The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Object tracking is a paramount task in video surveillance systems. Although many efforts have been accomplished on object tracking during the last years more work is still needed in order to generate more robust systems. A new fuzzy method for object tracking is presented in this paper. The proposed method is composed of two Sugeno type systems with weighted average memory output functions. One of...
We present a method for improving human segmentation results in calibrated, multi-view environments using features derived from both pixel (image) and voxel (volume) space. The main focus of this work is to develop a low-cost, vision-based system for passive activity monitoring of older adults in the home, to capture early signs of illness and functional decline and allow seniors to live independently...
Detecting humans in an image sequence is one of the most difficult problems in object recognition. It is necessary to define a robust descriptor which can extract human features from images, to improve the detecting performance. Histograms of Oriented Gradients(HOG) descriptor significantly outperforms compared with the others on human detection. The descriptor is known as a robustness descriptor...
Blind people navigate safely through a familiar room based on strong expectations about the location of objects. If something has been moved, added or removed, it can present a difficulty and potentially a danger. Human eyes are one of the most important body parts that help humans to understand and interact with their surroundings. Most learning and recognition of objects around us is accomplished...
This paper presents a wireless non-contact sensor that enables detection, localization, and monitoring of people along with their specific features such as gait and cardiopulmonary activities. These types of sensors can be embedded in the environment and networked with the existing wireless infrastructure to create an intelligent and responsive ambient where the health of children, patients, and the...
This paper presents a real-time system for hand gesture classification. The hands are detected using both the depth by the stereo camera and the skin color. The reconstructed trajectory of hands is classified into one of the gesture references.
In this paper, an object based bi-directional counting system is proposed, which comprises of an advanced object detection and tracking algorithm to count the people flow in the monitoring scene. The result of which shows that the approach can provide about 90% accuracy for bi-directional people counting with an angle of 45° to the scene.
In this paper, we solve the problem of human detection in crowded scenes using a Bayesian 3D model based method. Human candidates are first nominated by a head detector and a foot detector, then optimization is performed to find the best configuration of the candidates and their corresponding shape models. The solution is obtained by decomposing the mutually related candidates into un-occluded ones...
Human figure identification is always a challenging move in field of pattern recognition. This paper presents a complete algorithm to find a single object (human body) and identify the object as human being. The algorithm starts the segmentation process with basic frame difference method and use morphological operators, edge detection, feature point generation and finally spline interpolation to find...
A military multitasking environment was simulated to examine the effects of unreliable automation on the performance of robotics operators. The main task was to manage a team of four ground robots with the assistance of RoboLeader, an intelligent agent capable of coordinating the robots and changing their routes based upon developments in the mission environment. RoboLeader's recommendations were...
The prompt search and rescue of lifesaving target is very important in the case that a marine casualty occurs. To detect the small target in the wide views over the sea, we have proposed a machine vision system to aid search and rescue on the sea, which combines remote sensing, radar, infrared with visual light technology. One of the detection methods in this system, which is based on visual attention...
Human detection and tracking in high density crowds is an unsolved problem. Standard preprocessing techniques such as background modeling fail when most of the scene is in motion. Because of high levels of occlusion, dense features, and shadows, object detectors tend to produce large numbers of false detections. We introduce a new method based on 3D head plane estimation that reduces these false detections...
In many surveillance systems, an operator will have to make a decision on whether a target is present based on one or more sensor readings. For the latter, when an operator has at his disposal two or more sensor outputs his decision on a whether a target is present or not is likely to be influenced by those sensor readings. For instance, when both sensors report, the operator is more likely than not...
Nowadays, almost all the countries are facing threats from terrorists and intruders from their border areas, challenging the internal security of the country in those areas. So many civilian and military applications require locating an intruder in a secured area. Target tracking, data processing and analysis play a major role in this type of applications. The proposed system is to develop a centralized...
In automated video analysis, the performance of the detection stage is integral to the performance of subsequent stages such as tracking and behavior recognition. In this paper, we propose a method to boost the speed and accuracy of Wu and Nevatia's edgelet based detectors, by incorporating motion information to isolate active regions before actually performing detection. Experimental results show...
On roads, drivers can detect traffic sign extraordinarily fast and accurately; however, the computer vision system does not easily imitate this natural ability although using a lot of image processing techniques. This weakness can be tackled by a bottom-up visual saliency method based on traffic-sign colours which occupy certain ranges of RGB values. These values can be used to modulate the bottom-up...
Advances in technology continue to make both hardware and software affordable and accessible; we have seen a rapid growth in computer vision and image processing applications. One area of interest in vision and image processing is automated identification of objects in real-time or recorded video streams and analysis of these identified objects. An important topic of research in this context is identification...
Aiming at the human face detection in color images under complex background, a face detection method based on the combination of skin color model in YCgCr and AdaBoost algorithm is proposed in this article. Firstly, it uses skin color model in YCgCr color space to detect candidate face region in the tested image, and then further verifies the face region by the Adaboost algorithm with the added new...
For applications concerning target detection and tracking, an image fusion quality metric that considers only the information preservation from the source images is not enough. A new quality metric for image fusion that combines the structural information preservation from the source images and the influence of the fusion process on the detection probability is proposed. Thus, the results of the proposed...
An obstacle system based on visual selective feature and stereo vision is stated in this paper. By extracting feature vectors with color, intensity and direction, the corresponding saliency map is constructed. Then, obstacle area is figured out through threshold segmentation to the saliency map, and 3-D information of the obstacles is computed by using stereo vision. Finally, obstacle information...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.