机构

• 长春光学精密机械与物... [2]

采集方式

• OAI收割 [2]

内容类型

• 会议论文 [2]

发表日期

• 2006 [1]
• 2005 [1]

学科主题

筛选

浏览/检索结果: 共2条，第1-2条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 Adaptive Image Segmentation based on Fast Thresholding and Image Merging (EI CONFERENCE) 会议论文  OAI收割 16th International Conference on Artificial Reality and Telexistence - Workshops, ICAT 2006, November 29, 2006 - December 1, 2006, Hangzhou, China 作者:  Zhang Y.;  Wang Y.;  Wang Y.;  Wang Y.;  Wang Y. 收藏  |  浏览/下载：14/0  |  提交时间：2013/03/25 Image segmentation is the first essential and important step of low level vision. This paper proposes a novel algorithm for adaptive image segmentation  it can be applied in many conditions  based on thresholding technique and segments merging according to their characteristics combine with spatial position. Our earlier work of getting the entire information of the histogram could help choose the multiple thresholds. However  including complex target segmented. We describe the algorithm in detail and perform simulation experiments. The computation based on pixels can fully parallel processing to save time. 2006 IEEE.  not all the peaks of the histogram correspond to obvious structural unit in the image. Spatial information must be involved. This paper also suggests subjoining segments matching for video image tracking. They will give great help to image segmentation. The proposed algorithm can meet the real-time requirement and lead to higher segmentation accuracy  some types of texture can also be segmented well   Detecting of multi-target in sea or sky background based on wavelet energy (EI CONFERENCE) 会议论文  OAI收割 Advanced Sensor Systems and Applications II, November 8, 2004 - November 12, 2004, Beijing, China 作者:  Liu G. 收藏  |  浏览/下载：20/0  |  提交时间：2013/03/25 The technology of multi-target tracking is always detecting small targets in complex background. According to the frequency characteristic of nature background and small target  a method of detecting targets based on wavelet energy is suggested. The energy of targets in horizontal and vertical direction outclass that of background  or we can say  the gray degree of targets outclass that of background. Then through selecting adaptive region-value  targets and background can be divided. By the method of classifying  the figure centers of every target can be calculated. According to the figure centers of every target in several neighboring frames  the position and velocity of every target in next frame can be estimated by Kalman filter. Experiment results have shown that small targets in sea or sky nature background can be detected by this method  and they can be tracking.