检索结果-内蒙古大学图书馆

road detection based on simultaneous deep learning approaches

ROBOTICS AND AUTONOMOUS SYSTEMS 2020年 133卷 103605-103605页

作者： Almeida, Tiago Lourenco, Bernardo Santos, Vitor Univ Aveiro Dept Mech Engn Aveiro Portugal Univ Aveiro Inst Elect & Informat Engn Aveiro Aveiro Portugal

One of the most important challenges for Autonomous Driving and Driving Assistance systems is the detection of the road to perform or monitor navigation. Many works can be found in the literature to perform road and lane detection, using both algorithmic processing and learning based techniques. However, no single solution is mentioned to be applicable in any circumstance of mixed scenarios of structured, unstructured, lane based, line based or curb based limits, and other sorts of boundaries. So, one way to embrace this challenge is to have multiple techniques, each specialized on a different approach, and combine them to obtain the best solution from individual contributions. That is the central concern of this paper. By improving a previously developed architecture to combine multiple data sources, a solution is proposed to merge the outputs of two Deep Learning based techniques for road detection. A new representation for the road is proposed along with a workflow of procedures for the combination of two simultaneous Deep Learning models, based on two adaptations of the ENet model. The results show that the overall solution copes with the alternate failures or under -performances of each model, producing a road detection result that is more reliable than the one given by each approach individually. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Visual perception Data combination Deep learning Computer vision road map detection road lane lines detection road segmentation Driving assistance

来源：评论

学校读者我要写书评

暂无评论

3D Map Optimization with Fully Convolutional Neural Network and Dynamic Local NDT

3D Map Optimization with Fully Convolutional Neural Network ...

引用

IEEE Intelligent Transportation Systems Conference (IEEE-ITSC)

作者： Shen, Zebang Xu, Yichong Sun, Muchen Carballo, Alexander Zhou, Qingguo Lanzhou Univ Sch Informat Sci & Engn 222 Tianshui Rd Lanzhou Peoples R China Nagoya Univ Inst Innovat Future Soc Chikusa Ku Furo Cho Nagoya Aichi 4648601 Japan

ISBN: (纸本)9781538670248

Due to multi-path effects, GNSS-based localization methods are not always reliable in urban transportation scenes. To solve this problem, matching-based methods, which compare the real-time sensor data with a prior map, are widely used for urban autonomous driving. In these methods, high-precision noise-free 3D map plays an essential role in vehicle localization. This paper proposes a 3D map optimization framework to generate such map with high efficiency and low memory consumption. First, a deep learning based method is designed to automatically filter out non-map objects in mobile laser scans during mapping. Then, a method named dynamic local NDT is introduced for mapping and localization to improve efficiency and reduce memory usage. Furthermore, a road segmentation method is exploited for further optimization. The proposed framework only relies on LIDAR and GNSS-INS, which makes it simple and easily conducted. The mapping and positioning experimental results show that the proposed framework outperforms the conventional NDT method.

关键词： high precision map 3D object detection road segmentation deep learning autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Deep Learning Design and Training Tool for Unified Visual Driving Scene Understanding 19

Multi-Task Deep Learning Design and Training Tool for Unifie...

引用

19th International Conference on Control, Automation and Systems (ICCAS)

作者： Won, Woong-Jae Kim, Tae Hun Kwon, Soon DGIST Convergence Res Ctr Future Automot Technol Daegu 42988 South Korea

ISBN: (纸本)9788993215182

Visual driving scene perception systems have been gained popularity among the autonomous driving research community following the advent of deep learning technology. Moreover, the multi-task deep learning model has been an important tool with respect to unifying the tasks performed in a driving scene perception system, such as scene classification, object detection, segmentation, depth estimation. In this paper, we introduce our developed multi-task deep-learning model design and training tool, for unified road scene perception model. Additionally, we also propose a sequential auxiliary multi-task training method that can train a multi-task model, using different datasets for each tasks. Finally, we present a unified road segmentation and depth estimation model, based on multi-task deep learning, to verify the efficiency and feasibility of our developed tool. Experimental results for KITTI datasets show that our tool-based unified road segmentation and depth estimation model can successfully segment the driving road and estimate its depth.

