目的为了解决利用显著区域进行图像压缩已有方法中存在的对多目标的图像内容不能有效感知,从而影响重建图像的质量问题,提出一种基于多尺度深度特征显著区域检测图像压缩方法。方法利用改进的卷积神经网络(CNNs),进行多尺度图像深度特...目的为了解决利用显著区域进行图像压缩已有方法中存在的对多目标的图像内容不能有效感知,从而影响重建图像的质量问题,提出一种基于多尺度深度特征显著区域检测图像压缩方法。方法利用改进的卷积神经网络(CNNs),进行多尺度图像深度特征检测,得到不同尺度显著区域;然后根据输入图像尺寸自适应调整显著区域图的尺寸,同时引入高斯函数,对显著区域进行滤波,得到多尺度融合显著区域;最后结合编码压缩技术,对显著区域实行近无损压缩,非显著区域利用有损编码技术进行有损压缩,完成图像的压缩和重建工作。结果提出的图像压缩方法较JPEG压缩方法,编码码率为0.39 bit/像素左右时,在数据集Kodak Photo CD上,峰值信噪比(PSNR)提高了2.23 d B,结构相似性(SSIM)提高了0.024;在数据集Pascal Voc上,PSNR和SSIM两个指标分别提高了1.63 d B和0.039。同时,将提出的多尺度特征显著区域方法结合多级树集合分裂(SPIHT)和游程编码(RLE)压缩技术,在Kodak数据集上,PSNR分别提高了1.85 d B、1.98 d B,SSIM分别提高了0.006、0.023。结论提出的利用多尺度深度特征进行图像压缩方法得到了较传统编码技术更好的结果,该方法通过有效地进行图像内容的感知,使得在图像压缩过程中,减少了图像内容损失,从而提高了压缩后重建图像的质量。展开更多
In order to better represent infrared target features under different environments, a saliency detection method based on region covariance and global feature is proposed. Firstly, the region covariance features on dif...In order to better represent infrared target features under different environments, a saliency detection method based on region covariance and global feature is proposed. Firstly, the region covariance features on different scale spaces and different image regions are extracted and transformed into sigma features,then combined with central position feature, the local salient map is generated. Next, a global salient map is generated by gray contrast and density estimation. Finally, the saliency detection result of infrared images is obtained by fusing the local and global salient maps. The experimental results show that the salient map of the proposed method has complete target features and obvious edges,and the proposed method is better than the state of art method both qualitatively and quantitatively.展开更多
How to protect cultural retics is of great significance to the transmission and dissemination of history and culture.Digital 3-dimensional(3D)modeling of cultural relics is an effective way to preserve them.The effici...How to protect cultural retics is of great significance to the transmission and dissemination of history and culture.Digital 3-dimensional(3D)modeling of cultural relics is an effective way to preserve them.The efficiency and complexity of cultural relic model reconstruction algorithms are significant challenges due to redundant data.To tackle the above issue,a 3D reconstruction algorithm,named COLMAP+LSH,was proposed for movable cultural relics based on salient region optimization.COLMAP+LSH algorithm introduces saliency region detection and locality-sensetive Hashing(LSH)to achieve efficient,accurate,and robust digital 3D modeling of cultural relics.Specifically,400 cultural model data were collected through offline and online collection.COLMAP+LSH algorithm detects the salient region interactively and reduces the number of images in the salient region by feature diffusion.Additionally,COLMAP+LSH algorithm utilizes LSH to calculate the image selection scores and employs the image selection scores to reduce the redundant image.The experiments on the self-constructed cultural relics dataset show that COLMAP+LSH algorithm can efficiently achieve image feature diffusion and ensure the quality of artifact reconstruction while selecting most of the redundant image data.展开更多
文摘目的为了解决利用显著区域进行图像压缩已有方法中存在的对多目标的图像内容不能有效感知,从而影响重建图像的质量问题,提出一种基于多尺度深度特征显著区域检测图像压缩方法。方法利用改进的卷积神经网络(CNNs),进行多尺度图像深度特征检测,得到不同尺度显著区域;然后根据输入图像尺寸自适应调整显著区域图的尺寸,同时引入高斯函数,对显著区域进行滤波,得到多尺度融合显著区域;最后结合编码压缩技术,对显著区域实行近无损压缩,非显著区域利用有损编码技术进行有损压缩,完成图像的压缩和重建工作。结果提出的图像压缩方法较JPEG压缩方法,编码码率为0.39 bit/像素左右时,在数据集Kodak Photo CD上,峰值信噪比(PSNR)提高了2.23 d B,结构相似性(SSIM)提高了0.024;在数据集Pascal Voc上,PSNR和SSIM两个指标分别提高了1.63 d B和0.039。同时,将提出的多尺度特征显著区域方法结合多级树集合分裂(SPIHT)和游程编码(RLE)压缩技术,在Kodak数据集上,PSNR分别提高了1.85 d B、1.98 d B,SSIM分别提高了0.006、0.023。结论提出的利用多尺度深度特征进行图像压缩方法得到了较传统编码技术更好的结果,该方法通过有效地进行图像内容的感知,使得在图像压缩过程中,减少了图像内容损失,从而提高了压缩后重建图像的质量。
基金supported by the National Natural Science Foundation of China(61303192)the China Postdoctoral Science Foundation(2015M5726942016T90979)
文摘In order to better represent infrared target features under different environments, a saliency detection method based on region covariance and global feature is proposed. Firstly, the region covariance features on different scale spaces and different image regions are extracted and transformed into sigma features,then combined with central position feature, the local salient map is generated. Next, a global salient map is generated by gray contrast and density estimation. Finally, the saliency detection result of infrared images is obtained by fusing the local and global salient maps. The experimental results show that the salient map of the proposed method has complete target features and obvious edges,and the proposed method is better than the state of art method both qualitatively and quantitatively.
基金supported by the National Key Research and Development Project(2021YFF0901700)。
文摘How to protect cultural retics is of great significance to the transmission and dissemination of history and culture.Digital 3-dimensional(3D)modeling of cultural relics is an effective way to preserve them.The efficiency and complexity of cultural relic model reconstruction algorithms are significant challenges due to redundant data.To tackle the above issue,a 3D reconstruction algorithm,named COLMAP+LSH,was proposed for movable cultural relics based on salient region optimization.COLMAP+LSH algorithm introduces saliency region detection and locality-sensetive Hashing(LSH)to achieve efficient,accurate,and robust digital 3D modeling of cultural relics.Specifically,400 cultural model data were collected through offline and online collection.COLMAP+LSH algorithm detects the salient region interactively and reduces the number of images in the salient region by feature diffusion.Additionally,COLMAP+LSH algorithm utilizes LSH to calculate the image selection scores and employs the image selection scores to reduce the redundant image.The experiments on the self-constructed cultural relics dataset show that COLMAP+LSH algorithm can efficiently achieve image feature diffusion and ensure the quality of artifact reconstruction while selecting most of the redundant image data.
