Search

Visual surveillance in dynamic scenes, especially for humans and vehicles, is one of the current challenging research topics in computer vision. It is a key technology to fight against terrorism, crime, public safety and for efficient management of traffic. The work involves designing of efficient visual surveillance system in complex environments. In video surveillance, detection of moving objects from a video is important for object classification, target tracking, activity recognition, and behavior understanding. Detection of moving objects in video streams is the first relevant step of information and background subtraction is a very popular approach for foreground segmentation. In this thesis, we have simulated different background subtraction methods to overcome the problem of illumination variation, background clutter, shadows, and camouflage. Object classification is done using silhouette template based classification to categorize objects into human, group of human and vehicle. Detecting and tracking of human body parts is important in understanding human activities. We have proposed two methods to overcome the problem of object tracking in varying illumination condition and background clutter. For target tracking of interested object in the consecutive video frames, we have used normalized correlation coefficient (NCC). NCC is robust to varying illumination condition. Template is updated on every frame to minimize the template drift problem and it also tries to cope with short-lived occlusion and background clutter. In order to extend the surveillance area and overcome occlusion, fusion of data from multiple cameras is employed in our project. We have tracked objects across multiple cameras with non-overlapping FOVs based on object appearances. A brightness transfer function (BTF) is determined from the cumulative histograms of the images. Matching of the object is done, with the help of Bhattacharya distance.

Recent developments in the field of computer vision and the easy availability of low-cost digital cameras have spurred demands for video surveillance systems. These advancements have helped manufacturers to market surveillance cameras as a consumer electronic product for both personal and public use. Surveillance cameras have a wide range of applications such as security, anomaly detection, traffic control, congestion analysis, target tracking, and daycare/ nanny monitoring. Background subtraction (BS) is a fundamental step for moving object detection in various video surveillance applications. It detects a moving object by comparing every incoming frame with the up-to-date (learned) statistical background model. Based on the deviation from the background model, it classifies pixels into foreground or background pixels. Dynamic environments such as swaying trees, ripples in water, fast and gradual changes in illumination, relocation of background objects, initialization with moving objects, and crowded scenes make background modelling a challenging task. Moreover, problems like shadows, camera jitters, and noise make it even more difficult. Therefore, it is important to develop efficient BS algorithms that can address these challenges and offer effective performance in real-time scenarios. In this thesis, robust BS techniques are developed to handle dynamic background conditions. Initially, algorithms relating to background modelling are proposed. Here, new features which are robust to dynamic backgrounds are developed using Gabor filter and the concept of difference domain. In the later part of the thesis, new foreground detection algorithms are formulated using Wronskian change detection model (WM). A novel fuzzy colour difference histogram (FCDH) based BS algorithm has been proposed by employing fuzzy c-means (FCM) clustering and colour difference histogram (CDH). This is done by measuring the colour difference between a pixel and its neighbourhood. The use of CD

Recent developments in the field of computer vision and the easy availability of low-cost digital cameras have spurred demands for video surveillance systems. These advancements have helped manufacturers to market surveillance cameras as a consumer electronic product for both personal and public use. Surveillance cameras have a wide range of applications such as security, anomaly detection, traffic control, congestion analysis, target tracking, and daycare/ nanny monitoring. Background subtraction (BS) is a fundamental step for moving object detection in various video surveillance applications. It detects a moving object by comparing every incoming frame with the up-to-date (learned) statistical background model. Based on the deviation from the background model, it classifies pixels into foreground or background pixels. Dynamic environments such as swaying trees, ripples in water, fast and gradual changes in illumination, relocation of background objects, initialization with moving objects, and crowded scenes make background modelling a challenging task. Moreover, problems like shadows, camera jitters, and noise make it even more difficult. Therefore, it is important to develop efficient BS algorithms that can address these challenges and offer effective performance in real-time scenarios. In this thesis, robust BS techniques are developed to handle dynamic background conditions. Initially, algorithms relating to background modelling are proposed. Here, new features which are robust to dynamic backgrounds are developed using Gabor filter and the concept of difference domain. In the later part of the thesis, new foreground detection algorithms are formulated using Wronskian change detection model (WM). A novel fuzzy colour difference histogram (FCDH) based BS algorithm has been proposed by employing fuzzy c-means (FCM) clustering and colour difference histogram (CDH). This is done by measuring the colour difference between a pixel and its neighbourhood. The use of CD

