Background modeling has emerged as a popular foreground detection technique for various applicati... more Background modeling has emerged as a popular foreground detection technique for various applications in video surveillance. Background modeling methods have become increasing efficient in robustly modeling the background and hence detecting moving objects in any visual scene. Although several background subtraction and foreground detection have been proposed recently, no traditional algorithm today still seem to be able to simultaneously address all the key challenges of illumination variation, dynamic camera motion, cluttered background and occlusion. This limitation can be attributed to the lack of systematic investigation concerning the role and importance of features within background modeling and foreground detection. With the availability of a rather large set of invariant features, the challenge is in determining the best combination of features that would improve accuracy and robustness in detection. The purpose of this study is to initiate a rigorous and comprehensive survey of features used within background modeling and foreground detection. Further, this paper presents a systematic experimental and statistical analysis of techniques that provide valuable insight on the trends in background modeling and use it to draw meaningful recommendations for practitioners. In this paper, a preliminary review of the key characteristics of features based on the types and sizes is provided in addition to investigating their intrinsic spectral, spatial and temporal properties. Furthermore, improvements using statistical and fuzzy tools are examined and techniques based on multiple features are benchmarked against reliability and selection criterion. Finally, a description of the different resources available such as datasets and codes is provided.
IET Seminar on Target Tracking and Data Fusion: Algorithms and Applications, 2008
Automatic detection of objects is critical to video tracking systems. One of the simplest techniq... more Automatic detection of objects is critical to video tracking systems. One of the simplest techniques for detection is background subtraction (BS). BS refers to the process of segmenting moving regions from image sequences. The BS process involves building a model of the background and extracting regions of the foreground (moving objects). In this paper, we propose an extended cluster BS (CBS) technique based on symmetric alpha stable (SαS) distributions. The developed method functions at cluster-level as against the traditional pixel-level BS methods. An iterative self-adaptive mechanism is presented that allows automated learning of the distribution of the model parameters. The results for the CBS SαS algorithm on real video sequences show improvement compared with a CBS using a Gaussian mixture model.
IET Seminar on Target Tracking and Data Fusion: Algorithms and Applications, 2008
This paper proposes a novel particle filtering strategy by combining population Monte Carlo Marko... more This paper proposes a novel particle filtering strategy by combining population Monte Carlo Markov chain methods with sequential Monte Carlo chain particle which we call evolving population Monte Carlo Markov Chain (EP MCMC) filtering. Iterative convergence on groups of particles (populations) is obtained using a specified kernel moving particles toward more likely regions. The proposed technique introduces variety in the particles both in the sampling procedure and in the resampling step. The proposed EP MCMC filter is compared with the generic particle filter [1], with a population MCMC [2] and a sequential Monte Carlo sampler . Its effectiveness is illustrated over an example for object tracking in video sequences and over the bearing only tracking problem.
Procedings of the British Machine Vision Conference 2009, 2009
We describe a method for modelling and locating deformable objects using a combination of global ... more We describe a method for modelling and locating deformable objects using a combination of global and local shape models. An object is represented as a set of patches together with a geometric model of their relative positions. The geometry is modelled with a global pose and linear shape model, together with a Markov Random Field (MRF) model of local displacements from the global model. Matching to a new image involves an alternating scheme in which an MRF inference technique selects the best candidates for each point, which are then used to update the parameters of the global pose and shape model. A cascade of increasingly complex models is used to achieve robust matching to new images. We explore the effect of model parameters on system performance and show that the proposed method achieves better accuracy than other widely used methods on standard datasets.
Detecting people or other articulated objects and localizing their body parts is a challenging co... more Detecting people or other articulated objects and localizing their body parts is a challenging computer vision problem as their movement is unpredictable under circumstances of partial and full occlusions. In this paper, a framework for human body parts tracking in video sequences using a self-adaptive cluster background subtraction (CBS) scheme is proposed based on a Gaussian mixture model (GMM) and foreground matching with rectangular pictorial structures. The efficiency of the designed human body parts tracking framework is illustrated over various real-world video sequences.
