检索结果-内蒙古大学图书馆

3d Single Object Tracking With Cross-Modal Fusion Conflict Elimination

IEEE ROBOTICS ANd AUTOMATION LETTERS 2025年第5期10卷 4826-4833页

作者： Yang, Yushi Li, Wei Yao, Ying Zhou, Bo Fan, Baojie Southeast Univ Sch Automat Nanjing 210096 Peoples R China Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Nanjing 210023 Peoples R China

3d single object tracking based on point clouds is a key challenge in robotics and autonomous driving technology. Mainstream methods rely on point clouds for geometric matching or motion estimation between the target template and the search area. However, the lack of texture and the sparsity of incomplete point clouds make it difficult for unimodal trackers to distinguish objects with similar structures. To overcome the limitations of previous methods, this letter proposes a cross-modal fusion conflict elimination tracker (CCETrack). The point clouds collected by LidAR provide accurate depth and shape information about the surrounding environment, while the camera sensor provides RGB images containing rich semantic and texture information. CCETrack fully leverages both modalities to track 3d objects. Specifically, to address cross-modal conflicts caused by heterogeneous sensors, we propose a global context alignment module that aligns RGB images with point clouds and generates enhanced image features. Then, a sparse feature enhancement module is designed to optimize voxelized point cloud features using the rich image features. In the feature fusion stage, both modalities are converted into BEV features, with the template and search area features fused separately. A self-attention mechanism is employed to establish bidirectional communication between regions. Our method maximizes the use of effective information and achieves state-of-the-art performance on the KITTI and nuScenes datasets through multimodal complementarity.

关键词： Three-dimensional displays Point cloud compression Target tracking Feature extraction Object tracking Laser radar Cameras Proposals Search problems Location awareness 3d single object tracking point cloud multimodal

来源：评论

学校读者我要写书评

暂无评论

CASSC: Context-aware method for depth guided semantic scene completion

引用

IET image processing 2024年第14期18卷 4716-4730页

作者： Cao, Jinghao Li, Ming Liu, Sheng Li, Yang du, Sidan Nanjing Univ Sch Elect Sci & Engn Nanjing 210023 Jiangsu Peoples R China

Semantic scene completion is a crucial end-to-end 3d perception task, and the 3d information perception subjects is vital for autonomous driving. This paper presents CASSC, a novel adaptive context-aware method based on Transformer networks, aimed at realizing camera-based semantic scene completion algorithms. The key idea is to leverage rich context information from images to obtain pixel-level label proposals, followed by designing a multiscale fusion mechanism to merge this information and match it with voxel space. A weakly supervised training strategy is proposed to obtain semantic label distribution features from images and introduce an adaptive multiscale fusion module to fuse and adaptively match these features with voxel space. Here, CASSC achieves state-of-the-art performance on the SemanticKITTI dataset and demonstrates excellent performance on the SSC-Bench dataset. Ablation experiments validate the rationality and effectiveness of our design, and the model and code of CASSC will be open-sourced on .

关键词： computer vision convolutional neural nets image processing supervised learning

来源：评论

学校读者我要写书评

暂无评论

Single-Camera-Based 3d drone Trajectory Reconstruction for Surveillance Systems

引用

IEEE ACCESS 2025年 13卷 56413-56427页

作者： Hwang, Seo-Bin Cho, Yeong-Jun Chonnam Natl Univ Dept Artificial Intelligence Convergence Gwangju 61186 South Korea

drones have been utilized in various fields, but the number of drones being used illegally and for illegal and hazardous purposes has recently increased. These misuses have given rise to the development of an anti-drone system, C-UAS, comprising two key steps: engagement and detection. This detection step plays a crucial role in reconstructing the drone's trajectory for the subsequent engagement step. Therefore, we focus on a trajectory reconstruction approach that utilizes external data, such as CCTV view images, instead of internal drone data. While numerous methods have been explored for estimating 3d drone trajectory using multiple sensors, they are often unsuitable for surveillance systems. In this study, we use a calibrated single camera suitable for surveillance systems, leveraging the relationship between 2d and 3d spaces. We use a drone tracker to automatically track 2d images. The tracked images are used to estimate the 2d rotation of the drone in the image through principal component analysis (PCA). By combining the estimated 2d drone positions with the actual length, we geometrically infer the 3d drone trajectories. We also develop synthetic 2d and 3d drone datasets to address the lack of public drone datasets. Additionally, a real-world 3d dataset is generated and made available for public use. The experimental results demonstrate that the proposed method can accurately reconstruct drone trajectories in 3d space. With a MAE of 5.66 and RMSE of 7.93 showing low error rates, these findings validate the practical value and potential of our framework as a single-camera-based surveillance system.

