Object recognition using discriminative parts

The existing object recognition methods can be classified into two categories: interest-point-based and discriminative-part-based. The interest-point-based methods do not perform well if the interest points cannot be selected very carefully. The performance of the discriminative-part-base methods is not stable if viewpoints change, because they select discriminative parts from the interest points. In addition, the discriminative-part-based methods often do not provide an incremental learning ability. To address these problems, we propose a novel method that consists of three phases. First, we use some sliding windows that are different in scale to retrieve a number of local parts from each model object and extract a feature vector for each local part retrieved. Next, we construct prototypes for the model objects by using the feature vectors obtained in the first phase. Each prototype represents a discriminative part of a model object. Then, we establish the correspondence between the local parts of a test object and those of the model objects. Finally, we compute the similarity between the test object and each model object, based on the correspondence established. The test object is recognized as the model object that has the highest similarity with the test object. The experimental results show that our proposed method outperforms or is comparable with the compared methods in terms of recognition rates on the COIL-100 dataset, Oxford buildings dataset and ETH-80 dataset, and recognizes all query images of the ZuBuD dataset. It is robust enough for distortion, occlusion, rotation, viewpoint and illumination change. In addition, we accelerate the recognition process using the C4.5 decision tree technique, and the proposed method has the ability to build prototypes incrementally.     

A handwritten numeral character classification using tolerant roughset

Proposes a data classification method based on the tolerant rough set that extends the existing equivalent rough set. A similarity measure between two data is described by a distance function of all constituent attributes and they are defined to be tolerant when their similarity measure exceeds a similarity threshold value. The determination of optimal similarity threshold value is very important for accurate classification. So, we determine it optimally by using the genetic algorithm (GA), where the goal of evolution is to balance two requirements such that: 1) some tolerant objects are required to be included in the same class as many as possible; and 2) some objects in the same class are required to be tolerant as much as possible. After finding the optimal similarity threshold value, a tolerant set of each object is obtained and the data set is grouped into the lower and upper approximation set depending on the coincidence of their classes. We propose a two-stage classification method such that all data are classified by using the lower approximation at the first stage and then the nonclassified data at the first stage are classified again by using the rough membership functions obtained from the upper approximation set. We apply the proposed classification method to the handwritten numeral character classification problem and compare its classification performance and learning time with those of the feedforward neural network's backpropagation algorithm     

Continuous monitoring of range spatial keyword query over moving objects

In this paper, we propose an efficient solution for processing continuous range spatial keyword queries over moving spatio-textual objects (namely, CRSK-mo queries). Major challenges in efficient processing of CRSK-mo queries are as follows: (i) the query range is determined based on both spatial proximity and textual similarity; thus a straightforward spatial proximity based pruning of the search space is not applicable as any object far from a query location with a high textual similarity score can still be the answer (and vice versa), (ii) frequent location updates may invalidate a query result, and thus require frequent re-computing of the result set for any object updates. To address these challenges, the key idea of our approach is to exploit the spatial and textual upper bounds between queries and objects to form safe zones (at the client-side) and buffer regions (at the server-side), and then use these bounds to quickly prune objects and queries through smart in-memory data structures. We conduct extensive experiments with a synthetic dataset that verify the effectiveness and efficiency of our proposed algorithm.     

异构数据实体分辨多目标蚁群参考点选择

为提高异构数据实体分辨的准确性,提出了异构数据实体分辨的蚁群算法参考点选择方法。异构数据的相似性通常难以直接度量,可以将其映射到参照物构造的统一空间后,再进行相似度的度量。给定两个异构数据集,选取若干匹配的数据对象对作为参照物(称之为参考点),将两个数据集中对象转换为到各自参考点的距离向量,依据距离向量的相似性进行实体分辨。为选择出更优的参考点集,建立了以最大化查全率、最大化查准率和最小化参考点集合规模为目标的优化模型,通过约束参考点集合规模,将上述模型转换成两目标优化模型,进而设计求解模型的蚁群算法,实现了参考点集的优化选择。实验结果表明,上述方法能够有效提高异构数据实体分辨的准确性。     

A method of stepwise benchmarking for inefficient DMUs based on the proximity-based target selection

DEA is a useful nonparametric method of measuring the relative efficiency of a DMU and yielding a reference target for an inefficient DMU. However, it is very difficult for inefficient DMUs to be efficient by benchmarking a target DMU which has different input use. Identifying appropriate benchmarks based on the similarity of input endowment makes it easier for an inefficient DMU to imitate its target DMUs. But it is rare to find out a target DMU, which is both the most efficient and similar in input endowments, in real situation. Therefore, it is necessary to provide an optimal path to the most efficient DMU on the frontier through several times of a proximity-based target selection process. We propose a dynamic method of stepwise benchmarking for inefficient DMUs to improve their efficiency gradually.The empirical study is conducted to compare the performance between the proposed method and the prior methods with a dataset collected from Canadian Bank branches. The comparison result shows that the proposed method is very practical to obtain a gradual improvement for inefficient DMUs while it assures to reach frontier eventually.     

