Learning to classify by ongoing feature selection

Existing classification algorithms use a set of training examples to select classification features, which are then used for all future applications of the classifier. A major problem with this approach is the selection of a training set: a small set will result in reduced performance, and a large set will require extensive training. In addition, class appearance may change over time requiring an adaptive classification system. In this paper, we propose a solution to these basic problems by developing an on-line feature selection method, which continuously modifies and improves the features used for classification based on the examples provided so far. The method is used for learning a new class, and to continuously improve classification performance as new data becomes available. In ongoing learning, examples are continuously presented to the system, and new features arise from these examples. The method continuously measures the value of the selected features using mutual information, and uses these values to efficiently update the set of selected features when new training information becomes available. The problem is challenging because at each stage the training process uses a small subset of the training data. Surprisingly, with sufficient training data the on-line process reaches the same performance as a scheme that has a complete access to the entire training data.     

Efficient Object Detection and Classification Approach Using HTYOLOV4 and M²RFO-CNN

Object detection and classification are the trending research topics in the field of computer vision because of their applications like visual surveillance. However, the vision-based objects detection and classification methods still suffer from detecting smaller objects and dense objects in the complex dynamic environment with high accuracy and precision. The present paper proposes a novel enhanced method to detect and classify objects using Hyperbolic Tangent based You Only Look Once V4 with a Modified Manta-Ray Foraging Optimization-based Convolution Neural Network. Initially, in the pre-processing, the video data was converted into image sequences and Polynomial Adaptive Edge was applied to preserve the Algorithm method for image resizing and noise removal. The noiseless resized image sequences contrast was enhanced using Contrast Limited Adaptive Edge Preserving Algorithm. And, with the contrast-enhanced image sequences, the Hyperbolic Tangent based You Only Look Once V4 was trained for object detection. Additionally, to detect smaller objects with high accuracy, Grasp configuration was observed for every detected object. Finally, the Modified Manta-Ray Foraging Optimization-based Convolution Neural Network method was carried out for the detection and the classification of objects. Comparative experiments were conducted on various benchmark datasets and methods that showed improved accurate detection and classification results.     

采用精选Gabor小波和SVM分类的物体识别

提出了一种基于Gabor小波和支持向量机的物体识别通用框架. 在该框架中, 特征抽取采用选取的Gabor小波在物体的最佳位置卷积实现, 而分类则通过支持向量机实现. 相比传统的基于Gabor特征的识别系统, 该方法能够同时达到准确而快速的分类目的. 本论文成功地将该框架应用于两个实际的物体识别例子: 物体/非物体分类和人脸识别. 实验结果证明了所提出的方法相对于其它方法的优越性.     

Visual classification of waste material for nuclear decommissioning

Redundant and nonoperational buildings at nuclear sites go through the process of ‘decommissioning’, involving decontamination of nuclear waste material and demolition of physical infrastructure. One challenging problem currently faced by the nuclear industry during this process is the segregation of redundant waste material into a choice of ‘post-processes’ based upon the nature and extent of its radioactivity that may pose a serious threat to the environment. Following an initial inspection, waste materials are subjected to treatment, disruption and consigned to various types of export containers. To date, the process of objects (waste) classification is performed manually. In order to automate this process, robotic platforms can be deployed that utilise robust and fast vision systems for visual classification of nuclear waste material. This paper proposes a novel solution incorporating a machine vision system for autonomous identification of waste material from decommissioned nuclear plants. Rotation and scale invariant moments are used to describe object shapes in the visual scene whereas a random forest learning algorithm performs object classification. Using nuclear waste simulants (from the nuclear plant decommissioning process), an exhaustive ‘proof-of-concept’ quantitative assessment of the proposed technique is performed, in order to test its applicability within the current problem domain.     

Robust object tracking with background-weighted local kernels

Object tracking is critical to visual surveillance, activity analysis and event/gesture recognition. The major issues to be addressed in visual tracking are illumination changes, occlusion, appearance and scale variations. In this paper, we propose a weighted fragment based approach that tackles partial occlusion. The weights are derived from the difference between the fragment and background colors. Further, a fast and yet stable model updation method is described. We also demonstrate how edge information can be merged into the mean shift framework without having to use a joint histogram. This is used for tracking objects of varying sizes. Ideas presented here are computationally simple enough to be executed in real-time and can be directly extended to a multiple object tracking system.     

