论文部分内容阅读
~~
中国环境监测第32卷(2016)总目次
【摘 要】
：
~~
【出 处】
：
中国环境监测
【发表日期】
：
2016年06期
其他文献
Modern graph processing is widely used for solving a vast variety of real-world problems,e.g.,web sites ranking[1]and community detection[2].To better adapt and express the procedure of graph iteratio
期刊
针对非下采样金子塔(NSP)用于平移不变的剪切波变换(NSST)中不能有效捕获图像的结构信息问题,提出一种多尺度非局部均值滤波(MNLMF)和剪切波(SF)方向滤波的新变换,即利用MNLMF代替NSST中NSP分解,然后将其用到图像融合中,并将输入图像分解成不同子带.对于近似子带,采用区域像素能量(PE)与梯度能量(GE)加权和的融合规则;对于方向子带,提出基于GE与系数绝对值(CAV)混合的融合
期刊
Application of regularization technique in image super-resolution algorithm via sparse representatio
To make use of the prior knowledge of the image more effectively and restore more details of the edges and structures, a novel sparse coding objective function is proposed by applying the principle of
期刊
Low-resolution expression recognition based on central oblique average CS-LBP with adaptive threshol
In order to solve the problem of low recognition rate of traditional feature extraction operators under low-resolution images, a novel algorithm of expression recognition is proposed, named central ob
期刊
In this paper, a novel framework, named as global-local feature attention network with reranking strategy(GLAN-RS), is presented for image captioning task. Rather than only adopting unitary visual inf
期刊
Due to the lack of enough information to solve the equation of image degradation model, existing defogging methods generally introduce some parameters and set these values fixed. Inappropriate paramet
期刊
Text extraction is an important initial step in digitizing the historical documents. In this paper, we present a text extraction method for historical Tibetan document images based on block projection
期刊
针对某复杂场景下对特定目标进行精确定位测量的关键问题,依据双目立体视觉测量原理,结合OpenCV视觉开发库标定摄像机内外参数,利用结果校准目标图像,借助于标靶类型进行图像区域分割并计算出目标位置坐标,以此实现精确定位测量之目的。研究结果表明,对于所确定的1.4~1.6m目标测距范围,采用平行双目视觉测量模型和相机小孔测量模型,获得了距离误差小于10mm、横向误差小于2 mm和响应时间小于350ms
期刊
利用压缩感知(CS)矩阵建立压缩特征模版,通过在线学习,实现一种更高效的目标跟踪算法。首先利用符合有限等距性质的随机感知矩阵,取得跟踪目标表面特征的压缩模板;然后利用模板匹配确定目标区域,同时在跟踪过程中在线学习目标外观变化,并以此更新目标模板。采用了局部模板更新策略,使目标模板更为准确,更能体现目标的变化状况。采用了模板匹配的确定性跟踪方法,大大减少了大量正负样本的采样,降低了算法复杂度。实验结
期刊
针对正则化正交匹配追踪(ROMP)算法在压缩感知(CS)重构中需预估稀疏度导致重构精度不稳定的问题,提出一种改进的ROMP算法。由于观测信号能够继承原始信号特征,在选择候选集原子过程中引入自适应弱选择标准,依据观测信号的信息量设定弱选择标准,实现稀疏度自适应调整。将改进ROMP的算法应用于CS框架下的医学图像融合,并提出一种结合观测信号结构相似度的融合规则,当待融合的观测信号之间结构相似度较高时,
期刊