关键词： drones Three-dimensional displays Trajectory Cameras image reconstruction Surveillance Sensors Radar tracking Accuracy Estimation drone 3d trajectory reconstruction tracking single camera surveillance system

来源：评论

学校读者我要写书评

暂无评论

360^° Stereo image Composition With depth Adaption

引用

IEEE TRANSACTIONS ON VISUALIZATION ANd COMPUTER GRAPHICS 2024年第9期30卷 6177-6191页

作者： Huang, Kun Zhang, Fang-Lue Zhao, Junhong Li, Yiheng dodgson, Neil Victoria Univ Wellington Sch Engn & Comp Sci Wellington 6012 New Zealand Victoria Univ Wellington CMIC Wellington 6012 New Zealand

360(degrees) images and videos have become an economic and popular way to provide VR experiences using real-world content. However, the manipulation of the stereo panoramic content remains less explored. In this paper, we focus on the 360(degrees) image composition problem, and develop a solution that can take an object from a stereo image pair and insert it at a given 3d position in a target stereo panorama, with well-preserved geometry information. Our method uses recovered 3d point clouds to guide the composited image generation. More specifically, we observe that using only a one-off operation to insert objects into equirectangular images will never produce satisfactory depth perception and generate ghost artifacts when users are watching the result from different view directions. Therefore, we propose a novel view-dependent projection method that segments the object in 3d spherical space with the stereo camera pair facing in that direction. A deep depth densification network is proposed to generate depth guidance for the stereo image generation of each view segment according to the desired position and pose of the inserted object. We finally merge the synthesized view segments and blend the objects into the target stereo 360(degrees) scene. A user study demonstrates that our method can provide good depth perception and removes ghost artifacts. The view-dependent solution is a potential paradigm for other content manipulation methods for 360(degrees) images and videos.

关键词： Three-dimensional displays Cameras Stereo image processing Videos Estimation Geometry image synthesis image composition image synthesis stereoscopic panoramic image virtual reality

来源：评论

学校读者我要写书评

暂无评论

Refined 3d Modeling of Complex Models Based on Stereo Vision

引用

IEEE ACCESS 2024年 12卷 93487-93501页

作者： Ming, Haotian Li, Qi Xia, Haibo Li, Peng Guangxi Univ Sci & Technol Sch Civil & Architectural Engn Liuzhou 545006 Peoples R China Key Lab Disaster Prevent & Mitigat & Prestress Tec Liuzhou 545006 Peoples R China

despite the decreasing costs of stereo vision technologies, traditional 3d reconstruction methods still face challenges related to operational complexity and high costs, which somewhat limit their widespread adoption in various technical applications. Addressing these challenges, this paper presents an improved 3d reconstruction method combining COLMAP and OpenMVS, particularly suited for use with standard consumer-grade imaging devices such as smartphones and drones. By employing Structure from Motion (SFM) and Multi-View Stereo (MVS) techniques, this study significantly enhances image processing speed and achieves substantial improvements in model accuracy and detail reproduction. Systematic experimental validation has demonstrated that the combination of COLMAP and OpenMVS outperforms other open-source tools and combinations in terms of reconstruction speed and precision. This finding highlights the extensive potential and applicability of this combined approach in applications such as virtual reality, robotic navigation, and the digitization of cultural heritage.

