“…Where į is a constant that specify the relationship between two thresholds and T is a segmentation threshold that is calculated by (11). Experimentally, it is observed that with ߜ א ሾͳǤͷǡ ʹǤͷሿ good results can be obtained.…”
Section: Segmentation Thresholdmentioning
confidence: 82%
“…But this method is quite complicated and requiring a higher hardware, not suitable for real-time processing. In addition to approaches mentioned above, there are other methods used in moving objects detection, such as on statistical methods, genetic algorithm [9], or hybrid approaches that combine some of aforementioned methods [3,10,11]. However, because of advantages of background subtraction method, such as, higher reliability and lower complexity, the algorithm is one of the most widely used methods when the camera is fixed.…”
Based on the gray-level change characteristic between two successive video frames, gray information are broadly used for the detection of moving objects. However, the method will lose a lot of useful color information. In this paper, we propose a new approach to detect moving objects in the color space. The method utilizes the space vector difference to obtain a difference map between current video frame and background model. Then, by analyzing characteristic of the difference map histogram, an adaptive threshold is automatically calculated. The threshold can effectively separate moving objects and remove various significant noises in current video frame. The experimental results on several standard sequences demonstrate the efficiency and the high accuracy of the proposed method.
“…Where į is a constant that specify the relationship between two thresholds and T is a segmentation threshold that is calculated by (11). Experimentally, it is observed that with ߜ א ሾͳǤͷǡ ʹǤͷሿ good results can be obtained.…”
Section: Segmentation Thresholdmentioning
confidence: 82%
“…But this method is quite complicated and requiring a higher hardware, not suitable for real-time processing. In addition to approaches mentioned above, there are other methods used in moving objects detection, such as on statistical methods, genetic algorithm [9], or hybrid approaches that combine some of aforementioned methods [3,10,11]. However, because of advantages of background subtraction method, such as, higher reliability and lower complexity, the algorithm is one of the most widely used methods when the camera is fixed.…”
Based on the gray-level change characteristic between two successive video frames, gray information are broadly used for the detection of moving objects. However, the method will lose a lot of useful color information. In this paper, we propose a new approach to detect moving objects in the color space. The method utilizes the space vector difference to obtain a difference map between current video frame and background model. Then, by analyzing characteristic of the difference map histogram, an adaptive threshold is automatically calculated. The threshold can effectively separate moving objects and remove various significant noises in current video frame. The experimental results on several standard sequences demonstrate the efficiency and the high accuracy of the proposed method.
“…As it has previously been said, two different algorithms are used at this level. An "accumulative computation" approach [15], [16] has been chosen to work in the visual spectrum and will be used in the main monitored rooms, whilst human detection based on a single frame is used for infrared cameras and will be applied in rooms with special needs such as bathrooms or bedrooms. These algorithms will be described in detail in the following sections.…”
Section: Acquisition and Low Level Processingmentioning
The exponential increase of home-bound persons that live alone and are in need of continuous monitoring requires new solutions to current problems. Most of these cases present illnesses, such as motor or psychological disabilities, that deprive them of a normal living. Abnormal situations such as forgetfulness or falls are quite common and should be prevented or dealt with. This paper presents a system able to detect dangerous situations at home, such as falls, independently from existing environment conditions. The aim of the proposed system is to proactively offer support to the citizen or to warn the emergency services when needed.Multispectrum video; monitoring system; fall detection; personal assistant.
“…The segmentation phase is based on the accumulative computation approach and some infrared spectrum processing algorithms, which segment the original image, detect candidate to human blobs, and define and confirm region of interest (ROI) for segmented human [3]- [5]. The paper focuses on a novel fuzzy model which obtains fall patterns as function of geometrical, temporal and kinematic parameters of humans previously detected in video sequences [18], [11], [14].…”
Abstract. Vision-based fall detection is a challenging problem in pattern recognition. This paper introduces an approach to detect a fall as well as its type in infrared video sequences. The regions of interest of the segmented humans are examined image by image though calculating geometrical and kinematic features. The human fall pattern recognition system identifies true and false falls. The fall indicators used as well as their fuzzy model are explained in detail. The fuzzy model has been tested for a wide number of static and dynamic falls.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.