Visual surveillance in dynamic scenes, especially for humans and vehicles, is one of the current challenging research topics in computer vision. It is a key technology to fight against terrorism, crime, public safety and for efficient management of traffic. The work involves designing of efficient visual surveillance system in complex environments. In video surveillance, detection of moving objects from a video is important for object classification, target tracking, activity recognition, and behavior understanding. Detection of moving objects in video streams is the first relevant step of information and background subtraction is a very popular approach for foreground segmentation. In this thesis, we have simulated different background subtraction methods to overcome the problem of illumination variation, background clutter, shadows, and camouflage. Object classification is done using silhouette template based classification to categorize objects into human, group of human and vehicle. Detecting and tracking of human body parts is important in understanding human activities. We have proposed two methods to overcome the problem of object tracking in varying illumination condition and background clutter. For target tracking of interested object in the consecutive video frames, we have used normalized correlation coefficient (NCC). NCC is robust to varying illumination condition. Template is updated on every frame to minimize the template drift problem and it also tries to cope with short-lived occlusion and background clutter. In order to extend the surveillance area and overcome occlusion, fusion of data from multiple cameras is employed in our project. We have tracked objects across multiple cameras with non-overlapping FOVs based on object appearances. A brightness transfer function (BTF) is determined from the cumulative histograms of the images. Matching of the object is done, with the help of Bhattacharya distance.

Recent developments in the field of computer vision and the easy availability of low-cost digital cameras have spurred demands for video surveillance systems. These advancements have helped manufacturers to market surveillance cameras as a consumer electronic product for both personal and public use. Surveillance cameras have a wide range of applications such as security, anomaly detection, traffic control, congestion analysis, target tracking, and daycare/ nanny monitoring. Background subtraction (BS) is a fundamental step for moving object detection in various video surveillance applications. It detects a moving object by comparing every incoming frame with the up-to-date (learned) statistical background model. Based on the deviation from the background model, it classifies pixels into foreground or background pixels. Dynamic environments such as swaying trees, ripples in water, fast and gradual changes in illumination, relocation of background objects, initialization with moving objects, and crowded scenes make background modelling a challenging task. Moreover, problems like shadows, camera jitters, and noise make it even more difficult. Therefore, it is important to develop efficient BS algorithms that can address these challenges and offer effective performance in real-time scenarios. In this thesis, robust BS techniques are developed to handle dynamic background conditions. Initially, algorithms relating to background modelling are proposed. Here, new features which are robust to dynamic backgrounds are developed using Gabor filter and the concept of difference domain. In the later part of the thesis, new foreground detection algorithms are formulated using Wronskian change detection model (WM). A novel fuzzy colour difference histogram (FCDH) based BS algorithm has been proposed by employing fuzzy c-means (FCM) clustering and colour difference histogram (CDH). This is done by measuring the colour difference between a pixel and its neighbourhood. The use of CD

Visual surveillance in dynamic scenes, especially for humans and vehicles, is one of the current challenging research topics in computer vision. It is a key technology to fight against terrorism, crime, public safety and for efficient management of traffic. The work involves designing of efficient visual surveillance system in complex environments. In video surveillance, detection of moving objects from a video is important for object classification, target tracking, activity recognition, and behavior understanding. Detection of moving objects in video streams is the first relevant step of information and background subtraction is a very popular approach for foreground segmentation. In this thesis, we have simulated different background subtraction methods to overcome the problem of illumination variation, background clutter, shadows, and camouflage. Object classification is done using silhouette template based classification to categorize objects into human, group of human and vehicle. Detecting and tracking of human body parts is important in understanding human activities. We have proposed two methods to overcome the problem of object tracking in varying illumination condition and background clutter. For target tracking of interested object in the consecutive video frames, we have used normalized correlation coefficient (NCC). NCC is robust to varying illumination condition. Template is updated on every frame to minimize the template drift problem and it also tries to cope with short-lived occlusion and background clutter. In order to extend the surveillance area and overcome occlusion, fusion of data from multiple cameras is employed in our project. We have tracked objects across multiple cameras with non-overlapping FOVs based on object appearances. A brightness transfer function (BTF) is determined from the cumulative histograms of the images. Matching of the object is done, with the help of Bhattacharya distance.

Visual surveillance in dynamic scenes, especially for humans and vehicles, is one of the current challenging research topics in computer vision. It is a key technology to fight against terrorism, crime, public safety and for efficient management of traffic. The work involves designing of efficient visual surveillance system in complex environments. In video surveillance, detection of moving objects from a video is important for object classification, target tracking, activity recognition, and behavior understanding. Detection of moving objects in video streams is the first relevant step of information and background subtraction is a very popular approach for foreground segmentation. In this thesis, we have simulated different background subtraction methods to overcome the problem of illumination variation, background clutter, shadows, and camouflage. Object classification is done using silhouette template based classification to categorize objects into human, group of human and vehicle. Detecting and tracking of human body parts is important in understanding human activities. We have proposed two methods to overcome the problem of object tracking in varying illumination condition and background clutter. For target tracking of interested object in the consecutive video frames, we have used normalized correlation coefficient (NCC). NCC is robust to varying illumination condition. Template is updated on every frame to minimize the template drift problem and it also tries to cope with short-lived occlusion and background clutter. In order to extend the surveillance area and overcome occlusion, fusion of data from multiple cameras is employed in our project. We have tracked objects across multiple cameras with non-overlapping FOVs based on object appearances. A brightness transfer function (BTF) is determined from the cumulative histograms of the images. Matching of the object is done, with the help of Bhattacharya distance.