Object Recognition Based on Human Saccadic Behaviour

The automated recognition of targets in complex backgrounds is a difficult problem, yet humans perform such tasks with ease. We therefore propose a recognition model based on behavioural and physiological aspects of the human visual system. Emulating saccadic behaviour, an object is first memorised as a sequence of fixations. At each fixation an artificial visual field is constructed using a multi-resolution/ orientation Gabor filterbank, edge features are extracted, and a new saccadic location is automatically selected. When a new image is scanned and a ‘familiar’ field of view encountered, the memorised saccadic sequence is executed over the new image. If the expected visual field is found around each fixation point, the memorised object is recognised. Results are presented from trials in which individual objects were first memorised and then searched for in collages of similar objects acting as distractors. In the different collages, entries of the memorised objects were subjected to various combinations of rotation, translation and noise corruption. The model successfully detected the memorised object in over 93% of the ‘object present’ trials, and correctly rejected collages in over 98% of the trials in which the object was not present in the collage. These results are compared with those obtained using a correlation-based recogniser, and the behavioural model is found to provide superior performance. Received: 15 July 1998?Received in revised form: 24 December 1998?Accepted: 9 February 1999     

Object recognition and articulated object learning by accumulative Hopfield matching

In this paper, a novel object recognition method based on attributed relational graph matching is proposed, which is called accumulative Hopfield matching. We first divide the scene graph into many sub-graphs, and a modified Hopfield network is then constructed to obtain the sub-graph isomorphism between each sub-scene graph and model graph. The final result is deduced by accumulating the solutions of all small sub-networks. Comparing to the traditional Hopfield network, the proposed system has the advantage of finding homomorphic mappings between two graphs. Furthermore, the system can be applied for articulated object recognition and visual model learning, which is considered as a difficult topic till now. The proposed method has been evaluated with real images.     

基于实时视觉分析算法的智能图像传感器系统设计

设计了一种智能交通图像传感器系统以实现对监控场景的快速移动侦测和对象识别。该系统具有有线以太网和无线GPRS双重网络接入功能,硬件由基于Au1200嵌入式处理器的网络接口端和基于BlackFin 533 DSP处理器的图像分析端组成。软件系统包括运行于Au1200处理器上的基于嵌入式Linux架构的网络收发软件和运行于BlackFin 533 DSP上的视觉分析算法。本系统引入了基于区域分割的背景模型和基于特征的对象识别算法。实验结果表明该系统能够实时高效地进行自动移动检测和对象分类识别。     

基于视觉注意机制的目标跟踪方法

提出一种基于视觉注意机制的运动目标跟踪方法。该方法借鉴人类的视觉注意机制的研究成果,建立视觉注意机制的计算模型,计算视频中各部分内容的视觉显著性。结合视觉显著性计算结果,提取视频图像中的显著性目标。利用颜色分布模型作为目标的特征表示模型,与视频中各显著目标进行特征匹配,实现目标的跟踪。在多个视频序列中进行实验,并给出相应的实验结果及分析。实验结果表明,提出的目标检测与跟踪算法是正确有效的。     

一个基于移动视觉搜索技术的博物馆导览系统

为了对游客的参观过程提供个性化导览服务,使游客可以通过手机拍照的方式获取展品的相关资讯.提出一个基于移动视觉搜索技术的博物馆导览系统.针对手机性能的差异性,提出一种改进的移动视觉搜索系统的框架,使得系统既能在服务器端对海量展品进行识别,又能在手机端对特定区域内展品实时识别;并基于这一框架实现了一个原型系统.与现有的导览系统相比,文中系统的交互方式更加人性化,提供的展品信息更丰富、全面,且无需在馆内安装任何辅助设备,能够更广泛地适用于博物馆导览.实验结果证明了该系统的可行性和实用性.     

Familiarity based unified visual attention model for fast and robust object recognition

Even though visual attention models using bottom-up saliency can speed up object recognition by predicting object locations, in the presence of multiple salient objects, saliency alone cannot discern target objects from the clutter in a scene. Using a metric named familiarity, we propose a top-down method for guiding attention towards target objects, in addition to bottom-up saliency. To demonstrate the effectiveness of familiarity, the unified visual attention model (UVAM) which combines top-down familiarity and bottom-up saliency is applied to SIFT based object recognition. The UVAM is tested on 3600 artificially generated images containing COIL-100 objects with varying amounts of clutter, and on 126 images of real scenes. The recognition times are reduced by 2.7× and 2×, respectively, with no reduction in recognition accuracy, demonstrating the effectiveness and robustness of the familiarity based UVAM.     

