检索结果-内蒙古大学图书馆

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Weizhao Zhang, Yang Zhuo, Wei Shen, Linlin Yang, Jiaqi Deng, Songhe Sun, Liang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Computer Science University of Nottingham China

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the Segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt Generator (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

An Experimental Study of Keypoint Descriptor Fusion

学校读者我要写书评

暂无评论

An Experimental Study of Keypoint Descriptor Fusion

IEEE International Conference on robotics and Biomimetics

作者： Yaling Pan Li He Yisheng Guan Hong Zhang Biomimetic Intelligent Robotics Research Laboratory (BIRL) Guangdong University of Technology Guangzhou China Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9781665481106

Local feature descriptors play a crucial role in computer vision problems, especially robot motion. Existing descriptors are highly accurate, but their performance de-pends on the influence of distracting factors, such as illumi-nation and viewpoint. There is room for further improvement of these descriptors. In this paper, we provide an in-depth analysis of several exciting features of the descriptor fusion model (DFM) we have proposed in our recent work, which uses an autoencoder to combine descriptors and exploit their respective advantages. With this DFM framework, we fur-ther validate that fused descriptors can retain advantageous properties and that our DFM is a generally applicable method with respect to various component descriptors. Specifically, we evaluate multiple combinations of hand-crafted and CNN descriptors concerning their performance on a benchmark dataset with illumination and viewpoint changes to obtain comprehensive experimental results. The results show that the fused descriptors have better matching accuracy than their component descriptors.

关键词： Robot motion computer vision Analytical models Biomimetics Lighting Benchmark testing

Efficient Object Rearrangement via Multi-view Fusion

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Dehao Tang, Chao Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

The prospect of assistive robots aiding in object organization has always been compelling. In an image-goal setting, the robot rearranges the current scene to match the single image captured from the goal scene. The key to an image-goal rearrangement system is estimating the desired placement pose of each object based on the single goal image and observations from the current scene. In order to establish sufficient associations for accurate estimation, the system should observe an object from a viewpoint similar to that in the goal image. Existing image-goal rearrangement systems, due to their reliance on a fixed viewpoint for perception, often require redundant manipulations to randomly adjust an object’s pose for a better perspective. Addressing this inefficiency, we introduce a novel object rearrangement system that employs multi-view fusion. By observing the current scene from multiple viewpoints before manipulating objects, our approach can estimate a more accurate pose without redundant manipulation times. A standard visual localization pipeline at the object level is developed to capitalize on the advantages of multi-view observations. Simulation results demonstrate that the efficiency of our system outperforms existing single-view systems. The effectiveness of our system is further validated in a physical experiment. Copyright © 2023, The Authors. All rights reserved.

关键词：

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

Social Space Segmentation for Approaching Tasks

学校读者我要写书评

暂无评论

Social Space Segmentation for Approaching Tasks

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Aline F. F. Silva Douglas G. Macharet Department of Computer Science Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais Brazil Laboratório de Inteligência Computacional e Robótica (LICRo) Instituto Federal do Triângulo Mineiro (IFTM) Brazil

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

This paper introduces a novel methodology for the partitioning of the social space associated with arbitrary groups of individuals into approachable regions. The proposed method exploits boundary points within pre-identified social spaces and classifies them into three distinct levels based on the field of view between pairs of individuals within the group. The effectiveness of this approach was rigorously assessed across both static and dynamic scenarios, illustrating successful segmentation and classification of approachable regions. Furthermore, the methodology underwent comprehensive testing using publicly available datasets, yielding consistently satisfactory outcomes. This innovative approach represents a substantial contribution to the field of human-robot interaction, showcasing significant potential for future enhancements and advancements.

关键词： Human-robot interaction Robots Testing

Deep Learning-Enabled ISAC-OTFS Pre-equalization Design for Aerial-Terrestrial Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Weihao Guo, Jing Wang, Siqiang Wang, Xinyi Yuan, Weijie Fei, Zesong the School of Information and Electronics Beijing Institute of Technology Beijing100081 China the School of System Design and Intelligent Manufacturing The Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China

Orthogonal time frequency space (OTFS) modulation has been viewed as a promising technique for integrated sensing and communication (ISAC) systems and aerial-terrestrial networks, due to its delay-Doppler domain transmission property and strong Doppler-resistance capability. However, it also suffers from high processing complexity at the receiver. In this work, we propose a novel pre-equalization based ISAC-OTFS transmission framework, where the terrestrial base station (BS) executes pre-equalization based on its estimated channel state information (CSI). In particular, the mean square error of OTFS symbol demodulation and Cramér-Rao lower bound of sensing parameter estimation are derived, and their weighted sum is utilized as the metric for optimizing the pre-equalization matrix. To address the formulated problem while taking the time-varying CSI into consideration, a deep learning enabled channel prediction-based pre-equalization framework is proposed, where a parameter-level channel prediction module is utilized to decouple OTFS channel parameters, and a low-dimensional prediction network is leveraged to correct outdated CSI. A CSI processing module is then used to initialize the input of the pre-equalization module. Finally, a residual-structured deep neural network is cascaded to execute pre-equalization. Simulation results show that under the proposed framework, the demodulation complexity at the receiver as well as the pilot overhead for channel estimation, are significantly reduced, while the symbol detection performance approaches those of conventional minimum mean square error equalization and perfect CSI. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel estimation

