Novel 3D local feature descriptor of point clouds based on spatial voxel homogenization for feature matching

Obtaining a 3D feature description with high descriptiveness and robustness under complicated nuisances is a significant and challenging task in 3D feature matching.This paper proposes a novel feature description consisting of a stable local reference frame(LRF)and a feature descriptor based on local spatial voxels.First,an improved LRF was designed by incorporating distance weights into Z-and X-axis calculations.Subsequently,based on the LRF and voxel segmentation,a feature descriptor based on voxel homogenization was proposed.Moreover,uniform segmentation of cube voxels was performed,considering the eigenvalues of each voxel and its neighboring voxels,thereby enhancing the stability of the description.The performance of the descriptor was strictly tested and evaluated on three public datasets,which exhibited high descriptiveness,robustness,and superior performance compared with other current methods.Furthermore,the descriptor was applied to a 3D registration trial,and the results demonstrated the reliability of our approach.

Eye Detection-Based Deep Belief Neural Networks and Speeded-Up Robust Feature Algorithm

The ability to detect and localize the human eye is critical for use in security applications and human identification and verification systems.This is because eye recognition algorithms have multiple challenges,such as multi-pose variations,ocular parts,and illumination.Moreover,the modern security applica-tions fail to detect facial expressions from eye images.In this paper,a Speeded-Up Roust Feature(SURF)Algorithm was utilized to localize the face images of the enrolled subjects.We highlighted on eye and pupil parts to be detected based on SURF,Hough Circle Transform(HCT),and Local Binary Pattern(LBP).Afterward,Deep Belief Neural Networks(DBNN)were used to classify the input features results from the SURF algorithm.We further determined the correctly and wrongly classified subjects using a confusion matrix with two class labels to classify people whose eye images are correctly detected.We apply Stochastic Gradient Descent(SGD)optimizer to address the overfitting problem,and the hyper-parameters arefine-tuned based on the applied DBNN.The accuracy of the proposed system is determined based on SURF,LBP,and DBNN classifier achieved 95.54%for the ORL dataset,94.07%for the BioID,and 96.20%for the CASIA-V5 dataset.The proposed approach is more reliable and more advanced when compared with state-of-the-art algorithms.

Robust Lane Detection in Shadows and Low Illumination Conditions using Local Gradient Features

This paper presents a method for lane boundaries detection which is not affected by the shadows, illumination and un-even road conditions. This method is based upon processing grayscale images using local gradient features, characteris-tic spectrum of lanes, and linear prediction. Firstly, points on the adjacent right and left lane are recognized using the local gradient descriptors. A simple linear prediction model is deployed to predict the direction of lane markers. The contribution of this paper is the use of vertical gradient image without converting into binary image(using suitable thre-shold), and introduction of characteristic lane gradient spectrum within the local window to locate the preciselane marking points along the horizontal scan line over the image. Experimental results show that this method has greater tolerance to shadows and low illumination conditions. A comparison is drawn between this method and recent methods reported in the literature.

Vehicle Detection in Still Images by Using Boosted Local Feature Detector

Vehicle detectition in still images is a comparatively difficult task. This paper presents a method for this task by using boosted local pattern detector constructed from two local features including Haar-like and oriented gradient features. The whole process is composed of three stages. In the first stage, local appearance features of vehicles and non-vehicle objects are extracted. Haar-tike and oriented gradient features are extracted separately in this stage as local features. In the second stage, Adabeost algorithm is used to select the most discriminative features as weak detectors from the two local feature sets, and a strong local pattern detector is built by the weighted combination of these selected weak detectors. Finally, vehicle detection can be performed in still images by using the boosted strong local feature detector. Experiment results show that the local pattern detector constructed in this way combines the advantages of Haar-like and oriented gradient features, and can achieve better detection results than the detector by using single Haar-like features.

