We explored Google Street View (GSV) as a street-level, urban greenery assessment tool. Street-level greenery has long played a critical role in the visual quality of urban landscapes. This living landscape element can and should be assessed for the quality of visual impact with the GSV information, and the assessed street-level greenery information could be incorporated into urban landscape planning and management. Information on street-level views of urban greenery assessment, however, is rare or nonexistent. Planners and managers' ability to plan and manage urban landscapes effectively and efficiently is, therefore, limited. GSV is one tool that might provide street-level, profile views of urban landscape and greenery, yet no research on GSV for urban planning seems available in literature. We modified an existing Green View Index (GVI) formula and conducted a case study assessment of street greenery using GSV images in the area of East Village, Manhattan District, New York City. We found that GSV to be well suited for assessing street-level greenery. We suggest further that the modified GVI may be a relatively objective measurement of street-level greenery, and that GSV in combination with GVI may be well suited in guiding urban landscape planning and management.
translated by 谷歌翻译
在深度学习和计算机视觉的蓬勃发展中,在不同的科学领域,在城市发展方面,深度学习和计算机视觉应用仍然局限于智能城市和自动驾驶汽车的概念。实际上,在欠发达国家的城市和城市地区出现了很大的知识差距,其中非正规性的混乱是主导方案。深度学习和人工智能(AI)如何解决非正规性的复杂性,以促进城市建模和我们对城市的理解?在人工智能和计算机视觉范式中,可以提出关于北方和南方城市未来的各种问题和分歧。在本文中,我们引入了一种新的多目标逼真 - 动态城市建模方法,依靠深度学习和计算机视觉,使用深度卷积神经网络(CNN),除了探测之外,还可以从航空和街道视图图像中感知和检测城市场景中的非正规性和贫民窟。步行和运输模式。该模型已经在整个城市的城市场景图像上进行了训练。该模型很好地验证了计划区域和非计划区域之间的广泛差异,包括非正式区域和区域区域。我们尝试推进城市建模,以更好地了解城市发展的动态。我们还旨在举例说明人工智能在城市中的重要影响,而不仅仅是在主流中讨论和感知智慧城市的情况。 URBAN-i模型的算法在Python编程中使用预先训练的深度学习模型进行了完全编码,可用作全球各个角落的工具形成和城市建模,包括非正式聚落和贫民窟地区。
translated by 谷歌翻译
随着学习算法和硬件开发的最新进展,自动驾驶汽车在良好驾驶条件下在结构化环境中运行时显示出前景。然而,对于具有高度不确定性的复杂,混乱和不可见的环境,自动驾驶系统仍经常表现出错误或意外的行为,这可能导致灾难性的后果。自主车辆应该理想地适应驾驶条件;虽然这可以通过多种途径实现,但作为一个能够以某种量化形式表征驾驶性能的第一步将是有益的。为此,本文旨在创建一个框架,用于调查可能影响驾驶性能的不同因素。此外,自适应驾驶系统适应任何驾驶条件的主要机制之一是能够从代表性场景中学习和概括。目前这样做的机器学习算法主要以监督的方式学习,因此需要足够的数据来进行稳健和有效的学习。因此,我们还对45个公共驾驶数据集进行了比较概述,这些数据集可以实现学习并发布此数据集索引:http://sites.google.com/view/driveability-survey-datasets。具体而言,我们根据用例对数据集进行分类,并突出显示捕获复杂危险驾驶条件的数据集,这些数据集可以更好地用于训练强大的驾驶模型。此外,通过讨论现有公共数据集未涵盖哪些驾驶场景以及哪些驾驶性因素需要更多调查和数据采集,本文旨在鼓励有针对性的数据集收集和提高不可驾驶性指标的提议,以提高自动驾驶汽车在恶劣环境中的稳健性。
translated by 谷歌翻译
对于人类驾驶员而言,后视镜和侧视镜对于安全驾驶至关重要。它们可以更全面地了解汽车周围发生的事情。人类驾驶员也大量利用他们的心理地图进行导航。尽管如此,已经发布了几种方法,学习驾驶模型只有前置摄像头而没有路线规划器。缺乏这种信息使得自驾车的任务变得十分棘手。我们在一个更现实的环境中调查问题,该环境包括一个带有八个摄像头的环视摄像系统,一个路线规划器和一个CAN总线阅读器。特别是,我们开发了一种传感器设置,可以为车辆周围区域的360度视图,到目的地的行车路线以及人类驾驶员的低级驾驶操作(例如转向角和速度)提供数据。使用这种传感器设置我们收集了一个新的驾驶数据集,涵盖了多样化的场景和不同的天气/照明条件。最后,通过整合来自环绕视图相机和路线规划器的信息,我们学习了一种新颖的驾驶模型。利用两个路线规划器:1)通过将OpenStreetMap上的计划路线表示为一堆GPS坐标,以及2)通过在TomTom Go Mobile上渲染计划路线并将该演进记录到视频中。我们的实验表明:1)360度全景摄像机有助于避免单个前视摄像头发生的故障,特别是对于城市驾驶和交叉场景; 2)路线规划员有助于显着的驾驶任务,尤其是转向角度预测。
