检索结果-内蒙古大学图书馆

Vision-Based road segmentation With Active Gaze Control for Autonomous Vehicles

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2025年

作者： Xuan, Yuwen Chen, Jicheng Liu, Bin Wan, Xin Wen, Kai Chen, Long Zhang, Hui China Univ Petr Coll Mech & Transportat Engn Beijing 102249 Peoples R China Beihang Univ Sch Transportat Sci & Engn Beijing 102206 Peoples R China Beijing Inst Petrochem Technol Sch Informat Engn Beijing 102617 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In this article, we aim to enhance the accuracy and usefulness of vision-based road segmentation for autonomous vehicles across various scenarios by actively controlling the gaze of the camera. The camera is mounted on a pan-tilt with two degrees of freedom as azimuth and elevation. The control of the azimuth is a follow-up PID control method mimicking the preview mechanism of human drivers. It is mainly used to improve the usefulness of the road segmentation in turning conditions. The control of the elevation is mainly used to improve the accuracy of the road segmentation in extreme external conditions, at the same time, taking into consideration of the usefulness. The elevation control method is inspired by the saccade-fixation mechanism of human eyes that scans the surrounding environment in the saccade mode and focuses on the object of interesting in the fixation mode. Similarly, the active camera will capture images of the current scene at different candidate elevations and select the optimal elevation. Experimental results demonstrate that the proposed active gaze control method effectively improves the performance of various road segmentation techniques under challenging conditions such as toward-light scenarios, U-turns, and low-speed situations.

关键词： Active vision bird's-eye-view (BEV) features preview point road segmentation

来源：评论

学校读者我要写书评

暂无评论

Effective road segmentation With Selective State-Space Model and Frequency Feature Compensation

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Yang, Jing Liu, Ting Zhang, Lei Zhang, Yanning Northwestern Polytech Univ Sch Comp Sci Natl Engn Lab Integrated Aerosp Ground Ocean Big D Xian 710072 Peoples R China

road segmentation from high-resolution remote sensing imagery is critical for tasks such as autonomous driving, urban planning, and geographic information systems. However, challenges such as intensity nonuniformity, pixel ambiguity, and the visual similarity between roads and natural features make accurate segmentation difficult. In this article, we propose a road segmentation framework built upon the Mamba architecture, integrating a novel frequency feature compensation (FFC) approach to improve segmentation performance. Specifically, we introduce a progressive FFC method, leveraging wavelet decomposition to capture fine-grained details by separating features into high- and low-frequency components. Multistage features extracted from the Mamba backbone are decomposed using this approach and progressively integrated to compensate for the essential details for accurate road segmentation. We also introduce a wavelet loss (WL) to improve the model's ability to capture fine structural variations in the frequency domain. Furthermore, we develop a spatial perception Mamba block (SPMB) to enhance the capture of spatial relationships. By seamlessly integrating global context and local structures with the selective state-space model and FFC, our framework significantly boosts road segmentation accuracy. Extensive experiments on three publicly available road segmentation datasets demonstrate that our method achieves state-of-the-art performance, surpassing existing approaches in segmenting complex roads.

关键词： roads Feature extraction Image segmentation Computational modeling Remote sensing Computer architecture Accuracy Transformers Frequency-domain analysis Context modeling Frequency decomposition Mamba road extraction road segmentation selective state-space model

来源：评论

学校读者我要写书评

暂无评论

GAN-Assisted road segmentation from Satellite Imagery

引用

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2025年第1期21卷 1-29页

作者： Hu, Wenmiao Yin, Yifang Tan, Ying kiat Tran, An Kruppa, Hannes Zimmermann, Roger Natl Univ Singapore Grab NUS AI Lab COM113 Comp Dr Singapore Singapore ASTAR Inst Infocomm Res I2R 1 Fusionopolis Way21-01Connexis South Tower Singapore 117417 Singapore Natl Univ Singapore COM113 Comp Dr Singapore 117417 Singapore Mediacorp Pte Ltd 1 Stars Av Singapore 138507 Singapore Grabtaxi Holdings Pte Ltd 3 Media Close Singapore 138498 Singapore

