No. | Title・Author (Affiliation) |
---|---|
359 |
An Analysis of Characteristics of Law Violations Caused by Elderly Drivers in Pedestrian to Vehicle Collisions Yasufumi Sekine (Fukuyama University) In order to consider effective traffic safety countermeasures for elderly drivers, it is important to clarify the characteristics of accidents caused by elderly drivers through analysis of traffic accidents. In this study, the author conducted a statistical analysis of legal violations in pedestrian accidents and verified the pedestrian injury situation. And characteristics of legal violations by elderly drivers in pedestrian accidents have been clarified. |
360 |
Analysis of the Effect of Reducing Accidents Involving Bicyclists through the Coordination of Active Safety and Passive Safety Yuichi Omoda・Yuji Arai・Kazunori Kikuchi・Ryohei Homma (JARI)・Nobuhiko Takahashi (JAMA) In order to efficiently reduce traffic fatal accidents, it is important that all parties involved in traffic safety work in unison to implement countermeasures. For this purpose, it is necessary to analyze the reduction effects of vehicle safety measures and the accident patterns that remain after the vehicle safety measures are taken. In this study, the fatal accident reduction effect of vehicle safety measures combined with active and passive safety technologies was calculated for vehicle to bicycle accidents. In addition, the characteristics of the fatal accidents in which vehicle safety measures are not implemented are summarized. |
361 |
Near-Miss Incident Classification from Dashcam Video using SlowFast Networks Yucheng Zhang・Masataka Kato・Koichi Emura (Panasonic Automotive Systems)・Eiji Watanabe (National Institute for Basic Biology) This paper classifies near-miss traffic videos using the SlowFast deep neural network, which mimics the characteristics of slow and fast visual information processed by the two different streams from the M and P cells of the human brain. It analyzes the relation with human visual perception in the traffic environment, demonstrates how it can contribute to improving traffic safety, and provides new insights into future cognitive errors in traffic accidents. |
362 |
Efficient Traffic Scene Retrieval System by Vision-Language Model and Clustering Masafumi Tsuyuki (Hitachi)・Yoshitaka Atarashi・Trongmun Jiralerspong (Hitachi Astemo) Retrieving relevant traffic scene data from existing database is essential in the development of advanced driver-assistance systems but such task is time consuming and computationally expensive. This study proposes a traffic scene retrieval system that utilizes a vision-language model and clustering techniques. The proposed system is capable of executing data retrieval task by inputting an image data or text as a search query. Evaluation results showed that the system was able to retrieve complex scene data (e.g., traffic congestion) from a driving video database under 3 seconds. Overall, the results indicate that the prosed system is feasible for practical applications. |