Chunsun Zhang
/ ON
Feature extraction : ;
; 3D straight lines
Ya color —> Image matching —> F
aerial images
Ne P
- 2D road regions
[ À - Shadows
2D image analysis —»
» 8 y - Road marks,
CC 3 Cats, ...
a MA :
VEC25 and other » Subclass attribute pl Road attributes
input data derivation - Landcover
\ J - Slope
Figure 2. Details of image processing and derivation of subclass vector attributes.
3 STRAIGHT LINE MATCHING
3D edge generation is a crucial component of our procedure. We are interested in 3D straight lines because they are
prominent in most man-made environments, and usually correspond to objects of interest in images, such as buildings
and road segments. They can be detected and tracked relatively easily in image data, and they provide a great deal of
information about the structure of the scene. Additionally, since edge features have more support than point features,
they can be localized more accurately. The 3D information of straight lines is determined from the correspondences of
line segments between two images.
Due to the complexity of aerial images, different view angles and occlusions, straight line matching is a difficult task.
Existing approaches to line matching in the literature are generally categorised into two types. One is directly
comparing the attributes of a line in one image with those of a set of lines in another image and selecting the best
candidate based on a similarity measure (McIntosh and Mutch, 1988; Medioni and Nevatia, 1985; Greenfeld and
Schenk, 1989; Zhang, 1994). The similarity measure is a comparison of line attributes, such as orientation, length, line
support region information etc. In another strategy, the line correspondence is found by performing structural matching.
Structural matching seeks to find the mapping between two structural descriptions. A structural description consists of
not only features but also geometrical and topological information among features. A number of methods have been
developed for structural matching (Vosselman, 1992; Haralick and Shapiro, 1993; Christmas et al., 1995; Cho, 1996;
Wilson and Hancock, 1997).
The developed method in this paper exploits rich line attributes and line geometrical structure information (Fig. 3). The
rich line attributes include the geometrical description of the line and the photometrical information in the regions right
beside the line (flanking regions). The epipolar constraint is applied to reduce the search space. The similarity measure
for a line pair is first computed by comparing the line attributes. The similarity measure is used as prior information in
structural matching. The locally consistent matching is achieved through structural matching with probability
relaxation. The details of the method are described below.
Input Image
Y
Image preprocessing
Y
Computing similarity measure
e Determining epipolar band
e Computing similarity score
Structural matching:
Probability relaxation
Match pool:
Possible matches
3D computation & 3D
line segmentation:
3D straight lines
Figure 3. Flow-chart of straight line matching.
1010 International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B3. Amsterdam 2000.