Geo-information extraction from satellite imagery has become crucial to carry out large-scale ground surveys in a short amount of time. With the increasing number of commercial satellites launched into orbit in recent years, high-resolution RGB color remote sensing imagery has attracted a lot of attention. However, because of the high cost of image acquisition and even more complicated annotation procedures, there are limited high-resolution satellite datasets available. Compared to close-range imagery datasets, existing satellite datasets have a much lower number of images and cover only a few scenarios (cities, background environments, etc.). They may not be sufficient for training robust learning models that fit all environmental conditions or be representative enough for training regional models that optimize for local scenarios. Instead of collecting and annotating more data, using synthetic images could be another solution to boost the performance of a model. This article proposes a GAN-assisted training scheme for road segmentation from high-resolution RGB color satellite images, which includes three critical components: (a) synthetic training sample generation, (b) synthetic training sample selection, and (c) assisted training strategy. Apart from the GeoPalette and cSinGAN image generators introduced in our prior work, this article explains in detail how to generate new training pairs using OpenStreetMap (OSM) and introduces a new set of evaluation metrics for selecting synthetic training pairs from a pool of generated samples. We conduct extensive quantitative and qualitative experiments to compare different image generators and training strategies. Our experiments on the downstream road segmentation task show that (1) our proposed metrics are more aligned with the trained model performance compared to commonly used GAN evaluation metrics such as the Fr & eacute;chet inception distance (FID);and (2) by using synthetic data with the best training strategy,

关键词： GAN road segmentation satellite imagery data augmentation

来源：评论

学校读者我要写书评

暂无评论

DualStrip-Net: A Strip-Based Unified Framework for Weakly- and Semi-Supervised road segmentation From Satellite Images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Hu, Jingtao Li, Qiang Wang, Qi Northwestern Polytech Univ Sch Comp Sci Xian 710072 Peoples R China Northwestern Polytech Univ Sch Artificial Intelligence Opt & Elect iOPEN Xian 710072 Peoples R China

Automated road segmentation from remote sensing imagery remains a fundamental challenge in Earth observation systems. The primary bottleneck lies in acquiring dense pixel-wise annotations, which is both labor-intensive and time-prohibitive. This article presents DualStrip-Net, a novel deep learning framework for weakly supervised and semi-supervised road segmentation that effectively handles both sparse annotations and limited labeled data. Unlike conventional convolutional neural network (CNN)-based segmentation methods that lack explicit road topology modeling, DualStrip-Net exploits the inherent linear topology of road networks through a dual-stream architecture that combines patch-level annotation strategy and strip-based feature learning. The framework captures road characteristics through orthogonal strip processing in horizontal and vertical orientations. The proposed DualStrip Learning mechanism enables robust feature representation of road structures through complementary views. Extensive evaluations on the DeepGlobe, Massachusetts, and CHN6-CUG benchmark datasets demonstrate that DualStrip-Net achieves superior performance in both weakly supervised and semi-supervised settings. Notably, with only 20% of labeled training data, our method outperforms the supervised-only baselines on both Massachusetts and CHN6-CUG datasets. The code is available at https://***/jasonnhu/DualStrip-Net/.

关键词： roads Annotations Image segmentation Strips Remote sensing Topology Network topology Satellite images Representation learning Training DualStrip patch-level remote sensing imagery road segmentation semi-supervised weakly supervised

来源：评论

学校读者我要写书评

暂无评论

Evidence-Based Real-Time road segmentation With RGB-D Data Augmentation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第2期26卷 1482-1493页

作者： Xue, Feng Chang, Yicong Xu, Wenzhuang Liang, Wenteng Sheng, Fei Ming, Anlong Beijing Univ Posts & Telecommun Sch Comp Sci Beijing 100876 Peoples R China Univ Trento Dept Informat Engn & Comp Sci I-38123 Trento Italy Tencent Technol Beijing 100193 Peoples R China HuaAn Secur Co Ltd Hefei 230031 Peoples R China

Despite significant progress in RGB-D based road segmentation in recent years, the latest methods cannot achieve both state-of-the-art accuracy and real time due to the high-performance reliance on heavy structures. We argue that this reliance is due to unsuitable multimodal fusion. To be specific, RGB and depth data in road scenes are each sensitive to different regions, but current RGB-D based road segmentation methods generally combine features within sensitive regions which preserves false road representation from one of the data. Based on such findings, we design an Evidence-based road segmentation Method (Evi-roadSeg), which incorporates prior knowledge of the modal-specific characteristics. Firstly, we abandon the cross-modal fusion operation commonly used in existing multimodal based methods. Instead, we collect the road evidence from RGB and depth inputs separately via two low-latency subnetworks, and fuse the road representation of the two subnetworks by taking both modalities' evidence as a measure of confidence. Secondly, we propose an RGB-D data augmentation scheme tailored to road scenes to enhance the unique properties of RGB and depth data. It facilitates learning by adding more sensitive regions to the samples. Finally, the proposed method is evaluated on the widely used KITTI-road, ORFD, and R2D datasets. Our method achieves state-of-the-art accuracy at over 70 FPS, 5 $\times$ faster than comparable RGB-D methods. Furthermore, extensive experiments illustrate that our method can be deployed on a Jetson Nano 2GB with a speed of 8 $+$ FPS. The code will be released in https://***/xuefeng-cvr/Evi-roadSeg.