关键词： Three-dimensional displays Cameras Feature extraction Solid modeling image reconstruction Accuracy Point cloud compression Stereo vision Structure from motion multi view stereo 3d reconstruction model refinement

来源：评论

学校读者我要写书评

暂无评论

image edge smoothing method for light-field displays based on joint design of optical structure and elemental images

引用

OPTICS EXPRESS 2023年第11期31卷 18017-18025页

作者： Yu, Xunbo LI, Hanyu Su, Xiwen Gao, Xin Sang, Xinzhu Yan, Binbin Beijing Univ Posts & Telecommun BUPT State Key Lab Informat Photon & Opt Commun Beijing 100876 Peoples R China

image visual quality is of fundamental importance for three-dimensional (3d) light -field displays. The pixels of a light-field display are enlarged after the imaging of the light-field system, increasing the graininess of the image, which leads to a severe decline in the image edge smoothness as well as image quality. In this paper, a joint optimization method is proposed to minimize the "sawtooth edge" phenomenon of reconstructed images in light-field display systems. In the joint optimization scheme, neural networks are used to simultaneously optimize the point spread functions of the optical components and elemental images, and the optical components are designed based on the results. The simulations and experimental data show that a less grainy 3d image is achievable through the proposed joint edge smoothing method.& COPY;2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： image processing image quality image reconstruction Optical components Point spread function Three dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

A 2d image 3d reconstruction function adaptive denoising algorithm

引用

PEERJ COMPUTER SCIENCE 2023年 9卷 e1604页

作者： Wang, Feng Ni, Weichuan Liu, Shaojiang Xu, Zhiming Qiu, Zemin Wan, Zhiping Guangzhou Xinhua Univ Dongguan Guangdong Peoples R China

To address the issue of image denoising algorithms blurring image details during the denoising process, we propose an adaptive denoising algorithm for the 3d reconstruction of 2d images. This algorithm takes into account the inherent visual characteristics of human eyes and divides the image into regions based on the entropy value of each region. The background region is subject to threshold denoising, while the target region undergoes processing using an adversarial generative network. This network effectively handles 2d target images with noise and generates a 3d model of the target. The proposed algorithm aims to enhance the noise immunity of 2d images during the 3d reconstruction process and ensure that the constructed 3d target model better preserves the original image's detailed information. Through experimental testing on 2d images and real pedestrian videos contaminated with noise, our algorithm demonstrates stable preservation of image details. The reconstruction effect is evaluated in terms of noise reduction and the fidelity of the 3d model to the original target. The results show an average noise reduction exceeding 95% while effectively retaining most of the target's feature information in the original image. In summary, our proposed adaptive denoising algorithm improves the 3d reconstruction process by preserving image details that are often compromised by conventional denoising techniques. This has significant implications for enhancing image quality and maintaining target information fidelity in 3d models, providing a promising approach for addressing the challenges associated with noise reduction in 2d images during 3d reconstruction.

关键词： denoising algorithm Threshold Adversarial generative network 3d reconstruction

来源：评论

学校读者我要写书评

暂无评论

Real-Time deep Learning-Based Object Recognition in Augmented Reality

Real-Time Deep Learning-Based Object Recognition in Augmente...

引用

Conference on Real-Time processing of image, depth, and Video information

作者： Egipko, V Zhdanova, M. Gapon, N. Voronin, V. Semenishchev, E. Moscow State Univ Technol STANKIN Ctr Cognit Technol & Machine Vis Moscow Russia Don State Tech Univ Rostov Na Donu Russia

ISBN: (纸本)9781510673199;9781510673182

Augmented reality is a visualization technology that displays information by adding virtual images to the real world. Effective implementation of augmented reality requires recognition of the current scene. Identifying objects in real-time video on computationally limited hardware requires significant effort. One way to solve this problem is to create a hybrid system that, based on machine learning and computer vision technology, processes and analyzes visual data to identify and classify real-world objects. The proposed architecture is based on a combination of the Vuforia augmented system, which provides good performance by balancing prediction accuracy and efficiency. First, the Vuforia neural network architecture allows convenient interaction with AR in Unity and provides initial conditions for detecting 3d objects. The augmented reality construction algorithm is based on the ARCore framework and the OpenGL interface for embedded systems. The system integrates recognition data with an AR platform to display corresponding 3d models, allowing users to interact with them through the functionality of the AR application. This method also involves the development of an enhanced user interface for AR, making the augmented environment more accessible for navigation and control. Experimental research has shown that the proposed method significantly improves the accuracy of object recognition and the ease of working with 3d models in AR.