The maximal likelihood enumeration method for the problem of classifying piecewise regular objects

We study the recognition problem for composite objects based on a probabilistic model of a piecewise regular object with thousands of alternative classes. Using the model’s asymptotic properties, we develop a new maximal likelihood enumeration method which is optimal (in the sense of choosing the most likely reference for testing on every step) in the class of “greedy” algorithms of approximate nearest neighbor search. We show experimental results for the face recognition problem on the FERET dataset. We demonstrate that the proposed approach lets us reduce decision making time by several times not only compared to exhaustive search but also compared to known approximate nearest neighbors techniques.     

Evidence-based recognition of 3-D objects

An evidence-based recognition technique is defined that identifies 3-D objects by looking for their notable features. This technique makes use of an evidence rule base, which is a set of salient or evidence conditions with corresponding evidence weights for various objects in the database. A measure of similarity between the set of observed features and the set of evidence conditions for a given object in the database is used to determine the identity of an object in the scene or reject the object(s) in the scene as unknown. This procedure has polynomial time complexity and correctly identifies a variety of objects in both synthetic and real range images. A technique for automatically deriving the evidence rule base from training views of objects is shown to generate evidence conditions that successfully identify new views of those objects     

Free-form design using axial curve-pairs

Deformation of 3D shapes usually requires the use of a deformation tool. The freeform deformation technique requires the use of a lattice of control point for deforming an object. This may require a synchronized movement of the lattice control points in order to obtain the desired effects. The axial deformation technique allows an object to be deformed by manipulating an axial curve. However, unexpected twist of the object may be obtained. This is a result of the lack of control on the local coordinate frame of the curve. This paper presents a technique for deforming objects with a set of axial curve-pairs. The use of a curve-pair allows the local coordinate frame to be controlled intuitively. A curve-pair is composed of a primary and an orientation curve. The orientation curve is an approximate offset of the primary curve. A technique is proposed for maintaining the relation between the primary and the orientation curve when the curve-pair is adjusted. By associating a complex 3D object to a curve-pair, the object can be stretched, bended, and twisted intuitively through manipulating the curve-pair. This deformation technique is particularly suitable for manipulating complex shapes (e.g. decorative components) in industrial and aesthetic design, and is also suitable for modelling characters and animals with flexible bodies. Adjusting the curve-pair according to some motion constraints produces different postures of a character or animal model. This in turn can be used as decorative components for aesthetic design.     

Illumination planning for object recognition using parametriceigenspaces

Presents a novel approach to the problem of illumination planning for robust object recognition in structured environments. Given a set of objects, the goal is to determine the illumination for which the objects are most distinguishable in appearance from each other. Correlation is used as a measure of similarity between objects. For each object, a large number of images is automatically obtained by varying the pose and the illumination direction. Images of all objects together constitute the planning image set. The planning set is compressed using the Karhunen-Loeve transform to obtain a low-dimensional subspace, called the eigenspace. For each illumination direction, objects are represented as parametrized manifolds in the eigenspace. The minimum distance between the manifolds of two objects represents the similarity between the objects in the correlation sense. The optimal source direction is therefore the one that maximizes the shortest distance between the object manifolds. Several experiments have been conducted using real objects. The results produced by the illumination planner have been used to enhance the performance of an object recognition system     

无重叠视域的多摄像机之间的目标匹配

在无重叠视域的多摄像机监控中,由于不同摄像机的视域差别和视域分离,同一运动目标在不同的视域中的成像可能会非常不同,因此在这种情况下对运动目标进行匹配是一项具有挑战性的工作。提出了一种可以容忍光照的不同,在无重叠视域的多摄像机下进行目标匹配的方法。该方法经过初始聚类和K-means聚类对目标进行主颜色谱的提取,利用EMKM算法改善K-means对初始中心点的依赖性,把提取出来的主颜色谱直方图作为目标的特征,然后利用特征相似度测量来判定任意两个物体之间是否匹配;当无法对某些物体进行准确匹配时,再利用SIFT特征进行下一步匹配。该方法也可以用于有重叠视域的多摄像机目标匹配中,通过与其他匹配方法相结合,提高匹配的准确度。实验结果证实了该方法具有较高的准确度。     

