Efficient sub-window search with fixed shape sub-windows
MetadataShow full item record
This paper addresses the performance improvement of efficient sub-window search algorithms for object detection. The current algorithms are for flexible rectangle-shaped sub-window with high computation costs. In this paper, a restriction is applied on the sub-window shape from rectangle into square in order to reduce the number of possible sub-windows with an expectation to improve the computation speed. However, this may come with a consequence of accuracy loss for some objects. In addition, another variance of sub-window shape is also tested which based on the ratio between the height and width of an image. The experiment results on the proposed algorithms were analysed and compared with the performance of the original algorithms to determine whether the speed improvement is significantly large while making the accuracy loss acceptable. It was found that some new algorithms show a good speed improvement while maintaining small accuracy loss. Furthermore, there is an algorithm designed from a combination of a new algorithm and an original algorithm which gains the benefit from both algorithms and produces the best performance among all new algorithms.
Showing items related by title, author, creator and subject.
An, S.; Peursum, P.; Liu, Wan-Quan; Venkatesh, S. (2009)Recently, a simple yet powerful branch-and-bound method called Efficient Subwindow Search (ESS) was developed to speed up sliding window search in object detection. A major drawback of ESS is that its computational ...
An, Senjian; Peursum, Patrick; Liu, Wan-quan; Venkatesh, Svetha (2009)Recently, a simple yet powerful branch-and-bound method called Efficient Subwindow Search (ESS) was developed to speed up sliding window search in object detection. A major drawback of ESS is that its computational ...
Techniques for improving clustering and association rules mining from very large transactional databasesLi, Yanrong (2009)Clustering and association rules mining are two core data mining tasks that have been actively studied by data mining community for nearly two decades. Though many clustering and association rules mining algorithms have ...