检索结果-内蒙古大学图书馆

LF-PGVIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras using Points and Geodesic Segments

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Ze Yang, Kailun Shi, Hao Zhang, Yufan Xu, Zhijie Gao, Fei Wang, Kaiwei The State Key Laboratory of Extreme Photonics and Instrumentation The National Engineering Research Center of Optical Instrumentation Zhejiang University Hangzhou310027 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The School of Computing and Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom The State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China

In this paper, we propose LF-PGVIO, a Visual-Inertial-Odometry (VIO) framework for large Field-of-View (FoV) cameras with a negative plane using points and geodesic segments. The purpose of our research is to unleash the potential of point-line odometry with large-FoV omnidirectional cameras, even for cameras with negative-plane FoV. To achieve this, we propose an Omnidirectional Curve Segment Detection (OCSD) method combined with a camera model which is applicable to images with large distortions, such as panoramic annular images, fisheye images, and various panoramic images. The geodesic segment is sliced into multiple straight-line segments based on the radian and descriptors are extracted and recombined. Descriptor matching establishes the constraint relationship between 3D line segments in multiple frames. In our VIO system, line feature residual is also extended to support large-FoV cameras. Extensive evaluations on public datasets demonstrate the superior accuracy and robustness of LF-PGVIO compared to state-of-the-art methods. The source code will be made publicly available at https://***/flysoaryun/LF-PGVIO. Copyright © 2023, The Authors. All rights reserved.

关键词： Cameras

Domain-invariant Prototypes for Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Zhengeng Yu, Hongshan Sun, Wei Li-Cheng Mian, Ajmal The National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University Lushan South Rd. Yuelu410082 China The Department of Electrical and Computer Engineering University of Alberta EdmontonAB Canada The Department of Computer Science The University of Western Australia PerthWA6009 Australia

Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to domain adaptive semantic segmentation that focuses on transferring semantic knowledge from a labeled source domain to an unlabeled target domain. Existing self-training methods typically require multiple rounds of training, while another popular framework based on adversarial training is known to be sensitive to hyper-parameters. In this paper, we present an easy-to-train framework that learns domain-invariant prototypes for domain adaptive semantic segmentation. In particular, we show that domain adaptation shares a common character with few-shot learning in that both aim to recognize some types of unseen data with knowledge learned from large amounts of seen data. Thus, we propose a unified framework for domain adaptation and few-shot learning. The core idea is to use the class prototypes extracted from few-shot annotated target images to classify pixels of both source images and target images. Our method involves only one-stage training and does not need to be trained on large-scale un-annotated target images. Moreover, our method can be extended to variants of both domain adaptation and few-shot learning. Experiments on adapting GTA5-to-Cityscapes and SYNTHIA-to-Cityscapes show that our method achieves competitive performance to state-of-the-art. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantic Segmentation

AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lin, Jiacheng Chen, Jiajun Yang, Kailun Roitberg, Alina Li, Siyu Li, Zhiyong Li, Shutao The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The Institute for Artificial Intelligence The University of Stuttgart Stuttgart70569 Germany The College of Electrical and Information Engineering The Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province Hunan University Changsha410082 China

Interactive Image Segmentation (IIS) has emerged as a promising technique for decreasing annotation time. Substantial progress has been made in pre- and post-processing for IIS, but the critical issue of interaction ambiguity, notably hindering segmentation quality, has been under-researched. To address this, we introduce ADAPTIVECLICK – a click-aware transformer incorporating an adaptive focal loss that tackles annotation inconsistencies with tools for mask- and pixel-level ambiguity resolution. To the best of our knowledge, AdaptiveClick is the first transformer-based, mask-adaptive segmentation framework for IIS. The key ingredient of our method is the Click-Aware Mask-adaptive transformer Decoder (CAMD), which enhances the interaction between click and image features. Additionally, AdaptiveClick enables pixel-adaptive differentiation of hard and easy samples in the decision space, independent of their varying distributions. This is primarily achieved by optimizing a generalized Adaptive Focal Loss (AFL) with a theoretical guarantee, where two adaptive coefficients control the ratio of gradient values for hard and easy pixels. Our analysis reveals that the commonly used Focal and BCE losses can be considered special cases of the proposed AFL. With a plain ViT backbone, extensive experimental results on nine datasets demonstrate the superiority of AdaptiveClick compared to state-of-the-art methods. The source code is publicly available at https://***/lab206/AdaptiveClick. Copyright © 2023, The Authors. All rights reserved.

