Semantic segmentation is a challenging task that addresses most of the perception needs of Intelligent Vehicles (IV) in an unified way. Deep Neural Networks excel at this task, as they can be trained end-to-end to accurately classify multiple object categories in an image at pixel level. However, a good trade-off between high quality and computational resources is yet not present in state-of-the-art semantic segmentation approaches, limiting their application in real vehicles. In this paper, we propose a deep architecture that is able to run in real-time while providing accurate semantic segmentation. The core of our architecture is a novel layer that uses residual connections and factorized convolutions in order to remain efficient while retaining remarkable accuracy. Our approach is able to run at over 83 FPS in a single Titan X, and 7 FPS in a Jetson TX1 (embedded GPU). A comprehensive set of experiments on the publicly available Cityscapes dataset demonstrates that our system achieves an accuracy that is similar to the state of the art, while being orders of magnitude faster to compute than other architectures that achieve top precision. The resulting trade-off makes our model an ideal approach for scene understanding in IV applications. The code is publicly available at: https://github.com/Eromera/erfnet

语义分割是自主车辆了解周围场景的关键技术。当代模型的吸引力表现通常以牺牲重计算和冗长的推理时间为代价，这对于自行车来说是无法忍受的。在低分辨率图像上使用轻量级架构（编码器 - 解码器或双路）或推理，最近的方法实现了非常快的场景解析，即使在单个1080TI GPU上以100多件FPS运行。然而，这些实时方法与基于扩张骨架的模型之间的性能仍有显着差距。为了解决这个问题，我们提出了一家专门为实时语义细分设计的高效底座。所提出的深层双分辨率网络（DDRNET）由两个深部分支组成，之间进行多个双边融合。此外，我们设计了一个名为Deep聚合金字塔池（DAPPM）的新上下文信息提取器，以基于低分辨率特征映射放大有效的接收字段和熔丝多尺度上下文。我们的方法在城市景观和Camvid数据集上的准确性和速度之间实现了新的最先进的权衡。特别是，在单一的2080Ti GPU上，DDRNET-23-Slim在Camvid测试组上的Citycapes试验组102 FPS上的102 FPS，74.7％Miou。通过广泛使用的测试增强，我们的方法优于最先进的模型，需要计算得多。 CODES和培训的型号在线提供。

语义分割是将类标签分配给图像中每个像素的问题，并且是自动车辆视觉堆栈的重要组成部分，可促进场景的理解和对象检测。但是，许多表现最高的语义分割模型非常复杂且笨拙，因此不适合在计算资源有限且低延迟操作的板载自动驾驶汽车平台上部署。在这项调查中，我们彻底研究了旨在通过更紧凑，更有效的模型来解决这种未对准的作品，该模型能够在低内存嵌入式系统上部署，同时满足实时推理的限制。我们讨论了该领域中最杰出的作品，根据其主要贡献将它们置于分类法中，最后我们评估了在一致的硬件和软件设置下，所讨论模型的推理速度，这些模型代表了具有高端的典型研究环境GPU和使用低内存嵌入式GPU硬件的现实部署方案。我们的实验结果表明，许多作品能够在资源受限的硬件上实时性能，同时说明延迟和准确性之间的一致权衡。

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second, we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third, we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed "DeepLab" system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7% mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

Segblocks通过根据图像区域的复杂性动态调整处理分辨率来降低现有神经网络的计算成本。我们的方法将图像拆分为低复杂性的块和尺寸块块，从而减少了操作数量和内存消耗的数量。轻量级的政策网络选择复杂区域，是使用强化学习训练的。此外，我们介绍了CUDA中实现的几个模块以处理块中的图像。最重要的是，我们的新颖的阻止模块可以防止现有方法遭受的块边界的特征不连续性，同时保持记忆消耗受到控制。我们对语义分割的城市景观，Camvid和Mapillary Vistas数据集进行的实验表明，与具有相似复杂性的静态基准相比，动态处理图像与复杂性的折衷相对于复杂性更高。例如，我们的方法将SwiftNet-RN18的浮点操作数量降低了60％，并将推理速度提高50％，而CityScapes的MIOU准确性仅降低0.3％。