Tire Defect Detection Using Local and Global Features

In this paper, we present a tire defect detection algorithm based on sparse representation. The dictionary learned from reference images can efficiently represent the test image. As the representation coefficients of normal images have a specific distribution, the local feature can be estimate by comparing representation coefficient distribution. Meanwhile, a coding length is used to measure the global features of representation coefficients. The tire defect is located by both these local and global features. Experimental results demonstrate that the proposed method can accurately detect and locate the tire defects.

Supervised Feature Learning for Offline Writer Identification Using VLAD and Double Power Normalization

As an indispensable part of identity authentication,offline writer identification plays a notable role in biology,forensics,and historical document analysis.However,identifying handwriting efficiently,stably,and quickly is still challenging due to the method of extracting and processing handwriting features.In this paper,we propose an efficient system to identify writers through handwritten images,which integrates local and global features from similar handwritten images.The local features are modeled by effective aggregate processing,and global features are extracted through transfer learning.Specifically,the proposed system employs a pre-trained Residual Network to mine the relationship between large image sets and specific handwritten images,while the vector of locally aggregated descriptors with double power normalization is employed in aggregating local and global features.Moreover,handwritten image segmentation,preprocessing,enhancement,optimization of neural network architecture,and normalization for local and global features are exploited,significantly improving system performance.The proposed system is evaluated on Computer Vision Lab(CVL)datasets and the International Conference on Document Analysis and Recognition(ICDAR)2013 datasets.The results show that it represents good generalizability and achieves state-of-the-art performance.Furthermore,the system performs better when training complete handwriting patches with the normalization method.The experimental result indicates that it’s significant to segment handwriting reasonably while dealing with handwriting overlap,which reduces visual burstiness.

Robust Image Watermarking Using Local Invariant Features and Independent Component Analysis

This paper proposes a novel robust image watermarking scheme for digital images using local invariant features and Independent Component Analysis （ICA）. Most present watermarking algorithms are unable to resist geometric distortions that desynchronize the location. The method we propose here is robust to geometric attacks. In order to resist geometric distortions, we use a local invariant feature of the image called the scale invariant feature transform, which is invariant to translation and scaling distortions. The watermark is inserted into the circular patches generated by scale-invariant key point extractor. Rotation invariance is achieved using the translation property of the polar-mapped circular patches. Our method belongs to the blind watermark category, because we use Independent Component Analysis for detection that does not need the original image during detection. Experimental results show that our method is robust against geometric distortion attacks as well as signal-processing attacks.

Loop Closure Detection via Locality Preserving Matching With Global Consensus

A critical component of visual simultaneous localization and mapping is loop closure detection(LCD),an operation judging whether a robot has come to a pre-visited area.Concretely,given a query image(i.e.,the latest view observed by the robot),it proceeds by first exploring images with similar semantic information,followed by solving the relative relationship between candidate pairs in the 3D space.In this work,a novel appearance-based LCD system is proposed.Specifically,candidate frame selection is conducted via the combination of Superfeatures and aggregated selective match kernel(ASMK).We incorporate an incremental strategy into the vanilla ASMK to make it applied in the LCD task.It is demonstrated that this setting is memory-wise efficient and can achieve remarkable performance.To dig up consistent geometry between image pairs during loop closure verification,we propose a simple yet surprisingly effective feature matching algorithm,termed locality preserving matching with global consensus(LPM-GC).The major objective of LPM-GC is to retain the local neighborhood information of true feature correspondences between candidate pairs,where a global constraint is further designed to effectively remove false correspondences in challenging sceneries,e.g.,containing numerous repetitive structures.Meanwhile,we derive a closed-form solution that enables our approach to provide reliable correspondences within only a few milliseconds.The performance of the proposed approach has been experimentally evaluated on ten publicly available and challenging datasets.Results show that our method can achieve better performance over the state-of-the-art in both feature matching and LCD tasks.We have released our code of LPM-GC at https://github.com/jiayi-ma/LPM-GC.

