Improving 3d Pedestrian Detection for Wearable Sensor Data With 2d Human Pose

Kamalasanan, Vinu; Yu, Feng,; Sester, Monika

doi:10.5194/isprs-annals-v-4-2022-219-2022

Cited by 3 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such virtual lanes should be visually appealing both during the day and night to serve as effective pedestrian infrastructure. Furthermore, we also believe that AR glasses might become common in near future as smartphones today and perhaps become a mobility aid [16], which can further support the maturity of our concept towards safety.…”

Section: Discussionmentioning

confidence: 73%

Improving Pedestrian Priority via Grouping and Virtual Lanes

Li¹,

Kamalasanan²,

Batista³

et al. 2022

Preprint

View full text Add to dashboard Cite

The shared space design is applied in urban streets to support barrier-free movement and integrate traffic participants (such as pedestrians, cyclists and vehicles) into a common road space. Regardless of the low-speed environment, sharing space with motor vehicles can make vulnerable road users feel uneasy. Yet, walking in groups increases their confidence as well as influence the yielding behavior of drivers. Therefore, we propose an innovative approach to support the crossing of pedestrians via grouping and project the virtual lanes in shared spaces. This paper presents the important components of the crowd steering system, discusses the enablers and gaps in the current approach, and illustrates the proposed idea with concept diagrams.

show abstract

Section: Discussionmentioning

confidence: 73%

Improving Pedestrian Priority via Grouping and Virtual Lanes

Li¹,

Kamalasanan²,

Batista³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Stepping into safety: a systematic review of extended reality technology applications in enhancing vulnerable road user safety

Sudhakaran,

Prabhakaran,

Booth

et al. 2024

SASBE

View full text Add to dashboard Cite

PurposeIn alignment with the European Union’s Vision Zero initiative to eliminate road fatalities by 2050, leveraging technological advancements becomes crucial for addressing the challenges of vulnerable road users (VRUs), and for mitigating the impact of human error. Despite increasing scholarly interest in applications of extended reality (XR), a research gap persists, particularly in the role of XR in transportation safety. Therefore, the aim of the study was to fill this gap through a systematic literature review to evaluate comprehensively the potential scope and practical applicability of XR technologies in enhancing the safety of VRUs.Design/methodology/approachA systematic review was undertaken, following PRISMA guidelines meticulously, in which 80 relevant articles from databases, such as Scopus and Science Direct, were identified and analysed.FindingsThe results of the analysis revealed the potential of XR beyond pedestrians and cyclists, and highlighted a lack of research about the impact of XR with regard to the personal traits or abilities of VRUs. The results of a thorough analysis confirmed the potential of XR as a promising solution for an approach to collaborative co-creation in addressing the safety challenges of VRUs. In addition, the integration of eye-tracking with virtual reality emerged as a promising innovation for enhancing the safety of vulnerable road users.Research limitations/implicationsTheoretical implications include enhancing the understanding of applications of XR in VRUs’ safety and providing insights into future research possibilities and methodological approaches. Valuable insights into search strategies and inclusion-exclusion criteria can guide future research methodologies.Practical implicationsPractically, the findings from the study offer insights to assist urban planners and transportation authorities in incorporating XR technologies effectively for VRUs safety. Identifying areas for further development of XR technology could inspire innovation and investment in solutions designed to meet the safety needs of VRUs, such as enhanced visualisation tools and immersive training simulations.Originality/valueThe findings of previous research underscore the vast potential of XR technologies within the built environment, yet their utilisation remains limited in the urban transport sector. The intricacies of urban traffic scenarios pose significant challenges for VRUs, making participation in mobility studies hazardous. Hence, it is crucial to explore the scope of emerging technologies in addressing VRUs issues as a pre-requisite for establishing comprehensive safety measures.

show abstract

Synchronous End-to-End Vehicle Pedestrian Detection Algorithm Based on Improved YOLOv8 in Complex Scenarios

Lei,

Yi,

Sarmiento

2024

Sensors

View full text Add to dashboard Cite

In modern urban traffic, vehicles and pedestrians are fundamental elements in the study of traffic dynamics. Vehicle and pedestrian detection have significant practical value in fields like autonomous driving, traffic management, and public security. However, traditional detection methods struggle in complex environments due to challenges such as varying scales, target occlusion, and high computational costs, leading to lower detection accuracy and slower performance. To address these challenges, this paper proposes an improved vehicle and pedestrian detection algorithm based on YOLOv8, with the aim of enhancing detection in complex traffic scenes. The motivation behind our design is twofold: first, to address the limitations of traditional methods in handling targets of different scales and severe occlusions, and second, to improve the efficiency and accuracy of real-time detection. The new generation of dense pedestrian detection technology requires higher accuracy, less computing overhead, faster detection speed, and more convenient deployment. Based on the above background, this paper proposes a synchronous end-to-end vehicle pedestrian detection algorithm based on improved YOLOv8, aiming to solve the detection problem in complex scenes. First of all, we have improved YOLOv8 by designing a deformable convolutional improved backbone network and attention mechanism, optimized the network structure, and improved the detection accuracy and speed. Secondly, we introduced an end-to-end target search algorithm to make the algorithm more stable and accurate in vehicle and pedestrian detection. The experimental results show that, using the algorithm designed in this paper, our model achieves an 11.76% increase in precision and a 6.27% boost in mAP. In addition, the model maintains a real-time detection speed of 41.46 FPS, ensuring robust performance even in complex scenarios. These optimizations significantly enhance both the efficiency and robustness of vehicle and pedestrian detection, particularly in crowded urban environments. We further apply our improved YOLOv8 model for real-time detection in intelligent transportation systems and achieve exceptional performance with a mAP of 95.23%, outperforming state-of-the-art models like YOLOv5, YOLOv7, and Faster R-CNN.

show abstract

Improving 3d Pedestrian Detection for Wearable Sensor Data With 2d Human Pose

Cited by 3 publications

References 26 publications

Improving Pedestrian Priority via Grouping and Virtual Lanes

Improving Pedestrian Priority via Grouping and Virtual Lanes

Stepping into safety: a systematic review of extended reality technology applications in enhancing vulnerable road user safety

Synchronous End-to-End Vehicle Pedestrian Detection Algorithm Based on Improved YOLOv8 in Complex Scenarios

Contact Info

Product

Resources

About