View-based virtual learning and recognition of 3D object using view model obtained by motion-stereo

View-based approach for learning and recognition of 3D object and its pose detection was proved to be affective and efficient, except its high learning cost. In this research, we propose a virtual learning approach which generates learning samples of views of an object from its 3D view model obtained by motion-stereo method. From the generated learning sample views, features of high-order autocorrelation are extracted, and discriminant feature spaces for object recognition and pose detection are built. Recognition experiments on real objects are carried out to show the effectiveness of the proposed method. Caihua Wang, Ph.D.: He received his B.S. in mathematics and M.E. in electronic engineering from Renmin University of China, Beijing, China in 1983 and 1986, and his Ph. D. from Shizuoka University, Hamamatsu, Japan in 1996. He is a JST domestic fellow and is doing his post doctoral research at Electrotechnical Laboratory. His research interests are computer vision and image processing. He is a member of IEICE and IPSJ. Katsuhiko Sakaue, Ph.D.: He received the B.E., M.E., and Ph.D. degrees all in electronic engineering from University of Tokyo, in 1976, 1978 and 1981, respectively. In 1981, he joined the Electrotechnical Laboratory, Ministry of International Trade and Industry, and engaged in researches in image processing and computer vision. He received the Encouragement Prize in 1979 from IEICE, and the Paper Award in 1985 from Information.     

Registration of arbitrary multi-view 3D acquisitions

To register 3D meshes representing smooth surfaces we track the 3D digitization system using photogrammetric techniques and calibrations. We present an example by digitizing a 800 mm × 600 mm portion of a car door. To increase the tracking accuracy the 3D scanner is placed in a cubic frame of side 0.5 m covered with 78 targets. The target frame moves in a volume that is approximately 1100 mm × 850 mm × 900 mm, to digitize the area of interest. Using four cameras this target frame is tracked with of an accuracy of 0.03 mm spatially and 0.180 mrad angularly. A registration accuracy between 0.1 mm and 2 mm is reached. This method can be used for the registration of meshes representing featureless surfaces.     

深度学习及其在目标和行为识别中的新进展

深度学习是机器学习中的一个新的研究领域。通过深度学习的方法构建深度网络来抽取特征是目前目标和行为识别中得到关注的研究方向。为引起更多计算机视觉领域研究者对深度学习进行探索和讨论,并推动目标和行为识别的研究,本文对深度学习及其在目标和行为识别中的新进展给予了概述。本文先介绍深度学习领域研究的基本状况、主要概念和原理;然后介绍近期利用深度学习在目标和行为识别应用中的一些新进展;最后阐述了深度学习与神经网络之间的关系,深度学习的优缺点,以及目前深度学习理论需要解决的主要问题。这对拟将深度学习应用于目标和行为识别的研究人员应有所帮助。     

基于深度学习的三维点云人脸识别

为了增强三维点云人脸识别系统针对多表情、多姿态的鲁棒性,提出一种基于深度学习的点云特征提取网络ResPoint.ResPoint网络使用了分组、采样和局部特征提取(ResConv)等模块,而在ResConv模块中使用了跳跃式连接,因此所提网络对于稀疏点云有很好的识别结果.首先通过人脸几何特征点定位鼻尖点,并以该点为中心...     

基于路径轮廓的三维目标识别

骨架能更有效地反映出目标的拓扑结构和细节变化, 因而在三维目标识别中得到广泛应用, 但存在的基于骨架的识别方法均要求骨架端点位于轮廓曲线上, 并且识别精度受骨架端点排序的影响。针对该问题, 提出了一种新的基于路径轮廓的三维目标识别算法。该算法首先定义了一种新的特征点——骨切点, 并根据骨切点在轮廓曲线上的顺序关系, 对骨架端点进行排序; 然后利用路径轮廓对目标轮廓进行分割; 再构造一种新的局部不变特征, 并结合hash表以识别三维目标。实验结果表明, 该算法对存在部分遮挡或缺损的三维目标仍有较好的识别效果。     

