Source Camera Identification Algorithm Based on Multi-Scale Feature Fusion

The widespread availability of digital multimedia data has led to a new challenge in digital forensics.Traditional source camera identification algorithms usually rely on various traces in the capturing process.However,these traces have become increasingly difficult to extract due to wide availability of various image processing algorithms.Convolutional Neural Networks(CNN)-based algorithms have demonstrated good discriminative capabilities for different brands and even different models of camera devices.However,their performances is not ideal in case of distinguishing between individual devices of the same model,because cameras of the same model typically use the same optical lens,image sensor,and image processing algorithms,that result in minimal overall differences.In this paper,we propose a camera forensics algorithm based on multi-scale feature fusion to address these issues.The proposed algorithm extracts different local features from feature maps of different scales and then fuses them to obtain a comprehensive feature representation.This representation is then fed into a subsequent camera fingerprint classification network.Building upon the Swin-T network,we utilize Transformer Blocks and Graph Convolutional Network(GCN)modules to fuse multi-scale features from different stages of the backbone network.Furthermore,we conduct experiments on established datasets to demonstrate the feasibility and effectiveness of the proposed approach.

Vibration-based feature extraction of determining dynamic characteristic for engine block low vibration design

In order to maintain vibration performances within the limits of the design, a vibration-based feature extraction method for dynamic characteristic using empirical mode decomposition （EMD） and wavelet analysis was proposed. The proposed method was verified experimentally and numerically by implementing the scheme on engine block. In the implementation process, the following steps were identified to be important： 1） EMD technique in order to solve the feature extraction of vibration signals; 2） Vibration measurement for the purpose of confirming the structural weak regions of engine block in experiment; 3） Finite element modeling for the purpose of determining dynamic characteristic in time region and frequency region to affirm the comparability of response character corresponding to improvement schemes; 4） Adopting a feature index oflMF for structural improvement based on EMD and wavelet analysis. The obtained results show that IMF of signal is more sensitive to response character corresponding to improvement schemes. Finally, examination of the results confirms that the proposed vibration-based feature extraction method is very robust, and focuses on the relative merits of modification and full-scale structural optimization of engine, together with the creation of new low-vibration designs.

Underwater Terrain Image Stitching Based on Spatial Gradient Feature Block

At present,underwater terrain images are all strip-shaped small fragment images preprocessed by the side-scan sonar imaging system.However,the processed underwater terrain images have inconspicuous and few feature points.In order to better realize the stitching of underwater terrain images and solve the problems of slow traditional image stitching speed,we proposed an improved algorithm for underwater terrain image stitching based on spatial gradient feature block.First,the spatial gradient fuzzy C-Means algorithm is used to divide the underwater terrain image into feature blocks with the fusion of spatial gradient information.The accelerated-KAZE(AKAZE)algorithm is used to combine the feature block information to match the reference image and the target image.Then,the random sample consensus(RANSAC)is applied to optimize the matching results.Finally,image fusion is performed with the global homography and the optimal seam-line method to improve the accuracy of image overlay fusion.The experimental results show that the proposed method in this paper effectively divides images into feature blocks by combining spatial information and gradient information,which not only solves the problem of stitching failure of underwater terrain images due to unobvious features,and further reduces the sensitivity to noise,but also effectively reduces the iterative calculation in the feature point matching process of the traditional method,and improves the stitching speed.Ghosting and shape warping are significantly eliminated by re-optimizing the overlap of the image.