Object Class Recognition and Localization Using Sparse Features with Limited Receptive Fields

We investigate the role of sparsity and localized features in a biologically-inspired model of visual object classification. As in the model of Serre, Wolf, and Poggio, we first apply Gabor filters at all positions and scales; feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. We refine the approach in several biologically plausible ways. Sparsity is increased by constraining the number of feature inputs, lateral inhibition, and feature selection. We also demonstrate the value of retaining some position and scale information above the intermediate feature level. Our final model is competitive with current computer vision algorithms on several standard datasets, including the Caltech 101 object categories and the UIUC car localization task. The results further the case for biologically-motivated approaches to object classification. This paper updates and extends an earlier presentation (Mutch and Lowe 2006) of this research in CVPR 2006. J. Mutch’s research described in this paper was carried out at the University of British Columbia.     

智能视觉监控技术研究进展

新一代智能视觉监控技术的研究是一个极具挑战性的前沿课题,它旨在赋予监控系统观察分析场景内容的能力,实现监控的自动化和智能化,因而具有巨大的应用潜力。视觉监控系统的智能化分析过程由运动目标检测、分类、跟踪和视频内容分析等几个基本环节组成,其中视频内容分析又包括异常检测、人的身份识别以及视频内容理解描述等。本文在总结以上有关关键技术研究进展的基础上,进一步提出将超分辨率复原技术引入视觉监控领域,介绍了超分辨率复原的主要算法及其在智能视觉监控中的应用。     

Multi-spectral fusion for surveillance systems

Surveillance systems such as object tracking and abandoned object detection systems typically rely on a single modality of colour video for their input. These systems work well in controlled conditions but often fail when low lighting, shadowing, smoke, dust or unstable backgrounds are present, or when the objects of interest are a similar colour to the background. Thermal images are not affected by lighting changes or shadowing, and are not overtly affected by smoke, dust or unstable backgrounds. However, thermal images lack colour information which makes distinguishing between different people or objects of interest within the same scene difficult.By using modalities from both the visible and thermal infrared spectra, we are able to obtain more information from a scene and overcome the problems associated with using either modality individually. We evaluate four approaches for fusing visual and thermal images for use in a person tracking system (two early fusion methods, one mid fusion and one late fusion method), in order to determine the most appropriate method for fusing multiple modalities. We also evaluate two of these approaches for use in abandoned object detection, and propose an abandoned object detection routine that utilises multiple modalities. To aid in the tracking and fusion of the modalities we propose a modified condensation filter that can dynamically change the particle count and features used according to the needs of the system.We compare tracking and abandoned object detection performance for the proposed fusion schemes and the visual and thermal domains on their own. Testing is conducted using the OTCBVS database to evaluate object tracking, and data captured in-house to evaluate the abandoned object detection. Our results show that significant improvement can be achieved, and that a middle fusion scheme is most effective.     

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.     

Modeling multi-object interactions using “string of feature graphs”

In this paper, a novel generalized framework of activity representation and recognition based on a ‘string of feature graphs (SFG)’ model is introduced. The proposed framework represents a visual activity as a string of feature graphs, where the string elements are initially matched using a graph-based spectral technique, followed by a dynamic programming scheme for matching the complete strings. The framework is motivated by success of time sequence analysis approaches in speech recognition, but modified in order to capture the spatio-temporal properties of individual actions, the interactions between objects, and speed of activity execution. This framework can be adapted to various spatio-temporal motion features, and we show details on using STIP features and track features. Furthermore, we show how this SFG model can be embedded within a switched dynamical system (SDS) that is able to automatically choose the most efficient features for a particular video segment. This allows us to analyze a variety of activities in natural videos in a computationally efficient manner. Experimental results on the basic SFG model as well as its integration with the SDS are shown on some of the most challenging multi-object datasets available to the activity analysis community.     

A machine-vision system for iris recognition

This paper describes a prototype system for personnel verification based on automated iris recognition. The motivation for this endevour stems from the observation that the human iris provides a particularly interesting structure on which to base a technology for noninvasive biometric measurement. In particular, it is known in the biomedical community that irises are as distinct as fingerprints or patterns of retinal blood vessels. Further, since the iris is an overt body, its appearance is amenable to remote examination with the aid of a machine-vision system. The body of this paper details the design and operation of such a system. Also presented are the results of an empirical study in which the system exhibits flawless performance in the evaluation of 520 iris images.