Active Shape Models Using Scale Invariant Feature Transform

A new active shape models (ASMs) was presented, which is driven by scale invariant feature transform (SIFT) local descriptor instead of normalizing first order derivative profiles in the original formulation, to segment lung fields from chest radiographs. The modified SIFT local descriptor, more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel at each resolution level during the segmentation optimization procedure. Experimental results show that the proposed method is more robust and accurate than the original ASMs in terms of an average overlap percentage and average contour distance in segmenting the lung fields from an available public database.

Android Malware Detection Using Local Binary Pattern and Principal Component Analysis

Nowadays,analysis methods based on big data have been widely used in malicious software detection.Since Android has become the dominator of smartphone operating system market,the number of Android malicious applications are increasing rapidly as well,which attracts attention of malware attackers and researchers alike.Due to the endless evolution of the malware,it is critical to apply the analysis methods based on machine learning to detect malwares and stop them from leakaging our privacy information.In this paper,we propose a novel Android malware detection method based on binary texture feature recognition by Local Binary Pattern and Principal Component Analysis,which can visualize malware and detect malware accurately.Also,our method analyzes malware binary directly without any decompiler,sandbox or virtual machines,which avoid time and resource consumption caused by decompiler or monitor in this process.Experimentation on 5127 benigns and 5560 malwares shows that we obtain a detection accuracy of 90%.

视觉SLAM方法综述

实时定位与建图(SLAM)技术搭载特定传感器,使移动机器人在无任何环境先验条件下,在运动过程中自主建立环境模型来计算自身位姿,大幅提高其自主导航能力,以及对不同应用环境的适应性。视觉SLAM方法以相机作为外部传感器,通过采集周围环境信息来创建地图并实时估计机器人自身位姿。为此,介绍了具有代表性的经典视觉SLAM方法及与深度学习相结合的视觉SLAM方法,分析了视觉SLAM方法中采用的不同特征检测方法、后端优化、闭环检测,以及动态环境下视觉SLAM方法的应用,总结了视觉SLAM方法的问题,并探讨了视觉SLAM方法在未来的热点研究方向和发展前景。

A Progressive Approach to Generic Object Detection: A Two-Stage Framework for Image Recognition

Object detection in images has been identified as a critical area of research in computer vision image processing.Research has developed several novel methods for determining an object’s location and category from an image.However,there is still room for improvement in terms of detection effi-ciency.This study aims to develop a technique for detecting objects in images.To enhance overall detection performance,we considered object detection a two-fold problem,including localization and classification.The proposed method generates class-independent,high-quality,and precise proposals using an agglomerative clustering technique.We then combine these proposals with the relevant input image to train our network on convolutional features.Next,a network refinement module decreases the quantity of generated proposals to produce fewer high-quality candidate proposals.Finally,revised candidate proposals are sent into the network’s detection process to determine the object type.The algorithm’s performance is evaluated using publicly available the PASCAL Visual Object Classes Challenge 2007(VOC2007),VOC2012,and Microsoft Common Objects in Context(MS-COCO)datasets.Using only 100 proposals per image at intersection over union((IoU)=0.5 and 0.7),the proposed method attains Detection Recall(DR)rates of(93.17%and 79.35%)and(69.4%and 58.35%),and Mean Average Best Overlap(MABO)values of(79.25%and 62.65%),for the VOC2007 and MS-COCO datasets,respectively.Besides,it achieves a Mean Average Precision(mAP)of(84.7%and 81.5%)on both VOC datasets.The experiment findings reveal that our method exceeds previous approaches in terms of overall detection performance,proving its effectiveness.

