Proceedings. IEEE Conference on Advanced Video and Signal Based Surveillance, 2005., 2005
We present an integrated pixel segmentation and region tracking algorithm, designed for indoor en... more We present an integrated pixel segmentation and region tracking algorithm, designed for indoor environments. Vi- sual monitoring systems often use frame differencing tech- niques to independently classify each image pixel as either foreground or background. Typically, this level of process- ing does not take account of the global image structure, resulting in frequent misclassification. We use an adap- tive Gaussian
2008 IEEE Workshop on Motion and video Computing, 2008
We present a novel method for detecting unusual modes of behavior in video surveillance data, sui... more We present a novel method for detecting unusual modes of behavior in video surveillance data, suitable for supporting home-based care of elderly patients. Our approach is based on detecting unusual patterns of inactivity. We first learn a spatial map of normal inactivity for an observed scene, expressed as a two-dimensional mixture of Gaussians. The map components are used to construct
2011 18th IEEE International Conference on Image Processing, 2011
ABSTRACT Seabird populations are considered an important and accessible indicator of the health o... more ABSTRACT Seabird populations are considered an important and accessible indicator of the health of marine environments: variations have been linked with climate change and pollution [1]. However, manual monitoring of large populations is labour-intensive, and requires significant investment of time and effort. In this paper, we propose a novel detection system for monitoring a specific population of Common Guillemots on Skomer Island, West Wales (UK). We incorporate two types of features, Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP), to capture the edge/local shape information and the texture information of nesting seabirds. Optimal features are selected from a large HOG-LBP feature pool by boosting techniques, to calculate a compact representation suitable for the SVM classifier. A comparative study of two kinds of detectors, i.e., whole-body detector, head-beak detector, and their fusion is presented. When the proposed method is applied to the seabird detection, consistent and promising results are achieved.
2008 International Conference on Field-Programmable Technology, 2008
This paper introduces a real-time connected component labelling algorithm designed for Field Prog... more This paper introduces a real-time connected component labelling algorithm designed for Field Programmable Gate Array (FPGA) implementation. The algorithm run-length encodes the image, and performs connected component analysis on this representation. The ...
IEEE Transactions on Circuits and Systems for Video Technology, 2000
Abstract This paper introduces a tri-state logic self-organizing map (bSOM) designed and implemen... more Abstract This paper introduces a tri-state logic self-organizing map (bSOM) designed and implemented on a field programmable gate array (FPGA) chip. The bSOM takes binary inputs and maintains tri-state weights. A novel training rule is presented. The bSOM is well suited to FPGA implementation, trains quicker than the original self-organizing map (SOM), and can be used in clustering and classification problems with binary input data. Two practical applications, character recognition and appearance-based object identification, ...
Proceedings. IEEE Conference on Advanced Video and Signal Based Surveillance, 2005., 2005
We present an integrated pixel segmentation and region tracking algorithm, designed for indoor en... more We present an integrated pixel segmentation and region tracking algorithm, designed for indoor environments. Vi- sual monitoring systems often use frame differencing tech- niques to independently classify each image pixel as either foreground or background. Typically, this level of process- ing does not take account of the global image structure, resulting in frequent misclassification. We use an adap- tive Gaussian
2008 IEEE Workshop on Motion and video Computing, 2008
We present a novel method for detecting unusual modes of behavior in video surveillance data, sui... more We present a novel method for detecting unusual modes of behavior in video surveillance data, suitable for supporting home-based care of elderly patients. Our approach is based on detecting unusual patterns of inactivity. We first learn a spatial map of normal inactivity for an observed scene, expressed as a two-dimensional mixture of Gaussians. The map components are used to construct
2011 18th IEEE International Conference on Image Processing, 2011
ABSTRACT Seabird populations are considered an important and accessible indicator of the health o... more ABSTRACT Seabird populations are considered an important and accessible indicator of the health of marine environments: variations have been linked with climate change and pollution [1]. However, manual monitoring of large populations is labour-intensive, and requires significant investment of time and effort. In this paper, we propose a novel detection system for monitoring a specific population of Common Guillemots on Skomer Island, West Wales (UK). We incorporate two types of features, Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP), to capture the edge/local shape information and the texture information of nesting seabirds. Optimal features are selected from a large HOG-LBP feature pool by boosting techniques, to calculate a compact representation suitable for the SVM classifier. A comparative study of two kinds of detectors, i.e., whole-body detector, head-beak detector, and their fusion is presented. When the proposed method is applied to the seabird detection, consistent and promising results are achieved.
2008 International Conference on Field-Programmable Technology, 2008
This paper introduces a real-time connected component labelling algorithm designed for Field Prog... more This paper introduces a real-time connected component labelling algorithm designed for Field Programmable Gate Array (FPGA) implementation. The algorithm run-length encodes the image, and performs connected component analysis on this representation. The ...
IEEE Transactions on Circuits and Systems for Video Technology, 2000
Abstract This paper introduces a tri-state logic self-organizing map (bSOM) designed and implemen... more Abstract This paper introduces a tri-state logic self-organizing map (bSOM) designed and implemented on a field programmable gate array (FPGA) chip. The bSOM takes binary inputs and maintains tri-state weights. A novel training rule is presented. The bSOM is well suited to FPGA implementation, trains quicker than the original self-organizing map (SOM), and can be used in clustering and classification problems with binary input data. Two practical applications, character recognition and appearance-based object identification, ...
Uploads
Papers by Patrick Dickinson