Search Results

Now showing 1 - 3 of 3

Some of the metrics are blocked by your
consent settings
Real-Time Vehicle Maneuvering Detection with Digital Compass
(2021-01-01)
Leakkaw, Puttipong
;
Panichpapiboon, Sooksan
Vehicle maneuverings are important pieces of information for many applications such as traffic incident detection and driving behavior recognition. On a macroscopic level, an unusually large number of some maneuvering events (e.g., lane changes) may suggest that a road incident occurs. On a microscopic level, vehicle maneuverings can tell how each individual person drives (e.g., safely or unsafely). A number of smartphone-based maneuvering detection methods have been proposed. However, most of them typically rely on accelerometer and gyroscope, and thus require the smartphone to be placed at a specific position on a vehicle and in a specific orientation. In this work, we take a rather different approach from most of the existing methods. Particularly, we investigate how effective it is to detect vehicle maneuverings by relying only on a signal from a digital compass on a smartphone. To this end, we introduce a simple rule-based maneuvering detection method which only takes the heading angles measured by the digital compass as inputs. This allows the smartphone to be placed freely at any position on the vehicle and in any orientation. Our results show that the digital compass can be used to detect turns and u-turns extremely well, and its accuracy on lane change detection is at an acceptable level.
Some of the metrics are blocked by your
consent settings
Clearance Estimation through Mobile Sensing
(2018-08-21)
Leakkaw, Puttipong
;
Panichpapiboon, Sooksan
Clearance is a spatial gap between two successive vehicles, which can be used to indicate the traffic condition. Obviously, the average clearance in a congested traffic will be smaller than that in a free-flow traffic. In most current infrastructure-based traffic information systems, clearances between vehicles could be estimated from an image or a video captured by fixed sensors such as traffic surveillance cameras. However, using fixed sensors is not effective in terms of cost, coverage, and convenience. A mobile sensing approach, which vehicles act as mobile sensors and collect the traffic data as they travel, is more appealing. In this paper, we explore a possibility of using a built-in camera on a smartphone for clearance estimation. The estimation algorithm and its accuracy will be discussed. Particularly, our experimental results show that the mean absolute errors of the estimates are within 10% of the actual reference values. This is suitable for a traffic sensing application.
Some of the metrics are blocked by your
consent settings
Real-Time Lane Change Detection Through Steering Wheel Rotation
(2018-07-02)
Leakkaw, Puttipong
;
Panichpapiboon, Sooksan
Lane change is an important traffic information. An abnormally high number of lane changes on a particular road section typically suggests that some lanes are blocked due to traffic incidents such as accidents and vehicle break downs. As a result, the lane change information is useful for automatic traffic incident detection. Currently, the lane change information of vehicles on an urban road is typically obtained from over-roadway fixed sensors such as surveillance cameras. However, using fixed sensors has limitations in terms of cost and coverage. It would be more effective if the lane change information could be collected directly from each individual vehicle. In this paper, we introduce a new mobile sensing approach to automatic real-time lane change detection. The lane change event is detected through the corresponding pattern of steering wheel rotation. The results show that the detection algorithm performs extremely well. Overall, it is able to achieve higher than 95% both in terms of precision and recall.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results