Robust 3D SLAM with a stereo camera based on an edge-point ICP algorithm

Tomono, Masahiro

doi:10.1109/robot.2009.5152529

Cited by 68 publications

(46 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

supporting

confidence: 82%

“…In comparison to photometric registration techniques, our ICP technique has the conceptual advantage of requiring neither isotropic enlargement of the employed semi-dense regions, nor pyramidal subsampling. The work is in line with Feldmar et al [2], Tomono [9], and Klein and Murray [4], which already attempt curve or edge registration in 2D using ICP.Based on a hypothesized relative pose, the basic idea consists of warping a reference curve into the tracked image based on a prior 3D model or depth (in our case semi-dense) inside a reference frame. From a mathematical point of view, our idea may be formulated as follows.…”

supporting

confidence: 59%

See 1 more Smart Citation

SDICP: Semi-Dense Tracking based on Iterative Closest Points

Kneip

Zhou

2015

Procedings of the British Machine Vision Conference 2015

View full text Add to dashboard Cite

The paper addresses the problem of camera tracking, which denotes the continuous image-based computation of a camera's position and orientation with respect to a reference frame. The method aims at regular cameras, which means that 3D-3D registration methods applicable to RGB-D cameras are not an option. The tracked frame contains only 2D information, thus requiring a solution to the absolute pose or 2D-3D registration problem.While traditional solutions to camera tracking [3] rely on sparse feature correspondences, the community has recently seen a number of direct photometric registration methods such as Newcombe et al. [8] and Engel et al. [1]. [1] is conceptually similar to [8], however gains computational efficiency by reducing the computation from dense to semi-dense regions that correspond to a thresholded edge-map of the image.Photometric methods have the more general advantage of compensating for appearance variations caused by perspective view-point changes, whereas classical sparse methods often rely on static feature descriptors only (providing at most rotation and scale invariant properties [5,6]). However, photometric registration techniques inherently suffer from the disability to overcome large disparities, where large sometimes means even just a couple of pixels [7]. Many photometric registration techniques therefore depend on pyramidal subsampling schemes in order to alleviate this problem.The goal of the present paper is a novel 2D-3D registration paradigm for semi-dense depth maps that relies on the Iterative Closest Point (ICP) technique, and thus a reintroduction of geometric error minimization as a valid alternative for real-time monocular camera tracking in the case of semi-dense features. An example semi-dense depth map is indicated in Figure 1. In comparison to photometric registration techniques, our ICP technique has the conceptual advantage of requiring neither isotropic enlargement of the employed semi-dense regions, nor pyramidal subsampling. The work is in line with Feldmar et al. [2], Tomono [9], and Klein and Murray [4], which already attempt curve or edge registration in 2D using ICP.Based on a hypothesized relative pose, the basic idea consists of warping a reference curve into the tracked image based on a prior 3D model or depth (in our case semi-dense) inside a reference frame. From a mathematical point of view, our idea may be formulated as follows. Let)} denote the semi-dense depth map, where P = {p i } is the set of pixel locations that defines the semi-dense region in the reference frame F k , d i the inverse depth of a pixel, and π(p i ) = f i is a known function that transforms points in the image plane into unit direction vectors located on the unit sphere around the camera center. The warped semi-dense region is easily obtained byi − t }, where t and R denote the seeked position and orientation of the current frame. The final objective results in) is a function that returns the pixel from P F k+1 that is closest to ounder the Euclidean distance metric. We propose ite...

show abstract

supporting

confidence: 82%

supporting

confidence: 59%

SDICP: Semi-Dense Tracking based on Iterative Closest Points

Kneip

Zhou

2015

Procedings of the British Machine Vision Conference 2015

View full text Add to dashboard Cite

show abstract

“…The early vision of stereo-type algorithm by Moravec was implemented with a monocular camera on a mobile platform in order to estimate vehicle's ego-motion with 3D information [21]. Recently, edge feature-based tracking algorithm was used with binocular camera through ICP algorithm [22], which fits texture-less or noisy environment. Park, et al developed a binocular camera-based object tracking framework for mobile AR [23].…”