基于3D Gabor多视图主动学习的高光谱图像分类

针对高光谱遥感图像中标记样本获取困难的问题,研究如何选择少量高质量的查询样本进行交互标记的多视图主动学习算法。首先采用不同尺度和方向的三维Gabor滤波器组提取高光谱图像空谱特征;然后挑选出类别判别能力较强的三维Gabor特征来构建多视图;最后提出一种基于多视图后验概率差异最小（MPPD）的样本查询策略。实验初选30个标记样本,经过100次迭代后,三维Gabor特征多视图结合MPPD查询策略在ROSIS Pavia University和AVIRIS Indiana Pines两个数据集上的总体分类精度分别达到94.16%和91.30%,表明通过三维Gabor可以有效提取高光谱遥感图像空谱特征,提供具有多样性和互补性的特征视图。结合MPPD查询策略能挑选出最有价值的查询样本。     

3D object recognition based on curvature information of planar views

In this paper, a 3D object recognition algorithm is proposed. Objects are recognized by studying planar images corresponding to a sequence of views. Planar shape contours are represented by their adaptively calculated curvature functions, which are decomposed in the Fourier domain as a linear combination of a set of representative shapes. Finally, sequences of views are identified by means of Hidden Markov Models. The proposed system has been tested for artificial and real objects. Distorted and noisy versions of the objects were correctly clustered together.     

基于深度学习的胰腺图像自动三维重建

胰腺图像的三维重建对于辅助疾病诊断具有重要意义。提出一种全自动的胰腺图像三维重建方法,利用改进的U-Net深度学习网络对图像进行分割,并结合面绘制算法生成三维可视化模型。实验结果表明,该方法重建准确度较高,执行效率快,对辅助诊疗具有积极的作用。     

2D face recognition based on supervised subspace learning from 3D models

One of the main challenges in face recognition is represented by pose and illumination variations that drastically affect the recognition performance, as confirmed by the results of recent face recognition large-scale evaluations. This paper presents a new technique for face recognition, based on the joint use of 3D models and 2D images, specifically conceived to be robust with respect to pose and illumination changes. A 3D model of each user is exploited in the training stage (i.e. enrollment) to generate a large number of 2D images representing virtual views of the face with varying pose and illumination. Such images are then used to learn in a supervised manner a set of subspaces constituting the user's template. Recognition occurs by matching 2D images with the templates and no 3D information (neither images nor face models) is required. The experiments carried out confirm the efficacy of the proposed technique.     

Recent advances in 3D object detection based on RGB-D: A survey

3D object detection is a critical part of environmental perception systems and one of the most fundamental tasks in understanding the 3D visual world, which benefit a series of downstream real-world applications. RGB-D images include object texture and semantic information, as well as depth information describing spatial geometry. Recently, numerous 3D object detection models for RGB-D images have been proposed with excellent performance, but summaries in this area are still absent. To stimulate future research, this paper provides a detailed analysis of current developments in 3D object detection methods for RGB-D images to motivate future research. It covers three major parts, including background on 3D object detection, RGB-D data details, and comparative results of state-of-the-art methods on several publicly available datasets, with an emphasis on contributions, design ideas, and limitations, as well as insightful observations and inspiring future research directions.     

基于改进深度学习方法的人体动作识别综述

为了梳理深度学习方法在人体动作识别领域的发展脉络,对该领域近年来最具代表性的模型和算法进行了综述。以人体动作识别任务流程为线索,详细阐述了深度学习方法在视频预处理阶段、网络结构上的最新成果及其优缺点。介绍了人体动作识别相关的两类数据集,并选取常用的几种进行具体说明。最后,对人体动作识别未来的研究方向进行了探讨与展望。     

