兴趣区域优先的多尺度压缩感知渐进编码算法

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 光电信息技术研究室

	兴趣区域优先的多尺度压缩感知渐进编码算法
	杜梅; 赵怀慈; 赵春阳
刊名	光电子·激光
	2015
卷号	26 期号:10 页码:2016-2022
关键词	感兴趣区域(ROI) 渐进编码多尺度压缩感知(CS) 基于小波的轮廓变换(WBCT) 边界平滑
ISSN号	1005-0086
其他题名	ROI progressive coding algorithm based on multiscale compressed sensing
产权排序	2
中文摘要	针对面向目标探测识别的无线图像传输应用,为了解决探测识别任务对图像质量的高要求和无线信道带宽约束之间的冲突,提出一种感兴趣区域(ROI)优先的多尺度压缩感知(CS)渐进编码算法。首先,选取多尺度CS测量技术进行图像压缩,在相同压缩比情况下,可以保持更多的图像的细节信息;其次,针对目标探测识别对重构图像纹理、边缘信息完整保持的需求,选取基于小波的轮廓变换(WBCT)作为CS的稀疏表示方法,可更多地提取方向信息,从而可以较完整地保持边缘轮廓信息;最后,针对重构图像ROI与背景区过度划分、ROI周边相关信息损失过多的问题,给出ROI边界平滑处理的方法,可有效改善重构图像的主观视觉质量。实验结果表明:...
英文摘要	Aiming at the application of the wireless image transmission for target detection and identification, in order to solve the conflict between the requirement for high image quality in detection and recognition task and the constraint of wireless channel bandwidth, a region of interest(ROI) progressive coding algorithm based on multiscale compressed sensing is proposed. First, the technology of multiscale compressed sensing is selected to compress an image in order to preserve more details of the image in the condition of the same compression ratio. Then, wavelet based contourlet transform(WBCT)is chosen as the sparse representation to extract more direction information for the demand of completely maintaining the texture and boundaries of the reconstructed image. Finally, an ROI boundary smoothing method is provided to effectively improve the subjective visual quality of the reconstructed image, for overcoming the deficiency of over differentiating between ROI and background of the reconstructed image and loosing excessive ROI-related information. Experimental results indicate that the total compression ratio falls to 0.18in the case that the ROI compression rate is as high as 0.4,which both protects the ROI and significantly improves the overall compression ratio. The algorithm can enhance the efficiency of wireless image transmission, supplying subsequent detection and recognition task with high quality images.
收录类别	EI ; CSCD
语种	中文
CSCD记录号	CSCD:5557092
内容类型	期刊论文
源URL	[http://ir.sia.cn/handle/173321/17233]
专题	沈阳自动化研究所_光电信息技术研究室
推荐引用方式 GB/T 7714	杜梅,赵怀慈,赵春阳. 兴趣区域优先的多尺度压缩感知渐进编码算法[J]. 光电子·激光,2015,26(10):2016-2022.
APA	杜梅,赵怀慈,&赵春阳.(2015).兴趣区域优先的多尺度压缩感知渐进编码算法.光电子·激光,26(10),2016-2022.
MLA	杜梅,et al."兴趣区域优先的多尺度压缩感知渐进编码算法".光电子·激光 26.10(2015):2016-2022.