Brendon J. Woodford

Rule insertion and rule extraction from evolving fuzzy neural networks: algorithms and applications for building adaptive, intelligent expert systems

Discusses the concept of intelligent expert systems and suggests tools for building an adaptable, in an online or in an off-line mode, rule base during the system operation in a changing environment. It applies evolving fuzzy neural networks (EFuNNs) as associative memories for the purpose of dynamic storing and modifying a rule base. Algorithms for rule extraction and rule insertion from EFuNNs are explained and applied to a case study using gas furnace data and the iris data set.

Video background modeling: recent approaches, issues and our proposed techniques

Effective and efficient background subtraction is important to a number of computer vision tasks. We introduce several new techniques to address key challenges for background modeling using a Gaussian mixture model (GMM) for moving objects detection in a video acquired by a static camera. The novel features of our proposed model are that it automatically learns dynamics of a scene and adapts its parameters accordingly, suppresses ghosts in the foreground mask using a SURF features matching algorithm, and introduces a new spatio-temporal filter to further refine the foreground detection results. Detection of abrupt illumination changes in the scene is dealt with by a model shifting-based scheme to reuse already learned models and spatio-temporal history of foreground blobs is used to detect and handle paused objects. The proposed model is rigorously tested and compared with several previous models and has shown significant performance improvements.

A Self-adaptive CodeBook (SACB) model for real-time background subtraction

Effective and efficient background subtraction is important to a number of computer vision tasks. In this paper, we introduce a new background model that integrates several new techniques to address key challenges for background modeling for moving object detection in videos. The novel features of our proposed Self-adaptive CodeBook (SACB) background model are: a more effective color model using YCbCr color space, a statistical parameter estimation method, and a new algorithm for adding new background codewords into the permanent model and deleting noisy codewords from the models. Also, a new block-based approach is introduced to exploit the local spatial information. The proposed model is rigorously tested and has shown significant performance improvements over several previous models. This paper presents a Self-adaptive CodeBook background model for moving object segmentation in a video.Several new techniques are introduced to enhance the performance of standard CodeBook model.The proposed model gives better processing speed than the standard CodeBook model.New color model and the automatic parameter estimation mechanism help to achieve better accuracy than the standard CodeBook model.The proposed model gives a real-time performance and a good balance between segmentation accuracy and processing efficiency.

Ensembles of EFuNNs: an architecture for a multimodule classifier

This paper introduces an extension to the existing theory of the evolving fuzzy neural network (EFuNN) for it to be a multi-module classifier as well. We call this proposed architecture multi-EFuNN. The incorporation of the evolving clustering method is used to partition the input space of the dataset and also determine how many EFuNNs are to be used to classify it. The main advantages of this multi-module classifier is in the areas of online learning and recall of data where there are a growing number of classes with more data coming. Preliminary results conducted using this architecture are compared to the existing single EFuNN classifier and reported.

Illumination invariant background model using mixture of gaussians and SURF features

The Mixture of Gaussians (MoG) is a frequently used method for foreground-background separation. In this paper, we propose an on-line learning framework that allows the MoG algorithm to quickly adapt its localized parameters. Our main contributions are: local parameter adaptations, a feedback based updating method for stopped objects, and hierarchical SURF features matching based ghosts and local illumination suppression method. The proposed model is rigorously tested and compared with several previous models on BMC data set and has shown significant performance improvements.

Localized adaptive learning of Mixture of Gaussians models for background extraction

The Mixture of Gaussians (MoG) background subtraction model is one of the most popular methods for segmenting moving objects in videos. However, to achieve satisfactory background subtraction results, its parameters need to be hand-tuned specifically for each scenario. This becomes a major obstacle for this model to be employed in real-time applications. This paper proposes a self-adaptive method for tuning of the parameters of Mixture of Gaussians (MoG) background model based on the local intensity changes. To cope with different motion patterns in different regions of a video frames, we have introduced a local parameters for each pixel in the frame. The robustness of the proposed method is tested on a variety of complex data-sets. It can be seen from the result that, despite its simplicity, the proposed model has achieved significant improvements compared to the standard model.

Enhancing the mixture of Gaussians background model with local matching and local adaptive learning

The Mixture of Gaussians (MoG) is a frequently used method for foreground-background separation. Although it is quite capable of handling gradual illumination changes and multi-model background, it cannot cope with dynamic changes such as the presence of paused objects, shadows, and sudden illumination changes. Furthermore, it is a parametric model and in general, its parameter tuning for different scenes remains a manual effort. In this paper, we propose an online learning framework that tackles these issues. Our main contributions are: local adaptive parameter learning, a feedback based updating method for stopped objects, hierarchical SURF features matching based ghosts suppression, and a new sudden illumination detection and handling technique. The proposed model is rigorously tested and compared with several previous models and has shown significant performance improvements.

Enhanced Codebook Model for Real-Time Background Subtraction

The CodeBook is one of the popular real-time background models for moving object detection in a video. However, for some of the complex scenes, it does not achieve satisfactory results due to the lack of an automatic parameters estimation mechanism. In this paper, we present an improved CodeBook model, which is robust in sudden illumination changes and quasi-periodic motions. The major contributions of the paper are a robust statistical parameter estimation method, a controlled adaptation procedure, a simple, but effective technique to suppress shadows and a novel block based approach to utilize the local spatial information. The proposed model was tested on numerous complex scenes and results shows a significant performance improvement over standard model.

Online Weighted Clustering for Real-time Abnormal Event Detection in Video Surveillance

Detecting abnormal events in video surveillance is a challenging problem due to the large scale, stream fashion video data as well as the real-time constraint. In this paper, we present an online, adaptive, and real-time framework to address this problem. The spatial locations in a frame is partitioned into grids, in each grid the proposed Adaptive Multi-scale Histogram Optical Flow (AMHOF) features are extracted and modelled by an Online Weighted Clustering (OWC) algorithm. The AMHOFs which cannot be fit to a cluster with large weight are regarded as abnormal events. The OWC algorithm is simple to implement and computational efficient. In addition, we improve the detection performance by a Multiple Target Tracking (MTT) algorithm. Experimental results demonstrate our approach outperforms the state-of-the-art approaches in pixel-level rate of detection at a processing speed of 30 FPS.

Anomaly detection in crowd scenes via online adaptive one-class support vector machines

We propose a novel, online adaptive one-class support vector machines algorithm for anomaly detection in crowd scenes. Integrating incremental and decremental one-class support vector machines with a sliding buffer offers an efficient and effective scheme, which not only updates the model in an online fashion with low computational cost, but also discards obsolete patterns. Our method provides a unified framework to detect both global and local anomalies. Extensive experiments have been carried out on two benchmark datasets and the comparison to the state-of-the-art methods validates the advantages of our approach.