感知器残差网络和超限学习机融合的3D物体识别

目的 随着3D扫描技术和虚拟现实技术的发展,真实物体的3D识别方法已经成为研究的热点之一。针对现有基于深度学习的方法训练时间长,识别效果不理想等问题,提出了一种结合感知器残差网络和超限学习机（ELM）的3D物体识别方法。方法 以超限学习机的框架为基础,使用多层感知器残差网络学习3D物体的多视角投影特征,并利用提取的特征数据和已知的标签数据同时训练了ELM分类层、K最近邻（KNN）分类层和支持向量机（SVM）分类层识别3D物体。网络使用增加了多层感知器的卷积层替代传统的卷积层。卷积网络由改进的残差单元组成,包含多个卷积核个数恒定的并行残差通道,用于拟合不同数学形式的残差项函数。网络中半数卷积核参数和感知器参数以高斯分布随机产生,其余通过训练寻优得到。结果 提出的方法在普林斯顿3D模型数据集上达到了94.18%的准确率,在2D的NORB数据集上达到了97.46%的准确率。该算法在两个国际标准数据集中均取得了当前最好的效果。同时,使用超限学习机框架使得本文算法的训练时间比基于深度学习的方法减少了3个数量级。结论 本文提出了一种使用多视角图识别3D物体的方法,实验表明该方法比现有的ELM方法和深度学习等最新方法的识别率更高,抗干扰性更强,并且其调节参数少,收敛速度快。     

Efficient 3D reconstruction for face recognition

Face recognition with variant pose, illumination and expression (PIE) is a challenging problem. In this paper, we propose an analysis-by-synthesis framework for face recognition with variant PIE. First, an efficient two-dimensional (2D)-to-three-dimensional (3D) integrated face reconstruction approach is introduced to reconstruct a personalized 3D face model from a single frontal face image with neutral expression and normal illumination. Then, realistic virtual faces with different PIE are synthesized based on the personalized 3D face to characterize the face subspace. Finally, face recognition is conducted based on these representative virtual faces. Compared with other related work, this framework has following advantages: (1) only one single frontal face is required for face recognition, which avoids the burdensome enrollment work; (2) the synthesized face samples provide the capability to conduct recognition under difficult conditions like complex PIE; and (3) compared with other 3D reconstruction approaches, our proposed 2D-to-3D integrated face reconstruction approach is fully automatic and more efficient. The extensive experimental results show that the synthesized virtual faces significantly improve the accuracy of face recognition with changing PIE.     

3D object retrieval based on multi-view convolutional neural networks

Multimedia Tools and Applications - Recently, 3D objects have been widely designed and applied in various technical applications. In this paper, we propose a novel 3D model retrieval method based...     

Efficient 3D object recognition using foveated point clouds

Recent hardware technologies have enabled acquisition of 3D point clouds from real world scenes in real time. A variety of interactive applications with the 3D world can be developed on top of this new technological scenario. However, a main problem that still remains is that most processing techniques for such 3D point clouds are computationally intensive, requiring optimized approaches to handle such images, especially when real time performance is required. As a possible solution, we propose the use of a 3D moving fovea based on a multiresolution technique that processes parts of the acquired scene using multiple levels of resolution. Such approach can be used to identify objects in point clouds with efficient timing. Experiments show that the use of the moving fovea shows a seven fold performance gain in processing time while keeping 91.6% of true recognition rate in comparison with state-of-the-art 3D object recognition methods.     

深度学习背景下视觉显著性物体检测综述

视觉显著性物体检测是对人类视觉和认知系统的模拟,而深度学习则是对人类大脑计算方式的模拟,将两者有机结合可以有效推动计算机视觉的发展。视觉显著性物体检测的任务是从图像中定位并提取具有明确轮廓的显著性物体实例。随着深度学习的发展,视觉显著性物体检测的精度和效率都得到巨大提升,但仍然面临改进主流算法性能、减少对像素级标注样本的依赖等主要挑战。针对上述挑战,本文从视觉显著性物体检测思想与深度学习方法融合策略的角度对相关论述进行分类总结。1）分析传统显著性物体检测方法带来的启示及其缺点,指出视觉显著性物体检测的核心思路为多层次特征的提取、融合与修整;2）从改进特征编码方式与信息传递结构、提升边缘定位精度、改善注意力机制、提升训练稳定性和控制噪声的角度对循环卷积神经网络、全卷积神经网络和生成对抗网络3种主流算法的性能提升进行分析,从优化弱监督样本处理模块的角度分析了减少对像素级标注样本依赖的方法;3）对协同显著性物体检测、多类别图像显著性物体检测以及未来的研究问题和方向进行介绍,并给出了可能的解决思路。