IEEE Transactions on Circuits and Systems for Video Technology, 2000
Background subtraction (BS) is an efficient technique for detecting moving objects in video seque... more Background subtraction (BS) is an efficient technique for detecting moving objects in video sequences. A simple BS process involves building a model of the background and extracting regions of the foreground (moving objects) with the assumptions that the camera remains stationary and there exist no movements in the background. These assumptions restrict the applicability of BS methods to real-time object detection in video. In this paper, we propose an extended cluster BS technique with a mixture of symmetric alpha stable (SαS) distributions. An on-line self-adaptive mechanism is presented that allows automated estimation of the model parameters using the log moment method. Results over real video sequences from indoor and outdoor environments, with data from static and moving video cameras are presented. The SαS mixture model is shown to improve the detection performance compared with a cluster BS method using a Gaussian mixture model and the method of Li et al. .
Image segmentation is a challenging problem in computer vision. Feature clustering based image se... more Image segmentation is a challenging problem in computer vision. Feature clustering based image segmentation schemes are extensively researched topics in recent years. Particularly, colour clustering schemes are being widely applied for motion detection and tracking applications. In this paper we present a novel colour clustering methodology based on vector quantisation. The proposed method applies a learning vector quantisation approach with multi-scale image hierarchy to colour clustering using the hue, saturation, value (HSV) colour space model in order to obtain robust colour image segmentation. Results from experiments are presented, including a comparative analysis with the c-means algorithm.
Background modeling has emerged as a popular foreground detection technique for various applicati... more Background modeling has emerged as a popular foreground detection technique for various applications in video surveillance. Background modeling methods have become increasing efficient in robustly modeling the background and hence detecting moving objects in any visual scene. Although several background subtraction and foreground detection have been proposed recently, no traditional algorithm today still seem to be able to simultaneously address all the key challenges of illumination variation, dynamic camera motion, cluttered background and occlusion. This limitation can be attributed to the lack of systematic investigation concerning the role and importance of features within background modeling and foreground detection. With the availability of a rather large set of invariant features, the challenge is in determining the best combination of features that would improve accuracy and robustness in detection. The purpose of this study is to initiate a rigorous and comprehensive survey of features used within background modeling and foreground detection. Further, this paper presents a systematic experimental and statistical analysis of techniques that provide valuable insight on the trends in background modeling and use it to draw meaningful recommendations for practitioners. In this paper, a preliminary review of the key characteristics of features based on the types and sizes is provided in addition to investigating their intrinsic spectral, spatial and temporal properties. Furthermore, improvements using statistical and fuzzy tools are examined and techniques based on multiple features are benchmarked against reliability and selection criterion. Finally, a description of the different resources available such as datasets and codes is provided.
IET Seminar on Target Tracking and Data Fusion: Algorithms and Applications, 2008
Automatic detection of objects is critical to video tracking systems. One of the simplest techniq... more Automatic detection of objects is critical to video tracking systems. One of the simplest techniques for detection is background subtraction (BS). BS refers to the process of segmenting moving regions from image sequences. The BS process involves building a model of the background and extracting regions of the foreground (moving objects). In this paper, we propose an extended cluster BS (CBS) technique based on symmetric alpha stable (SαS) distributions. The developed method functions at cluster-level as against the traditional pixel-level BS methods. An iterative self-adaptive mechanism is presented that allows automated learning of the distribution of the model parameters. The results for the CBS SαS algorithm on real video sequences show improvement compared with a CBS using a Gaussian mixture model.
IET Seminar on Target Tracking and Data Fusion: Algorithms and Applications, 2008
This paper proposes a novel particle filtering strategy by combining population Monte Carlo Marko... more This paper proposes a novel particle filtering strategy by combining population Monte Carlo Markov chain methods with sequential Monte Carlo chain particle which we call evolving population Monte Carlo Markov Chain (EP MCMC) filtering. Iterative convergence on groups of particles (populations) is obtained using a specified kernel moving particles toward more likely regions. The proposed technique introduces variety in the particles both in the sampling procedure and in the resampling step. The proposed EP MCMC filter is compared with the generic particle filter [1], with a population MCMC [2] and a sequential Monte Carlo sampler . Its effectiveness is illustrated over an example for object tracking in video sequences and over the bearing only tracking problem.
