the real-time maritime obstacle detection for autonomous berthing, we propose an improved network, named YOLOv5s-CBAM, which employs the convolutional block attention module to boost the representation power of YOLOv5s. In addition, we propose another network, named YOLOv5-SE, in which a squeeze-and-excitation block is introduced to recalibrate the channel-wise features adaptively. The experimental results demonstrate that YOLOv5s-CBAM outperforms YOLOv5s in the detection of large obstacles. Both YOLOv5s-CBAM and YOLOv5s-SE achieve state-of-the-art performance in various metrics compared with previous related work for maritime obstacle detection. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Ships