Abstract
High-efficiency image corner detection, one of the most important and critical basic technology in industrial image processing, is to detect point features from an input image in real-time. In this article, we propose a new corner detection method which has both good performance of corner detection and real-time processing abilities. Firstly, the integral image and the box filter are combined to obtain the second-order derivative response in each direction of the image. Secondly, a new coarse screening mechanism for candidate corners is presented to reduce the complexity of the corner metric. Thirdly, a non-maximum suppression operation is utilized to obtain corners. Finally, the performance evaluation on accuracy of corner detection, localization error, average repeatability, region repeatability, different lighting conditions, and execution time are used to assess the proposed method against twelve state-of-the-art methods. The experimental results show that our proposed detector has good corner detection performance and achieves the requirement of real-time processing.
Highlights
C ORNERS are one of the most important local features in an image, which have been widely applied in many computer vision and image processing tasks such as 3D reconstruction [1], autonomous driving [2], object recognition [3], and image registration [4]
Our research indicates that convolution operation of multidirectional filtering increases the computational complexity of the second-order generalized Gaussian directional derivative (SOGGDD) algorithm [27], which makes the SOGGDD algorithm unable to meet the needs of real-time corner detection
Following the SOGGDD algorithm [27], the secondorder directional derivative correlation (SODDC) matrix is constructed for each image pixel, which is given in Equation (10)
Summary
C ORNERS are one of the most important local features in an image, which have been widely applied in many computer vision and image processing tasks such as 3D reconstruction [1], autonomous driving [2], object recognition [3], and image registration [4]. Zhang and Sun [27] presented the second-order generalized Gaussian directional derivative (SOGGDD) method for detecting corners from images. Wang et al [35] applied Zhang and Sun methods [5], [27] and multi-scale shearlet filters with multiple directions are used to smooth the input image for detecting corners. Our research indicates that the detector proposed by Zhang and Sun [27] has the ability to properly extract the local structure information from each input image for detecting corners. Inspired by the SURF method [20], the integral image and box filter are combined to approximate the second-order Gaussian directional derivative (SOGDD) filters In this way, the time complexity of the convolution operation can be reduced from O(N 2) (N represents the size of the convolution template) to O(1).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