translated by 谷歌翻译
Intersections are known for their integral and complex nature due to a variety of the participants' behaviors and interactions. This paper presents a review of recent studies on the behavior at intersections and the safety analysis for three types of participants at intersections: vehicles, drivers, and pedestrians. This paper emphasizes on techniques which are strong candidates for automation with visual sensing technology. A new behavior and safety classification is presented based on key features used for intersection design, planning, and safety. In addition, performance metrics are introduced to evaluate different studies, and insights are provided regarding the state of the art, inputs, algorithms, challenges, and shortcomings.
translated by 谷歌翻译
设计自主车辆感知系统的基本挑战之一是在各种各样的操作条件下验证每种算法的性能。在基于视觉的语义分割的情况下,当遇到与训练数据足够不同的新场景时存在已知问题。此外,即使照明和降水等环境条件的微小变化也会影响分割模型的分类性能。鉴于对视觉信息的依赖,这些影响通常转化为诗歌像素分类,这可能潜在地导致自动驾驶时的灾难性后果。本文提出了一种新的方法来分析语义分割模型的鲁棒性,并提供了许多指标来评估各种环境条件下的分类性能。该过程包含一个额外的传感器(激光雷达),以自动化该过程,消除了对劳动密集型验证数据的手动标记的需要。可以监视系统完整性,因为视觉传感器的性能针对不同的传感器模态进行验证。这对于检测视觉技术固有的故障是必要的。基于在一年中不同时间收集的具有不同环境条件的多个数据集来呈现实验结果。这些结果表明,语义分割性能取决于天气,摄像机参数,阴影的存在等。结果还说明了在对模型进行改进后如何使用度量来比较和验证性能,并比较不同的性能。网络。
translated by 谷歌翻译
灾难发生后,结构工程师团队从受损建筑物中收集大量图像,以获取新知识并从事件中汲取教训。然而,在许多情况下,所捕获的图像在没有足够空间背景的情况下被捕获。当损坏严重时,甚至可能很难识别建筑物。需要访问建筑物的灾前状况的图像以准确地识别故障原因或建筑物中的实际损失。在这里,为了解决这个问题,我们开发了一种方法,可以自动从360度全景图像(全景图)中提取事件前建筑图像。通过提供在目标建筑附近收集的地理标记图像作为输入,靠近通过街景服务(例如,Google或Bing在美国)下载的输入图像位置区域的全景图。通过计算全景图和目标建筑物之间的几何关系,识别最合适的全景图投影方向以生成建筑物的高质量2D图像。基于区域的卷积神经网络被用于识别那些2D图像内的建筑物。使用几个全景图,使得检测到的建筑物图像提供建筑物的各种视点。为了说明这项技术的能力,我们考虑了美国德克萨斯州假日海滩的住宅楼,它们在2017年的飓风哈维中经历了重大的破坏。利用在实际的灾后建筑侦察任务中收集的地理标记图像,我们通过成功提取住宅建筑图像来验证该方法。 Google街景视图,在活动前拍摄。
translated by 谷歌翻译
Designing autonomous vehicles suitable for urban environments remains an unresolved problem. One of the major dilemmas faced by autonomous cars is how to understand the intention of other road users and communicate with them. The existing datasets do not provide the necessary means for such higher level analysis of traffic scenes. With this in mind, we introduce a novel dataset which in addition to providing the bounding box information for pedestrian detection, also includes the behavioral and contextual annotations for the scenes. This allows combining visual and semantic information for better understanding of pedestri-ans' intentions in various traffic scenarios. We establish baseline approaches for analyzing the data and show that combining visual and contextual information can improve prediction of pedestrian intention at the point of crossing by at least 20%.
