Prioritization of Lane-based Traffic Jam Detection for Automotive Navigation System utilizing Suddenness Index Calculation Method for Aggregated Values

Car navigation systems provide traffic jam information. We attempt to provide more detailed traffic jam information that considers the lane of a traffic jam so that the users can avoid waiting for a long time in a line going toward an unintended destination. Lane-based traffic jam detection utilizes image processing, which causes long processing time and high cost. To reduce them, we propose a “suddenness index” to categorize candidate areas as sudden or periodic because sudden traffic jams that may lead to accidents are considered to be more important. The proposed index quickly quantifies differences between the current aggregated number of cars and ordinary state values to label the area that contains more cars than usual as a high priority candidate for image processing. In this paper, we evaluated the proposed method using actual global positioning system (GPS) data and found that the proposed index can cover 100% of sudden traffic jams by lane while excluding 82.2% of traffic jam candidates. We also demonstrate the effectiveness of time savings by integrating the proposed method to a demonstration framework.