How-Lung Eng

Regularized Common Spatial Pattern With Aggregation for EEG Classification in Small-Sample Setting

Common spatial pattern (CSP) is a popular algorithm for classifying electroencephalogram (EEG) signals in the context of brain-computer interfaces (BCIs). This paper presents a regularization and aggregation technique for CSP in a small-sample setting (SSS). Conventional CSP is based on a sample-based covariance-matrix estimation. Hence, its performance in EEG classification deteriorates if the number of training samples is small. To address this concern, a regularized CSP (R-CSP) algorithm is proposed, where the covariance-matrix estimation is regularized by two parameters to lower the estimation variance while reducing the estimation bias. To tackle the problem of regularization parameter determination, R-CSP with aggregation (R-CSP-A) is further proposed, where a number of R-CSPs are aggregated to give an ensemble-based solution. The proposed algorithm is evaluated on data set IVa of BCI Competition III against four other competing algorithms. Experiments show that R-CSP-A significantly outperforms the other methods in average classification performance in three sets of experiments across various testing scenarios, with particular superiority in SSS.

LBP-Based Edge-Texture Features for Object Recognition

This paper proposes two sets of novel edge-texture features, Discriminative Robust Local Binary Pattern (DRLBP) and Ternary Pattern (DRLTP), for object recognition. By investigating the limitations of Local Binary Pattern (LBP), Local Ternary Pattern (LTP) and Robust LBP (RLBP), DRLBP and DRLTP are proposed as new features. They solve the problem of discrimination between a bright object against a dark background and vice-versa inherent in LBP and LTP. DRLBP also resolves the problem of RLBP whereby LBP codes and their complements in the same block are mapped to the same code. Furthermore, the proposed features retain contrast information necessary for proper representation of object contours that LBP, LTP, and RLBP discard. Our proposed features are tested on seven challenging data sets: INRIA Human, Caltech Pedestrian, UIUC Car, Caltech 101, Caltech 256, Brodatz, and KTH-TIPS2-a. Results demonstrate that the proposed features outperform the compared approaches on most data sets.

Laplacian Eigenmap With Temporal Constraints for Local Abnormality Detection in Crowded Scenes

This paper addresses the problem of detecting and localizing abnormal activities in crowded scenes. A spatiotemporal Laplacian eigenmap method is proposed to extract different crowd activities from videos. This is achieved by learning the spatial and temporal variations of local motions in an embedded space. We employ representatives of different activities to construct the model which characterizes the regular behavior of a crowd. This model of regular crowd behavior allows the detection of abnormal crowd activities both in local and global contexts and the localization of regions which show abnormal behavior. Experiments on the recently published data sets show that the proposed method achieves comparable results with the state-of-the-art methods without sacrificing computational simplicity.

Human Detection by Quadratic Classification on Subspace of Extended Histogram of Gradients

This paper proposes a quadratic classification approach on the subspace of Extended Histogram of Gradients (ExHoG) for human detection. By investigating the limitations of Histogram of Gradients (HG) and Histogram of Oriented Gradients (HOG), ExHoG is proposed as a new feature for human detection. ExHoG alleviates the problem of discrimination between a dark object against a bright background and vice versa inherent in HG. It also resolves an issue of HOG whereby gradients of opposite directions in the same cell are mapped into the same histogram bin. We reduce the dimensionality of ExHoG using Asymmetric Principal Component Analysis (APCA) for improved quadratic classification. APCA also addresses the asymmetry issue in training sets of human detection where there are much fewer human samples than non-human samples. Our proposed approach is tested on three established benchmarking data sets - INRIA, Caltech, and Daimler - using a modified Minimum Mahalanobis distance classifier. Results indicate that the proposed approach outperforms current state-of-the-art human detection methods.

A particle swarm optimisation algorithm with interactive swarms for tracking multiple targets

We propose a novel particle swarm optimisation algorithm that uses a set of interactive swarms to track multiple pedestrians in a crowd. The proposed method improves the standard particle swarm optimisation algorithm with a dynamic social interaction model that enhances the interaction among swarms. In addition, we integrate constraints provided by temporal continuity and strength of person detections in the framework. This allows particle swarm optimisation to be able to track multiple moving targets in a complex scene. Experimental results demonstrate that the proposed method robustly tracks multiple targets despite the complex interactions among targets that lead to several occlusions.