FusionPortableV2: A Unified Multi-Sensor Dataset for Generalized SLAM Across Diverse Platforms and Scalable Environments

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wei, Hexiang Jiao, Jianhao Hu, Xiangcheng Yu, Jingwen Xie, Xupeng Wu, Jin Zhu, Yilong Liu, Yuxuan Wang, Lujia Liu, Ming Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Robot Perception and Learning Lab Department of Computer Science University College London United Kingdom Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology China Guangzhou China

Simultaneous Localization and Mapping (SLAM) technology has been widely applied in various robotic scenarios, from rescue operations to autonomous driving. However, the generalization of SLAM algorithms remains a significant challenge, as current datasets often lack scalability in terms of platforms and environments. To address this limitation, we present FusionPortableV2, a multi-sensor SLAM dataset featuring sensor diversity, varied motion patterns, and a wide range of environmental scenarios. Our dataset comprises 27 sequences, spanning over 2.5 hours and collected from four distinct platforms: a handheld suite, a legged robot, a unmanned ground vehicle (UGV), and a vehicle. These sequences cover diverse settings, including buildings, campuses, and urban areas, with a total length of 38.7km. Additionally, the dataset includes ground-truth (GT) trajectories and RGB point cloud maps covering approximately 0.3km2. To validate the utility of our dataset in advancing SLAM research, we assess several state-of-the-art (SOTA) SLAM algorithms. Furthermore, we demonstrate the dataset's broad application beyond traditional SLAM tasks by investigating its potential for monocular depth estimation. The completae dataset, including sensor data, GT, and calibration details, is accessible at https://***/dataset/fusionportable v2. Copyright © 2024, The Authors. All rights reserved.

关键词： SLAM robotics

Category-level metric scale object shape and pose estimation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lee, Taeyeop Lee, Byeong-Uk Kim, Myungchul Kweon, In So Robotics and Computer Vision Laboratory KAIST Daejeon Korea Republic of

Advances in deep learning recognition have led to accurate object detection with 2D images. However, these 2D perception methods are insufficient for complete 3D world information. Concurrently, advanced 3D shape estimation approaches focus on the shape itself, without considering metric scale. These methods cannot determine the accurate location and orientation of objects. To tackle this problem, we propose a framework that jointly estimates a metric scale shape and pose from a single RGB image. Our framework has two branches: the Metric Scale Object Shape branch (MSOS) and the Normalized Object Coordinate Space branch (NOCS). The MSOS branch estimates the metric scale shape observed in the camera coordinates. The NOCS branch predicts the normalized object coordinate space (NOCS) map and performs similarity transformation with the rendered depth map from a predicted metric scale mesh to obtain 6d pose and size. Additionally, we introduce the Normalized Object Center Estimation (NOCE) to estimate the geometrically aligned distance from the camera to the object center. We validated our method on both synthetic and real-world datasets to evaluate category-level object pose and shape. Copyright © 2021, The Authors. All rights reserved.

关键词： Cameras

Graph Neural Networks for Human-Aware Social Navigation 21st

学校读者我要写书评

暂无评论

Graph Neural Networks for Human-Aware Social Navigation

21st International Workshop of Physical Agents, WAF 2020

作者： Manso, Luis J. Jorvekar, Ronit R. Faria, Diego R. Bustos, Pablo Bachiller, Pilar Department of Computer Science College of Engineering and Physical Sciences Aston University Birmingham United Kingdom Department of Computer Engineering Pune Institute of Computer Technology Pune India Robotics and Artificial Vision Laboratory University of Extremadura Badajoz Spain

ISBN: (纸本)9783030625788

Autonomous navigation is a key skill for assistive and service robots. To be successful, robots have to comply with social rules, such as avoiding the personal spaces of the people surrounding them, or not getting in the way of human-to-human and human-to-object interactions. This paper suggests using Graph Neural Networks to model how inconvenient the presence of a robot would be in a particular scenario according to learned human conventions so that it can be used by path planning algorithms. To do so, we propose two automated scenario-to-graph transformations and benchmark them with different Graph Neural Networks using the SocNav1 dataset [1]. We achieve close-to-human performance in the dataset and argue that, in addition to its promising results, the main advantage of the approach is its scalability in terms of the number of social factors that can be considered and easily embedded in code in comparison with model-based approaches. The code used to train and test the resulting graph neural network is available in a public repository. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Human robot interaction