Appearance models based on kernel canonical correlation analysis

This paper introduces a new approach to constructing appearance models based on kernel canonical correlation analysis (kernel-CCA). Kernel-CCA is a non-linear extension of CCA, where a non-linear transformation of the input data is performed implicitly using kernel methods. Although, in this respect, it is similar to other generalized linear methods, kernel-CCA is especially well suited for relating two sets of measurements. The benefits of our method compared to standard feature extraction methods based on PCA will be illustrated experimentally for the task of estimating an object's pose from raw brightness images.     

Repetitive assembly action recognition based on object detection and pose estimation

The present study employs deep learning methods to recognize repetitive assembly actions and estimate their operating times. It is intended to monitor the assembly process of workers and prevent assembly quality problems caused by the lack of key operational steps and the irregular operation of workers. Based on the characteristics of the repeatability and tool dependence of the assembly action, the recognition of the assembly action is considered as the tool object detection in the present study. Moreover, the YOLOv3 algorithm is initially applied to locate and judge the assembly tools and recognize the worker's assembly action. The present study shows that the accuracy of the action recognition is 92.8 %. Then, the pose estimation algorithm CPM based on deep learning is used to realize the recognition of human joint. Finally, the joint coordinates are extracted to judge the operating times of repetitive assembly actions. The accuracy rate of judging the operating times for repetitive assembly actions is 82.1 %.     

Localization of primitives using adaptive projections

An application of an active method in order to compute highly accurate 3D localization of point features from few projections is presented. The angle of projection of the image is controlled by the system and directed to extract 3D information from the environment in a manner leading to accurate location in less computation.This model is relevant for tomographic reconstruction, for feature based stereo and for model based robot registration.     

Using natural class hierarchies in multi-class visual classification

We address the problem of computationally efficient visual classification of objects, and propose a system for solving multi-class problems in domains that have inherent hierarchic structure, such as subclass-superclass-relationships based on visual similarity. Class relationships are used at runtime to select the computationally simplest feature space that allows classification at high level of confidence for each example view. Classification accuracies can then be further improved using rank-order voting over multiple views. Our experimental results show that our system compares favorably to previously published results using a demanding benchmark. The results support the hypothesis that class hierarchies based on visual similarities are feasible and useful in controlling the accuracy vs. speed tradeoffs in classification.     

基于Adaboost和CART结合的优化分类算法

提出了一种基于Adaboost算法和CART算法结合的分类算法。以特征为节点生成CART二叉树,用CART二叉树代替传统Adaboost算法中的弱分类器,再由这些弱分类器生成强分类器。将强分类器对数字样本和人脸样本分类,与传统Adaboost算法相比,该方法的错误率分别减少20%和86.5%。将分类器应用于目标检测上,实现了对这两种目标的快速检测和定位。结果表明,改进算法既减小了对样本分类的错误率,又保持了传统Adboost算法对目标检测的快速性。     

Customized classification learning based on query projections

We develop a customized classification learning method QPL, which is based on query projections. Given an instance to be classified (query instance), QPL explores the projections of the query instance (QPs), which are essentially subsets of attribute values shared by the query and training instances. QPL investigates the associated training data distribution of a QP to decide whether it is useful. The final prediction for the query is made by combining some statistics of the selected useful QPs. Unlike existing instance-based learning, QPL does not need to compute a distance measure between instances. The utilization of QPs for learning can explore a richer hypothesis space and achieve a balance between precision and robustness. Another characteristic of QPL is that the target class may vary for different query instances in a given data set. We have evaluated our method with synthetic and benchmark data sets. The results demonstrate that QPL can achieve good performance and high reliability.     