关键词： Pixels

DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds

学校读者我要写书评

暂无评论

arXiv 2023年

作者： He, Yong Yu, Hongshan Yang, Zhengeng Sun, Wei Feng, Mingtao Mian, Ajmal The National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University Lushan South Rd. Yuelu Dist. Changsha410082 China The School of Computer Science and Technology Xidian University Xi’an710071 China The Department of Computer Science The University of Western Australia PerthWA6009 Australia

Local features and contextual dependencies are crucial for 3D point cloud analysis. Many works have been devoted to designing better local convolutional kernels that exploit the contextual dependencies. However, current point convolutions lack robustness to varying point cloud density. Moreover, contextual modeling is dominated by non-local or self-attention models which are computationally expensive. To solve these problems, we propose density adaptive convolution, coined DAConv. The key idea is to adaptively learn the convolutional weights from geometric connections obtained from the point density and position. To extract precise context dependencies with fewer computations, we propose an interactive attention module (IAM) that embeds spatial information into channel attention along different spatial directions. DAConv and IAM are integrated in a hierarchical network architecture to achieve local density and contextual direction-aware learning for point cloud analysis. Experiments show that DAConv is significantly more robust to point density compared to existing methods and extensive comparisons on challenging 3D point cloud datasets show that our network achieves state-of-the-art classification results of 93.6% on ModelNet40, competitive semantic segmentation results of 68.71% mIoU on S3DIS and part segmentation results of 86.7% mIoU on ShapeNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsampling

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Yong Yu, Hongshan Ibrahim, Muhammad Liu, Xiaoyan Chen, Tongjia Ulhaq, Anwaar Mian, Ajmal The National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University Lushan South Rd. Yuelu Dist. Changsha410082 China The Department of Computer Science The University of Western Australia WA6009 Australia Central Queensland University Sydney Campus Australia

Point cloud processing methods leverage local and global point features to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that integrating task-level information into the encoding stage significantly enhances performance. To that end, we propose SMTransformer which incorporates task-level information into a vector-based transformer by utilizing a soft mask generated from task-level queries and keys to learn the attention weights. Additionally, to facilitate effective communication between features from the encoding and decoding layers in high-level tasks such as segmentation, we introduce a skip-attention-based up-sampling block. This block dynamically fuses features from various resolution points across the encoding and decoding layers. To mitigate the increase in network parameters and training time resulting from the complexity of the aforementioned blocks, we propose a novel shared position encoding strategy. This strategy allows various transformer blocks to share the same position information over the same resolution points, thereby reducing network parameters and training time without compromising accuracy. Experimental comparisons with existing methods on multiple datasets demonstrate the efficacy of SMTransformer and skip-attention-based up-sampling for point cloud processing tasks, including semantic segmentation and classification. In particular, we achieve state-of-the-art semantic segmentation results of 73.4% mIoU on S3DIS Area 5 and 62.4% mIoU on SWAN dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yi, Zhonghua Shi, Hao Yang, Kailun Jiang, Qi Ye, Yaozu Wang, Ze Ni, Huajian Wang, Kaiwei The State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China The School of Robotics Hunan University Changsha410012 China The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Shanghai SUPREMIND Technology Company Ltd. Shanghai201210 China

Key-point-based scene understanding is fundamental for autonomous driving applications. At the same time, optical flow plays an important role in many vision tasks. However, due to the implicit bias of equal attention on all points, classic data-driven optical flow estimation methods yield less satisfactory performance on key points, limiting their implementations in key-point-critical safety-relevant scenarios. To address these issues, we introduce a points-based modeling method that requires the model to learn key-point-related priors explicitly. Based on the modeling method, we present FocusFlow, a framework consisting of 1) a mix loss function combined with a classic photometric loss function and our proposed Conditional Point control Loss (CPCL) function for diverse point-wise supervision;2) a conditioned controlling model which substitutes the conventional feature encoder by our proposed Condition control Encoder (CCE). CCE incorporates a Frame Feature Encoder (FFE) that extracts features from frames, a Condition Feature Encoder (CFE) that learns to control the feature extraction behavior of FFE from input masks containing information of key points, and fusion modules that transfer the controlling information between FFE and CFE. Our FocusFlow framework shows outstanding performance with up to +44.5% precision improvement on various key points such as ORB, SIFT, and even learning-based SiLK, along with exceptional scalability for most existing data-driven optical flow methods like PWC-Net, RAFT, and FlowFormer. Notably, FocusFlow yields competitive or superior performances rivaling the original models on the whole frame. The source code will be available at https://***/ZhonghuaYi/FocusFlow_official. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous vehicles

Exploring Event-based Human Pose Estimation with 3D Event Representations

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yin, Xiaoting Shi, Hao Chen, Jiaan Wang, Ze Ye, Yaozu Yang, Kailun Wang, Kaiwei State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China School of Robotics Hunan University Changsha410012 China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Shanghai SUPREMIND Technology Company Ltd. Shanghai201210 China