关键词： roads Accuracy Data augmentation Uncertainty Image segmentation Deep learning Real-time systems Laser radar Data models Computer science road segmentation evidence learning RGB-D data augmentation

来源：评论

学校读者我要写书评

暂无评论

DCN-Deeplabv3+: A Novel road segmentation Algorithm Based on Improved Deeplabv3+

引用

IEEE ACCESS 2024年 12卷 87397-87406页

作者： Peng, Hongming Xiang, Siyu Chen, Mingju Li, Hongyang Su, Qin Sichuan Univ Sci & Engn Artificial Intelligence Key Lab Sichuan Prov Yibin 644005 Peoples R China Sichuan Univ Sci & Engn Sch Automat & Informat Engn Yibin 644005 Peoples R China Power Internet Things Key Lab Sichuan Prov Chengdu 610095 Peoples R China

road segmentation is an important task in the field of semantic segmentation, and the Deeplabv3+ algorithm, which is commonly used for road segmentation, has shortcomings, such as numerous parameters and a tendency to lose detailed information. Therefore, this paper proposes DCN-Deeplabv3+, an improved road segmentation algorithm with dual attention modules based on the Deeplabv3+ network, aiming to reduce the model parameters and computation while improving the segmentation accuracy. (1) MobileNetV2 is used as the backbone network to reduce model parameters and memory consumption. (2) DenseASPP+SP is used for multi-scale information fusion to obtain a larger sensory field for improved model performance. (3) The deep learning model's understanding of the spatial structure of the input data is enhanced by using CA (coordinate attention) to improve the model's performance in dealing with spatial structure-related tasks. (4) The neural attention mechanism (NAM) is applied to better focus on key regions in the image, thereby improving the accuracy of target detection. The experimental results show that mIoU and mPA are improved by 1.20% and 2.30% on the PASCAL VOC 2012 dataset, mIoU and mPA are improved by 3.15% and 3.90% on the Cityscapes dataset, respectively. It can be concluded that the method proposed in this paper outperforms the baseline method and has excellent segmentation accuracy on roads.

关键词： Convolutional neural networks Feature extraction Semantic segmentation Task analysis Semantics road traffic Data integration road segmentation Deeplabv3+ multi-scale information fusion attention mechanism

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Loss Function for Semantic road segmentation in Remote Sensing Images

引用

IEEE ACCESS 2024年 12卷 74218-74229页

作者： Nanni, Loris Brahnam, Sheryl Loreggia, Andrea Univ Padua Dept Informat Engn DEI I-35131 Padua Italy Missouri State Univ Informat Technol & Cybersecur Springfield MO 65804 USA Univ Brescia Dept Informat Engn DII I-25123 Brescia Italy

The analysis of road continuity in satellite images is a complex challenge. This is due to the difficulty in identifying the directional vector of road sections, especially when the satellite view of roads is obstructed by trees or other structures. Today, most research focuses on optimizing the deep learning network topology, however, the accuracy of segmentation is affected by the loss function used in training;currently, little research has been published on ad-hoc loss functions for road segmentation. To solve this problem, we proposed loss functions based on topological pixel analysis, in which more weight is given to problematic pixels representing non-real road breaks. We report the results of different tests, obtaining state-of-the-art performance among convolution neural network-based approaches. For instance, on the Massachusetts roads dataset, our method achieved a Dice score of 75.34% and an IoU of 60.44%, compared to the best baseline scores of 74.64% and 59.51% achieved by GapLoss. Similarly, on the DeepGlobe roads dataset, our method obtained a Dice score of 79.78% and an IoU of 66.36%, outperforming the best baseline scores of 78.62% and 64.47% by GapLoss. Both the code and information for replicating our experiments are available at https://***/LorisNanni/An-Enhanced-Loss-Function-for-Semantic-road-segmentation-in-Remote-Sensing-Images, so as to enable future reliable comparisons.

关键词： roads Image segmentation Remote sensing Task analysis Convolution Feature extraction Deep learning Convolutional neural networks road segmentation optimization ensemble

来源：评论

学校读者我要写书评

暂无评论

Exploiting Low-Level Representations for Ultra-Fast road segmentation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第8期25卷 9909-9919页

作者： Zhou, Huan Xue, Feng Li, Yucong Gong, Shi Li, Yiqun Zhou, Yu Huazhong Univ Sci & Technol Hubei Key Lab Smart Internet Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China Univ Trento Dept Informat Engn & Comp Sci I-38123 Trento Italy Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China

