Abstract
Dark target detection is important for engineering applications but the existing methods do not consider the imaging environment of dark targets, such as the adjacency effect. The adjacency effect will affect the quantitative applications of remote sensing, especially for high contrast images and images with ever-increasing resolution. Further, most studies have focused on how to eliminate the adjacency effect and there is almost no research about the application of the adjacency effect. However, the adjacency effect leads to some unique characteristics for the dark target surrounded by a bright background. This paper utilizes these characteristics to assist in the detection of the dark object, and the low-high threshold detection strategy and the adaptive threshold selection method under the assumption of Gaussian distribution are designed. Meanwhile, preliminary case experiments are carried out on the crack detection of concrete slope protection. Finally, the experiment results show that it is feasible to utilize the adjacency effect for dark target detection.
Highlights
Dark target detection based on high resolution and high contrast images, such as crack detection and shadow detection, is important for engineering applications
For the high-resolution and high-contrast images where the dark target is surrounded by a bright background, the reflectance of the target pixel contains the contribution of the scattering of background pixels, namely the adjacency effect
The Gaussian probability density function is often used as the distribution hypothesis for the statistical model of images; this paper introduces the Gaussian distribution into the selection of high and low thresholds
Summary
Dark target detection based on high resolution and high contrast images, such as crack detection and shadow detection, is important for engineering applications. The third type of method is connected component analysis [15,16,17], such as the percolation model [18,19] and stroke width transform (SWT) algorithm [20], which mainly utilizes the relationship between the target and its neighboring regions. These methods do not consider the imaging environment of a dark target, such as the adjacency effect. The canny-morphology method and SWT algorithm are used to compare with the proposed method
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have