Localization of a mobile robot based on an ultrasonic sensor using dynamic obstacles

In this article, we propose a localization scheme for a mobile robot based on the distance between the robot and moving objects. This method combines the distance data obtained from ultrasonic sensors in a mobile robot, and estimates the location of the mobile robot and the moving object. The movement of the object is detected by a combination of data and the object’s estimated position. Then, the mobile robot’s location is derived from the a priori known initial state. We use kinematic modeling that represents the movement of a robot and an object. A Kalman-filtering algorithm is used for addressing estimation error and measurement noise. Throughout the computer simulation experiments, the performance is verified. Finally, the results of experiments are presented and discussed. The proposed approach allows a mobile robot to seek its own position in a weakly structured environment. This work was presented in part at the 12th International Symposium on Artificial Life and Robotics, Oita, Japan, January 25–27, 2007     

Object Detection and Localization by Dynamic Template Warping

A simple method is presented for detecting, localizing and recognizing instances of classes of objects, while accommodating a wide variation in an object's pose. The method utilizes a small two-dimensional template that is warped into an image, and converts localization to a one-dimensional sub-problem, with the search for a match between image and template executed by dynamic programming. For roughly cylindrical objects (like heads), the method recovers three of the six degrees of freedom of motion (2 translation, 1 rotation), and accommodates two more degrees of freedom in the search process (1 rotation, 1 translation). Experiments demonstrate that the method provides an efficient search strategy that outperforms normalized correlation. This is demonstrated in the example domain of face detection and localization, and can extended to more general detection tasks. An additional technique recovers rough object pose from the match results, and is used in a two stage recognition experiment in conjunction with maximization of mutual information.     

Real-Time Body Pose Recognition Using 2D or 3D Haarlets

This article presents a novel approach to markerless real-time pose recognition in a multicamera setup. Body pose is retrieved using example-based classification based on Haar wavelet-like features to allow for real-time pose recognition. Average Neighborhood Margin Maximization (ANMM) is introduced as a powerful new technique to train Haar-like features. The rotation invariant approach is implemented for both 2D classification based on silhouettes, and 3D classification based on visual hulls.     

多姿态人脸识别

人脸识别在很多场合都有重要的作用,传统的身份验证是采用某种识别号码等方法, 以阻止伤造的发生。由于人的视觉特征如面部,姿态等是相对稳定而且各不相同的,因此采用这些特征进行身份的识别是可行的本文提出了一种处理多姿态人脸识别的多候选类加权识别方法,为了减少姿态变化的影响,提出了相应的预处理法。     

Object recognition based on image sequences by using inter-feature-line consistencies

An image sequence-based framework for appearance-based object recognition is proposed in this paper. Compared with the methods of using a single view for object recognition, inter-frame consistencies can be exploited in a sequence-based method, so that a better recognition performance can be achieved. We use the nearest feature line (NFL) method (IEEE Trans. Neural Networks 10 (1999) 439) to model each object. The NFL method is extended in this paper by further integrating motion-continuity information between features lines in a probabilistic framework. The associated recognition task is formulated as maximizing an a posteriori probability measure. The recognition problem is then further transformed to a shortest-path searching problem, and a dynamic-programming technique is used to solve it.     

对深度学习中目标定位不确定度评定的讨论

得益于深度学习技术的快速发展,高准确率的目标自动定位得以实现,这为各领域的智能化转型提供了极大的助力。然而,尽管大多数情况下基于深度学习的目标定位方法都能够获得较为精确的输出,但一些误差较大的定位结果还是难以避免。正因为缺少规范的不确定度评定,所以那些误差较大的定位结果难以被有效地消除,进而影响了基于深度学习的目标定位方法的工程化应用。从符合计量规范的测量不确定度入手,讨论了当前深度学习中目标定位技术评价指标的意义和不足,并提出了对规范化目标定位技术不确定度评定的建议。     

基于单目视觉的在线人体康复动作识别

为了进一步提高居家监护场景下人体动作识别的可靠性与实时性,更好地辅助出院后的卒中患者进行康复训练,提出一种基于单目视觉的在线人体动作识别算法.融合姿态估计OpenPose与最近邻匹配算法对监控视频流中的目标人体生成动作序列.通过滑动窗口选取原始姿态特征并对其预处理转化为鲁棒性特征,输入到多层LSTM长短时记忆网络中进行...     