Quantifying Limb Movements in Epileptic Seizures Through Color-Based Video Analysis

This paper proposes a color-based video analytic system for quantifying limb movements in epileptic seizure monitoring. The system utilizes colored pyjamas to facilitate limb segmentation and tracking. Thus, it is unobtrusive and requires no sensor/marker attached to patients body. We employ Gaussian mixture models in background/foreground modeling and detect limbs through a coarse-to-fine paradigm with graph-cut-based segmentation. Next, we estimate limb parameters with domain knowledge guidance and extract displacement and oscillation features from movement trajectories for seizure detection/analysis. We report studies on sequences captured in an epilepsy monitoring unit. Experimental evaluations show that the proposed system has achieved comparable performance to EEG-based systems in detecting motor seizures.

A Literature Review on Video Analytics of Crowded Scenes

This chapter presents a review and systematic comparison of the state of the art on crowd video analysis. The rationale of our review is justified by a recent increase in intelligent video surveillance algorithms capable of analysing automati- cally visual streams of very crowded and cluttered scenes, such as those of airport concourses, railway stations, shopping malls and the like. Since the safety and se- curity of potentially very crowded public spaces have become a priority, computer vision researchers have focused their research on intelligent solutions. The aim of this chapter is to propose a critical review of existing literature pertaining to the au- tomatic analysis of complex and crowded scenes. The literature is divided into two broad categories: the macroscopic and the microscopic modelling approach. The effort is meant to provide a reference point for all computer vision practitioners cur- rently working on crowd analysis. We discuss the merits and weaknesses of various approaches for each topic and provide a recommendation on how existing methods can be improved.

Intelligent Monitoring of Complex Environments

Many countries around the world have implemented or are in the process of implementing tighter security measures in public and private places. Such measures are becoming widespread and are applied not only at government, military, and corporate facilities, but also in civilian infrastructures. Modern surveillance system consist of different modules. A sensor layer usually consists of a network of cameras, audio arrays, physical perimeter sensors, and other types of information feeders. A surveillance layer represents the core of the intelligent system. Its role is to process all the data generated by the sensor layer.This module includes several components. A feature extraction step is responsible for reducing the enormous amount of data that the network generates. Time properties are commonly derived by keeping track of any action within the monitored environment. The module in charge of the event analysis is at the highest processing level of modern monitoring systems. Human-computer interaction is fundamental to providing relevant, timely information.

Learning video manifold for segmenting crowd events and abnormality detection

This paper addresses the problem of analyzing video events in crowded scenes. A novel manifold learning method is proposed to achieve visualization and modeling of video events in a low dimensional space. In the proposed approach, a video is considered as a trajectory of frames in a low-dimensional space. This low-dimensional representation of a video preserves the spatio-temporal property of a video as well as the characteristic of the video. Different tasks of video content analysis such as visualization, video event segmentation and abnormality detection are achieved by analyzing these video trajectories based on the Hausdorff distance similarity measure. We evaluate our proposed method on the state-of-the-art public data-sets containing different crowd events. Qualitative and quantitative results show the promising performance of the proposed method.

Extended Histogram of Gradients feature for human detection

Unsigned Histogram of Gradients (UHoG) is a popular feature used for human detection. Despite its superior performance as reported in recent literature, an inherent limitation of UHoG is that gradients of opposite directions in a cell are mapped into the same histogram bin. This is undesirable as it will produce the same UHoG feature for two different patterns. To address this problem, we propose a new feature named the Extended Histogram of Gradients (ExHoG) in this paper. It comprises two components: UHoG and a histogram of absolute bin value differences of opposite gradient directions computed from Histogram of Gradients (HoG). Our experimental results show that the proposed ExHoG consistently outperforms the standard HoG and UHoG for human detection.