Generalizing prefix filtering to improve set similarity joins

Identification of all pairs of objects in a dataset whose similarity is not less than a specified threshold is of major importance for management, search, and analysis of data. Set similarity joins are commonly used to implement this operation; they scale to large datasets and are versatile to represent a variety of similarity notions. Most methods proposed so far present two main phases at a high level of abstraction: candidate generation producing a set of candidate pairs and verification applying the actual similarity measure to the candidates and returning the correct answer. Previous work has primarily focused on the reduction of candidates, where candidate generation presented the major effort to obtain better pruning results. Here, we propose an opposite approach. We drastically decrease the computational cost of candidate generation by dynamically reducing the number of indexed objects at the expense of increasing the workload of the verification phase. Our experimental findings show that this trade-off is advantageous: we consistently achieve substantial speed-ups as compared to known algorithms.     

结合时空一致性的FairMOT跟踪算法优化

目的 视频多目标跟踪(multiple object tracking, MOT)是计算机视觉中的一项重要任务,现有研究分别针对目标检测和目标关联部分进行改进,均忽视了多目标跟踪中的不一致问题。不一致问题主要包括3方面,即目标检测框中心与身份特征中心不一致、帧间目标响应不一致以及训练测试过程中相似度度量方式不一致。为了解决上述不一致问题,本文提出一种基于时空一致性的多目标跟踪方法,以提升跟踪的准确度。方法 从空间、时间以及特征维度对上述不一致性进行修正。对于目标检测框中心与身份特征中心不一致,针对每个目标检测框中心到特征中心之间的空间差异,在偏移后的位置上提取目标的ReID(re-identification)特征;对帧间响应不一致,使用空间相关计算相邻帧之间的运动偏移信息,基于该偏移信息对前一帧的目标响应进行变换后得到帧间一致性响应信息,然后对目标响应进行增强;对训练和测试过程中的相似度度量不一致,提出特征正交损失函数,在训练时考虑目标两两之间的相似关系。结果 在3个数据集上与现有方法进行比较。在MOT17、MOT20和Hieve数据集中,MOTA(multiple object t...     

A diversity-based search approach to support annotation of a large fish image dataset

Label propagation consists in annotating an unlabeled dataset starting from a set of labeled items. However, most current methods exploit only image similarity between labeled and unlabeled images in order to find propagation candidates, which may result, especially in very large datasets, in retrieving mostly near-duplicate images. While such approaches are technically correct, as they maximize the propagation precision, the resulting annotated dataset may not be as useful, since they lack intra-class variability within the set of images sharing the same label. In this paper, we propose an approach for label propagation which favors the propagation of an object’s label to a set of images representing as many different views of that object as possible, while at the same time preserving the relevance of the retrieved items to the query. Our method is based on a diversity-based clustering technique using a random forest framework and a label propagation approach which is able to effectively and efficiently propagate annotations using a similarity-based approach operating on clusters. The method was tested on a very large dataset of fish images achieving good performance in automated label propagation, ensuring diversification of the annotated items while preserving precision.     

Hierarchical fusion and divergent activation based weakly supervised learning for object detection from remote sensing images

Object detection and location from remote sensing (RS) images is challenging, computationally expensive, and labor intense. Benefiting from research on convolutional neural networks (CNNs), the performance in this field has improved in the recent years. However, object detection methods based on CNNs require a large number of images with annotation information for training. For object location, these annotations must contain bounding boxes. Furthermore, objects in RS images are usually small and densely co-located, leading to a high cost of manual annotation. We tackle the problem of weakly supervised object detection under such conditions, aiming to learn detectors with only image-level annotations, i.e., without bounding box annotations. Based on the fact that the feature maps of a CNN are localizable, we hierarchically fuse the location information from the shallow feature map with the class activation map to obtain accurate object locations. In order to mitigate the loss of small or densely distributed objects, we introduce a divergent activation module and a similarity module into the network. The divergent activation module is used to improve the response strength of the low-response areas in the shallow feature map. Densely distributed objects in RS images, such as aircraft in an airport, often exhibit a certain similarity. The similarity module is used to improve the feature distribution of the shallow feature map and to suppress background noise. Comprehensive experiments on a public dataset and a self-assembled dataset (which we made publicly available) show the superior performance of our method compared to state-of-the-art object detectors.     

