Digital image stabilization technique plays important roles in video surveillance and object acquisition.Many useful electronic image stabilization algorithms have been studied.A real-time algorithm is proposed based ...Digital image stabilization technique plays important roles in video surveillance and object acquisition.Many useful electronic image stabilization algorithms have been studied.A real-time algorithm is proposed based on field image gray projection which enables the regional odd and even field image to be projected into x and y directions and thus to get the regional gray projection curves in x and y directions,respectively.For the odd field image channel,motion parameters can be estimated via iterative minimum absolute difference based on two successive field image regional gray projection curves.Then motion compensations can be obtained after using the Kalman filter method.Finally,the odd field image is adjusted according to the compensations.In the mean time,motion compensation is applied to the even field image channel with the odd field image gray projection curves of the current frame.By minimizing absolute difference between odd and even field image gray projection curves of the current frame,the inter-field motion parameters can be estimated.Therefore,the even field image can be adjusted by combining the inter-field motion parameters and the odd field compensations.Finally,the stabilized image sequence can be obtained by synthesizing the adjusted odd and even field images.Experimental results show that the proposed algorithm can run in real-time and have a good stabilization performance.In addition,image blurring can be improved.展开更多
To get the high compression ratio as well as the high-quality reconstructed image, an effective image compression scheme named irregular segmentation region coding based on spiking cortical model（ISRCS） is presented...To get the high compression ratio as well as the high-quality reconstructed image, an effective image compression scheme named irregular segmentation region coding based on spiking cortical model（ISRCS） is presented. This scheme is region-based and mainly focuses on two issues. Firstly, an appropriate segmentation algorithm is developed to partition an image into some irregular regions and tidy contours, where the crucial regions corresponding to objects are retained and a lot of tiny parts are eliminated. The irregular regions and contours are coded using different methods respectively in the next step. The other issue is the coding method of contours where an efficient and novel chain code is employed. This scheme tries to find a compromise between the quality of reconstructed images and the compression ratio. Some principles and experiments are conducted and the results show its higher performance compared with other compression technologies, in terms of higher quality of reconstructed images, higher compression ratio and less time consuming.展开更多
为了克服基于单一视差合成的光场图像编码方法在遮挡区域无法恢复纹理细节的问题,提出一种基于多特征融合和几何感知网络的光场图像编码方法,以进一步提升遮挡场景下光场图像的压缩性能.首先,对密集光场稀疏采样,使用通用视频编码器(ver...为了克服基于单一视差合成的光场图像编码方法在遮挡区域无法恢复纹理细节的问题,提出一种基于多特征融合和几何感知网络的光场图像编码方法,以进一步提升遮挡场景下光场图像的压缩性能.首先,对密集光场稀疏采样,使用通用视频编码器(versatile video coding,VVC)对稀疏光场进行压缩;然后,在解码端使用2个关键分支模块,即视差估计模块和空间角度联合卷积模块,以获取光场图像全局的几何信息,确保在密集纹理和遮挡区域能够更充分地恢复特征;最后,为了挖掘2个分支融合特征的结构信息,构建了双向视图的堆栈结构,并运用几何感知的细化网络以重建高质量的密集光场.实验结果表明,与已有国际上流行的光场图像编码方法相比,所提出的方法具有显著优势.展开更多
基金supported by the National Natural Science Foundation of China(6110118561302145)
文摘Digital image stabilization technique plays important roles in video surveillance and object acquisition.Many useful electronic image stabilization algorithms have been studied.A real-time algorithm is proposed based on field image gray projection which enables the regional odd and even field image to be projected into x and y directions and thus to get the regional gray projection curves in x and y directions,respectively.For the odd field image channel,motion parameters can be estimated via iterative minimum absolute difference based on two successive field image regional gray projection curves.Then motion compensations can be obtained after using the Kalman filter method.Finally,the odd field image is adjusted according to the compensations.In the mean time,motion compensation is applied to the even field image channel with the odd field image gray projection curves of the current frame.By minimizing absolute difference between odd and even field image gray projection curves of the current frame,the inter-field motion parameters can be estimated.Therefore,the even field image can be adjusted by combining the inter-field motion parameters and the odd field compensations.Finally,the stabilized image sequence can be obtained by synthesizing the adjusted odd and even field images.Experimental results show that the proposed algorithm can run in real-time and have a good stabilization performance.In addition,image blurring can be improved.
基金supported by the National Science Foundation of China(60872109)the Program for New Century Excellent Talents in University(NCET-06-0900)
文摘To get the high compression ratio as well as the high-quality reconstructed image, an effective image compression scheme named irregular segmentation region coding based on spiking cortical model（ISRCS） is presented. This scheme is region-based and mainly focuses on two issues. Firstly, an appropriate segmentation algorithm is developed to partition an image into some irregular regions and tidy contours, where the crucial regions corresponding to objects are retained and a lot of tiny parts are eliminated. The irregular regions and contours are coded using different methods respectively in the next step. The other issue is the coding method of contours where an efficient and novel chain code is employed. This scheme tries to find a compromise between the quality of reconstructed images and the compression ratio. Some principles and experiments are conducted and the results show its higher performance compared with other compression technologies, in terms of higher quality of reconstructed images, higher compression ratio and less time consuming.
文摘为了克服基于单一视差合成的光场图像编码方法在遮挡区域无法恢复纹理细节的问题,提出一种基于多特征融合和几何感知网络的光场图像编码方法,以进一步提升遮挡场景下光场图像的压缩性能.首先,对密集光场稀疏采样,使用通用视频编码器(versatile video coding,VVC)对稀疏光场进行压缩;然后,在解码端使用2个关键分支模块,即视差估计模块和空间角度联合卷积模块,以获取光场图像全局的几何信息,确保在密集纹理和遮挡区域能够更充分地恢复特征;最后,为了挖掘2个分支融合特征的结构信息,构建了双向视图的堆栈结构,并运用几何感知的细化网络以重建高质量的密集光场.实验结果表明,与已有国际上流行的光场图像编码方法相比,所提出的方法具有显著优势.
