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.
In this paper, for the purpose of monitoring people moving on the ground from a low-altitude aerial vehicle, we propose a method for stable image stabilization using planar information of the ground. In existing methods the homography-based method has been popularly used for image stabilization. However, in case that captured images consist of non-planar areas, the performance of the homography-based...
We consider the challenge of testing lane centering ADAS control systems using a differential global positioning system localization strategy. Rather than constructing test scenarios using lane line markers or driving test vehicles on public roads, we develop a testing framework that can be used in both simulation and on open test surfaces with no lane demarcation. The primary sensor we leverage is...
Sensor fusion is an important part of modern cyber-physical systems that observe and analyse real-world environments. Time-of-Flight depth cameras provide high frame rate low-resolution depth data that can be efficiently used in many applications related to cyber-physical systems. In this paper, we address the critical issue of upsampling and enhancing the low-quality depth data using a calibrated...
In this paper, we present a near real time approach to lane detection in highway and urban streets using images captured from monocular cameras as an input. The proposed method includes four main steps. First, the input image is transformed to a bird's eye view image by using warp perspective mapping. Second, an edge image is produced by applying a custom edge detection and morphology operation on...
Outdoor visual surveillance systems have studied object tracking in non-overlapping multiple cameras. In this paper, we present a data association method for multi-object tracking in a non-overlapping camera network. Proposed method is based on similarity function which consists of a multi-camera topology obtained from local tracking results and matching results from person re-identification. Simulation...
This paper presents the color reproduction method for dual camera system. The proposed method uses the input images acquired in different exposure conditions. The brightness of short-exposure image is restored using conventional haze removal-based low-light image enhancement method. Next, the color components of the brightness enhanced image are restored using the weight map, which is computed between...
A record of food intake contains information that is useful for health care. We propose a new method for obtaining food intake data using intra-body communication. In this system, a transmitter is attached to each dish, and signals are sent to a receiver via dishes, food, and cutlery; the human body is the medium connecting the transmitter and the receiver. A receiver can detect the moment when the...
In this paper, we propose a hardware compatible queue-based image segmentation algorithm for refining initial depth maps obtained from light field cameras. In the algorithm, an array is created to record the ranges of positions and intensities of possible segments, which make following segment merging steps much more efficient. An ASIC chip based on the proposed algorithm with a plane fitting calculator...
This study proposes a new system for learners to master double-under skill. In terms of proposing methodology, it assumes four training phases. First and second phases deal with the primitive motion training but the latter two phases do their combination. This paper focuses mainly on the third one that treats combination of primitive dyad of the former phases without a rope instrument. The prototype...
Haze is mainly occurred by atmospheric phenomena. Recently, many researchers in haze removal algorithm area are using single image. At the single image, we can't use depth information. To estimate the thickness of haze without depth information is not easy. As a result, single image haze removal method includes halo effect. In this paper, we propose halo effect suppression for single image haze removal...
We have developed a collaborative system for location-based AR that enables users to handle virtual object by simple hand gestures. Through a combination of depth sensor and motion capture system, it makes possible to calculate global coordinates of hands and recognize hand gestures without pattern images or hand mounted instruments. We believe that this system would be useful for inter-user communication...
We propose the DeepPose-based pose estimation system that is flexible with the change of bounding-box range for top-view images. Our purpose is to link person detection system and pose estimation system. We introduce Bounding-box Curriculum Learning (BCL) and Recurrent Pose Estimation (RPE). BCL is a learning technique of CNN inspired from Curriculum Learning. RPE is a recurrent process of pose estimation...
Image retargeting methods change the size of images to an arbitrary resolution while protecting visually important regions from distortion. Since retargeting methods deform contents of an image based on these importance, importance calculation methods suitable for image retargeting is needed. In this paper, we propose a framework to improve an importance map by using depth and segmentation information...
By the near-field and side-view eye camera, the eyeball in captured images is ellipse shape generally, and it is not always circular shape. In this paper, fast iris ellipse fitting based visible light gaze tracking system is studied for wearable eye tracker applications. After pre-processing, the iris contour is recognized by the two-stage binarizations, and the binaried iris contour is applied to...
In this paper, we presented a comparison between different approaches of person re-identification in camera network based on the-state-of-the-art. We studied the different descriptors of objects for identifying people and existing classifier at the re-identification step. We seek to develop video surveillance systems online in controlled areas and improve their reliability and their processing time...
In this paper, we introduce a vision-based localization algorithm that can accurately track responders during rescue operations in urban areas that are Global Navigation Satellite System (GNSS)-denied. The proposed algorithm works successfully with the rich visual features of an urban environment and obtains an average localization accuracy of 2.5 ft. In addition, we also provide a 3D representation...
This paper presents an application of LabVIEW and camera interface which is used for taking attendance in classroom. The system use a camera which is connected to PC on USB interface and attached to each and every classroom for taking snap of students presented. LabVIEW graphical programming environment is a tool for realizing the image acquisition and processing. This software has several advantages:...
Today image processing and utilizations based on RGB-D data have huge interest in various research areas. Regarding segmentation, colour correction, depth information, comprehensive description of 3-Dimension scenes in RGB-Depth data provides useful hints from another dimension to segregate substance in close colours. Here, super pixel segmentation based a new method is discussed to resolve such mixed,...
Many emerging motion-related applications, such as virtual reality, decision making, and health monitoring, demand reliability and quick response upon input changes. Motion capture has been a well-researched topic in the past decades with applications in many industries. The ability to capture motion goes hand in hand with real-time capability in a system. This paper gives an overview on real-time...
Human can quickly and effortlessly focus on a few most interesting points in an image. Different observers tend to have the same fixations towards the same scene. In order to predict observer's fixations, eye gaze information can be used to reveal human attention and interest. This paper presents a real-time eye gaze tracking system. Haar cascade classifier is used to calculate the position of eye...
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.