Human pose estimation is a fundamental and appealing task in computer vision. Although traditional cameras are commonly applied, their reliability decreases in scenarios under high dynamic range or heavy motion blur, where event cameras offer a robust solution. Predominant event-based methods accumulate events into frames, ignoring the asynchronous and high temporal resolution that is crucial for distinguishing distinct actions. To address this issue and to unlock the 3D potential of event information, we introduce two 3D event representations: the Rasterized Event Point Cloud (RasEPC) and the Decoupled Event Voxel (DEV). The RasEPC aggregates events within concise temporal slices at identical positions, preserving their 3D attributes along with statistical information, thereby significantly reducing memory and computational demands. Meanwhile, the DEV representation discretizes events into voxels and projects them across three orthogonal planes, utilizing decoupled event attention to retrieve 3D cues from the 2D planes. Furthermore, we develop and release EV-3DPW, a synthetic event-based dataset crafted to facilitate training and quantitative analysis in outdoor scenes. Our methods are tested on the DHP19 public dataset, MMHPSD dataset, and our EV-3DPW dataset, with further qualitative validation via a derived driving scene dataset EV–JAAD and an outdoor collection vehicle. Our code and dataset have been made publicly available at https://***/MasterHow/EventPointPose. Copyright © 2023, The Authors. All rights reserved.

关键词： 3D modeling

E-3DGS: Gaussian Splatting with Exposure and Motion Events

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yin, Xiaoting Shi, Hao Bao, Yuhan Bing, Zhenshan Liao, Yiyi Yang, Kailun Wang, Kaiwei State Key Laboratory of Modern Optical Instrumentation Zhejiang University China School of Robotics National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China College of Information Science and Electronic Engineering Zhejiang University China The Chair of Robotics AI and Real-Time Systems Technical University of Munich Germany

Estimating Neural Radiance Fields (NeRFs) from images captured under optimal conditions has been extensively explored in the vision community. However, robotic applications often face challenges such as motion blur, insufficient illumination, and high computational overhead, which adversely affect downstream tasks like navigation, inspection, and scene visualization. To address these challenges, we propose E-3DGS, a novel event-based approach that partitions events into motion (from camera or object movement) and exposure (from camera exposure), using the former to handle fast-motion scenes and using the latter to reconstruct grayscale images for high-quality training and optimization of event-based 3D Gaussian Splatting (3DGS). We introduce a novel integration of 3DGS with exposure events for high-quality reconstruction of explicit scene representations. Our versatile framework can operate on motion events alone for 3D reconstruction, enhance quality using exposure events, or adopt a hybrid mode that balances quality and effectiveness by optimizing with initial exposure events followed by high-speed motion events. We also introduce EME-3D, a real-world 3D dataset with exposure events, motion events, camera calibration parameters, and sparse point clouds. Our method is faster and delivers better reconstruction quality than event-based NeRF while being more cost-effective than NeRF methods that combine event and RGB data by using a single event sensor. By combining motion and exposure events, E-3DGS sets a new benchmark for event-based 3D reconstruction with robust performance in challenging conditions and lower hardware demands. The source code and dataset will be available at https://***/MasterHow/E-3DGS. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

Computational Imaging for Machine perception: Transferring Semantic Segmentation beyond Aberrations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Qi Shi, Hao Gao, Shaohua Zhang, Jiaming Yang, Kailun Sun, Lei Ni, Huajian Wang, Kaiwei The State Key Laboratory of Extreme Photonics and Instrumentation The National Engineering Research Center of Optical Instrumentation Zhejiang University Hangzhou310027 China The Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe76131 Germany The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Shanghai SUPREMIND Technology Company Ltd Shanghai201210 China

Semantic scene understanding with Minimalist Optical Systems (MOS) in mobile and wearable applications remains a challenge due to the corrupted imaging quality induced by optical aberrations. However, previous works only focus on improving the subjective imaging quality through the Computational Imaging (CI) technique, ignoring the feasibility of advancing semantic segmentation. In this paper, we pioneer the investigation of Semantic Segmentation under Optical Aberrations (SSOA) with MOS. To benchmark SSOA, we construct Virtual Prototype Lens (VPL) groups through optical simulation, generating Cityscapes-ab and KITTI-360-ab datasets under different behaviors and levels of aberrations. We look into SSOA via an unsupervised domain adaptation perspective to address the scarcity of labeled aberration data in real-world scenarios. Further, we propose Computational Imaging Assisted Domain Adaptation (CIADA) to leverage prior knowledge of CI for robust performance in SSOA. Based on our benchmark, we conduct experiments on the robustness of classical segmenters against aberrations. In addition, extensive evaluations of possible solutions to SSOA reveal that CIADA achieves superior performance under all aberration distributions, bridging the gap between computational imaging and downstream applications for MOS. The project page is at https://***/zju-jiangqi/CIADA. Copyright © 2022, The Authors. All rights reserved.

关键词： Aberrations