Procedings of the British Machine Vision Conference 2009, 2009
We describe a method for modelling and locating deformable objects using a combination of global ... more We describe a method for modelling and locating deformable objects using a combination of global and local shape models. An object is represented as a set of patches together with a geometric model of their relative positions. The geometry is modelled with a global pose and linear shape model, together with a Markov Random Field (MRF) model of local displacements from the global model. Matching to a new image involves an alternating scheme in which an MRF inference technique selects the best candidates for each point, which are then used to update the parameters of the global pose and shape model. A cascade of increasingly complex models is used to achieve robust matching to new images. We explore the effect of model parameters on system performance and show that the proposed method achieves better accuracy than other widely used methods on standard datasets.
Detecting people or other articulated objects and localizing their body parts is a challenging co... more Detecting people or other articulated objects and localizing their body parts is a challenging computer vision problem as their movement is unpredictable under circumstances of partial and full occlusions. In this paper, a framework for human body parts tracking in video sequences using a self-adaptive cluster background subtraction (CBS) scheme is proposed based on a Gaussian mixture model (GMM) and foreground matching with rectangular pictorial structures. The efficiency of the designed human body parts tracking framework is illustrated over various real-world video sequences.
IEEE Transactions on Circuits and Systems for Video Technology, 2000
Background subtraction (BS) is an efficient technique for detecting moving objects in video seque... more Background subtraction (BS) is an efficient technique for detecting moving objects in video sequences. A simple BS process involves building a model of the background and extracting regions of the foreground (moving objects) with the assumptions that the camera remains stationary and there exist no movements in the background. These assumptions restrict the applicability of BS methods to real-time object detection in video. In this paper, we propose an extended cluster BS technique with a mixture of symmetric alpha stable (SαS) distributions. An on-line self-adaptive mechanism is presented that allows automated estimation of the model parameters using the log moment method. Results over real video sequences from indoor and outdoor environments, with data from static and moving video cameras are presented. The SαS mixture model is shown to improve the detection performance compared with a cluster BS method using a Gaussian mixture model and the method of Li et al. .
Image segmentation is a challenging problem in computer vision. Feature clustering based image se... more Image segmentation is a challenging problem in computer vision. Feature clustering based image segmentation schemes are extensively researched topics in recent years. Particularly, colour clustering schemes are being widely applied for motion detection and tracking applications. In this paper we present a novel colour clustering methodology based on vector quantisation. The proposed method applies a learning vector quantisation approach with multi-scale image hierarchy to colour clustering using the hue, saturation, value (HSV) colour space model in order to obtain robust colour image segmentation. Results from experiments are presented, including a comparative analysis with the c-means algorithm.
Uploads
Papers by H. Bhaskar
variation, dynamic camera motion, cluttered background and occlusion. This limitation can be attributed to the lack of systematic investigation concerning the role and importance of features within background modeling and foreground detection. With the availability of a rather large set of invariant features, the challenge is in determining the best combination of features that would improve accuracy and robustness in detection. The purpose of this study is to initiate a rigorous and comprehensive survey of features used within background modeling and foreground detection. Further, this paper presents a systematic experimental and statistical analysis of techniques that provide valuable insight on the trends in background modeling and use it to draw
meaningful recommendations for practitioners. In this paper, a preliminary review of the key characteristics of features based on the types and sizes is provided in addition to investigating their intrinsic spectral, spatial and temporal properties. Furthermore,
improvements using statistical and fuzzy tools are examined and techniques based on multiple features are benchmarked against reliability and selection criterion. Finally, a description of the different resources available such as datasets and codes is provided.
variation, dynamic camera motion, cluttered background and occlusion. This limitation can be attributed to the lack of systematic investigation concerning the role and importance of features within background modeling and foreground detection. With the availability of a rather large set of invariant features, the challenge is in determining the best combination of features that would improve accuracy and robustness in detection. The purpose of this study is to initiate a rigorous and comprehensive survey of features used within background modeling and foreground detection. Further, this paper presents a systematic experimental and statistical analysis of techniques that provide valuable insight on the trends in background modeling and use it to draw
meaningful recommendations for practitioners. In this paper, a preliminary review of the key characteristics of features based on the types and sizes is provided in addition to investigating their intrinsic spectral, spatial and temporal properties. Furthermore,
improvements using statistical and fuzzy tools are examined and techniques based on multiple features are benchmarked against reliability and selection criterion. Finally, a description of the different resources available such as datasets and codes is provided.