Abstract This paper is focused on the recognition of moving objects for an autonomous vehicle driving. In particular, a method for detecting straight lines and their correspondences in successive image frames by means of a straight-line extraction and matching process is proposed. The main advantage offered by the described approach is the possibility of extracting and matching straight lines directly in the feature space, without requiring complex inverse transformations. In particular, the Direct Hough Transform (DHT) algorithm for straight-segment is proposed. It aims to avoid the most important problems associated with the classical HT: (a) spatial information loss, (b) spurious peaks, and (c) discretization effects. Then, a Straight-Line Matching (SLM) algorithm is presented, which utilizes only four attributes to describe a segment: (a) position ρ, (b) orientation θ, (c) length 1, and (d) midpoint m. Finally, results of some experiments performed using synthetic and real monocular image sequences are reported.
[1]
James H. McIntosh,et al.
Matching straight lines
,
1988,
Comput. Vis. Graph. Image Process..
[2]
Gian Luca Foresti,et al.
Distributed spatial reasoning for multisensory image interpretation
,
1993,
Signal Process..
[3]
Thomas S. Huang,et al.
Determining straight line correspondences from intensity images
,
1991,
Pattern Recognit..
[4]
Josef Kittler,et al.
A survey of the hough transform
,
1988,
Comput. Vis. Graph. Image Process..
[5]
Jake K. Aggarwal,et al.
On the computation of motion from sequences of images-A review
,
1988,
Proc. IEEE.