translated by 谷歌翻译
基于场景的高度自动化车辆安全验证测试是一种有前途的方法,正在研究和工业中进行检验。这种方法严重依赖于来自真实场景的数据来获取测试所需的场景信息。测量数据应该以合理的努力收集,包含道路使用者的自然行为,并包括与所识别的场景的质量不足相关的所有数据。然而,目前的测量方法不能满足至少一个要求。因此,我们提出了一种从空中角度测量数据的新方法,用于满足上述要求的基于场景的验证。此外,我们提供了一个名为highD的德国高速公路的大型自然车辆轨迹数据集。我们根据数量,种类和所包含的情景来评估数据。我们的数据集包括来自6个地点的11.5小时测量,其中110,000个车辆,总驱动距离为45 000 km,5600个记录完整的车道变换。 highD数据集可在线获取:http://www.highD-dataset.com
translated by 谷歌翻译
Autonomous and assisted driving are undoubtedly hot topics in computer vision. However, the driving task is extremely complex and a deep understanding of drivers' behavior is still lacking. Several researchers are now investigating the attention mechanism in order to define computational models for detecting salient and interesting objects in the scene. Nevertheless, most of these models only refer to bottom up visual saliency and are focused on still images. Instead, during the driving experience the temporal nature and peculiarity of the task influence the attention mechanisms, leading to the conclusion that real life driving data is mandatory. In this paper we propose a novel and publicly available dataset acquired during actual driving. Our dataset, composed by more than 500,000 frames, contains drivers' gaze fixations and their temporal integration providing task-specific saliency maps. Geo-referenced locations, driving speed and course complete the set of released data. To the best of our knowledge, this is the first publicly available dataset of this kind and can foster new discussions on better understanding, exploiting and reproducing the driver's attention process in the autonomous and assisted cars of future generations.
translated by 谷歌翻译
提出了一种深度学习模型,用于实时预测区块级停车事故。该模型利用图形卷积神经网络(GCNN)提取大规模网络中交通流的空间关系,并利用具有长短期记忆(LSTM)的递归神经网络(RNN)来捕获时间特征。此外,该模型能够将多个异构结构的交通数据源作为输入,例如停车计时器交易,交通速度和天气条件。通过位于匹兹堡市区的案例研究评估模型性能。所提出的模型优于其他基线方法,包括多层LSTM和Lasso,当提前30分钟预测块级停车占用时,平均测试MAPE为12.0 \%。案例研究还表明,一般来说,预测模型对于商业领域比休闲场所更好。我们发现,结合交通速度和天气信息可以显着提高预测性能。天气数据对于改善休闲区域的预测准确性特别有用。
translated by 谷歌翻译
Realizing autonomy is a hot research topic for automatic vehicles in recent years. For a long time, most of the efforts to this goal concentrate on understanding the scenes surrounding the ego-vehicle (autonomous vehicle itself). By completing low-level vision tasks, such as detection, tracking and segmentation of the surrounding traffic participants, e.g., pedestrian, cyclists and vehicles, the scenes can be interpreted. However, for an autonomous vehicle, low-level vision tasks are largely insufficient to give help to comprehensive scene understanding. What are and how about the past, the ongoing and the future of the scene participants? This deep question actually steers the vehicles towards truly full automation, just like human beings. Based on this thoughtfulness, this paper attempts to investigate the interpretation of traffic scene in autonomous driving from an event reasoning view. To reach this goal, we study the most relevant literatures and the state-of-the-arts on scene representation, event detection and intention prediction in autonomous driving. In addition, we also discuss the open challenges and problems in this field and endeavor to provide possible solutions.
