QQ客服 官方微博 反馈留言

浏览/检索结果: 共2条，第1-2条 帮助 已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 A new two-layer nearest neighbor selection method for kNN classifier 期刊论文 KNOWLEDGE-BASED SYSTEMS, 2022, 卷号: 235, 页码: 14 作者:  Wang, Yikun;  Pan, Zhibin;  Dong, Jing 收藏  |  浏览/下载：35/0  |  提交时间：2021/12/28 kNN classifier  Two-layer nearest neighbor rule  First-layer neighborhood  Second-layer neighborhood  Extended neighborhood   Research on tracking approach to low-flying weak small target near the sea (EI CONFERENCE) 会议论文 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China Zhang S.-Y.; Liu W.-N.; Xue X.-C. 收藏  |  浏览/下载：24/0  |  提交时间：2013/03/25 Automatic target detection is very difficult in complicate background of sea and sky because of the clutter caused by waves and clouds nearby the sea-level line. In this paper  in view of the low-flying target near the sea is always above the sea-level line  we can first locate the sea-level line  and neglect the image data beneath the sea-level line. Thus the noise under the sea-level line can be suppressed  and the executive time of target segmentation is also much reduced. A new method is proposed  which first uses neighborhood averaging method to suppress background and enhance targets so as to increase SNR  and then uses the multi-point multi-layer vertical Sobel operator combined with linear least squares fitting to locate the sea-level line  lastly uses the centroid tracking algorithm to detect and track the target. In the experiment  high frame rate and high-resolution digital CCD camera and high performance DSP are applied. Experimental results show that this method can efficiently locate the sea-level line on various conditions of lower contrast  and eliminate the negative impact of the clutter caused by waves and clouds  and capture and track target real-timely and accurately.