Feature point detection in HDR images based on coefficient of variation
This addresses a domain-specific problem for computer vision applications in extreme light conditions, but it is incremental as it adapts an existing statistical measure to HDR images.
The paper tackles feature point detection in high dynamic range (HDR) images, where standard methods degrade due to saturated pixels and differential operation issues, by proposing a detector based on the coefficient of variation that adapts to pixel standard deviation, resulting in better performance in uniformity metrics but mixed results in repeatability rate compared to state-of-the-art detectors.
Feature point (FP) detection is a fundamental step of many computer vision tasks. However, FP detectors are usually designed for low dynamic range (LDR) images. In scenes with extreme light conditions, LDR images present saturated pixels, which degrade FP detection. On the other hand, high dynamic range (HDR) images usually present no saturated pixels but FP detection algorithms do not take advantage of all the information present in such images. FP detection frequently relies on differential methods, which work well in LDR images. However, in HDR images, the differential operation response in bright areas overshadows the response in dark areas. As an alternative to standard FP detection methods, this study proposes an FP detector based on a coefficient of variation (CV) designed for HDR images. The CV operation adapts its response based on the standard deviation of pixels inside a window, working well in both dark and bright areas of HDR images. The proposed and standard detectors are evaluated by measuring their repeatability rate (RR) and uniformity. Our proposed detector shows better performance when compared to other standard state-of-the-art detectors. In uniformity metric, our proposed detector surpasses all the other algorithms. In other hand, when using the repeatability rate metric, the proposed detector is worse than Harris for HDR and SURF detectors.