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.
A novel strategy of simultaneously tracking and segmentation is proposed for human respiratory rate estimation from thermal infrared, which can be applicable to contact-free polygraphy, airport health screening and patient monitoring system. In this framework, by carefully selecting the adaptive observation model for the tracking template and taking the intensity variation pattern of breathing into...
Two main problems for front projection systems when a user appears between a screen and a projector are 1) shadows being cast on a screen and 2) the user being illuminated due to undesirable strong projection light. To solve these problems, it is necessary to know which projectors are occluded by a user and cast a shadow. We propose a method that suppresses occluder light from a single image based...
Top-down class-specific knowledge is crucial for accurate image segmentation, as low-level color and texture cues alone are insufficient to identify true object boundaries. However, existing methods such as conditional random field models (CRFs) generally impose the class-specific knowledge only at the “node” level, evaluating class membership probabilities at the (super)pixels that define the random...
Natural human-robot interaction requires leveraging viewing direction information in order to recognize, respond to, and even emulate human behavior. Knowledge of the eye gaze and point of regard gives us insight into what the subject is interested in and/or who the subject is addressing. In this paper, we present a novel eye gaze estimation approach for point-of-regard (PoG) tracking. To allow for...
CAMShift is a well-established and fundamental algorithm for kernel-based visual object tracking. While it performs well with objects that have a simple and constant appearance, it is not robust in more complex cases. As it solely relies on back projected probabilities it can fail in cases when the object's appearance changes (e.g., due to object or camera movement, or due to lighting changes), when...
This paper introduces a new segmentation-based approach for disparity optimization in stereo vision. The main contribution is a significant enhancement of the matching quality at occlusions and textureless areas by segmenting either the left color image or the calculated texture image. The local cost calculation is done with a Census-based correlation method and is compared with standard sum of absolute...
In this paper, we describe a real-time vision-based tracking system to help students who are blind or visually impaired (SBVI) to follow instructional discourse that employs graphical illustrations. The vision system employs a color model based tracking for both the instructor's pointing behavior and the SBVI's reading behavior, and maps the pointing positions into the same coordinates. Our Haptic...
We consider the task of automatic detection and recognition of traffic signs in video. We show that successful off-the-shelf detection (Viola-Jones) and classification (SVM) systems yield unsatisfactory results. Our main concern are high false positive detection rates which occur due to sparseness of the traffic signs in videos. We address the problem by enforcing spatio-temporal consistency of the...
We present a simple yet elegant feature, RelCom, and a boosted selection method to achieve a very low complexity object detector. We generate combinations of low-level feature coefficients and apply relational operators such as margin based similarity rule over each possible pair of these combinations to construct a proposition space. From this space we define combinatorial functions of Boolean operators...
The application of digital technologies to culture history preservation and interpretation is a rapidly growing field that has captured the imagination of many. In this work, we explore the application of image classification systems for use in the reconstruction of archaeologically excavated 18th and 19th-century ceramic fragments. In specific, we investigate the classification of thin-shell ceramics...
Recent advances in electronics and sensor design have enabled the development of a hyperspectral video camera that can capture hyperspectral datacubes at near video rates. The sensor offers the potential for novel and robust methods for surveillance by combining methods from computer vision and hyperspectral image analysis. Here, we focus on the problem of tracking objects through challenging conditions,...
We present a real-time multi-sensor architecture for video-based pedestrian detection used within a road side unit for intersection assistance. The entire system is implemented on available PC hardware, combining a frame grabber board with embedded FPGA and a graphics card into a powerful processing network. Giving classification performance top priority, we use HOG descriptors with a Gaussian kernel...
Scene classification is used to categorize images into different classes, such as urban, mountain, beach, or indoor. This paper presents work on scene classification of television shows and feature films. These types of media bring unique challenges that are not present in photographs, as many shots are close-ups in which few characteristics of the scene are visible. In our work, the video is first...
Real-time stereo vision systems have many applications - from autonomous navigation for vehicles through surveillance to materials handling. Accurate scene interpretation depends on an ability to process high resolution images in real-time, but, although the calculations for stereo matching are basically simple, a practical system needs to evaluate at least 109 disparities every second - beyond the...
Recent studies have shown that 3D imaging provides some unique advantages over traditional 2D imaging for minimal invasive surgery. However, most existing endoscopes still use single-lens cameras, and the use of dual-lens 3D imaging techniques is still limited. This paper proposes an approach to enabling 3D imaging from a single-lens endoscope by automatically synthesizing stereoscopic views from...
We estimate and track articulated human poses in sequences from a single view, real-time range sensor. We use a data driven MCMC approach to find an optimal pose based on a likelihood that compares synthesized depth images to the observed depth image. To speed up convergence of this search, we make use of bottom up detectors that generate candidate head, hand and forearm locations. Our Markov chain...
We present a novel viewpoint which approaches the structural correspondence across an image stack in the 3D space as solving a contour grouping problem. Finding 3D cellular tubes becomes finding closed contours. We derive grouping cues between cells in adjacent slices based on their ability to relate in the 3D space. Those that form a long 3D tube in the space become the most salient contour, while...
Multiple camera views of a scene are utilized to detect and reconstruct object surfaces in three dimensions. Special attention is paid to the reconstruction of occluded objects which are only partially visible. Input images can be obtained from either an array of cameras or a single moving camera. The formulation is based on a capture and display technique developed in the optics community. Various...
This paper presents a new method for improving region segmentation in sequences of images when temporal and spatial prior context is available. The proposed technique uses elementary classifiers on infra-red, polarimetic and video data to obtain a coarse segmentation per-pixel. Contextual information is exploited in a Bayesian formulation to smooth the segmentation between frames. This is a general...
Among the top-performing stereo algorithms on the Middlebury Stereo Database, Semi-Global Matching (SGM) is commonly regarded as the most efficient algorithm. Consequently, real-time implementations of the algorithm for graphics hardware (GPU) and reconfigurable hardware (FPGA) exist. However, the computation time on general purpose PCs is still more than a second. In this paper, a real-time SGM implementation...
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.