Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique

Fischler, Martin A.; Tenenbaum, Jay M.; Wolf, H. C.

doi:10.1016/0146-664x(81)90056-3

Cited by 285 publications

(123 citation statements)

References 14 publications

Supporting

Mentioning

121

Contrasting

Unclassified

Order By: Relevance

“…It is therefore natural to look for paths of maximum curvature in the curvature images" introduced in Section 3.2 and computed using the terrain mesh. As shown in dynamic programming algorithm Fischler et al, 1981 to nd a path C that minimizes E Curv C= Z C max f s , C 1 max 2 ds ; 2 where f s i s a v ector function mapping the arc length s to points u; v along the curve, C max u; v is the terrain's surface maximal curvature at image location u; v , and C 1 max is the largest value of C max u; v in the curvature image. Using recent dynamic programming implementations Mortensen andBarrett, 1995, Cohen andKimmel, 1996 , this can be done in near real time on a regular workstation, making this approach a v ery attractive w a y t o s k etch the drainage pattern.…”

Section: Steep Terrainmentioning

confidence: 99%

“…Furthermore, Koenderink and Van Doorn have shown 1993 that the strictly local di erential criteria many of these systems use to detect valleys have inherent problems that must be addressed using a more global approach. Much work has also been devoted to the extraction of linear patterns from single images using techniques such as dynamic programming Fischler andWolf, 1983, Merlet andZerubia, 1995 or graph-based techniques Fischler et al, 1981 . These techniques typically do not use the terrain information or guarantee that the recovered drainage pattern satis es the physical constraints discussed above.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Untitled

Fua

1998

International Journal of Computer Vision

View full text Add to dashboard Cite

We propose an automated approach to modeling drainage channels|and, more generally, linear features that lie on the terrain|from multiple images. It produces models of the features and of the surrounding terrain that are accurate and consistent and requires only minimal human intervention.We take advantage of geometric constraints and photommetric knowledge. First, rivers ow d o wnhill and lie at the bottom valleys whose oors tend to be either V-or U-shaped. Second, the drainage pattern appears in gray-level images as a network of linear features that can be visually detected.Many approaches have explored individual facets of this problem. Ours uni es these elements in a common framework. We accurately model terrain and features as 3 dimensional objects from several information sources that may be in error and inconsistent with one another. This approach allows us to generate models that are faithful to sensor data, internally consistent and consistent with physical constraints. We h a v e proposed generic models that have been applied to the speci c task at hand. We show that the constraints can be expressed in a computationally e ective w a y and, therefore, enforced while initializing the models and then tting them to the data. Furthermore, these techniques are general enough to work on other features that are constrained by predictable forces.

show abstract

Section: Steep Terrainmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Untitled

Fua

1998

International Journal of Computer Vision

View full text Add to dashboard Cite

show abstract

“…al. [9] apply the F algorithm based on line extraction from low-resolution images. Neuenschwander et.…”

Section: Introductionmentioning

confidence: 99%

Automatic extraction of roads from aerial images based on scale space and snakes

Laptev¹,

Mayer

Lindeberg³

et al. 2000

Machine Vision and Applications

198

123

View full text Add to dashboard Cite

We propose a new approach for automatic road extraction from aerial imagery with a model and a strategy mainly based on the multi-scale detection of roads in combination with geometry-constrained edge extraction using snakes. A main advantage of our approach is, that it allows for the rst time a bridging of shadows and partially occluded areas using the heavily disturbed evidence in the image. Additionally, it has only few parameters to be adjusted. The road network is constructed after extracting crossings with varying shape and topology. We show the feasibility of the approach not only by presenting reasonable results but also by e v aluating them quantitatively based on ground truth.A revised version of this paper will appear in Machine Vision and Applications, 2000.

show abstract

“…Therefore, most practical approaches to model-based vision use models that may be either specific (Brooks 1981;Binford 1982;Ayache and Faugeras 1986;Bolles and Horaud 1986;Shneier et al 1986) or generic (Ohta et al, 1979;Quam 1978;Fischler et al 1981;Mckeown et al 1985;Huertas and Nevatia 1988). They usually rely on heuristic rules and measures to generate object hypotheses and select among competing ones.…”

Section: Introductionmentioning

confidence: 99%

An optimization framework for feature extraction

Fua

Hanson

1991

Machine Vis. Apps.

View full text Add to dashboard Cite

Abstract:In this paper, we propose a unified optimization framework for feature extraction that lets us simultaneously take into account image data and semantic knowledge: We model objects using a language that specifies both photometric and geometric constraints and defines an information-theoretic objective function that measures the fit of the models to the data. We then treat the problem of finding objects as one of generating the optimal description of the image in terms of this language.We have validated our framework by performing extensive experiments on detecting objects in aerial imagery described by simple geometric constraints and have developed two algorithms for generating optimal descriptions. The first one starts with a rough sketch of a polygonal object and deforms the initial contour to maximize the objective function, thus finding object outlines. The second one automatically extracts complex rectilinear buildings from complex aerial images.

show abstract

Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique

Cited by 285 publications

References 14 publications

Untitled

Untitled

Automatic extraction of roads from aerial images based on scale space and snakes

An optimization framework for feature extraction

Contact Info

Product

Resources

About