Seamless patches for GPU-based terrain rendering

In this paper we present a novel approach for interactive rendering of large terrain datasets. Our approach is based on subdividing a terrain into rectangular patches at different resolutions. Each patch is represented by four triangular tiles that are selected form different resolutions, and four strips which are used to stitch the four tiles in a seamless manner. Such a scheme maintains resolution changes within patches through the stitching strips, and not across patches. At runtime, these patches are used to construct a level-of-detail representation of the input terrain based on view-parameters. A selected level of detail only includes the layout of the patches and their boundary edges resolutions. The layout includes the location and dimension of each patch. Within the graphics hardware, the GPU generates the meshes of the patches by using scaled instances of cached tiles and assigns elevation for each vertex from cached textures. Since adjacent rectangular patches agree on the resolution of the common edges, the resulted mesh does not include cracks or degenerate triangles. Our algorithm manages to achieve quality images at high frame rates while providing seamless transition between different levels of detail.     

基于视觉显著性的空间图像序列放大算法*

针对已有的图像序列放大方法存在空间运动目标放大后细节不清晰的问题,提出基于视觉显著性的图像序列放大算法。算法首先采用视觉显著性技术获取空间运动目标区域;而后设计不同的放大策略;最后提出分区插值计算和区域能量保护方法,提升放大过程中的空间运动目标清晰度。与已有的放大算法对比的实验结果表明,提出的算法取得了更好的视觉效果和更高的平均梯度指标值、边缘强度指标值、信息熵指标值和图像功率谱指标值。     

多特征融合的瓷砖表面缺陷检测算法研究

鉴于单一特征在瓷砖种类较多的情况下,存在对瓷砖表面缺陷内容表达不明显,导致复杂瓷砖识别率较低。针对这个问题,在词袋模型（BoF）框架的基础上,提出一种有效的多特征融合算法用于瓷砖缺陷检测。该算法采用改进后的SIFT和颜色矩融合特征作为瓷砖图像的区域特征描述;根据每种特征对瓷砖被分类的准确率大小,给提取到的两种区域特征分配各自的权重系数实现特征的加权融合;形成综合特征向量送入SVM分类器达到瓷砖缺陷分类的目的。通过不同类型的瓷砖样本进行实验表明,该算法识别率高,对复杂瓷砖能实现较好的分类。     

A 4-quadrant curvelet transform for denoising digital images

The conventional discrete wavelet transform (DWT) introduces artifacts during denoising of images containing smooth curves. Finite ridgelet transform (FRIT) solved this problem by mapping the curves in terms of small curved ridges. However, blind application of FRIT all over an image is computationally heavy. Finite curvelet transform (FCT) selectively applies FRIT only to the tiles containing small portions of a curve. In this work, a novel curvelet transform named as 4-quadrant finite curvelet transform (4QFCT) based on a new concept of 4-quadrant finite ridgelet transform (4QFRIT) has been proposed. An image is band pass filtered and the high frequency bands are divided into small non-overlapping square tiles. The 4QFRIT is applied to the tiles containing at least one curve element. Unlike FRIT, the 4QFRIT takes 4 sets of radon projections in all the 4 quadrants and then averages them in time and frequency domains after denoising. The proposed algorithm is extensively tested and benchmarked for denoising of images with Gaussian noise using mean squared error (MSE) and peak signal to noise ratio (PSNR). The results confirm that 4QFCT yields consistently better denoising performance quantitatively and visually.     

A New Approach to Identify Big Rocks with Applications to the Mining Industry

Detection of big rocks is an important, even critical, problem in the mining industry due to the risk of machine blockage causing high costs. This paper presents a computer-vision-based method to detect big rocks in a real mining industry. Our system, based on a mixture of image processing techniques and neural networks, works as follows: once the image is taken, a pre-processing step is performed, filtering the image and extracting a set of candidate rocks. Then a neural network processes the candidate rocks to ensure correct detection. A tracking algorithm is then applied to avoid false detection due to rock grouping. Using geometrical information, it is possible to estimate the real dimensions of the rocks. Our computer vision system satisfies time constraints imposed by the industry to work in real time and is currently operating. The algorithm presented is independent of the rock's shape. Results obtained during nine months of unsupervized work are provided, showing that our system is able to work under different light conditions and is robust enough to face real work conditions.     

多空间分辨率自适应特征融合的相关滤波目标跟踪算法

相关滤波算法因无法充分利用深度特征和浅层特征的互补特性而限制跟踪性能.针对该问题,文中提出多空间分辨率自适应特征融合的相关滤波目标跟踪算法.首先,使用更深的ResNet-50网络提取深度特征,提高特征表示在跟踪过程中的鲁棒性和鉴别性.再针对不同特征具有不同空间分辨率的特点,从视频帧中分割不同尺度的图像块作为搜索区域,更好地平衡边界效应和样本数目.最后,引入自适应特征融合方法,以自适应的权重融合两类特征的响应图,充分利用其互补特性.在多个标准数据集上的实验证实文中算法的有效性和鲁棒性.     

