A new edge detection method combining the scanning window central edge (SWCE) detector and an improved active contour model is proposed. The method first emploies the SWCE detector based on the difference of area pi...A new edge detection method combining the scanning window central edge (SWCE) detector and an improved active contour model is proposed. The method first emploies the SWCE detector based on the difference of area pixel value means to perform an optimal edge detection, and then proposes an improved active contour model with modified energy functions to refine the location of the edges. The initial nodes of the improved active contour model are automatically found from the vectorised results of the SWCE detector. Tests on simulated speckled images and real airborne SAR images show that the combined method can benefit from the advantages of the both techniques and get satisfactory edge detection and localization abilities at the same time.展开更多
由于遥感图像景观边缘具有复杂非线性结构,受光照与场景影响,使得图像边缘存在极多样化纹理和噪声,导致景观边缘难以捕捉。于是提出基于超像素分割算法的景观边缘提取方法。采用超像素分割算法,将图像映射至CIE-LAB(International Commi...由于遥感图像景观边缘具有复杂非线性结构,受光照与场景影响,使得图像边缘存在极多样化纹理和噪声,导致景观边缘难以捕捉。于是提出基于超像素分割算法的景观边缘提取方法。采用超像素分割算法,将图像映射至CIE-LAB(International Commission on Illumination-Lightness-L*A*B)色彩空间中,利用最小化梯度,将超像素置于梯度对应区域中,获取标准化度量,将水平与垂直梯度加入特征矢量中,组建景观弱边缘超像素分割模型,分割景观弱边缘超像素,利用高斯滤波器,模糊处理超像素分割结果,构建能量函数,通过迭代处理,实现景观边缘提取。实验结果表明,所提方法能准确分割显著边缘与细节边缘,精准提取景观边缘,且边缘线连贯、平滑,有效避免了伪轮廓问题,对实现城市与景观的合理规划具有较高的实际应用价值。展开更多
对基于熔化极气体保护(Metal active gas,MAG)焊的管道打底焊过程中通过电荷耦合器件(Charge-coupled device,CCD)摄像机与复合滤光技术组成的光学系统实时采集的正面焊缝区域图像进行分析,实现熔池图像边缘提取。对获取的焊缝区域图像...对基于熔化极气体保护(Metal active gas,MAG)焊的管道打底焊过程中通过电荷耦合器件(Charge-coupled device,CCD)摄像机与复合滤光技术组成的光学系统实时采集的正面焊缝区域图像进行分析,实现熔池图像边缘提取。对获取的焊缝区域图像,经过高斯平滑后,考虑到初始轮廓对Chan-Vese主动轮廓模型提取边缘效率的影响,使用基于阈值的方法,用矩形标出熔池的初始区域,即实现熔池区域粗定位,求取矩形区域中心,以该中心设定一椭圆作为熔池初始轮廓,使用Chan-Vese主动轮廓模型提取熔池边缘。借助该模型实现了MAG管道打底焊焊缝区域图像的熔池边缘提取,与Sobel变换等方法比较,该方法提高了熔池边缘提取的精度。展开更多
文摘A new edge detection method combining the scanning window central edge (SWCE) detector and an improved active contour model is proposed. The method first emploies the SWCE detector based on the difference of area pixel value means to perform an optimal edge detection, and then proposes an improved active contour model with modified energy functions to refine the location of the edges. The initial nodes of the improved active contour model are automatically found from the vectorised results of the SWCE detector. Tests on simulated speckled images and real airborne SAR images show that the combined method can benefit from the advantages of the both techniques and get satisfactory edge detection and localization abilities at the same time.
文摘由于遥感图像景观边缘具有复杂非线性结构,受光照与场景影响,使得图像边缘存在极多样化纹理和噪声,导致景观边缘难以捕捉。于是提出基于超像素分割算法的景观边缘提取方法。采用超像素分割算法,将图像映射至CIE-LAB(International Commission on Illumination-Lightness-L*A*B)色彩空间中,利用最小化梯度,将超像素置于梯度对应区域中,获取标准化度量,将水平与垂直梯度加入特征矢量中,组建景观弱边缘超像素分割模型,分割景观弱边缘超像素,利用高斯滤波器,模糊处理超像素分割结果,构建能量函数,通过迭代处理,实现景观边缘提取。实验结果表明,所提方法能准确分割显著边缘与细节边缘,精准提取景观边缘,且边缘线连贯、平滑,有效避免了伪轮廓问题,对实现城市与景观的合理规划具有较高的实际应用价值。
文摘对基于熔化极气体保护(Metal active gas,MAG)焊的管道打底焊过程中通过电荷耦合器件(Charge-coupled device,CCD)摄像机与复合滤光技术组成的光学系统实时采集的正面焊缝区域图像进行分析,实现熔池图像边缘提取。对获取的焊缝区域图像,经过高斯平滑后,考虑到初始轮廓对Chan-Vese主动轮廓模型提取边缘效率的影响,使用基于阈值的方法,用矩形标出熔池的初始区域,即实现熔池区域粗定位,求取矩形区域中心,以该中心设定一椭圆作为熔池初始轮廓,使用Chan-Vese主动轮廓模型提取熔池边缘。借助该模型实现了MAG管道打底焊焊缝区域图像的熔池边缘提取,与Sobel变换等方法比较,该方法提高了熔池边缘提取的精度。