基于SSU-SGD的动态手持物体识别

连续目标中包含更加丰富的信息,为了更好地获取动态手持物体中的视觉信息,以不同背景下的动态手持物体为目标,基于步长自学习更新的SGD算法（简称SSU-SGD）提出了适用于动态手持物体识别的三个基准,通过自学习出不同的步长,分别在已知类、未知类和已知对象的基础上进行巩固训练,用于后续的动态手持物体识别中。用AlexNet和VGG网络对三个不同基准下的naive策略和累积策略进行了编程实验与仿真,经实验验证,该方法可以有效提高运行速度和训练精确度,并且有效提高了动态手持物体识别过程的实时性,可以进一步应用于实际。     

Face posture estimation using eigen analysis on an IBR (image based rendered) database

In this paper, we present a novel representation of the human face for estimating the orientation of the human head in a two dimensional intensity image. The method combines the use of the much familiar eigenvalue based dissimilarity measure with image based rendering. There are two main components of the algorithm described here: the offline hierarchical image database generation and organization, and the online pose estimation stage. The synthetic images of the subject's face are automatically generated offline, for a large set of pose parameter values, using an affine coordinate based image reprojection technique. The resulting database is formally called as the IBR (or image based rendered) database. This is followed by the hierarchical organization of the database, which is driven by the eigenvalue based dissimilarity measure between any two synthetic image pair. This hierarchically organized database is a detailed, yet structured, representation of the subject's face. During the pose estimation of a subject in an image, the eigenvalue based measure is invoked again to search the synthetic (IBR) image closest to the real image. This approach provides a relatively easy first step to narrow down the search space for complex feature detection and tracking algorithms in potential applications like virtual reality and video-teleconferencing applications.     

基于双线性卷积网络的细粒度图像定位

细粒度图像识别是计算机视觉领域的一个难题,也是大数据时代和人工智能的一个具有挑战性的难题。为了解决该问题,提出了一种基于双线性卷积网络的对象定位方法,该方法通过双线性网络来得到VGG网络不同层的特征,将其交集作为最终的定位框。为了验证所提方法的可行性,在CUB-200-2011数据集和Stanford Cars-196上对所提方法进行验证,实验结果表明所提的方法的对象定位精确度远远高于其他具有代表性的方法,同时在加入了软最大化分类器后,所提方法得到的分类准确率比原始图像有了较大提高。     

Polyhedral Object Localization in an Image by Referencing to a Single Model View

Identifying a three-dimensional (3D) object in an image is traditionally dealt with by referencing to a 3D model of the object. In the last few years there has been a growing interest of using not a 3D shape but multiple views of the object as the reference. This paper attempts a further step in the direction, using not multiple views but a single clean view as the reference model. The key issue is how to establish correspondences from the model view where the boundary of the object is explicitly available, to the scene view where the object can be surrounded by various distracting entities and its boundary disturbed by noise. We propose a solution to the problem, which is based upon a mechanism of predicting correspondences from just four particular initial point correspondences. The object is required to be polyhedral or near-polyhedral. The correspondence mechanism has a computational complexity linear with respect to the total number of visible corners of the object in the model view. The limitation of the mechanism is also analyzed thoroughly in this paper. Experimental results over real images are presented to illustrate the performance of the proposed solution.     

Estimating 3D hand pose using hierarchical multi-label classification

This paper presents an analysis of the design of classifiers for use in a hierarchical object recognition approach. In this approach, a cascade of classifiers is arranged in a tree in order to recognize multiple object classes. We are interested in the problem of recognizing multiple patterns as it is closely related to the problem of locating an articulated object. Each different pattern class corresponds to the hand in a different pose, or set of poses. For this problem obtaining labelled training data of the hand in a given pose can be problematic. Given a parametric 3D model, generating training data in the form of example images is cheap, and we demonstrate that it can be used to design classifiers almost as good as those trained using non-synthetic data. We compare a variety of different template-based classifiers and discuss their merits.