Scanning the Issue

Azim Eskandarian
2021 IEEE transactions on intelligent transportation systems (Print)  
The technical maturity of autonomous driving enables the discussion of beneficial use cases to leverage its full potential. This article targets one such use case: Platooning is the efficient convoying of vehicles which makes use of selfdriving capabilities and inter-vehicle communication. Indeed, the grouping of vehicles in platoons with a small inter-vehicle distance can result in numerous advantages, such as energy savings, congestion reduction, and safety improvements. Yet, given the
more » ... ty of involved stakeholders, a wide range of objectives must be balanced to make effective use of platooning's full potential. Moreover, these objectives depend on various factors that influence their optimization, increasing the complexity of this endeavor. So far, existent work mainly targets a limited subset of related objectives and underlying factors. To further stimulate the optimization of platooning, this article categorizes objectives and influencing factors and proposes metrics for the evaluation of objective attainment. Detection of Motorcycles in Urban Traffic Using Video Analysis: A Review J. E. Espinosa, S. A. Velastín, and J. W. Branch This paper reviews algorithms used for the detection and tracking of motorcycles on surveillance infrastructure provided by CCTV cameras. The paper considers the usual pipeline processes reported in the recent literature on topics such as detection, classification, and tracking. The review includes work on deep learning techniques used in this application field. The paper ends with the description of detection and tracking performance measures generally used, identifying the main publicly available datasets, it introduces the new Urban Motorbike Dataset (UMD) and reports quantitative evaluation results using different detection algorithms, discussing the challenges ahead and presenting a set of conclusions with proposed future work in this dynamic area. Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized highstreets. Unlike static obstacles, pedestrians are active agents with complex, interactive motions. Planning AV actions in the presence of pedestrians thus requires modeling of their
doi:10.1109/tits.2021.3113361 fatcat:x2xuoh2qefcdrmqpbwqfttcvhm