Abstract
To avoid using a large 4D-Hough counting space (HCS) and complex invariant features of generalized Hough transform (GHT) or its extensions when detecting objects in remote sensing image (RSI), a tensored GHT (TGHT) is proposed to extract object contour by simple gradient angle feature in a 2D-HCS using a single training sample. Considering that tensor can record the structure relationship of object contour, tensor representation R -table is constructed to record the contour information of template. For slice centered at each position of RSI, the tensor-space-based voting mechanism is presented to use the tensor that records the contour information of slice to gather votes at the same entry of 2D-HCS. Furthermore, a multiorder binary-tree-based searching method is presented to accelerate voting by searching the index numbers of elements in tensors. In addition, by solving the tensor-space-based optimization problem that is used to determine the candidates objects, the cause of false alarms (FAs) caused by interferences with complex contour and FAs caused by interferences that are partial-similar to objects is revealed, and the matching rate and matching sparsity-based strategies are then proposed to remove these FAs. Using public RSI datasets with different scenes, experimental results demonstrate that TGHT reduces nearly 99% storage requirement compared with GHT for RSI with size exceeding 1000 × 1000 under small time consumption, and outperforms the well-known contour extraction methods and state-of-the-art deep-learning-based methods in terms of precision and recall.
Highlights
W ITH the development of imaging sensor technology, there is a growing interest in various applications for remote sensing information processes, such as object detection [1]–[3], unmixing [4], and hyperspectral image classification [5]
Inspired by the search tree [31] method that is widely used in data searching, we propose a multiorder binary tree (BT)-based searching method to accelerate obtaining the number of votes at each entry of 2D-Hough counting space (HCS) by reducing comparison operations for index number searching
The main contributions of tensored GHT (TGHT) can be concluded as three aspects
Summary
W ITH the development of imaging sensor technology, there is a growing interest in various applications for remote sensing information processes, such as object detection [1]–[3], unmixing [4], and hyperspectral image classification [5]. We replace the GHT voting mechanism that traverses CPs to accumulate votes in a large 4D-HCS with the novel approach of using the contour information of slices centered at arbitrary positions in the RSI to calculate the number of votes at the corresponding position Based on this idea and considering that a tensor can record the structure relationship of an object contour, it makes sense to exploit the tensor to describe the contour information of a slice to develop a contour extraction method and analyze the cause of FAs. we propose the tensored GHT (TGHT) to extract object contours with a single sample in 2D-HCS by using a simple gradient angle feature.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: 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.
