Context-supported vehicle detection in optical satellite images of urban areas

Abstract

Due to increasing traffic there is high demand in traffic monitoring of densely populated urban areas. In our approach we focus on the detection of vehicle queues and use a priori information of roads location and direction. In high resolution satellite imagery single vehicles can hardly be separated since they are merged to either dark or bright ribbons. Initial hypotheses for the queues can be extracted as lines in scale space which represent the centres of the queues. We exploit the context information that vehicle queues are composed of repetitive patterns. For discrimination of single vehicles a width function of the queues is calculated in the gradient image and the variations of the width function are analyzed. We show intermediate and final results of processing a panchromatic QuickBird image covering a part of an inner city area. ‡ A preliminary version of this article has been presented at the ISPRS-Workshop on "High Resolution Earth Imaging for Geo-Information", Hanover, 2005.

Vehicle detection from high-resolution satellite imagery using morphological shared-weight neural networks

“…Because of the limited spatial resolution of IKONOS data, we conclude that reliable vehicle detection can only be achieved by incorporating contextual information. Hence, we use a GIS road vector map to constrain vehicle detection to road networks and this is consistent with a large body of previous work using context-supported approaches [4,6,[9][10][11][12]14]. Road networks can also be obtained by automated road extraction systems [1].…”

“…Most vehicle detection research has been done using aerial imagery with a spatial resolution of 0.35 m or less [3][4][5][6][7][8][9][10]. Vehicle detection research has seldom been done using high-resolution satellite imagery where spatial resolutions of the panchromatic band are presently in the range of 0.6-1.0 m [11,12]. Burlina et al [6] postulated that vehicles are context-sensitive objects whose detection requires information about the surrounding environment.…”

One for Vehicle Detection and Adaptive Background Updating Algorithm

“…But the dynamic changes of scene, the method independent of the incident light and other external interference is particularly sensitive. Because we need to consider many factors, the establishment of an appropriate dynamic background model is more difficult [6] . …”

Vehicle detection from parking lot aerial images

“…The vehicle information in parking lots is rarely collected. Hence, area-wide images are required to complement these selectively acquired data [1] [2]. Vehicles can be observed very clearly on these high resolution aerial images.…”