Australian Centre for Robotic Vision {guosheng.lin;anton.milan;chunhua.shen;

Semantic segmentation works on the computer vision algorithm for assigning each pixel of an image into a class. The task of semantic segmentation should be performed with both accuracy and efficiency. Most of the existing deep FCNs yield to heavy computations and these networks are very power hungry, unsuitable for real-time applications on portable devices. This project analyzes current semantic segmentation models to explore the feasibility of applying these models for emergency response during catastrophic events. We compare the performance of real-time semantic segmentation models with non-real-time counterparts constrained by aerial images under oppositional settings. Furthermore, we train several models on the Flood-Net dataset, containing UAV images captured after Hurricane Harvey, and benchmark their execution on special classes such as flooded buildings vs. non-flooded buildings or flooded roads vs. non-flooded roads. In this project, we developed a real-time UNet based model and deployed that network on Jetson AGX Xavier module.

Image segmentation is a key topic in image processing and computer vision with applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among many others. Various algorithms for image segmentation have been developed in the literature. Recently, due to the success of deep learning models in a wide range of vision applications, there has been a substantial amount of works aimed at developing image segmentation approaches using deep learning models. In this survey, we provide a comprehensive review of the literature at the time of this writing, covering a broad spectrum of pioneering works for semantic and instance-level segmentation, including fully convolutional pixel-labeling networks, encoder-decoder architectures, multi-scale and pyramid based approaches, recurrent networks, visual attention models, and generative models in adversarial settings. We investigate the similarity, strengths and challenges of these deep learning models, examine the most widely used datasets, report performances, and discuss promising future research directions in this area.

我们展示了一个下一代神经网络架构，马赛克，用于移动设备上的高效和准确的语义图像分割。MOSAIC是通过各种移动硬件平台使用常用的神经操作设计，以灵活地部署各种移动平台。利用简单的非对称编码器 - 解码器结构，该解码器结构由有效的多尺度上下文编码器和轻量级混合解码器组成，以从聚合信息中恢复空间细节，Mosaic在平衡准确度和计算成本的同时实现了新的最先进的性能。基于搜索的分类网络，马赛克部署在定制的特征提取骨架顶部，达到目前行业标准MLPerf型号和最先进的架构，达到5％的绝对精度增益。

We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer. The architecture of the encoder network is topologically identical to the 13 convolutional layers in the VGG16 network [1]. The role of the decoder network is to map the low resolution encoder feature maps to full input resolution feature maps for pixel-wise classification. The novelty of SegNet lies is in the manner in which the decoder upsamples its lower resolution input feature map(s). Specifically, the decoder uses pooling indices computed in the max-pooling step of the corresponding encoder to perform non-linear upsampling. This eliminates the need for learning to upsample. The upsampled maps are sparse and are then convolved with trainable filters to produce dense feature maps. We compare our proposed architecture with the widely adopted FCN [2] and also with the well known DeepLab-LargeFOV [3], DeconvNet [4] architectures. This comparison reveals the memory versus accuracy trade-off involved in achieving good segmentation performance. SegNet was primarily motivated by scene understanding applications. Hence, it is designed to be efficient both in terms of memory and computational time during inference. It is also significantly smaller in the number of trainable parameters than other competing architectures and can be trained end-to-end using stochastic gradient descent. We also performed a controlled benchmark of SegNet and other architectures on both road scenes and SUN RGB-D indoor scene segmentation tasks. These quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures. We also provide a Caffe implementation of SegNet and a web demo at http://mi.eng.cam.ac.uk/projects/segnet/.

We focus on the challenging task of real-time semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference. We propose an image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address this challenge. We provide in-depth analysis of our framework and introduce the cascade feature fusion unit to quickly achieve highquality segmentation. Our system yields real-time inference on a single GPU card with decent quality results evaluated on challenging datasets like Cityscapes, CamVid and COCO-Stuff.