对不同分辨率图象进行空间分辨率改善的频域方法

图象空间分辨率的改善在遥感图象和计算机视觉的一些应用中非常必要。已有的一些空间分辨率改善的频域方法是针对多幅相同空间分辨率图象的频谱解混叠方法。本文从分辨率低的欠采样图象会导致相应空间频率域频谱混叠的理论出发，给出了多次欠采样图象在频率域混叠的更一般的公式，并给出一种针对不同分辨率图象解频谱混叠的逐行迭代方法。最后通过计算机仿真实验对本文所述理论进行了验证。实验表明，该迭代解法在有噪声情形下也具有很好的收敛性。     

A multi-processor NoC-based architecture for real-time image/video enhancement

The paper presents a multi-processor architecture for real-time and low-power image and video enhancement applications. Differently from other state-of-the-art parallel architectures the proposed solution is composed of heterogeneous tiles. The tiles have computational and memory capabilities, support different algorithmic classes and are connected by a novel Network-on-Chip (NoC) infrastructure. The proposed packet-switched data transfer scheme avoids communication bottlenecks when more tiles are working concurrently. The functional performances of the NoC-based multi-processor architecture are assessed by presenting the achieved results when the platform is programmed to support different enhancement algorithms for still images or videos. The implementation complexity of the NoC-based multi-tile platform, integrated in 65 nm CMOS technology, is reported and discussed.     

基于归一化方差的多分辨率图像融合方法

针对遥感多光谱图像空间分辨率较低的问题,论文提出了一种基于归一化方差的多分辨率图像融合方法。该方法首先对图像进行二维小波变换,然后根据高频小波系数的均值和方差来定义图像局部灰度相关矩,从而得到包含更多信息和有效特征的融合图像。试验结果证明融合图像在保留地物光谱信息和提高空间细节表现能力上都具有很好的效果。     

船舶目标重叠下马赛克图像数据增强方法研究

目标识别中的重叠遮挡问题一直以来是研究的难点,船舶目标在狭窄水域发生相互遮挡的情况依然存在.本文提出了一种改进的马赛克数据增强方法,将训练图片拼接变换成3种不同的尺度,并按照不同比例输入网络进行训练,强化了检测算法对局部特征的学习能力,在保持测试速度不变的情况下,提高了对重叠目标的识别准确率,降低了不同分辨率下识别能力的衰弱速度,加强了算法的鲁棒性.基于小型移动测试平台的实测实验证明,相对于原始算法,经过改进后的算法在重叠目标的识别准确率上提高了2.5%,目标丢失时间减少了17%,在不同视频分辨率下的识别稳定性上提高了27.01%.     

基于加权相关矩的多传感器图像融合方法

针对遥感多光谱图像和全色图像的融合问题,提出了一种基于局部区域特征的多分辨率图像融合方法。该方法首先对图像进行二维小波变换,然后根据高频小波系数的一阶、二阶统计特征来计算加权相关矩,从而得到包含更多信息和有效特征的融合图像。试验结果证明融合图像在保留地物光谱信息和提高空间细节表现能力上都具有很好的效果。     

一种基于小波变换的分形零树混合编码方法

为了降低分形编码的复杂度和提高编码效率 ,提出了一种基于小波变换的分形零树混合图象编码方法 .该方法首先利用小波变换将图象分解为不同方向不同分辨率的子图象 ,然后分别在不同分辨率层将这些子图象以类似于零树的结构 ,构成一棵棵的小波子树 (wavelet subtree) ,最后在编码时 ,对每一棵小波子树进行具体的分析 ,或采用分形编码 (fractal coding) ,或采用零树编码 (zerotree coding) .与传统的基于小波变换的分形编码相比 ,此算法在充分利用子带图象间的相似性和块内存在的自相似性的同时 ,也充分利用了小波变换后子图象块内 ,特别是高分辨层的子图象块内所存在的大量局域性的冗余性 .实验结果表明 ,此方法在较大的压缩范围内 ,都能够获得较好的压缩效果 .     

