Autonomous driving significantly benefits from data-driven deep neural networks. However, the data in autonomous driving typically fits the long-tailed distribution, in which the critical driving data in adverse conditions is hard to collect. Although generative adversarial networks (GANs) have been applied to augment data for autonomous driving, generating driving images in adverse conditions is still challenging. In this work, we propose a novel framework, SUSTechGAN, with customized dual attention modules, multi-scale generators, and a novel loss function to generate driving images for improving object detection of autonomous driving in adverse conditions. We test the SUSTechGAN and the well-known GANs to generate driving images in adverse conditions of rain and night and apply the generated images to retrain object detection networks. Specifically, we add generated images into the training datasets to retrain the well-known YOLOv5 and evaluate the improvement of the retrained YOLOv5 for object detection in adverse conditions. The experimental results show that the generated driving images by our SUSTechGAN significantly improved the performance of retrained YOLOv5 in rain and night conditions, which outperforms the well-known GANs. The open-source code, video description and datasets are available on the page 1 to facilitate image generation development in autonomous driving under adverse conditions.
We presented a method for improving computer vision tasks on images affected by adverse weather conditions, including distortions caused by adherent raindrops. Overcoming the challenge of applying computer vision to images affected by adverse weather conditions is essential for autonomous vehicles utilizing RGB cameras. For this purpose, we trained an appropriate generative adversarial network and showed that it was effective at removing the effect of the distortions, in the context of image reconstruction and computer vision tasks. We showed that object recognition, a vital task for autonomou…
Cornell University（康奈尔大学）；the Ohio State University（俄亥俄州立大学）
A self-driving car must be able to reliably handle adverse weather conditions (e.g., snowy) to operate safely. In this paper, we investigate the idea of turning sensor inputs (i.e., images) captured in an adverse condition into a benign one (i.e., sunny), upon which the downstream tasks (e.g., semantic segmentation) can attain high accuracy. Prior work primarily formulates this as an unpaired image-to-image translation problem due to the lack of paired images captured under the exact same camera poses and semantic layouts. While perfectly-aligned images are not available, one can easily obtain…
Road scene understanding tasks have recently become crucial for self-driving vehicles. In particular, real-time semantic segmentation is indispensable for intelligent self-driving agents to recognize roadside objects in the driving area. As prior research works have primarily sought to improve the segmentation performance with computationally heavy operations, they require far significant hardware resources for both training and deployment, and thus are not suitable for real-time applications. As such, we propose a doubly contrastive approach to improve the performance of a more practical ligh…
ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception
ETH Zürich（苏黎世联邦理工学院）；Max Planck Institute for Informatics（马克斯·普朗克信息研究所）；Toyota Motor Europe（丰田欧洲公司）；INSAIT；Sofia University St. Kliment Ohridski（索菲亚大学圣克莱门特·奥赫里迪斯）
Reliable point cloud data is essential for perception tasks \textit{e.g.} in robotics and autonomous driving applications. Adverse weather causes a specific type of noise to light detection and ranging (LiDAR) sensor data, which degrades the quality of the point clouds significantly. To address this issue, this letter presents a novel point cloud adverse weather denoising deep learning algorithm (4DenoiseNet). Our algorithm takes advantage of the time dimension unlike deep learning adverse weather denoising methods in the literature. It performs about 10\% better in terms of intersection over …
Object detection in adverse weather conditions for autonomous vehicles using Instruct Pix2Pix
High-Performance Embedded Systems (HPES) Lab（高性能嵌入式系统实验室）；Barcelona Supercomputing Center（巴塞罗那超级计算中心）；Computer Science Dept.（计算机科学系）；Univ. Politècnica de Catalunya（巴塞罗那理工大学）；IDEAI-UPC- Research Center（IDEAI-UPC研究中心）
Recently, self-driving vehicles have been introduced with several automated features including lane-keep assistance, queuing assistance in traffic-jam, parking assistance and crash avoidance. These self-driving vehicles and intelligent visual traffic surveillance systems mainly depend on cameras and sensors fusion systems. Adverse weather conditions such as heavy fog, rain, snow, and sandstorms are considered dangerous restrictions of the functionality of cameras impacting seriously the performance of adopted computer vision algorithms for scene understanding (i.e., vehicle detection, tracking…
Finnish Geospatial Research Institute FGI, National Land Survey of Finland（芬兰国家土地调查局芬兰地理空间研究所（FGI））；Aalto University School of Science（阿尔托大学理学院）
Autonomous driving is challenging in adverse road and weather conditions in which there might not be lane lines, the road might be covered in snow and the visibility might be poor. We extend the previous work on end-to-end learning for autonomous steering to operate in these adverse real-life conditions with multimodal data. We collected 28 hours of driving data in several road and weather conditions and trained convolutional neural networks to predict the car steering wheel angle from front-facing color camera images and lidar range and reflectance data. We compared the CNN model performances…