基于改进Faster R-CNN的苹果采摘视觉定位与检测方法

针对采摘机器人对场景中目标分布密集、果实相互遮挡的检测及定位能力不理想问题,提出一种引入高效通道注意力机制(ECA)和多尺度融合特征金字塔(FPN)改进Faster R-CNN果实检测及定位方法。首先,利用表达能力较强的融合FPN的残差网络ResNet50替换原VGG16网络,消除了网络退化问题,进而提取更加抽象和丰富的语义信息,提升模型对多尺度和小目标的检测能力;其次,引入注意力机制ECA模块,使特征提取网络聚焦特征图像的局部高效信息,减少无效目标的干扰,提升模型检测精度;最后,采用一种枝叶插图数据增强方法改进苹果数据集,解决图像数据不足问题。基于构建的数据集,使用遗传算法优化K-means++聚类生成自适应锚框,提高模型定位准确性。试验结果表明,改进模型对可抓取和不可直接抓取苹果的精度均值分别为96.16%和86.95%,平均精度均值为92.79%,较传统Faster R-CNN提升15.68个百分点;对可抓取和不可直接抓取的苹果定位精度分别为97.14%和88.93%,较传统Faster R-CNN分别提高12.53个百分点和40.49个百分点;内存占用量减少38.20%,每帧平均计算时间缩短40.7%,改进后的模型参数量小且实时性好,能够更好地应用于果实采摘机器人视觉系统。

基于非线性各向异性滤波的图像特征匹配算法

图像特征匹配是增强现实系统中的关键技术,匹配精度是提升特征匹配性能的关键。提出了一种多尺度特征匹配加强算法(I-AKAZE),通过对非线性各向异性滤波过程中传导函数的改进,减缓图像梯度值大的区域非线性扩散速度,极大程度地保留了匹配图像的边缘特征;同时,结合改进的非线性量化加速稳健特征描述符(NLG-SURF),提高了描述符的识别率。实验结果表明I-AKAZE算法在Mikolajczyk数据集上的可重复性得分相比目前先进的AKAZE算法有着大幅度提升,对应的特征描述符的平均识别率提升8.4%,并且运行速度比经典的SIFT算法快约19%,算法整体在检测和描述阶段上的性能都有提升。

基于直线段检测和LT描述符的矿井图像线特征匹配算法

图像匹配是同步定位与地图构建(SLAM)技术中极为重要的一环,用于根据图像之间的变换关系确定相机位姿。基于线特征的图像匹配方法具有较强的鲁棒性和抗噪能力,更加适用于井下图像匹配,基于深度学习的线描述符对线段遮挡等场景具有较高的鲁棒性,性能优于传统描述符,但卷积神经网络架构的描述符将可变长度线段抽象为固定维进行描述,不利于线段长度及视差变化较大图像的匹配。针对上述问题,提出一种基于直线段检测和线描述符的矿井图像线特征匹配算法。在频域利用单参数同态滤波降低图像的照射分量,并增强反射分量,提升亮度及对比度;在YUV空间利用对比度受限的自适应直方图均衡化(CLAHE)算法对亮度分量进行均衡,使亮度分布更加均匀;变换至RGB空间提取直线段检测(LSD)线,引入一种基于Transformer架构的LT描述符构建LSD线的特征向量,最后完成线特征匹配。实验结果表明:该算法结合了同态滤波和CLAHE算法的优点,增强后图像的亮度适中,对比度良好,灰度分布均匀,增强效果优于单参数同态滤波算法、EnlightenGAN算法;该算法提取的线特征数较原图平均提升了32.92%,在不同相似纹理占比、不同程度旋转与平移变化的井下图像匹配中鲁棒性好,平均正确匹配数为61.75对,平均精度为86.83%,优于线二进制描述符(LBD)算法、LBD_NNDR算法、LT算法,能够满足矿井图像稳健匹配的需求。

利用局部特征匹配的运动小目标光流估计

基于深度光流估计的动态背景运动小目标检测,为了保证小目标的检测性能,一般采用较少的下采样次数以维持较高的分辨率,但由此带来了较大的计算耗时。特征匹配是深度光流估计的一个核心处理环节,其耗时在光流估计整体耗时中的占比较大,且对下采样次数非常敏感。据此,提出一种基于局部特征匹配的快速光流估计算法:引入目标运动信息,缩小特征匹配的空间范围,减少待处理的数据量;设计分块局部匹配策略,引入批处理机制,避免出现逐点局部匹配策略数据处理耗时过大问题,实现算法加速。在此基础上,在光流估计获取的光流场上,采用CenterNet网络检测运动目标对应的光流异常区域。从光流估计耗时、检测精度等方面开展了实验验证,结果表明:针对运动小目标检测,分块特征匹配光流估计比全局特征匹配光流估计耗时减少约25%,目标检测性能相当。

