Related papers: Adversarial 3D Virtual Patches using Integrated Gr…

Machine learning is increasingly critical for analysis of the ever-growing corpora of overhead imagery. Advanced computer vision object detection techniques have demonstrated great success in identifying objects of interest such as ships,…

Our study assesses the adversarial robustness of LiDAR-camera fusion models in 3D object detection. We introduce an attack technique that, by simply adding a limited number of physically constrained adversarial points above a car, can make…

This paper describes an optimized single-stage deep convolutional neural network to detect objects in urban environments, using nothing more than point cloud data. This feature enables our method to work regardless the time of the day and…

Autonomous vehicles need to have a semantic understanding of the three-dimensional world around them in order to reason about their environment. State of the art methods use deep neural networks to predict semantic classes for each point in…

In GPS-denied scenarios, a robust environmental perception and localization system becomes crucial for autonomous driving. In this paper, a LiDAR-based online localization system is developed, incorporating road marking detection and…

Conducting safety simulations in various simulators, such as the Gazebo simulator, became a very popular means of testing vehicles against potential safety risks (i.e. crashes). However, this was not the case with security testing.…

The recently proposed pseudo-LiDAR based 3D detectors greatly improve the benchmark of monocular/stereo 3D detection task. However, the underlying mechanism remains obscure to the research community. In this paper, we perform an in-depth…

Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…

Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background. Many existing methods usually require fine-grained…

LiDAR has become one of the primary 3D object detection sensors in autonomous driving. However, LiDAR's diverging point pattern with increasing distance results in a non-uniform sampled point cloud ill-suited to discretized volumetric…

A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper. We leverage rich supervision from both detection and segmentation labels rather than using just one of them. In…

Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due to heavy token processing. To accelerate these models, token compression has been widely…

In this study, we address a gap in existing unsupervised domain adaptation approaches on LiDAR-based 3D object detection, which have predominantly concentrated on adapting between established, high-density autonomous driving datasets. We…

Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger misclassifications. Most existing defenses assume a single patch…

Real-time semantic segmentation of LiDAR data is crucial for autonomously driving vehicles, which are usually equipped with an embedded platform and have limited computational resources. Approaches that operate directly on the point cloud…

Pseudo-LiDAR 3D detectors have made remarkable progress in monocular 3D detection by enhancing the capability of perceiving depth with depth estimation networks, and using LiDAR-based 3D detection architectures. The advanced stereo 3D…

Patch attacks, one of the most threatening forms of physical attack in adversarial examples, can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous region. Certifiable patch defense can guarantee…

Event cameras report local changes of brightness through an asynchronous stream of output events. Events are spatially sparse at pixel locations with little brightness variation. We propose using a visual transformer (ViT) architecture to…

In this paper, we propose a new deep architecture for fusing camera and LiDAR sensors for 3D object detection. Because the camera and LiDAR sensor signals have different characteristics and distributions, fusing these two modalities is…

Vision sensors are versatile and can capture a wide range of visual cues, such as color, texture, shape, and depth. This versatility, along with the relatively inexpensive availability of machine vision cameras, played an important role in…