This study analyzes the basic principles and structural models of multi-sensor data fusion, and emphasizes the importance of effective fusionalgorithms. The proposed improved weighted information fusion algorithm com...
详细信息
This review surveyed infrastructure-based sensor technologies for protecting vulnerable road users (vRUs) in traffic safety systems, focusing on four key components of the roadside system: calibration methods, sensor ...
详细信息
This review surveyed infrastructure-based sensor technologies for protecting vulnerable road users (vRUs) in traffic safety systems, focusing on four key components of the roadside system: calibration methods, sensorfusion approaches, trajectory prediction, and risk analysis frameworks. The paper analyzes different sensor types, discussing their characteristics, advantages, and limitations. Key challenges in sensor calibration for roadside deployment are addressed, alongside various fusion strategies at data, feature, and decision levels. The review covers trajectory prediction methods, from classical approaches to deep learning architectures, examining their applications in vRU behavior analysis. A comprehensive evaluation of safety assessment methodologies using surrogate safety measures is provided, considering both single and multi-sensor implementations. Technical challenges including scalability, real-time processing, and sensor synchronization are discussed, while identifying opportunities in emerging technologies such as advanced AI and vehicle-to-everything (v2X) integration. The paper concludes by addressing future research directions and ethical implications for improving urban vRU safety.
The neuromuscular dysfunction known as Freezing of Gait (FoG), which is more prevalent in individuals suffering from Parkinson's Disease (PD), significantly reduces the quality of life and increases their risk of ...
详细信息
The neuromuscular dysfunction known as Freezing of Gait (FoG), which is more prevalent in individuals suffering from Parkinson's Disease (PD), significantly reduces the quality of life and increases their risk of falling. Wearable FoG sensing technologies provide timely biofeedback cues to assist people regain control over their gait. However, the devices being bulky, intrusive, and annoyance of current FoG detection algorithms limit their usability in real-world applications. This study proposes a more efficient approach by integrating the FoG detection fusion algorithm into a Functional Electrical Stimulation (FES) module. The design leverages features with low computational requirements and specialized hardware to minimize the use of physical space and memory. The Convolutional Neural Networks (CNN) approach with SvM output was deployed to classify FoG and non-FoG periods in real-time. Additionally, the study uses CNN algorithms in fusion with data from a triaxial accelerometer, strain sensors, and piezoelectric plantar sensors to test shank-worn FoG detection devices. The study demonstrates that electrical stimulation-based cueing strategies significantly improve gait control and mitigate FoG episodes in people with Parkinson's disease. The AiCareGaitRehabilitation system employs a multi-modal sensorfusion strategy to improve the efficacy of the FES device. Data from various sensors-such as strain sensor, 18 plantar sensors, and four quadriceps sensors-the system provides a holistic view of both pre-freezing of Gait (pre-FOG) and post-freezing of Gait (post-FOG) scenarios. This research aims to improve mobility, reduce fall risks, and eventually improve the quality of life for individuals with Parkinson's disease.
Wearable inertial measurement units offer opportunities to monitor and study running kinematics in relatively unconstrained environments. However, there remain many challenges for accurately estimating joint angles fr...
详细信息
Wearable inertial measurement units offer opportunities to monitor and study running kinematics in relatively unconstrained environments. However, there remain many challenges for accurately estimating joint angles from inertial measurement unit sensor data. One important challenge involves determining the sensor-to-segment alignment parameters which specify the relative positions and orientations between the sensor and anatomical coordinate frames. Errors in these parameters can lead to errors in joint angle estimates, so it is important for practitioners, researchers, and algorithm developers to understand the required accuracy of sensor-to-segment alignment parameters for different applications. In this study, 480,000 simulations were used to investigate the effects of varying levels of simultaneous sensor-to-segment alignment errors on the accuracy of joint angle estimates from an inertial measurement unit-based method for running. The results demonstrate that accurate lower limb joint angle estimates are obtainable with this method when sensor-to-segment alignment errors are low, but these estimates rapidly degrade as errors in the relative orientations between frames grow. The results give guidance on how accurate sensor-to-segment alignment parameters must be for different applications. The methods used in this paper may also provide a valuable framework for assessing the impact of simultaneous sensor-to-segment alignment errors for other inertial measurement unit based algorithms and activities.
