1,721,024 research outputs found
Heterogeneous Data Fusion for Accurate Road User Tracking: A Distributed Multi-Sensor Collaborative Approach
Full text linkThis work presents the design and validation of a distributed multi-sensor object tracking algorithm designed to integrate heterogeneous sensory data from multiple static acquisition stations. The primary challenge addressed is the accurate tracking of targets in complex urban environments, where occlusions and the dynamic nature of traffic frequently hinder detection and tracking efforts. This challenge is particularly relevant in multimodal exchange areas, where vehicular traffic merges with heavy pedestrian and bicycle flow. We also address the scenario of delayed detection, which can easily occur when data from multiple stations are combined or when intensive data processing is performed. Our algorithm ensures high coverage and accuracy by maintaining dual Extended Kalman Filter states for each object, thus allowing for the assimilation of delayed detections and preserving optimal filter estimates at all times. The results of the proposed pipeline, tested using a digital twin of the Milano Bovisa Campus, demonstrate its efficacy, achieving high tracking precision across various scenarios and sensor combinations. Moreover, the results highlight the advantages of a distributed multi-sensor acquisition system compared to a single central station
Traffic lights detection and tracking for HD map creation
No full text: HD-maps are one of the core components of the self-driving pipeline. Despite the effort of many companies to develop a completely independent vehicle, many state-of-the-art solutions rely on high-definition maps of the environment for localization and navigation. Nevertheless, the creation process of such maps can be complex and error-prone or expensive if performed via ad-hoc surveys. For this reason, robust automated solutions are required. One fundamental component of an high-definition map is traffic lights. In particular, traffic light detection has been a well-known problem in the autonomous driving field. Still, the focus has always been on the light state, not the features (i.e., shape, orientation, pictogram). This work presents a pipeline for lights HD-map creation designed to provide accurate georeferenced position and description of all traffic lights seen by a camera mounted on a surveying vehicle. Our algorithm considers consecutive detection of the same light and uses Kalman filtering techniques to provide each target's smoother and more precise position. Our pipeline has been validated for the detection and mapping task using the state-of-the-art dataset DriveU Traffic Light Dataset. The results show that our model is robust even with noisy GPS data. Moreover, for the detection task, we highlight how our model can correctly identify even far-away targets which are not labeled in the original dataset
Multi-layer occupancy grid mapping for autonomous vehicles navigation
Full text linkPerception of the surrounding is a crucial task in most of the autonomous driving scenarios. For this reason most vehicles are equipped with a broad range of sensors like lidar, radar, cameras and ultrasound to sense the space around the car. On the other end, planning algorithms need a simple and usable representation of the obstacle around. One of the biggest drawbacks of such a wide range of sensors is the need to resolve conflicting information and identify false positives. What we propose in this paper is an effective framework for sensor fusion and occupancy grid creation capable of retrieving a uniform representation of the ambient around the vehicle and able to handle conflictual information from different sensors
RadarLCD: Learnable Radar-based Loop Closure Detection Pipeline
No full textLoop Closure Detection (LCD) is an essential task in robotics and computer vision, serving as a fundamental component for various applications across diverse domains. These applications encompass object recognition, image retrieval, and video analysis. LCD consists in identifying whether a robot has returned to a previously visited location, referred to as a loop, and then estimating the related roto-translation with respect to the analyzed location. Despite the numerous advantages of radar sensors, such as their ability to operate under diverse weather conditions and provide a wider range of view compared to other commonly used sensors (e.g., cameras or LiDARs), integrating radar data remains an arduous task due to intrinsic noise and distortion. To address this challenge, this research introduces RadarLCD, a novel supervised deep learning pipeline specifically designed for Loop Closure Detection using the FMCW Radar (Frequency Modulated Continuous Wave) sensor. RadarLCD, a learning-based LCD methodology explicitly designed for radar systems, makes a significant contribution by leveraging the pre-trained HERO (Hybrid Estimation Radar Odometry) model. Being originally developed for radar odometry, HERO's features are used to select key points crucial for LCD tasks. The methodology undergoes evaluation across a variety of FMCW Radar dataset scenes, and it is compared to state-of-the-art systems such as Scan Context for Place Recognition and ICP for Loop Closure. The results demonstrate that RadarLCD surpasses the alternatives in multiple aspects of Loop Closure Detection
Beyond Image-Plane-Level: A Dataset for Validating End-to-End Line Detection Algorithms for Autonomous Vehicles
No full textOptimusLine: Consistent Road Line Detection Through Time
No full textIn the field of autonomous vehicles, the detection of road line markings is a crucial yet versatile component. It provides real-time guidance for navigation and low-level vehicle control, while it also enables the generation of lane-level HD maps. These maps require high precision to provide low-level details to all future map users. At the same time, control-oriented detection pipelines require increased inference frequency and high robustness to be deployed on a safety-critical system. With this work, we present OptimusLine, a versatile line detection pipeline tackling with ease both scenarios. Built around a frame-by-frame transformer-based neural model operating in image segmentation, we show that OptimusLine achieves state-of-the-art performance and analyze its computational impact. To provide robustness to perturbations when deployed on an actual vehicle, OptimusLine introduces a scheme exploiting temporal links between consecutive frames. Enforcing temporal consistency on each new line prediction, OptimusLine can generate more robust line descriptions and produce an estimate of its prediction uncertainty
RobustStateNet: Robust ego vehicle state estimation for Autonomous Driving
Full text linkControl of an ego vehicle for Autonomous Driving (AD) requires an accurate definition of its state. Implementation of various model-based Kalman Filtering (KF) techniques for state estimation is prevalent in the literature. These algorithms use measurements from IMU and input signals from steering and wheel encoders for motion prediction with physics-based models, and a Global Navigation Satellite System(GNSS) for global localization. Such methods are widely investigated and majorly focus on increasing the accuracy of the estimation. Ego motion prediction in these approaches does not model the sensor failure modes and assumes completely known dynamics with motion and measurement model noises. In this work, we propose a novel Recurrent Neural Network (RNN) based motion predictor that parallelly models the sensor measurement dynamics and selectively fuses the features to increase the robustness of prediction, in particular in scenarios where we witness sensor failures. This motion predictor is integrated into a KF-like framework, RobustStateNet that takes a global position from the GNSS sensor and updates the predicted state. We demonstrate that the proposed state estimation routine outperforms the Model-Based KF and KalmanNet architecture in terms of estimation accuracy and robustness. The proposed algorithms are validated in the modified NuScenes CAN bus dataset, designed to simulate various types of sensor failures
Event-based eye tracking for smart eyewear
Full text linkThis paper presents an innovative approach to gaze tracking in the context of smart eyewear, utilizing a fully event-based algorithm. Traditional gaze-tracking methods often rely on grayscale or infrared imaging, which can be computationally intensive and raise privacy concerns. Our research addresses these issues by developing an algorithm that exclusively uses data from event-based sensors, optimizing for the limited computational capabilities of smart eyewear. The system uses simple geometrical operations, enabling efficient real-time processing. Experimental results demonstrate the feasibility of this approach, offering a promising solution for gaze tracking in compact, computationally constrained devices. Despite certain limitations in accuracy due to optimization for efficiency, the research underscores the practicality of this approach for practical, privacy-conscious applications in smart eyewear technology
- …