未经我们的知识，偏差可以过滤到AI技术。通常，开创性深度学习网络冠军高于其他一切。在本文中，我们试图通过迭代训练的无学习算法来缓解城市驾驶场景中的语义分段模型遇到的偏差。已经显示卷积神经网络依赖于颜色和纹理而不是几何形状。当安全关键型应用（例如自动驾驶汽车）时，在测试时间遇到具有协变量的图像时，这会提高问题 - 通过照明变化或季节性等变化引起的变化。在诸如MNIST之类的简单数据集上显示了偏见无线的概念证明。但是，该策略从未应用于高度变量培训数据的像素明智语义分割的安全关键领域 - 例如城市场景。对于基线和偏置未经学习方案的培训模型已经过针对颜色操纵验证集的性能进行了测试，从原始RGB图像中显示出在Miou中的差异高达85.50％ - 确认细分网络强烈取决于培训数据中的颜色信息进行分类。偏置未经学习方案表明，在最佳观察的情况下处理高达61％的调节的改善 - 并且在与基线模型相比，将“人”和“车辆”类始终如一地执行。

语义细分任务的目的是在像素级别上进行密集分类。深层模型在解决这项任务方面表现出进展。但是，这些方法的剩余问题是空间精度的丧失，通常是在分段对象的边界上产生的。我们提出的模型通过为特征表示形式提供内部结构来解决此问题，同时提取支持前者的全局表示。为了适应内部结构，在训练过程中，我们预测数据中的高斯混合模型，该模型与跳过连接和解码阶段合并，有助于避免换动态偏见。此外，我们的结果表明，我们可以通过提供集群行为并将其组合来通过提供学习表征（全球和本地）来改善语义细分。最后，我们提出的结果证明了我们在城市景观和合成数据集方面的进步。

TU Dresden www.cityscapes-dataset.net train/val -fine annotation -3475 images train -coarse annotation -20 000 images test -fine annotation -1525 images

Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "semantic image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Qualitatively, our "DeepLab" system is able to localize segment boundaries at a level of accuracy which is beyond previous methods. Quantitatively, our method sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 71.6% IOU accuracy in the test set. We show how these results can be obtained efficiently: Careful network re-purposing and a novel application of the 'hole' algorithm from the wavelet community allow dense computation of neural net responses at 8 frames per second on a modern GPU.

语义分割是图像的像素明智标记。由于在像素级别定义了问题，因此确定图像类标签是不可接受的，而是在原始图像像素分辨率下本地化它们是必要的。通过卷积神经网络（CNN）在创建语义，高级和分层图像特征方面的非凡能力推动;在过去十年中提出了几种基于深入的学习的2D语义分割方法。在本调查中，我们主要关注最近的语义细分科学发展，特别是在使用2D图像的基于深度学习的方法。我们开始分析了对2D语义分割的公共图像集和排行榜，概述了性能评估中使用的技术。在研究现场的演变时，我们按时间顺序分类为三个主要时期，即预先和早期的深度学习时代，完全卷积的时代和后FCN时代。我们在技术上分析了解决领域的基本问题的解决方案，例如细粒度的本地化和规模不变性。在借阅我们的结论之前，我们提出了一张来自所有提到的时代的方法表，每个方法都概述了他们对该领域的贡献。我们通过讨论现场当前的挑战以及他们已经解决的程度来结束调查。

现代车辆配备各种驾驶员辅助系统，包括自动车道保持，这防止了无意的车道偏离。传统车道检测方法采用了手工制作或基于深度的学习功能，然后使用基于帧的RGB摄像机进行通道提取的后处理技术。用于车道检测任务的帧的RGB摄像机的利用易于照明变化，太阳眩光和运动模糊，这限制了车道检测方法的性能。在自主驾驶中的感知堆栈中结合了一个事件摄像机，用于自动驾驶的感知堆栈是用于减轻基于帧的RGB摄像机遇到的挑战的最有希望的解决方案之一。这项工作的主要贡献是设计车道标记检测模型，它采用动态视觉传感器。本文探讨了使用事件摄像机通过设计卷积编码器后跟注意引导的解码器的新颖性应用了车道标记检测。编码特征的空间分辨率由致密的区域空间金字塔池（ASPP）块保持。解码器中的添加剂注意机制可提高促进车道本地化的高维输入编码特征的性能，并缓解后处理计算。使用DVS数据集进行通道提取（DET）的DVS数据集进行评估所提出的工作的功效。实验结果表明，多人和二进制车道标记检测任务中的5.54 \％$ 5.54 \％$ 5.54 \％$ 5.03 \％$ 5.03 \％$ 5.03。此外，在建议方法的联盟（$ iou $）分数上的交叉点将超越最佳最先进的方法，分别以6.50 \％$ 6.50 \％$ 6.5.37 \％$ 9.37 \％$ 。