Section: Cameramentioning

confidence: 99%

Application of Augmented Reality and Robotic Technology in Broadcasting: A Survey

Yan

2017

Robotics

View full text Add to dashboard Cite

Abstract:As an innovation technique, Augmented Reality (AR) has been gradually deployed in the broadcast, videography and cinematography industries. Virtual graphics generated by AR are dynamic and overlap on the surface of the environment so that the original appearance can be greatly enhanced in comparison with traditional broadcasting. In addition, AR enables broadcasters to interact with augmented virtual 3D models on a broadcasting scene in order to enhance the performance of broadcasting. Recently, advanced robotic technologies have been deployed in a camera shooting system to create a robotic cameraman so that the performance of AR broadcasting could be further improved, which is highlighted in the paper.

show abstract

“…In many instances, it has been demonstrated that visual sensing is a feasible alternative to previous approaches based on laser range data. Existing models acquired by means of visual sensing consider different features, such as sparse set of point features [11] or line segments [28], [3] acquired by monocular [6] or binocular systems [23]. While maps comprised of dense or sparse cloud of points are often suitable for accurate localization, they are often insufficient for more advanced planning and reasoning tasks.…”

Section: A Related Workmentioning

confidence: 99%

Acquiring semantics induced topology in urban environments

Singh

Košecká

2012

2012 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-Methods for acquisition and maintenance of an environment model are central to a broad class of mobility and navigation problems. Towards this end, various metric, topological or hybrid models have been proposed. Due to recent advances in sensing and recognition, acquisition of semantic models of the environments have gained increased interest in the community. In this work, we will demonstrate a capability of using weak semantic models of the environment to induce different topological models, capturing the spatial semantics of the environment at different levels. In the first stage of the model acquisition, we propose to compute semantic layout of the street scenes imagery by recognizing and segmenting buildings, roads, sky, cars and trees. Given such semantic layout, we propose an informative feature characterizing the layout and train a classifier to recognize street intersections in challenging urban inner city scenes. We also show how the evidence of different semantic concepts can induce useful topological representation of the environment, which can aid navigation and localization tasks. To demonstrate the approach, we carry out experiments on a challenging dataset of omnidirectional inner city street views and report the performance of both semantic segmentation and intersection classification. I. INTRODUCTIONThe problem of robot localization and mapping constitutes one of the basic capabilities of autonomous robotics systems and has attracted a lot of attention in the community. There have been a large variety of maps proposed ranging from metric, topological and hybrid maps. Lot of progress has been made in the Simultaneous Localization and Mapping (SLAM) approach for acquisition of metric models with a single reference frame. The topological models represent environments as graphs and differ in how the nodes and connections between them are defined [17], [4], [16]. An example of an on-line topological model acquisition by means of place recognition was tackled in [5] and was instrumental in solving the loop detection problem.Despite the progress in acquiring different types of representations of the environment, the connections between different types of models were explored in more limited settings. Examples of hybrid metric and topological maps have been introduced in indoors environments, where topology was induced by Voronoi tessellation of the occupancy map or polygonal model of the environment [1], [4]. Numerous approaches to topological mapping although providing the discrete representation of the environment, typically focus on the representation which would maximize the performance of loop detection [5] or place recognition tasks [18] without considerations of how well the topology captures the spatial layout of the environment.

show abstract

Robust 3D SLAM with a stereo camera based on an edge-point ICP algorithm

Cited by 68 publications

References 14 publications

SDICP: Semi-Dense Tracking based on Iterative Closest Points

SDICP: Semi-Dense Tracking based on Iterative Closest Points

Application of Augmented Reality and Robotic Technology in Broadcasting: A Survey

Acquiring semantics induced topology in urban environments

Contact Info

Product

Resources

About