The development of Society of Automotive Engineers (SAE) Level 5 Autonomous vehicles (Avs), which are capable of navigating a variety of roads and weather situations on their own, is examined in this study. Through th...
详细信息
The integration of Traffic Light Detection (TLD) systems with Advanced Emergency Braking Systems (AEBS) marks a critical milestone in enhancing road safety and paving the way for advanced autonomous driving. This surv...
详细信息
ISBN:
(纸本)9789819783540
The integration of Traffic Light Detection (TLD) systems with Advanced Emergency Braking Systems (AEBS) marks a critical milestone in enhancing road safety and paving the way for advanced autonomous driving. This survey paper provides a panoramic and extensive overview of the state-of-the-art TLD solutions leveraging sensors and deep learning techniques. With an increasing emphasis on accident prevention and traffic management, the intersection of TLD and AEBS has become a focal point of research and development. This survey begins by elucidating the fundamental challenges associated with TLD, including varying environmental conditions, occlusions, and complex traffic scenarios. We explore the pivotal role of sensors such as cameras, LiDAR, and radar in providing the requisite data for TLD, and delve into the intricacies of sensorfusion techniques for enhanced perception. Deep Learning has emerged as a cornerstone technology in TLD, enabling robust object detection, classification, and real-time decision-making. We meticulously analyze a spectrum of deep learning architectures including Single-Shot Detectors (SSD), Faster R-CNN, YOLO, and custom-designed networks tailored for TLD applications. Furthermore, the survey examines critical components of the TLD pipeline, encompassing data collection, preprocessing, model training, real-time inference, and integration with AEBS. Emphasis is placed on real-time constraints, multi-modal sensorfusion, and adaptability to diverse traffic light configurations. The paper also delves into the significance of accurate traffic light state prediction, going beyond mere detection to anticipate traffic light changes and optimize vehicle control actions. Human-centric interaction and privacy concerns are addressed, encompassing driver warnings, user interfaces, and data anonymization strategies. Moreover, the survey discusses the importance of safety, validation, and collaboration within the TLD and AEBS ecosystem, emphasizing compl
The lost Saraswati River offers a significant challenge for geomorphologists and archaeologists. It is believed that the river used to flow through the present-day Thar Desert during the vedic age. It desiccated betwe...
详细信息
The lost Saraswati River offers a significant challenge for geomorphologists and archaeologists. It is believed that the river used to flow through the present-day Thar Desert during the vedic age. It desiccated between similar to 7000 and similar to 1200 BC due to tectonic and climatic changes, leaving behind palaeochannels and playas in northwestern Rajasthan. This study aims to delineate the ancient Saraswati River and its associated palaeochannels using multi-sensor satellite data, including SAR (Sentinel-1A, ALOS PALSAR), multispectral (Sentinel-2A), and DEM. Multiple fusionalgorithms (IHS, GS, PCA, Wavelet, and Ehlers) were used to fuse SAR and optical data, enhancing the visibility of the river course and palaeochannels. various image indices assessing surface moisture and vegetation patterns further helped in palaeochannel detection. Among the fused images, the IHS, GS, and PCA techniques, combining Sentinel-2 and ALOS PALSAR data, were found to be the most effective in highlighting palaeochannels. Further, image indices such as NDvI, NDWI and NDMI led to confirm palaeochannels and the old river course by showing linearly oriented vegetation and soil moisture. The study successfully traced two major palaeo-courses of the Saraswati River, originating from the Ghaggar River near Anupgarh and flowing through Beriyawali, Bahla, Tanot, and Jaisalmer before emptying into the Great Rann of Kutch. Additionally, three major palaeo-drainage systems of the Saraswati River could be delineated. Moreover, the association of the Harappan archaeological sites distribution along with the delineated Saraswati River course and its paleochannels, evidence from the historical maps, and bore-well drilling data (groundwater levels and lithologs) also confirm the results of this study.
暂无评论