Image Authenticity Detection Using DWT and Circular Block-Based LTrP Features

Copy-move forgery is the most common type of digital image manipulation,in which the content from the same image is used to forge it.Such manipulations are performed to hide the desired information.Therefore,forgery detection methods are required to identify forged areas.We have introduced a novel method for features computation by employing a circular block-based method through local tetra pattern(LTrP)features to detect the single and multiple copy-move attacks from the images.The proposed method is applied over the circular blocks to efficiently and effectively deal with the post-processing operations.It also uses discrete wavelet transform(DWT)for dimension reduction.The obtained approximate image is distributed into circular blocks on which the LTrP algorithm is employed to calculate the feature vector as the LTrP provides detailed information about the image content by utilizing the direction-based relation of central pixel to its neighborhoods.Finally,Jeffreys and Matusita distance is used for similarity measurement.For the evaluation of the results,three datasets are used,namely MICC-F220,MICC-F2000,and CoMoFoD.Both the qualitative and quantitative analysis shows that the proposed method exhibits state-of-the-art performance under the presence of post-processing operations and can accurately locate single and multiple copy-move forgery attacks on the images.

Earthquake Activity Features Before Earthquakes with M_S≥7.0 in the Central-Northern Qinghai-Xizang(Tibet) Block

We have studied the seismicity features of M_S≥5.0 earthquakes two years before strong earthquakes with M_S≥7.0 occurred in the central-northern Qinghai-Xizang (Tibet) block since 1920. The results have showed that there is an obvious gap or quiescence of M_S5.0～6.9 earthquakes near epicenters. We have also studied statistical seismicity parameters of M_S5.0～6.9 earthquakes in the same region since 1950. The results have showed that earthquakes with M_S≥7.0 occurred when earthquake frequency is relatively high and earthquake time, space accumulation degrees are rising. And the prediction effect R value scores are between 0.4～0.7. We have concluded that, before earthquakes with M_S≥7.0 in the central-northern Qinghai-Xizang (Tibet) block, M_S5.0～6.0 earthquake activity in the whole area increased and accumulated in time and space, but earthquakes with M_S≥7.0 occurred where M_S5.0～6.0 earthquake activity was relatively quiet.

Correlated Features of Horizontal Movement-Deformation on the North and East Margins of the Qinghai-Xizang Block before the Kunlun Earthquake with M_S=8.1

The high-precision GPS data observed from the northeast margin of the Qinghai-Xizang （Tibet） block and the Sichuan-Yunnan GPS monitoring areas in 1991 （1993）, 1999 and 2001 revealed that： before the Kunlun earthquake with Ms =8.1 on November 14, 2001, the dynamic variation features of horizontal movement-deformation field in the north and east marginal tectonic areas of the Qinghai-Xizang （Tibet） block had some correlated features. That is to say, under the general background of inherited movement, the movement intensifies in the two areas weakened synchronously and the state of deformation changed when the great earthquake was impending. Analysis and study in connection with geological structures showed that before the Kunlun Ms8.1 earthquake, the correlated variations of movement-deformation on the boundaries of Qinghai-Xizang （Tibet） block were related to the disturbing stress field caused by the extensive and rapid stress-strain accumulation in the late stage of large earthquake preparation. Owing to the occurrence of large earthquake inside the block, the release of large amount of strain energy, and the adjustment of tectonic stress field, in relevant structural positions （especially zones not penetrated by historical strong earthquake ruptures） in boundary zones where larger amount of strain energy was accumulated, stress-strain may be further accumulated or else released through rupture.

The Landscape Style and Features of Historical and Cultural Blocks in Handan,Hebei Province,China

The landscape style and features of historical and cultural blocks in Handan show the landscape characteristics of Handan in the specific cultural and historical period.To explore the landscape style and features of historical and cultural blocks in Handan is of great practical significance to maintain the characteristics of historical and cultural blocks,improve city quality,continue city culture and retain cultural characteristics.According to the advantaged natural geography,human geography factors and the current situation of landscape style and features in Handan City,this study discussed the landscape style and features of historical and cultural blocks through practical investigation and scientific research,found out the main problems and put forward corresponding protection and promotion strategies,in order to create a landscape pattern of historical and cultural blocks with cultural connotation,harmony and order,and distinctive characteristics.

