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.
Salient object detection using RGB-D data is an emerging field in computer vision. Salient regions are often characterized by an unusual surface orientation profile with respect to the surroundings. To capture such profile, we introduce the histogram of surface orientation (HOSO) feature to measure surface orientation distribution contrast for RGB-D saliency. We propose a new unified model that integrates...
In many 3-D perception applications, ground segmentation is a necessary preprocessing phase together with point cloud cleaning and outlier removal. This letter presents a method for ground segmentation in large-scale point clouds of industrial environments acquired using a terrestrial laser scanner (TLS). TLSs provide high-precision, dense 3-D measurements, and therefore, such instruments are becoming...
In this paper we propose a fast method for detecting the ground plane in 3D scenes for an arbitrary roll angle rotation of a stereo vision camera. The method is based on the analysis of the disparity map and its “V-disparity” representation. First, the roll angle of the camera is identified from the disparity map. Then, the image is rotated to a zero-roll angle position and the ground plane is detected...
We presents a method to generate and track AR space using plane geometry information in AR environment. Our method calculates the major plane correspondences between frames and defines the relation. Using this relationship, we can create the virtual space that is unaffected by object position changes in images and can be used for AR tracking.
Human body analysis raises special interest because it enables a wide range of interactive applications. In this paper we present a gesture estimator that discriminates body poses in depth images. A novel collaborative method is proposed to learn 3D features of the human body and, later, to estimate specific gestures. The collaborative estimation framework is inspired by decision forests, where each...
Many current LIDAR systems generate huge amounts of 3D points, therefore efficient and fast data processing is essential. In urban areas surfaces are often planar and plane patches are an efficient representation for localization purposes. Our approach thus stores the points in a voxel grid and afterwards extracts the dominant plane using RANSACbased plane fitting. Classical RANSAC-based plane extraction...
This paper presents a parallax adjustment method for 3D video to improve the visual comfort of the 3D video. Firstly, matching algorithm based on SIFT (Scale Invariant Feature Transform) is used to obtain the accurate horizontal parallax and vertical parallax of the feature points between the left-view and the right-view of the 3D video. Then the range of horizontal parallax with comfort viewing is...
In this work we present the Probabilistic Primitive Refinement (PPR) algorithm, an iterative method for accurately determining the inliers of an estimated primitive (such as planes and spheres) parametrization in an unorganized, noisy point cloud. The measurement noise of the points belonging to the proposed primitive surface are modelled using a Gaussian distribution and the measurements of extraneous...
This work proposes a novel method for 3D direction of arrival (DOA) estimation based on the sound intensity vector estimation, via the encoding of the signals of a spherical microphone array from the space domain to the spherical harmonic domain. The sound intensity vector is estimated on detected single source zones (SSZs), where one source is dominant. A smoothed 2D histogram of these estimates...
Recent years have shown increases in virtual 3D perception and applications, many of these applications require 3D model reconstruction from high quality LIDAR scans. High quality 3D models may be acquired from a collection of overlapping LIDAR scans which need to be registered or aligned to a common coordinate system. This paper investigates the use of a novel implementation of trilateration for...
In this paper, we present an object-centric, fixed-dimensional 3D shape representation for robust matching of partially observed object shapes, which is an important component for object categorization from 3D data. A main problem when working with RGB-D data from stereo, Kinect, or laser sensors is that the 3D information is typically quite noisy. For that reason, we accumulate shape information...
Basic and compound pose invariant geometric features are explored to conduct pre-alignment, down sampling, and outlier removal to improve the speed and accuracy of Iterative Closest Point (ICP) registration on dense 3D laser scanning data for metallic part modeling. Rectification of planar surfaces, which are segmented from point normals and matched on similarity of clustered viewpoint feature histogram...
To be relevant in copyright protection scenarios, watermarking systems need to provide appropriate levels of security. This paper investigates the security of a popular 3D watermarking method that alters the histogram of distances between the vertices of a surface mesh and its center of mass using a quadratic programming formulation.We study two conventional security mechanisms, namely (i) obfuscating...
Currently, in 3D point cloud data field, different methods based on multi-value characteristics, which are utilized to measure the similarity between different point cloud data, are developed. These features are more dependent on low dimensional normal vector and curvature. In this paper, feature histogram of each point of the point cloud is calculated in high dimensional space. Through global feature...
Obstacle detection is a fundamental task for Advanced Driver Assistance Systems (ADAS) and Self-driving cars. Several commercial systems like Adaptive Cruise Controls and Collision Warning Systems depend on them to notify the driver about a risky situation. Several approaches have been presented in the literature in the last years. However, most of them are limited to specific scenarios and restricted...
In this paper we present an approach to automatic object annotation. We are given a set of positive images which all contain a certain object and our goal is to automatically determine the position of said object in each image. Our approach first applies a heuristic to identify initial bounding boxes based on color and gradient features. This heuristic is based on image and feature statistics. Then,...
Holoscopic 3D Imaging is a technique for producing natural 3D objects that exist in our world without the need for wearing specific eyewear. An Auto-Feature-Edge (AFE) descript-tor algorithm is used to simplify the edge detection of objects that uses a Multi-Quantize Adaptive Local Histogram Analysis (MQALHA) algorithm. This paper presents an exploitation of available depth estimation and Feature...
The prediction of the position of a given volume sample in a full body atlas, also known as a volume localization, is a part of an initial stage of image retrieval in most of the dedicated CAD systems. In this paper we present two methods for volume localization, namely histogram matching and classifier regression. Since the histogram matching method ignores the spatial orientation, it is used when...
A novel method for predicting the ratings of video content on the basis of a viewer's behavior in a typical home environment is proposed. Using an input signal provided by a Kinect sensor, it identifies the presence of a viewer by extracting key point trajectories in video sequences of that viewer. It then estimates whether the viewer is gazing at the video content or not on the basis of the viewer's...
At the core of every object recognition system lies the development and integration of distinct feature descriptors to create object representations robust against varying perspectives or lightning conditions. Recent work has primarily focused on the development of distinct point features. While these features achieve impressive recognition results, point features fail to capture the shape and appearance...
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.