关键词： visual driving scene perception autonomous vehicle multi-task deep learning model road segmentation depth estimation

来源：评论

学校读者我要写书评

暂无评论

Development of a road asset management database for quantitative landslide risk assessment along roads in Colombia

Development of a road asset management database for quantita...

引用

作者： Isip, Marcius University of Twente

学位级别：硕士

Landslides represent an important hazard that can result in significant damage to properties and may cause substantial economic impacts when they affect essential transportation corridors. Over the past 40 years, landslides in Colombia have resulted in about 400 Million USD in damages. Moreover, 60% of the country's road networks are affected by landslide problems. In response to this, a proactive approach of conducting quantified landslide risk assessments along the roadways is being conceptualized by the Colombian Geological Survey and the road agency INVIAS. This study contributes to the starting point for this proactive and risk-based approach by developing a proposed method for the generation of a road asset management database that allows future quantitative landslide risk assessments (QRA). Fieldwork was conducted along an initial road section transecting the towns of Copacabana and Girardota of the highway that connects Medellin and Bogota, Colombia to subdivide it into homogenous road segments and characterize each road segment and the immediate slopes while analyzing data sets presently available for integration in the database. The concept of delineating "areas of influence" (AOI) was formulated which are part of the standard units for road risk analysis. The AOI was defined as the immediate sloping areas in the vicinity of a road segment, possessing a homogenous set of characteristics related to the terrain, geology, land cover, mitigation measures and type of mass movements that may affect the road segment. The road network was segmented using the criteria mentioned above, and an AOI was delineated per segment. Different methods of delineating road segment AOI's were evaluated and compared to the field/ground- based AOI's produced. Of these methods, the field-based approach of delineating AOI's works best as a standalone method while the other approaches evaluated were applicable as a supplement. A method for predictive identification of landslide sourc

关键词： database structure road segmentation landslides risk analysis road management

来源：评论

学校读者我要写书评

暂无评论

Efficient road specular reflection removal based on gradient properties

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2018年第23期77卷 30615-30631页

作者： Wang, Yao Fu, Fangfa Lai, Fengchang Xu, Weizhe Shi, Jinjin Wang, Jinxiang Harbin Inst Technol Microelect Ctr Harbin 150000 Heilongjiang Peoples R China China Three Gorges Univ Coll Mech & Power Engn Yichang 443000 Peoples R China

Highlights caused by changes in sunlight throughout any given day cause failure in stereo matching, object recognition, and road segmentation. This is a serious challenge in advanced driver assistance systems (ADAS), because local high brightness and color discontinuities generally result in noticeable blurring of the road surface or object. This paper presents a novel strategy for removing specular reflection from highlight images by gradients distribution to optimize the diffuse image. The dark channel is introduced as a prior to initially estimate and locate the highlight. The threshold filter is then adopted to divide the high-intensity highlight and the weak highlight - the weak highlight affect neither the stereo matching nor road segmentation process. Finally, gradient properties (varying smoothness of specular and diffuse reflections) are presented to optimize the layer separation. Experimental results in speed and accuracy of road segmentation show that proposed method outperforms other techniques for separating highlights from road surfaces.

关键词： road segmentation ADAS Highlight removal Threshold filter Layer separation

来源：评论

学校读者我要写书评

暂无评论

Robust Lane Detection for Complicated road Environment Based on Normal Map

引用

IEEE ACCESS 2018年 6卷 49679-49689页

作者： Yuan, Chang Chen, Hui Liu, Ju Zhu, Di Xu, Yanyan Shandong Univ Sch Informat Sci & Engn Jinan 250100 Shandong Peoples R China MIT Dept Civil & Environm Engn 77 Massachusetts Ave Cambridge MA 02139 USA Univ Calif Berkeley Dept City & Reg Planning Berkeley CA 94720 USA