The Landscape Style and Features of Historical and Cultural Blocks in Zhengding,Hebei Province,China

Historical and cultural blocks in Zhengding are important parts of China’s famous historical and cultural city.Combined with the natural geography,human geography factors and the current situation of landscape style and features of the historical and cultural blocks and through practical investigation and scientific research,the protection and development law of the historical and cultural blocks in Zhengding was discussed,the main problems existing were found out,and suggestions for the protection and improvement of the historical and cultural blocks in Zhengding was put forward based on the results of questionnaire survey and psychological evaluation,in order to create a harmonious and orderly,profound culture and distinctive historical and cultural landscape style and features.

Feature-Enhanced RefineDet: Fast Detection of Small Objects

Object detection has been studied for many years.The convolutional neural network has made great progress in the accuracy and speed of object detection.However,due to the low resolution of small objects and the representation of fuzzy features,one of the challenges now is how to effectively detect small objects in images.Existing target detectors for small objects:one is to use high-resolution images as input,the other is to increase the depth of the CNN network,but these two methods will undoubtedly increase the cost of calculation and time-consuming.In this paper,based on the RefineDet network framework,we propose our network structure RF2Det by introducing Receptive Field Block to solve the problem of small object detection,so as to achieve the balance of speed and accuracy.At the same time,we propose a Medium-level Feature Pyramid Networks,which combines appropriate high-level context features with low-level features,so that the network can use the features of both the low-level and the high-level for multi-scale target detection,and the accuracy of the small target detection task based on the low-level features is improved.Extensive experiments on the MS COCO dataset demonstrate that compared to other most advanced methods,our proposed method shows significant performance improvement in the detection of small objects.

PRODUCT IMAGE RETRIEVAL BASED ON CO-FEATURES OF THE OBJECT

In this paper, we propose a product image retrieval method based on the object contour corners, image texture and color. The product image mainly highlights the object and its background is very simple. According to these characteristics, we represent the object using its contour, and detect the corners of contour to reduce the number of pixels. Every corner is described using its approximate curvature based on distance. In addition, the Block Difference of Inverse Probabilities (BDIP) and Block Variation of Local Correlation (BVLC) texture features and color moment are extracted from image's HIS color space. Finally, dynamic time warping method is used to match features with different length. In order to demonstrate the effect of the proposed method, we carry out experiments in Mi-crosoft product image database, and compare it with other feature descriptors. The retrieval precision and recall curves show that our method is feasible.

Learning a Discriminative Feature Attention Network for pancreas CT segmentation

Accurate pancreas segmentation is critical for the diagnosis and management of diseases of the pancreas. It is challenging to precisely delineate pancreas due to the highly variations in volume, shape and location. In recent years, coarse-to-fine methods have been widely used to alleviate class imbalance issue and improve pancreas segmentation accuracy. However,cascaded methods could be computationally intensive and the refined results are significantly dependent on the performance of its coarse segmentation results. To balance the segmentation accuracy and computational efficiency, we propose a Discriminative Feature Attention Network for pancreas segmentation, to effectively highlight pancreas features and improve segmentation accuracy without explicit pancreas location. The final segmentation is obtained by applying a simple yet effective post-processing step. Two experiments on both public NIH pancreas CT dataset and abdominal BTCV multi-organ dataset are individually conducted to show the effectiveness of our method for 2 D pancreas segmentation. We obtained average Dice Similarity Coefficient(DSC) of 82.82±6.09%, average Jaccard Index(JI) of 71.13± 8.30% and average Symmetric Average Surface Distance(ASD) of 1.69 ± 0.83 mm on the NIH dataset. Compared to the existing deep learning-based pancreas segmentation methods, our experimental results achieve the best average DSC and JI value.

Style and Feature Construction of Handan Chuancheng Street from the Perspective of Style and Features

Rapid urbanization and ignorance of the characteristics of the city have led to all cities in the same pattern in China,homogeneity of the urban material space,and lack of humanistic spirits.With the development and transformation,China has paid increasing attention to the characteristics of cities,and the historic and cultural block is the most representative carrier of the traditional style of a city.Taking the historic and cultural block of Chuancheng Street in Handan City as an example,this paper combined Handan's urban style and features,started from the status quo of the block,analyzed the design positioning,explored the style and feature elements,and finally proposed the style and feature construction strategy of Chuancheng Street,explored from the perspective of style and feature creation the strategies of building the traditional style for historic and cultural blocks.