translated by 谷歌翻译
对于在人行道上航行的移动机器人,必须能够跨越街道交叉口。大多数现有方法依赖于交通灯信号的识别以作出明智的交叉决定。尽管这些方法已成为城市导航的关键促成因素,但采用这种方法的机器人的能力仍然有限,仅限于在包含信号交叉口的街道上。在本文中,我们解决了这一挑战,并提出了一种多模式卷积神经网络框架,以预测交叉口的街道交叉口的安全性。 Ourarchitecture包含两个子网络;交互感知轨迹估计流IA-TCNN,其预测场景中所有观察到的交通参与者的未来状态,以及交通灯识别流AthtteNet。我们的IA-TCNN利用扩张的因果卷积来模拟场景中可观察的动态代理的行为,而无需明确地为它们之间的交互分配优先级。虽然AtteNet利用挤压激励块来学习用于从数据中选择相关特征的内容感知机制,从而提高噪声鲁棒性。来自交通灯识别流的学习表示与来自运动预测流的估计轨迹融合以学习交叉决策。此外,我们扩展了我们之前引入的FreiburgStreet Crossing数据集,其中包含了在不同类型的交叉点捕获的序列,展示了交通参与者之间复杂的相互作用。对公共基准数据集和我们提出的数据集的广泛实验评估表明,我们的网络实现了每个子任务的最新性能,以及交叉安全性预测。
translated by 谷歌翻译
驾驶员注意力预测目前正成为安全驾驶研究界的焦点,例如DR(eye)VE项目和新出现的BerkeleyDeepDrive Attention(BDD-A)数据库在危急情况下。在安全驾驶中,一项基本任务是尽早预测即将发生的事故.BDD-A意识到了这个问题并且由于这种场景的罕见性而在实验室中收集了驾驶员的注意力。然而,BDD-A专注于不会遇到实际事故的危急情况,只是面对驾驶员注意预测任务,没有事故预测的紧密步骤。与此形成对比的是,我们探索驾驶员眼睛捕捉多种事故的观点,并建立一个比以往更加多样化和更大的视频基准,同时引起驾驶员注意和驾驶事故注释(命名为DADA-2000),其中有2000年视频片段在54种事故中拥有约658,476帧。这些剪辑是在各种场合(高速公路,城市,乡村和隧道),天气(晴天,下雨和下雪)和光线条件(白天和夜晚)中获取和捕获的。对于驾驶员注意力表示,我们收集地图附加物,扫视扫描路径和聚焦时间。事故由他们的类别,剪辑中的事故窗口和崩溃对象的空间位置注释。在分析的基础上,我们得到了本文中问题的定量和正向性。
translated by 谷歌翻译
深度学习的最新进展使得可以使用街道级图像在精细分辨率和大范围内量化城市度量。在这里,我们专注于使用谷歌街景(GSV)图像来测量城市树木覆盖。首先,我们提供一个小规模的标记验证数据集,并提出标准指标,以比较使用GSV自动估算街道树木覆盖的性能。我们应用最先进的深度学习模型,并将其性能与先前建立的无监督方法基准进行比较。我们的深度学习模型的训练程序是新颖的;我们利用丰富的公开可用和类似标记的街道级图像数据集来预训我们的模型。然后,我们对由GSV图像组成的小型训练数据集执行额外训练。我们发现深度学习模型明显优于无人监督的基准方法。我们的语义分割模型相对于无监督方法将平均交叉联合(IoU)从44.10%增加到60.42%,而oundnd-end模型将平均绝对误差从10.04%减少到4.67%。我们还采用了最近开发的一种称为梯度加权类激活图(Grad-CAM)的方法来解释端到端模型学到的特征。该技术证实,端到端模型已经准确地学会识别树覆盖区域作为预测百分比树木覆盖的关键特征。我们的论文提供了一个将高级深度学习技术应用于大规模,地理标记和基于图像的数据集的示例,以有效地估计重要的城市指标。结果表明,深度学习模型非常准确,可以解释,并且在数据标记工作和计算资源方面也可以是高效的。
translated by 谷歌翻译
Currently autonomous or self-driving vehicles are at the heart of academia and industry research because of its multi-faceted advantages that includes improved safety, reduced congestion , lower emissions and greater mobility. Software is the key driving factor underpinning autonomy within which planning algorithms that are responsible for mission-critical decision making hold a significant position. While transporting passengers or goods from a given origin to a given destination, motion planning methods incorporate searching for a path to follow, avoiding obstacles and generating the best trajectory that ensures safety, comfort and efficiency. A range of different planning approaches have been proposed in the literature. The purpose of this paper is to review existing approaches and then compare and contrast different methods employed for the motion planning of autonomous on-road driving that consists of (1) finding a path, (2) searching for the safest manoeuvre and (3) determining the most feasible trajectory. Methods developed by researchers in each of these three levels exhibit varying levels of complexity and performance accuracy. This paper presents a critical evaluation of each of these methods, in terms of their advantages/disadvantages, inherent limitations , feasibility, optimality, handling of obstacles and testing operational environments. Based on a critical review of existing methods, research challenges to address current limitations are identified and future research directions are suggested so as to enhance the performance of planning algorithms at all three levels. Some promising areas of future focus have been identified as the use of vehicular communications (V2V and V2I) and the incorporation of transport engineering aspects in order to improve the look-ahead horizon of current sensing technologies that are essential for planning with the aim of reducing the total cost of driverless vehicles. This critical review on planning techniques presented in this paper, along with the associated discussions on their constraints and limitations, seek to assist researchers in accelerating development in the emerging field of autonomous vehicle research. Crown