Achieving real-time and accuracy on embedded platforms has always been the pursuit of road segmentation methods. To this end, they have proposed many lightweight networks. However, they ignore the fact that roads are "stuff" (background or environmental elements) rather than "things" (specific identifiable objects), which inspires us to explore the feasibility of representing roads with low-level instead of high-level features. Surprisingly, we find that the primary stage of mainstream network models is sufficient to represent most pixels of the road for segmentation. Motivated by this, we propose a Low-level Feature Dominated road segmentation network (LFD-roadSeg). Specifically, LFD-roadSeg employs a bilateral structure. The spatial detail branch is firstly designed to extract low-level feature representation for the road by the first stage of ResNet-18. To suppress texture-less regions mistaken as the road in the low-level feature, the context semantic branch is then designed to extract the context feature in a fast manner. To this end, in the second branch, we asymmetrically downsample the input image and design an aggregation module to achieve comparable receptive fields to the third stage of ResNet-18 but with less time consumption. Finally, to segment the road from the low-level feature, a selective fusion module is proposed to calculate pixel-wise attention between the low-level representation and context feature, and suppress the non-road low-level response by this attention. On KITTI-road, LFD-roadSeg achieves a maximum F1-measure (MaxF) of 95.21% and an average precision of 93.71%, while reaching 238 FPS on a single TITAN Xp and 54 FPS on a Jetson TX2, all with a compact model size of just 936k parameters. The source code is available at https://***/zhouhuan-hust/LFD-roadSeg.

关键词： roads Feature extraction Semantics Semantic segmentation Graphics processing units Object recognition Electronic mail road segmentation real-time low-level representation selective fusion

来源：评论

学校读者我要写书评

暂无评论

road segmentation from High-Fidelity Remote Sensing Images using a Context Information Capture Network

引用

COGNITIVE COMPUTATION 2022年第2期14卷 780-793页

作者： Zhu, Yuting Long, Lihong Wang, Jinjie Yan, Jingwen Wang, Xiaoqing Sun Yat Sen Univ Sch Elect & Commun Engn Guangzhou Peoples R China Shantou Univ Dept Elect Engn Shantou Guangdong Peoples R China

The automatic extraction of roads or buildings from remote sensing imagery plays a significant role in many urban applications. Recently, due to the impressive performance of deep learning, various road segmentation methods based on the fully convolutional network (FCN) have been proposed for optical remote sensing images. However, the existing FCN-based high-fidelity remote sensing image segmentation methods still have some limitations. As the repeated convolution and pooling operations employed in an FCN reduce the feature resolution and lose some detailed information, FCNs have a limited capacity to mine long-range dependencies among features. To address this issue, a context information capture network (CM-FCN) for road segmentation is proposed. To capture and aggregate multiscale contextual information, a dilated convolution module is designed. Furthermore, to boost the long-range dependencies of features for road detection, two attention modules employing the attention mechanism to adaptively combine local features with their global dependencies are designed. The context features extracted from the dilated convolution module are then fused into the attention modules to further improve the segmentation performance. The proposed model is evaluated on three challenging remote sensing image road segmentation datasets and one building segmentation dataset, including a dataset with our own manual labels. Comparisons demonstrate the effectiveness of our proposed method. We conclude that our proposed CM-FCN has the potential to automatically segment roads and buildings from high-resolution remote sensing images with an accuracy that renders it a useful tool for practical application scenarios.

关键词： Remote sensing road segmentation Contextual information Dilated convolution Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

"Where Does the Devil Lie?": Multimodal Multitask Collaborative Revision Network for Trusted road segmentation

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 10306-10317页

作者： Hua, Guoguang Zheng, Dalian Tian, Shishun Zou, Wenbin Liu, Shenglan Li, Xia Shenzhen Univ Coll Elect & Informat Engn Guangdong Key Lab Intelligent Informat Proc Shenzhen Key Lab Adv Machine Learning & Applicat Shenzhen 518060 Peoples R China Dalian Univ Technol Sch Comp Sci & Technol Dalian 116024 Peoples R China

road segmentation is an essential component of navigation systems. Although recent advancements in road segmentation, the occurrence of failure segmentations remains inevitable. For safety-critical tasks, e.g., navigation, knowing when and where road segmentation fails is crucial. In this paper, we propose a novel trusted road segmentation architecture, namely Multimodal Multitask Collaborative Revision Network (M2CRN), to improve the trust of road segmentation. Our approach incorporates two strategies to predict and rectify segmentation errors. First, a joint learning framework is devised to generate road segmentation results while estimating failure segmentation masks. Second, the road segmentation branch is equipped with an Uncertainty-Aware Revision Module (UARM), which eliminates the error in road segmentation. Additionally, we suppress the response of error regions in the road segmentation branch with an innovative design, called Adaptive Soft Error Suppression (ASES). To validate our methods, extensive experiments are conducted on three benchmark road segmentation datasets. The results demonstrate significant performance improvements with a real-time inference speed of 33.3 FPS, reaffirming the soundness of our revision model.

关键词： Deep learning multi-task learning road segmentation failure detection

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：