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.
Urban environment constitutes a challenging area for pedestrian navigation. However, with the recent increase of pedestrians owning devices (e.g. smartphones), complementary data provided by integrated low cost sensors (camera, Inertial and Magnetic Measurement Unit and GNSS receiver) may be used in a coupling process to accurately estimate the pose (i.e. 3D position and 3D orientation) of a handheld...
ORB-SLAM is a feature-based simultaneous localization and mapping (SLAM) system. It has achieved good results in tracking, mapping and loop closing. However, the map created by ORB-SLAM with the monocular camera can not get the real scale. This paper presents an improving ORB SLAM system that helps to alleviate this issue by defining a baseline initialization procedure. We take two relative poses...
We investigate the pose estimation of a semi-unknown object for stereo-vision-based navigation of a mobile manipulator. A new computationally fast vision algorithm is developed to extract the object's pose at a high rate from the captured scenes. Moreover, we present a method to deal with range dependent noise characteristics of the stereo vision to fulfill requirements for mobile manipulation tasks...
Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D correspondences between keypoints in the current image and points in the scene in order to estimate the...
Understanding the camera wearers activity is central to egocentric vision, yet one key facet of that activity is inherently invisible to the camera—the wearers body pose. Prior work focuses on estimating the pose of hands and arms when they come into view, but this 1) gives an incomplete view of the full body posture, and 2) prevents any pose estimate at all in many frames, since the hands...
Localizing a query image against a 3D model at large scale is a hard problem, since 2D-3D matches become more and more ambiguous as the model size increases. This creates a need for pose estimation strategies that can handle very low inlier ratios. In this paper, we draw new insights on the geometric information available from the 2D-3D matching process. As modern descriptors are not invariant against...
We explore 3D human pose estimation from a single RGB image. While many approaches try to directly predict 3D pose from image measurements, we explore a simple architecture that reasons through intermediate 2D pose predictions. Our approach is based on two key observations (1) Deep neural nets have revolutionized 2D pose estimation, producing accurate 2D predictions even for poses with self-occlusions...
We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences. In common with recent work [10, 14, 16], we use an end-to-end learning approach with view synthesis as the supervisory signal. In contrast to the previous work, our method is completely unsupervised, requiring only monocular video sequences for training. Our...
Given the recent advances in depth prediction from Convolutional Neural Networks (CNNs), this paper investigates how predicted depth maps from a deep neural network can be deployed for the goal of accurate and dense monocular reconstruction. We propose a method where CNN-predicted dense depth maps are naturally fused together with depth measurements obtained from direct monocular SLAM, based on a...
This paper addresses the task of estimating the 6D-pose of a known 3D object from a single RGB-D image. Most modern approaches solve this task in three steps: i) compute local features, ii) generate a pool of pose-hypotheses, iii) select and refine a pose from the pool. This work focuses on the second step. While all existing approaches generate the hypotheses pool via local reasoning, e.g. RANSAC...
For solving camera pose problem, a novel accurate and fast pose estimation algorithm based on Lie group representation is proposed. Firstly, object function based on total space error of all feature points is built. Secondly, object function is linearized based on Lie group representation. The Jacobian matrix of camera pose is deduced and pose parameters are updated. Finally, the computation efficiency...
The registration of an observed point set to a known model to estimate its 3D pose is a common task for the autonomous manipulation of objects. Especially in industrial environments, robotic systems need to accurately estimate the pose of objects in order to successfully perform picking, placing or assembly tasks. However, the characteristics of industrial objects often cause difficulties for classical...
In this paper, a visual navigation system is implemented to control a UAV in unknown and GPS-denied environments, using a monocular camera. The navigation system is based on the Semi-direct Visual Odometry algorithm, whose absolute scale is estimated by fusing visual output with altitude measurements. The main contribution of the paper is the recovery mechanisms to reinitialize the visual map when...
Feature point matching for camera localization suffers from scalability problems. Even when feature descriptors associated with 3D scene points are locally unique, as coverage grows, similar or repeated features become increasingly common. As a result, the standard distance ratio-test used to identify reliable image feature points is overly restrictive and rejects many good candidate matches. We propose...
This paper presents the design of a new landing pad and its recognition algorithm to achieve relative pose estimation with high sampling rate. The landing pad consists of multiple markers, which is a kind of simplified Apriltags. Small markers are overlaid on the large marker, make it possible to have a wide detection range in a limited pad area. Utilization of monocular gimbaled camera expand the...
Human pose analysis has been known to be an effective means to evaluate athlete's performance. Marker-less 3D human pose estimation is one of the most practical methods to acquire human pose but lacks sufficient accuracy required to achieve precise performance analysis for sports. In this paper, we propose a human pose estimation algorithm that utilizes multiple types of random forests to enhance...
This article considers the establishment of a dynamic visual sensor from monocular cameras to enable a reconfigurable environmental perception. The cameras are mounted on Micro Aerial Vehicles (MAV) which are coordinated by a Model Predictive Control (MPC) scheme to retain overlapping field of views and form a global sensor with varying baseline. The specific merits of the proposed scheme are: a)...
In this paper, we propose a wearable camera-based pose estimation of a user's head and shoulders. The proposed system is mounted on a user's chest and the camera looks upward to observe a user's head and shoulders region. The proposed method is based on histograms of orientated gradient (HoG) features and support vector regression (SVR). This paper shows the preliminary experimental results that demonstrate...
In this paper, we propose the design of artificial underwater retro-reflective markers and their recognition algorithm. Retro-reflective materials, which are used for some portion of the marker, are used to overcome the limitation of underwater visibility. Owing to the distortion in the image captured by an underwater camera, the recognition algorithm consists of image preprocessing and 6-DOF pose...
This paper proposes a method of vision based pose estimation of randomly piled objects. It is necessary to estimate precise rotation angle of picking objects. However, it is non-trivial task because an object placed in every position makes distorted image far from right position image. We propose a precise pose estimation method of bin picking objects. The landmark feature of a picking object is extracted...
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.