translated by 谷歌翻译
Urbanization's rapid progress has modernized many people's lives but also engendered big issues, such as traffic congestion, energy consumption, and pollution. Urban computing aims to tackle these issues by using the data that has been generated in cities (e.g., traffic flow, human mobility, and geographical data). Urban computing connects urban sensing, data management, data analytics, and service providing into a recurrent process for an unobtrusive and continuous improvement of people's lives, city operation systems, and the environment. Urban computing is an interdisciplinary field where computer sciences meet conventional city-related fields, like transportation, civil engineering, environment, economy, ecology, and sociology in the context of urban spaces. This article first introduces the concept of urban computing, discussing its general framework and key challenges from the perspective of computer sciences. Second, we classify the applications of urban computing into seven categories, consisting of urban planning, transportation, the environment, energy, social, economy, and public safety and security, presenting representative scenarios in each category. Third, we summarize the typical technologies that are needed in urban computing into four folds, which are about urban sensing, urban data management, knowledge fusion across heterogeneous data, and urban data visualization. Finally, we give an outlook on the future of urban computing, suggesting a few research topics that are somehow missing in the community.
translated by 谷歌翻译
In autonomous driving systems a strong relation to highly accurate maps is taken to be inevitable, although street scenes change frequently. However, a preferable system would be to equip the automated cars with a sensor system that is able to navigate urban scenarios without an accurate map. We present a novel pipeline using a deep neural network to detect lane semantics and topology given RGB images. On the basis of this classification, the information about the road scene can be extracted just from the sensor setup supporting mapless autonomous driving. In addition to superseding the huge effort of creating and maintaining highly accurate maps, our system reduces the need for precise localization. Using an extended Cityscapes dataset, we show accurate ego lane detection including lane semantics on challenging scenarios for autonomous driving.
translated by 谷歌翻译
In this work we aim to predict the driver's focus of attention. The goal is to estimate what a person would pay attention to while driving, and which part of the scene around the vehicle is more critical for the task. To this end we propose a new computer vision model based on a multi-branch deep architecture that integrates three sources of information: raw video, motion and scene semantics. We also introduce DR(eye)VE, the largest dataset of driving scenes for which eye-tracking annotations are available. This dataset features more than 500,000 registered frames, matching ego-centric views (from glasses worn by drivers) and car-centric views (from roof-mounted camera), further enriched by other sensors measurements. Results highlight that several attention patterns are shared across drivers and can be reproduced to some extent. The indication of which elements in the scene are likely to capture the driver's attention may benefit several applications in the context of human-vehicle interaction and driver attention analysis.
translated by 谷歌翻译