A Lightweight Multiscale Feature Fusion Network for Solar Cell Defect Detection

Solar cell defect detection is crucial for quality inspection in photovoltaic power generation modules.In the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it challenging to collect defective samples.Additionally,the complex surface background of polysilicon cell wafers complicates the accurate identification and localization of defective regions.This paper proposes a novel Lightweight Multiscale Feature Fusion network(LMFF)to address these challenges.The network comprises a feature extraction network,a multi-scale feature fusion module(MFF),and a segmentation network.Specifically,a feature extraction network is proposed to obtain multi-scale feature outputs,and a multi-scale feature fusion module(MFF)is used to fuse multi-scale feature information effectively.In order to capture finer-grained multi-scale information from the fusion features,we propose a multi-scale attention module(MSA)in the segmentation network to enhance the network’s ability for small target detection.Moreover,depthwise separable convolutions are introduced to construct depthwise separable residual blocks(DSR)to reduce the model’s parameter number.Finally,to validate the proposed method’s defect segmentation and localization performance,we constructed three solar cell defect detection datasets:SolarCells,SolarCells-S,and PVEL-S.SolarCells and SolarCells-S are monocrystalline silicon datasets,and PVEL-S is a polycrystalline silicon dataset.Experimental results show that the IOU of our method on these three datasets can reach 68.5%,51.0%,and 92.7%,respectively,and the F1-Score can reach 81.3%,67.5%,and 96.2%,respectively,which surpasses other commonly usedmethods and verifies the effectiveness of our LMFF network.

Women's Basic Block Based on the Body Recognition

Body analysis is an important method to clothing construction design. It not only gets the measurement of body, but also analyze the style of body shape. We have discussed the method of woman body fuzzy recognition in another paper and from that we divide woman bodies into thirty-six groups. In each group,bodies have one kind of basic block and there is difference between any two kinds. This paper puts forward thirty-six basic block modes based on various woman bodies.

基于改进YOLOv5s的轻量级绝缘子缺失检测

针对现有绝缘子缺失检测模型计算复杂度高和小目标难以检测等问题,提出一种基于改进的YOLOv5s轻量级检测模型。首先,移除主干网络中的C3模块来减少模型的参数量。其次,在多尺度特征融合网络中引入卷积块注意力机制来提高复杂背景下模型的特征提取能力。同时,采用加权双向特征金字塔网络结构对特征进行双向跨尺度加权融合,提升网络在遮挡物、相似目标干扰下目标的检测性能。最后,选用SIoU损失函数提升网络的收敛速度和检测精度。实验结果表明,所提模型的平均精准率为96.8%,浮点运算数为2.8 GFLOPS,而原始YOLOv5s在保证97.4%的平均精准率下的浮点运算数为16.3 GFLOPS。相较于原始模型,所提模型对小目标、遮挡目标以及模糊等场景有着较强的鲁棒性,且在保证近似检测精度的同时极大减少了计算量。

市镇型历史文化街区价值特征及保护策略研究

市镇型历史文化街区是传统市镇被现代城市吞并后形成的特殊形态的城市文化遗产。它们既保留着整体性的传统市镇空间结构,又呈现了层层积淀的城市遗产空间形态,具有街区类型的特殊性。文章立足市镇型历史文化街区的价值内涵和整体性遗产特征,探究其时空发展规律及保护问题的发生逻辑,并从市镇空间赓续、街区空间更新、街城空间融合3个方面,提出市镇型历史文化街区的保护策略和方法,以期为此类街区的保护传承提供借鉴。