Detection of road or lane is indispensable for the environmental perception of advanced driver assistance systems. It has been an active field of research with a wide application prospect. However, due to the complex illumination and interferences, such as vehicles and shadows in the real driving environment, lane detection is still a challenging task today. To address these issues, a robust method for road segmentation and lane detection based on a normal map is proposed. The first step of this approach is to generate the normal map by using the depth information and then extract a segmented road pavement without vehicles and buildings based on the normal map. Second, we improve an adaptive threshold segmentation method and denoising operations to enhance the lane markings. Third, the combination of Hough transform and vanishing point makes it more accurate to determine the starting points of host lanes, and then the lanes in the following image sequence can be detected in the adaptive region of interest. Compared with the state-of-the-art methods, the experimental results on the data sets in two countries demonstrate that our approach produces more credible performance under various light conditions or dense traffic.

关键词： Advanced driver assistance systems complicated road environment lane detection road segmentation normal map

来源：评论

学校读者我要写书评

暂无评论

A distributed time-limited multicast algorithm for VANETs using incremental power strategy

引用

COMPUTER NETWORKS 2018年第Nov.9期145卷 141-155页

作者： Bousbaa, Fatima Zohra Lagraa, Nasreddine Kerrache, Chaker Abdelaziz Zhou, Fen Yagoubi, Mohamed Bachir Hussain, Rasheed Univ Laghouat Lab Informat & Math Route GhardaiaBP 37G Laghouat Algeria Univ Ghardaia Ghardaia Algeria Univ Avignon CERI LIA Avignon France Innopolis Univ Inst Informat Syst Innopolis Russia

Efficient information dissemination is the pinnacle of Vehicular Ad-hoc Networks (VANETs). In case of delay-sensitive information such as safety-related messages, it is imperative to minimize the transmission delay and increase the message reliability in VANETs. In a previous work, we proposed a Time-Limited Reliable Broadcast Incremental Power (TRBIP) algorithm, which is a centralized heuristic to reduce transmission interferences for safety message dissemination in VANETs. By reducing the total transmission energy and the number of hops, TRBIP is able to reduce the transmission interference and thus-forth maximizes the reliability. Furthermore, in TRBIP, VANETs' features such as vehicle mobility and frequent network fragmentation are also taken into account through store-carry-and-forward and the periodic multicast tree reconstruction strategies. However, multicast tree management is hard to maintain in urban environments due to the high density of nodes in VANETs (large trees), and is affected by the city streets organizations (intersections, roundabout, ... etc.). To address the afore-mentioned issues, in this paper we propose a Distributed version of Time-Limited Reliable Broadcast Incremental Power (DTRBIP) based on a road segmentation technique. Our proposal is extended to handle both delay-sensitive and delay-tolerant applications, and also both low and high dynamic VANETs scenarios respectively urban and highway environments. The results of the simulation conducted using NS-2 simulator advocate for the efficiency of our proposed method in term of reducing the total emission energy (at least by 150 dBm), reducing the average delay by 52%, increasing the packet delivery ratio by more than to 5%, and reducing the protocol overhead up to 3%. Obtained results show a clear enhancement compared to the previous solutions (i.e, RGRP-SA, RBIP, and TRBIP). (C) 2018 Elsevier B.V. All rights reserved.

关键词： VANET Multicast Delay-tolerant applications Delay-sensitive applications TRBIP DTRBIP road segmentation Group routing Safety and comfort applications

来源：评论

学校读者我要写书评

暂无评论

Passive Vision Region-Based road Detection: A Literature Review

引用

ACM COMPUTING SURVEYS 2019年第2期52卷 31-31页

作者： Rateke, Thiago Justen, Karla A. Chiarella, Vito F. Sobieranski, Antonio C. Comunello, Eros von Wangenheim, Aldo Univ Fed Santa Catarina Grad Program Comp Sci PPGCC Dept Informat & Stat Campus Joao David Ferreira Lima Trindade BR-88040970 Florianopolis SC Brazil Brazilian Inst Digital Convergence Image Proc & Comp Graph Lab Florianopolis SC Brazil Univ Fed Santa Catarina Florianopolis SC Brazil Univ Fed Santa Catarina Dept Comp Ararangua Brazil Univ Fed Santa Catarina Grad Program Mat Sci & Engn Program Florianopolis SC Brazil Univ Vale Itajai Itajai SC Brazil Univ Vale Itajai Appl Comp MCA Itajai SC Brazil

