Traffic extraction and characterisation from optical remote sensing data

Abstract

This paper presents a generic scheme to extract traffic information from both optical satellite imagery and optical airborne image sequences. The extraction is based on an explicit semantic model of traffic, from which, depending on the characteristics of the input data, different strategies for vehicle detection, vehicle queue extraction and motion estimation are derived. The model comprises different scales to exploit the scale‐dependent properties of traffic imaged by optical sensors. It is furthermore extended by context information to include knowledge about background objects as well as metadata from a road database in a consistent way. Various tests with different input data have been carried out and compared with manually acquired ground truth data of vehicles and vehicle tracks. The results show clearly the high potential of airborne and spaceborne traffic monitoring, but also indicate room for methodological improvements and exhibit some inherent sensor‐related drawbacks.

Airborne analysis and assessment of urban traffic scenes from LiDAR data — Theory and experiments

“…The motion analysis can be formulated as a binary classification problem. The input to the Lie distance classifier comprises a set of labeled samples from two vehicle categories ( 1,2) The classification of vehicle status can successfully run based solely on the first principal geodesics. Although there are significant variations in shape over one category, the first principal geodesics (1) v H is assumed to summarize the essential shape features of vehicle points in view of distinguishing the motion statuses.…”

“…Approaches rely not only on airborne video but on nearly the whole range of available sensors [2][3] [4]. The principal argument for the utilization of such sensors is that they complement stationary data collectors in the sense that they deliver not only local data but also observe the traffic situation over a larger region.…”

Extraction and motion estimation of vehicles in single-pass airborne LiDAR data towards urban traffic analysis

“…Traffic monitoring remains as one of the few fields which are still not as intensively analyzed in the LiDAR community compared to other modern sensor techniques such as frame and linear optical cameras (Zhao and Nevatia, 2003;Eikvil et al, 2009;Hinz et al, 2008;Larsen et al, 2009), Synthetic Aperture Radar (SAR) (Meyer et al, 2006;Bethke et al, 2006), and infrared (IR) cameras (Kirchhof and Stilla, 2006;Yao et al, 2009). The most relevant research to our work came from Toth and Grejner-Brzezinska (2006).…”

Model based traffic congestion detection in optical remote sensing imagery

“…Traffic monitoring from optical satellites is still limited due to the not sufficiently high spatial resolution, but the detection of vehicle queues seems to be promising [5]. As it is shown already in [6,7] airborne optical remote sensing technology has a great potential in traffic monitoring applications. Several airborne optical remote sensing systems are already in experimental use at the German Aerospace Center DLR, e.g.…”