交通场景边缘壳体的语义分割的鲁棒性是智能运输安全的重要因素。然而，交通事故的大多数关键场景都是非常动态和以前看不见的，这严重损害了语义分割方法的性能。另外，在高速驾驶期间传统相机的延迟将进一步降低时间尺寸中的上下文信息。因此，我们建议从基于事件的数据提取动态上下文，以更高的时间分辨率来增强静态RGB图像，即使对于来自运动模糊，碰撞，变形，翻转等的流量事故而言，此外，为评估分割交通事故中的性能，我们提供了一个像素 - 明智的注释事故数据集，即Dada-Seg，其中包含来自交通事故的各种临界情景。我们的实验表明，基于事件的数据可以通过在事故中保留快速移动的前景（碰撞物体）的微粒运动来提供互补信息以在不利条件下稳定语义分割。我们的方法在拟议的事故数据集中实现了+ 8.2％的性能增益，超过了20多种最先进的语义细分方法。已经证明该提案对于在多个源数据库中学到的模型，包括CityScapes，Kitti-360，BDD和Apolloscape的模型始终如一。

在本文中，我们专注于探索有效的方法，以更快，准确和域的不可知性语义分割。受到相邻视频帧之间运动对齐的光流的启发，我们提出了一个流对齐模块（FAM），以了解相邻级别的特征映射之间的\ textit {语义流}，并将高级特征广播到高分辨率特征有效地，有效地有效。 。此外，将我们的FAM与共同特征的金字塔结构集成在一起，甚至在轻量重量骨干网络（例如Resnet-18和DFNET）上也表现出优于其他实时方法的性能。然后，为了进一步加快推理过程，我们还提出了一个新型的封闭式双流对齐模块，以直接对齐高分辨率特征图和低分辨率特征图，在该图中我们将改进版本网络称为SFNET-LITE。广泛的实验是在几个具有挑战性的数据集上进行的，结果显示了SFNET和SFNET-LITE的有效性。特别是，建议的SFNET-LITE系列在使用RESNET-18主链和78.8 MIOU以120 fps运行的情况下，使用RTX-3090上的STDC主链在120 fps运行时，在60 fps运行时达到80.1 miou。此外，我们将四个具有挑战性的驾驶数据集（即CityScapes，Mapillary，IDD和BDD）统一到一个大数据集中，我们将其命名为Unified Drive细分（UDS）数据集。它包含不同的域和样式信息。我们基准了UDS上的几项代表性作品。 SFNET和SFNET-LITE仍然可以在UDS上取得最佳的速度和准确性权衡，这在如此新的挑战性环境中是强大的基准。所有代码和模型均可在https://github.com/lxtgh/sfsegnets上公开获得。

在这项工作中，我们将全景景观分割介绍为最整体的场景理解，无论是在视野（FOV）和图像级别的理解方面，用于基于标准摄像机的输入。完整的围绕理解为移动代理提供了最大的信息，这对于任何智能车辆至关重要，以便在安全至关重要的动态环境（例如现实世界流量）中做出明智的决定。为了克服缺乏带注释的全景图像，我们提出了一个框架，该框架允许在标准针孔图像上进行模型训练，并以成本限制的方式将学习的功能传输到不同的域。使用我们提出的方法和密集的对比度学习，我们设法对非适应方法实现了重大改进。根据有效的综合分割体系结构，我们可以在我们已建立的野生全景泛滥分割（WILDPPS）数据集中，以圆锥体质量（PQ）测量的3.5-6.5％提高3.5-6.5％。此外，我们的有效框架不需要访问目标域的图像，使其成为适合有限硬件设置的可行域概括方法。作为其他贡献，我们发布了WILDPPS：第一个全景全景图像数据集，以促进周围感知的进展，并探索一种结合受监督和对比度培训的新型培训程序。