Predictive uncertainty estimation is essential for safe deployment of Deep Neural Networks in real-world autonomous systems. However, disentangling the different types and sources of uncertainty is non trivial for most datasets, especially since there is no ground truth for uncertainty. In addition, while adverse weather conditions of varying intensities can disrupt neural network predictions, they are usually under-represented in both training and test sets in public datasets.We attempt to mitigate these setbacks and introduce the MUAD dataset (Multiple Uncertainties for Autonomous Driving), …
CADENet: Condition-Adaptive Asynchronous Dual-Stream Enhancement Network for Adverse Weather Perception in Autonomous Driving
Computer Science & Engineering Department, German University in Cairo (GUC), Egypt（德国开罗大学（GUC）计算机科学与工程系，埃及）；C-DRiVeS Lab: Cognitive Driving Research in Vehicular Systems, Cairo, Egypt（认知驾驶系统实验室（C-DRiVeS Lab），开罗，埃及）
KIOS Research and Innovation Center of Excellence（KIOS研究与卓越创新中心）；University of Cyprus（塞浦路斯大学）
Autonomous vehicles increasingly rely on cameras to provide the input for perception and scene understanding and the ability of these models to classify their environment and objects, under adverse conditions and image noise is crucial. When the input is, either unintentionally or through targeted attacks, deteriorated, the reliability of autonomous vehicle is compromised. In order to mitigate such phenomena, we propose DriveGuard, a lightweight spatio-temporal autoencoder, as a solution to robustify the image segmentation process for autonomous vehicles. By first processing camera images with…
Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time
Institute for Automotive Engineering RWTH Aachen University（亚琛工业大学汽车工程研究所）；Institute of Imaging and Computer Vision RWTH Aachen University（亚琛工业大学图像与计算机视觉研究所）
Accurate depth estimation under adverse night conditions has practical impact and applications, such as on autonomous driving and rescue robots. In this work, we studied monocular depth estimation at night time in which various adverse weather, light, and different road conditions exist, with data captured in both RGB and event modalities. Event camera can better capture intensity changes by virtue of its high dynamic range (HDR), which is particularly suitable to be applied at adverse night conditions in which the amount of light is limited in the scene. Although event data can retain visual …
Diffusion-Based Restoration for Multi-Modal 3D Object Detection in Adverse Weather
School of Xingzhi College, South China Normal University（星智学院，华南师范大学）；College of Big Data and Internet, Shenzhen Technology University（大数据与互联网学院，深圳科技大学）；School of Data Science and Engineering, Xingzhi College, South China Normal University（数据科学与工程学院，星智学院，华南师范大学）；Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology（电子与计算机工程系，香港科技大学）；College of Intelligence Science and Technology, National University of Defense Technology（智能科学与技术学院，国防科技大学）
Oxford Brookes University（牛津布鲁克斯大学）；University of Oxford（牛津大学）
In an autonomous driving system, perception - identification of features and objects from the environment - is crucial. In autonomous racing, high speeds and small margins demand rapid and accurate detection systems. During the race, the weather can change abruptly, causing significant degradation in perception, resulting in ineffective manoeuvres. In order to improve detection in adverse weather, deep-learning-based models typically require extensive datasets captured in such conditions - the collection of which is a tedious, laborious, and costly process. However, recent developments in Cycl…
3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds
Nanyang Technological University（南洋理工大学）；Waseda University（早稻田大学）；Technical University of Denmark（丹麦技术大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Ottawa（渥太华大学）；Carnegie Mellon University（卡内基梅隆大学）
When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration
School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学）；School of Electrical Engineering, Southeast University（电气工程学院，东南大学）；School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院，南京大学）
The fusion of multimodal sensor streams, such as camera, lidar, and radar measurements, plays a critical role in object detection for autonomous vehicles, which base their decision making on these inputs. While existing methods exploit redundant information in good environmental conditions, they fail in adverse weather where the sensory streams can be asymmetrically distorted. These rare "edge-case" scenarios are not represented in available datasets, and existing fusion architectures are not designed to handle them. To address this challenge we present a novel multimodal dataset acquired in o…
University of Stuttgart（斯图加特大学）；Robert Bosch GmbH（罗伯特·博世有限公司）
Integrating different representations from complementary sensing modalities is crucial for robust scene interpretation in autonomous driving. While deep learning architectures that fuse vision and range data for 2D object detection have thrived in recent years, the corresponding modalities can degrade in adverse weather or lighting conditions, ultimately leading to a drop in performance. Although domain adaptation methods attempt to bridge the domain gap between source and target domains, they do not readily extend to heterogeneous data distributions. In this work, we propose an unsupervised d…