关键词： deep learning augmented reality computer vision object recognition robotic systems real-time processing

来源：评论

学校读者我要写书评

暂无评论

MonoMPV: Monocular 3d Object detection With Multiple Projection Views on Edge devices

引用

IEEE ACCESS 2024年 12卷 136599-136612页

作者： deng, Zhaoxue Hao, Bingsen Liu, Guofang Li, Xingquan Wei, Hanbing Huang, Fei Liu, Shengshu Chongqing Jiaotong Univ Sch Mechatron & Vehicle Engn Chongqing 400074 Peoples R China Chongqing Changan Automobile Co Ltd Res & Dev Dept Chongqing 400023 Peoples R China China Soc Automot Engineers Beijing 100176 Peoples R China Chongqing Univ Technol Vehicle Engn Inst Chongqing 400054 Peoples R China China Rd & Bridge Corp Beijing 100010 Peoples R China

In the field of autonomous driving, monocular 3d object detection is focused on the task of representing 3d scenes using a single camera image and conducting 3d object detection. While Bird's-Eye View (BEV) method effectively decreases the computational burden associated with 3d scene representation, its limitation in considering height information can lead to a less accurate depiction of complex 3d structures. This study introduces an innovative monocular 3d object detection framework called MonoMPV. This framework represents a complete 3d scene by mapping spatial objects onto Multi-Projection Views (MPV) without the need for voxelization, thus simplifying the process. Notably, MPV systems consist of Feature Cross-Attention (FCA) and Projection Cross-Attention (PCA) components. FCA aims to enhance image features to MPV level, while PCA enables direct information interaction among the views within MPV. Furthermore, Triplet Loss for Top Feature (TLTF) was employed in conjunction with FCA and PCA to distinguish effectively between top-plane and background features. By engaging in this practice, it is possible to develop more complex 3d structural models and establish precise optimization objectives through TLTF. Consequently, this approach enhances the effective utilization of data by the model. Experimental results on the nuScenes dataset illustrate that this approach surpasses existing monocular 3d object detection methods. To implement algorithms on on-board edge computing devices, the monocular 3d object detection task has been executed on the edge device Jetson Orin NX, ensuring high precision.

关键词： Three-dimensional displays Object detection Feature extraction Computational modeling Autonomous vehicles Accuracy Solid modeling Autonomous driving 3d object detection multi-projection views edge computing

来源：评论

学校读者我要写书评

暂无评论

Adaptive CLIP for open-domain 3d model retrieval

引用

information processing & MANAGEMENT 2025年第2期62卷

作者： Song, dan Qiang, Zekai Zhang, Chumeng Wang, Lanjun Liu, Qiong Yang, You Liu, An-An Tianjin Univ Sch Elect & Informat Engn Tianjin 300110 Peoples R China Tianjin Univ Sch New Media & Commun Tianjin 300110 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China

In order to effectively enhance the practicality of 3d model retrieval, we adopt a single real image as the query sample for retrieving 3d models. However, the significant differences between 2d images and 3d models in terms of lighting conditions, textures and backgrounds, posing a great challenge for accurate retrieval. Existing work on 3d model retrieval mainly focuses on closed-domain research, while the open-domain condition where the category relationship between the query image and the 3d model is unknown is more in line with the needs of real scenarios. CLIP shows significant promise in comprehending open-world visual concepts, facilitating effective zero-shot image recognition. Based on this multimodal pre-training large language model, we introduce Adaptive Open-domain Semantic Nearest-neighbor Contrast (AOSNC), a method for learning and aligning multi-modal text, image, and 3d model. In order to solve the issue of inconsistent cross-domain categories and difficult sample correlation in open-domain, we construct a cross-modal bridge using CLIP. This model utilizes textual features to bridge the gap between 2d images and 3d model views. Additionally, we design an adaptive network layer to address the limitations of the pre-training model for 3d model views and enhance cross-modal alignment. We propose a mutual nearest-neighbor semantic alignment loss to address the challenge of aligning features from disparate modalities (text, images, and 3d models). This loss function enhances cross-modal learning by effectively associating and distinguishing features, improving retrieval accuracy. We conducted comprehensive experiments using the image-based 3d model retrieval dataset MI3dOR and the cross-domain 3d model retrieval dataset NTU-PSB to validate the superiority of the proposed method. Our results show significant improvements in several evaluation metrics, underscoring the efficacy of our method in augmenting cross-modal feature alignment and retrieval perfor

关键词： 3d model retrieval Open-domain retrieval Contrastive learning

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：