| 徐利刚,朱可卿,韦琳哲,王 朋.一种基于弱监督学习的声图小目标快速检测方法*[J].,2020,39(3):386-394 |
| 一种基于弱监督学习的声图小目标快速检测方法* |
| A fast weak supervised detection method of small objects in sonar imagery |
| 投稿时间：2019-07-08 修订日期：2020-04-30 |
| 中文摘要: |
| 小目标检测是声纳图像理解中最引人瞩目,同时又极具挑战性的任务之一。本文基于离散余弦变换和K-近邻聚类,提出了一种快速检测方法。DCT用于生成图像的指纹,是原始图像在二维频域的一种稀疏表达；改进的KNN模型对于带有标签数据的需求量相对较低,提升了算法的处理效率和对弱监督场景的适应性。经实验验证,本文方法可在准确率和召回率之间达到一个恰当的平衡点,同时在实时成像的合成孔径声纳(synthetic aperture sonar, SAS)图像小目标检测中,获得了较为可靠的结果。 |
| 英文摘要: |
| Detection of small objects is one of the most attractive and challenging tasks in the comprehension of sonar imagery. In the paper, a fast detection method is presented under a framework of Discrete Cosine Transform (DCT) and K-Nearest Neighbor (KNN) Clustering. DCT is used in the generation of image fingerprint, which contributes a certain spectral sparseness to the original image; and the modified KNN model provides efficiency with a relatively low demand of labeled data. It is shown in a series of experiments that the method we propose can reach a compromise of precision and recall rate, and achieve considerably reliable detection result on synthetic aperture sonar (SAS) images in real time imaging. |
| DOI：10.11684/j.issn.1000-310X.2020.03.010 |
| 中文关键词: 小目标检测,合成孔径声纳成像,弱监督学习,离散余弦变换,K-近邻 |
| 英文关键词: Object detection, synthetic aperture sonar imagery, weak-supervised, Discrete Cosine Transform, K-Nearest Neighbo |
| 基金项目: |
|
| 摘要点击次数: 1555 |
| 全文下载次数: 1417 |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