基于改进YOLOv5的遥感图像目标检测

目前目标检测技术虽然已经趋于成熟,但是对遥感图像的检测仍存在不少挑战。针对遥感图像的背景复杂、目标尺度差异大、目标方向任意等特点造成目标检测精度低下的问题,提出一种基于改进YOLOv5的遥感图像目标检测算法。首先,构建一种联合注意力的多尺度特征增强网络,充分融合高低层特征,使特征层具有语义信息的同时包含丰富的细节信息,并在融合过程中利用设计的特征聚焦模块帮助模型选择关键特征,抑制无关信息。其次,使用感受野模块(RFB)对融合后的特征图进行更新,扩大特征图的感受野,减少特征信息损失。最后,对目标增加旋转角度,并采用圆形平滑标签将回归问题转化成分类问题,提高遥感目标定位的准确性。在用于航拍图像目标检测的大规模数据集(DOTA)上的实验结果表明,与YOLOv5算法相比,所提算法的交并比(Io U)为0.5和0.5~0.95时的平均精度均值(m AP@0.5和m AP@0.5∶0.95)分别提高了7.3和3.3个百分点,能够明显提高复杂背景下遥感图像目标的检测精度,并改善对遥感目标的漏检和误检情况。

基于改进YOLOv5s的面向自动驾驶场景的道路目标检测算法

在复杂道路场景中检测车辆、行人、自行车等目标时,存在因多尺度目标及部分遮挡易造成漏检及误检等情况,提出一种基于改进YOLOv5s的面向自动驾驶场景的道路目标检测算法。首先,利用深度可分离卷积替换部分普通卷积,减少模型的参数量以提升检测速度。其次,在特征融合网络中引入基于感受野模块(receptive field block,RFB)改进的RFB-s,通过模仿人类视觉感知,增强特征图的有效感受野区域,提高网络特征表达能力及对目标特征的可辨识性。最后,使用自适应空间特征融合(adaptively spatial feature fusion,ASFF)方式以提升PANet对多尺度特征融合的效果。实验结果表明,在PASCAL VOC数据集上,所提算法检测平均精度均值相较于YOLOv5s提高1.71个百分点,达到84.01%,在满足自动驾驶汽车实时性要求的前提下,在一定程度上减少目标检测时的误检及漏检情况,有效提升模型在复杂驾驶场景下的检测性能。

基于CNN和Transformer并行编码的腹部多器官图像分割

针对现有方法在腹部中小器官图像分割性能方面存在的不足,提出一种基于局部和全局并行编码的网络模型用于腹部多器官图像分割.首先,设计一种提取多尺度特征信息的局部编码分支;其次,全局特征编码分支采用分块Transformer,通过块内Transformer和块间Transformer的组合,既捕获了全局的长距离依赖信息又降低了计算量;再次,设计特征融合模块,以融合来自两条编码分支的上下文信息;最后,设计解码模块,实现全局信息与局部上下文信息的交互,更好地补偿解码阶段的信息损失.在Synapse多器官CT数据集上进行实验,与目前9种先进方法相比,在平均Dice相似系数(DSC)和Hausdorff距离(HD)指标上都达到了最佳性能,分别为83.10%和17.80 mm.

ERP全景视频VVC帧内编码CU快速划分算法

针对等矩柱状投影(equirectangular projection,ERP)全景视频多功能视频编码(versatile video coding,VVC)帧内编码复杂度过高的问题,提出一种编码单元(coding unit,CU)快速划分算法。根据ERP采样特性,将编码帧分为不同纬度区域。基于不同纬度区域CU四叉树深度的分布特性和相邻CU的相关性,对当前CU的划分模式进行提前终止决策;利用梯度差异评估当前CU纹理特性,跳过冗余的水平或垂直划分模式。针对纹理模糊CU,通过纬度采样权重加权的二次比较,判断是否跳过垂直划分模式;利用二维哈尔小波变换系数评估当前CU子块间的差异,判断是否跳过三叉树划分模式。实验结果表明,在全帧内模式下,与VVC官方测试平台相比,所提算法能节省43.85%的编码时间,码率仅增加0.85%,视频质量没有明显下降。