We present a literature review to analyze the state of the art in the area of road detection based upon frontal images. For this purpose, a systematic literature review (SLR) was conducted that focuses on analyzing region-based works, since they can adapt to different surface types and do not depend on road geometry or lane markings. Through the comprehensive study of publications in a 11-year time frame, we analyze the methods that are being used, on which types of surface they are applied, whether they are adaptive in relation to surface changes, and whether they are able to distinguish possible faults or changes in the road, such as potholes, shadows, and puddles.

关键词： Systematic literature review road detection road segmentation passive vision visual navigation

来源：评论

学校读者我要写书评

暂无评论

Real-Time Hybrid Multi-Sensor Fusion Framework for Perception in Autonomous Vehicles

引用

SENSORS 2019年第20期19卷 4357-4357页

作者： Jahromi, Babak Shahian Tulabandhula, Theja Cetin, Sabri Univ Illinois Mech & Ind Engn Chicago IL 60607 USA Univ Illinois Informat & Decis Sci Chicago IL 60607 USA

There are many sensor fusion frameworks proposed in the literature using different sensors and fusion methods combinations and configurations. More focus has been on improving the accuracy performance;however, the implementation feasibility of these frameworks in an autonomous vehicle is less explored. Some fusion architectures can perform very well in lab conditions using powerful computational resources;however, in real-world applications, they cannot be implemented in an embedded edge computer due to their high cost and computational need. We propose a new hybrid multi-sensor fusion pipeline configuration that performs environment perception for autonomous vehicles such as road segmentation, obstacle detection, and tracking. This fusion framework uses a proposed encoder-decoder based Fully Convolutional Neural Network (FCNx) and a traditional Extended Kalman Filter (EKF) nonlinear state estimator method. It also uses a configuration of camera, LiDAR, and radar sensors that are best suited for each fusion method. The goal of this hybrid framework is to provide a cost-effective, lightweight, modular, and robust (in case of a sensor failure) fusion system solution. It uses FCNx algorithm that improve road detection accuracy compared to benchmark models while maintaining real-time efficiency that can be used in an autonomous vehicle embedded computer. Tested on over 3K road scenes, our fusion algorithm shows better performance in various environment scenarios compared to baseline benchmark networks. Moreover, the algorithm is implemented in a vehicle and tested using actual sensor data collected from a vehicle, performing real-time environment perception.

关键词： environment perception sensor fusion LiDAR road segmentation fully convolutional network object detection and tracking extended Kalman filter autonomous vehicle

来源：评论

学校读者我要写书评

暂无评论

Complex Conditional Generative Adversarial Nets for Multiple Objectives Detection in Aerial Images 25th

Complex Conditional Generative Adversarial Nets for Multiple...

引用

25th International Conference on Neural Information Processing (ICONIP)

作者： Popescu, Dan Ichim, Loretta Docea, Andrei Univ Politehn Bucuresti Fac Automat Control & Comp Bucharest Romania

ISBN: (纸本)9783030042127;9783030042110

Simultaneously detection and evaluation of small regions of interest from aerial images is successfully achieved by conditional generative adversarial nets (cGAN). As novelty, the paper proposes a cheap and accurate method based on a cGAN structure, containing two generators, and graphics processing units (GPU) to segment small flooded areas and respectively, roads from images taken by unmanned aerial vehicles. In the learning phase the weights for the discriminator and the two generators are established by a back propagation method. The real mask is created by using information of the color components R, G, B, H and a voting scheme in a supervised process. A set of 40 images were used for the learning phase and another set of 100 images were used for method validation. The method presents the advantages of accuracy and time processing (especially in the operational phase).

关键词： Aerial images Flood segmentation road segmentation GPU image processing Conditional generative adversarial nets

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：