Object tracking method based on joint global and local feature descriptor of 3D LIDAR point cloud

To fully describe the structure information of the point cloud when the LIDAR-object distance is long,a joint global and local feature(JGLF)descriptor is constructed.Compared with five typical descriptors,the object recognition rate of JGLF is higher when the LIDAR-object distances change.Under the situation that airborne LIDAR is getting close to the object,the particle filtering(PF)algorithm is used as the tracking frame.Particle weight is updated by comparing the difference between JGLFs to track the object.It is verified that the proposed algorithm performs 13.95%more accurately and stably than the basic PF algorithm.

基于锚点的快速三维手部关键点检测算法

在人机协作任务中,手部关键点检测为机械臂提供目标点坐标,A2J(Anchor-to-Joint)是具有代表性的一种利用锚点进行关键点检测的方法。A2J以深度图为输入,可实现较好的检测效果,但对全局特征获取能力不足。文中设计了全局-局部特征融合模块(Global-Local Feature Fusion,GLFF)对骨干网络浅层和深层的特征进行融合。为了提升检测速度,文中将A2J的骨干网络替换为ShuffleNetv2并对其进行改造,用5×5深度可分离卷积替换3×3深度可分离卷积,增大感受野,有效提升了骨干网络对全局特征的提取能力。文中在锚点权重估计分支引入高效通道注意力模块(Efficient Channel Attention,ECA),提升了网络对重要锚点的关注度。在主流数据集ICVL和NYU上进行的训练和测试结果表明,相比于A2J,文中所提方法的平均误差分别降低了0.09 mm和0.15 mm。在GTX1080Ti显卡上实现了151 frame·s^(-1)的检测速率,满足人机协作任务对于实时性的要求。

Modulating a Local Shape Descriptor through Biologically Inspired Color Feature

This paper presents a biologically inspired local image descriptor that combines color and shape features. Compared with previous descriptors, red-cyan cells associated with L, M, and S cones （L for long, M for medium, and S for short） are used to indicate one of the opponent color channels. Stepping forward from state-of-the-art color feature extraction, we exploit a new approach to compute the color orientation and magnitudes of three opponent color channels, namely, red-green, blue-yellow, and red-cyan, in two-dimensional space. Color orientation is calculated in histograms with magnitude weighting. We linearly concatenate the four-color-opponent-channel histogram and scale-invariant-feamre-transform histogram in the final step. We apply our biologically inspired descriptor to describe the local image feature. Quantitative comparisons with state-of-the-art descriptors demonstrate the significant advantages of maintaining invariance to photometric and geometric changes in image matching, particularly in cases, such as illumination variation and image blurring, where more color contrast information is observed.

基于关键特征增强机制的3D人脸识别

3D人脸识别是计算机视觉领域的重要组成部分,Pointnet依靠深度学习解决了点云的无序性,实现了3D点云的全局特征提取,但由于点云数据缺乏细节纹理,仅靠全局特征很难实现复杂情况下的人脸识别。针对以上问题,基于Pointnet提出了一种局部特征描述子,用于描述点云局部空间的几何特征,并引入关键特征增强机制,通过特征概率分布增强人脸关键信息,该机制能减少不必要特征对任务的干扰,有效提升模型的准确率。在公共数据集CASIA-3D、Lock3DFace、Bosphorus上进行实验测试,结果表明该方法能很好地应对表情变化、部分遮挡以及头部姿态的干扰,在弱光环境下其准确率高于RP-Net 1.1%,并具有良好的实时性。