We introduce a new approach to image super-resolution. The idea is to use a simple wavelet-based linear interpolation scheme as our initial estimate of high-resolution image;and to intensify geometric structure in ini...We introduce a new approach to image super-resolution. The idea is to use a simple wavelet-based linear interpolation scheme as our initial estimate of high-resolution image;and to intensify geometric structure in initial estimation with an iterative projection process based on hard-thresholding scheme in a new angular multiselectivity domain. This new domain is defined by combining of laplacian pyramid and angular multiselectivity decomposition, the result is multiselective contourlets which can capture and restore adaptively and slightly better geometric structure of image. The experimental results demonstrate the effectiveness of the proposed approach.展开更多
在遮挡目标识别中,目标可能会被其他物体遮挡,导致目标的部分有效特征丢失或变形。目标有效特征的减少,使得单一YOLOv4(You Only Look Once version 4)无法准确识别锚框的初始值,使得模型目标识别困难。为此,引入K-means++算法改进单一Y...在遮挡目标识别中,目标可能会被其他物体遮挡,导致目标的部分有效特征丢失或变形。目标有效特征的减少,使得单一YOLOv4(You Only Look Once version 4)无法准确识别锚框的初始值,使得模型目标识别困难。为此,引入K-means++算法改进单一YOLOv4算法,提出基于改进YOLOv4的遮挡目标识别算法。通过非下采样Contourlet变换划分图像为低频部分和高频部分,分别利用线性增强函数和改进的自适应阈值增强图像,并经由非下采样Contourlet逆变换生成重建图像,对其执行模糊对比度增强。选取YOLOv4作为目标识别基础模型,采用深度可分离卷积替代模型中部分卷积,并替换特征金字塔为递归特征金字塔,提升小目标和遮挡目标的特征学习能力。引入K-means++算法自适应获取锚框,优化锚框初始值,并利用完全交并比和交叉熵构建损失函数,训练改进的YOLOv4并将增强后图像输入其中,实现遮挡目标识别。实验结果表明,所提方法能够有效识别图像目标,且识别结果P-R曲线更理想。展开更多
文摘We introduce a new approach to image super-resolution. The idea is to use a simple wavelet-based linear interpolation scheme as our initial estimate of high-resolution image;and to intensify geometric structure in initial estimation with an iterative projection process based on hard-thresholding scheme in a new angular multiselectivity domain. This new domain is defined by combining of laplacian pyramid and angular multiselectivity decomposition, the result is multiselective contourlets which can capture and restore adaptively and slightly better geometric structure of image. The experimental results demonstrate the effectiveness of the proposed approach.
文摘在遮挡目标识别中,目标可能会被其他物体遮挡,导致目标的部分有效特征丢失或变形。目标有效特征的减少,使得单一YOLOv4(You Only Look Once version 4)无法准确识别锚框的初始值,使得模型目标识别困难。为此,引入K-means++算法改进单一YOLOv4算法,提出基于改进YOLOv4的遮挡目标识别算法。通过非下采样Contourlet变换划分图像为低频部分和高频部分,分别利用线性增强函数和改进的自适应阈值增强图像,并经由非下采样Contourlet逆变换生成重建图像,对其执行模糊对比度增强。选取YOLOv4作为目标识别基础模型,采用深度可分离卷积替代模型中部分卷积,并替换特征金字塔为递归特征金字塔,提升小目标和遮挡目标的特征学习能力。引入K-means++算法自适应获取锚框,优化锚框初始值,并利用完全交并比和交叉熵构建损失函数,训练改进的YOLOv4并将增强后图像输入其中,实现遮挡目标识别。实验结果表明,所提方法能够有效识别图像目标,且识别结果P-R曲线更理想。