基于多尺度卷积神经网络和类内mixup操作的磁瓦表面质量识别

铁氧体磁瓦由于形状的不规则性和表面缺陷的多样性给基于计算机视觉的表面质量识别带来很大的挑战。针对该问题,将深度学习技术引入到磁瓦表面质量识别中,提出一种基于卷积神经网络的磁瓦表面质量识别系统。首先将磁瓦目标从采集到的图像中分割出来并进行旋转从而得到标准图像,然后把改进后的多尺度ResNet18作为骨干网络来设计识别系统。训练时,设计一种新颖的类内mixup操作来提高系统对样本的泛化能力。为了更加贴近实际应用场景,在考虑到光线变化、姿态差异等因素的前提下构建了磁瓦缺陷数据集。在自建的数据集中进行实验的结果表明,该系统可以达到97.9%的识别准确率,为磁瓦缺陷的自动识别提供了可行的思路。     

A supervised approach for automated surface defect detection in ceramic tile quality control

Surface defect detection is very important to guarantee the quality of ceramic tiles production. At present, this process is usually performed manually in the ceramic tile industry, which is low efficiency and time-consuming. For small surface defects detection of high-resolution ceramic tiles image, an intelligent detection method for surface defects of ceramic tiles based on an improved you only look once version 5 (YOLOv5) algorithm is presented. Firstly, the high-resolution ceramic tile images are cropped into slices, and the Bottleneck module in the YOLOv5s network is optimized by introducing depthwise convolution and replaced in the whole network. Then, feature extraction is performed using the improved Shufflenetv2 backbone, and an attention mechanism is added to the backbone network to improve the feature extraction ability. The path aggregation network (PAN) and Feature Pyramid Networks (FPN) neck are used to enhance the feature extraction, and finally, the YOLO head is used to identify and locate the ceramic tile defects. The multiple sliding windows detection method is proposed to detect the original ceramic tile image which is faster than the single sliding window detection method. The experimental results show that compared with the original YOLOv5s detection algorithm, the parameters of the model are reduced by 20.46 %, the floating point operations are reduced by 26.22 %, and the mean average precision (mAP) of the proposed method is 96.73 % in the ceramic tile image slice test set which has 1.93 % improvement in mAP than the original YOLOv5s. Compare with other object detection methods, the method proposed in this paper also has certain advantages. In the high-resolution ceramic tile images test set, the mAP of the proposed algorithm is 86.44 % by using the multiple sliding window detection method. The ceramic defect detection experiment has verified the feasibility of the method proposed in this paper.     

Singular point detection by shape analysis of directional fields in fingerprints

This paper presents a new fingerprint singular point detection method that is type-distinguishable and applicable to various fingerprint images regardless of their resolutions. The proposed method detects singular points by analyzing the shapes of the local directional fields of a fingerprint image. Using the predefined rules, all types of singular points (upper core, lower core, and delta points) can be extracted accurately and delineated in terms of the type of singular points. In case of arch-type fingerprints there exists no singular point, but reference points for arch-type fingerprints are required to be detected for registration. Therefore, we propose a new reference point detection method for arch-type fingerprints as well. The result of the experiments on the two public databases (FVC2000 2a, FVC2002 2a) with different resolutions demonstrates that the proposed method has high accuracy in locating each types of singular points and detecting the reference points of arch-type fingerprints without regard to their image resolutions.     

基于归一化相关矩的多分辨率遥感图象融合

多传感器数据融合技术已广泛应用于遥感图象处理方面 .针对遥感多光谱图象空间分辨率较低的问题 ,提出了一种基于归一化相关矩的多分辨率图象融合方法 .该方法首先对图象进行二维小波变换 ,然后根据所得到的高频小波系数的一阶、二阶统计特征来定义图象局部灰度相关矩 ,并以此作为图象融合测度来对遥感图象进行多分辨率特征融合 ,从而得到包含更多信息和有效特征的融合图象 .仿真结果表明 ,融合后的图象在保留多光谱信息和提高空间分辨率上均能获得较好的效果 ,因而可以更好地用于目标识别、分类等遥感图象处理方面     

基于小波多尺度分解的互补全景图像融合

为了解决折反射成像内外环分辨率低且不均匀的问题,针对互补全景图像的特点,提出了一种基于小波多尺度分解的图像融合方法。首先对两幅互补的源图像分别进行小波多尺度分解,得到不同分辨率、不同方向的分量;其次,按照特定的融合策略,低频采用平均算子进行融合,高频采用逐层互换的融合策略进行融合;最后,通过小波逆变换得到融合图像。实验结果表明,该方法在互补全景图像的融合中简单有效,并且拥有较好的效果。     

基于相关系数的快速分形图像编码算法

自Jacquin提出的分形块编码以来,各种改进算法不断出现,不同程度地减少了编码时间.该文基于相关系数的快速分形图像编码算法,从理论上研究了图像块匹配误差度量和图像块相关系数之间的关系,论证了极小化图像块的均方误差等价于极大化图像块的相关系数,提出了基于相关系数的分形图像编码算法,实现了在解码图像不降质的情况下大大地缩短了编码时间.     

一种基于IHS和DWT变换的遥感图像融合方法

为了更好地进行不同分辨率图像的融合,提出了一种在Maflab平台上实现基于IHS变换与离散小波变换相结合的多光谱图像与高分辨率图像融合方法.实验结果分析表明,得到的融合图像与原多光谱图像相比,细节信息更为突出,整体信息更为丰富,基本达到了提高融合增强的目的.