Class-based feature matching across unrestricted transformations

We develop a novel method for class-based feature matching across large changes in viewing conditions. The method is based on the property that when objects share a similar part, the similarity is preserved across viewing conditions. Given a feature and a training set of object images, we first identify the subset of objects that share this feature. The transformation of the feature's appearance across viewing conditions is determined mainly by properties of the feature, rather than of the object in which it is embedded. Therefore, the transformed feature will be shared by approximately the same set of objects. Based on this consistency requirement, corresponding features can be reliably identified from a set of candidate matches. Unlike previous approaches, the proposed scheme compares feature appearances only in similar viewing conditions, rather than across different viewing conditions. As a result, the scheme is not restricted to locally planar objects or affine transformations. The approach also does not require examples of correct matches. We show that by using the proposed method, a dense set of accurate correspondences can be obtained. Experimental comparisons demonstrate that matching accuracy is significantly improved over previous schemes. Finally, we show that the scheme can be successfully used for invariant object recognition.     

Fully Automatic Registration of Image Sets on Approximate Geometry

The photorealistic acquisition of 3D objects often requires color information from digital photography to be mapped on the acquired geometry, in order to obtain a textured 3D model. This paper presents a novel fully automatic 2D/3D global registration pipeline consisting of several stages that simultaneously register the input image set on the corresponding 3D object. The first stage exploits Structure From Motion (SFM) on the image set in order to generate a sparse point cloud. During the second stage, this point cloud is aligned to the 3D object using an extension of the 4 Point Congruent Set (4PCS) algorithm for the alignment of range maps. The extension accounts for models with different scales and unknown regions of overlap. In the last processing stage a global refinement algorithm based on mutual information optimizes the color projection of the aligned photos on the 3D object, in order to obtain high quality textures. The proposed registration pipeline is general, capable of dealing with small and big objects of any shape, and robust. We present results from six real cases, evaluating the quality of the final colors mapped onto the 3D object. A comparison with a ground truth dataset is also presented.     

Performance evaluation of Web proxy cache replacement policies

The continued growth of the World-Wide Web and the emergence of new end-user technologies such as cable modems necessitate the use of proxy caches to reduce latency, network traffic and Web server loads. In this paper we analyze the importance of different Web proxy workload characteristics in making good cache replacement decisions. We evaluate workload characteristics such as object size, recency of reference, frequency of reference, and turnover in the active set of objects. Trace-driven simulation is used to evaluate the effectiveness of various replacement policies for Web proxy caches. The extended duration of the trace (117 million requests collected over 5 months) allows long term side effects of replacement policies to be identified and quantified.

Our results indicate that higher cache hit rates are achieved using size-based replacement policies. These policies store a large number of small objects in the cache, thus increasing the probability of an object being in the cache when requested. To achieve higher byte hit rates a few larger files must be retained in the cache. We found frequency-based policies to work best for this metric, as they keep the most popular files, regardless of size, in the cache. With either approach it is important that inactive objects be removed from the cache to prevent performance degradation due to pollution.     

Design of a control algorithm for objects with parametric uncertainty,disturbances, and input signal saturation

We design a control algorithm for objects under parametric uncertainty, external bounded disturbances, and saturation of the controlled signal. We assume that the object model is described by a linear dynamical system with arbitrary relative degree and several inputs and outputs. The developed algorithm provides approximate tracking of the output of the control object for a reference signal. We obtain sufficient stability conditions for the closed system that depend on object parameters, reference model, and the controller. We show modeling results that illustrate the operation of the developed scheme.     

Fast Image Correspondence with Global Structure Projection

This paper presents a method for recognizing images with flat objects based on global keypoint structure correspondence.This technique works by two steps:reference keypoint selection and structure projection.The using of global keypoint structure is an extension of an orderless bag-of-features image representation,which is utilized by the proposed matching technique for computation efficiency.Specifically,our proposed method excels in the dataset of images containing "flat objects" such as CD covers,books,newspaper.The efficiency and accuracy of our proposed method has been tested on a database of nature pictures with flat objects and other kind of objects.The result shows our method works well in both occasions.