Omnidirectional visual SLAM under severe occlusions

Gamallo, C.; Mucientes, Manuel; Regueiro, Carlos V.

doi:10.1016/j.robot.2014.11.008

Cited by 19 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, a new view initialization mechanism was presented for the map building process within the problem of EKF-based visual SLAM [12]. Gamallo et al [13] proposed a SLAM algorithm (OV-FastSLAM) for omniVision cameras operating with severe occlusions. Chapoulie et al [14] presented an approach which was applied to SLAM that addressed qualitative loop closure detection using a spherical view.…”

Section: Omnidirectional-vision Slammentioning

confidence: 99%

Spherical-Model-Based SLAM on Full-View Images for Indoor Environments

Wang

2018

Applied Sciences

View full text Add to dashboard Cite

As we know, SLAM (Simultaneous Localization and Mapping) relies on surroundings. A full-view image provides more benefits to SLAM than a limited-view image. In this paper, we present a spherical-model-based SLAM on full-view images for indoor environments. Unlike traditional limited-view images, the full-view image has its own specific imaging principle (which is nonlinear), and is accompanied by distortions. Thus, specific techniques are needed for processing a full-view image. In the proposed method, we first use a spherical model to express the full-view image. Then, the algorithms are implemented based on the spherical model, including feature points extraction, feature points matching, 2D-3D connection, and projection and back-projection of scene points. Thanks to the full field of view, the experiments show that the proposed method effectively handles sparse-feature or partially non-feature environments, and also achieves high accuracy in localization and mapping. An experiment is conducted to prove that the accuracy is affected by the view field.

show abstract

Section: Omnidirectional-vision Slammentioning

confidence: 99%

Spherical-Model-Based SLAM on Full-View Images for Indoor Environments

Wang

2018

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…A common approach has been to use on-board sensors that capture features of the world from the point of view of the robot. The most typical features are: (a) distances to objects provided by sonars [9] or 2D [1] and 3D laser range finders [10], (b) images provided by monocular [17] or omnidirectional cameras [11], (c) combinations of both provided by RGBD [16] or stereo cameras [18]. Usually, algorithms using these sensors are able to achieve sub-metre accuracy, but suffer from common problems that impact their robustness.…”

Section: Related Workmentioning

confidence: 99%

“…4(c)). Additionally, dynamic and crowded environments are still an active area of research in Visual SLAM techniques [19,11]. For instance, in crowded environments Visual SLAM algorithms might not be able to extract significant visual cues due to the presence of people close to the camera, or even worse, they might extract visual cues from humans and fail [8].…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, the robot must determine its pose (position and orientation) relative to the map that we have created. Most localisation systems rely on the information provided by one sensor, such as sonar sensors [9], 2D lasers [1], 3D lasers [10], cameras mounted on the robot [11], etc. Nevertheless, there is not such a thing as a perfect sensor: each sensor has its limitations, and no sensor is applicable to all situations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Particle filter robot localisation through robust fusion of laser, WiFi, compass, and a network of external cameras

et al. 2016

Self Cite

View full text Add to dashboard Cite

“…This problem is one of the most important in mobile robotics, because most robotic tasks require knowledge of the robot pose [ 1 ]. Sonar sensors [ 2 ], cameras [ 3 ] and, above all, 2D laser range finders [ 1 ] mounted on the robot have been three popular choices to locate a robot indoors. Another alternative is to infer the robot position based on the characteristics of the signal received from wireless transmitters placed in the environment (wireless localization).…”

Section: Introductionmentioning

confidence: 99%

Mobile Robot Positioning with 433-MHz Wireless Motes with Varying Transmission Powers and a Particle Filter

Canedo-Rodriguez

Rodríguez

Alvarez-Santos³

et al. 2015

Sensors

View full text Add to dashboard Cite

In wireless positioning systems, the transmitter's power is usually fixed. In this paper, we explore the use of varying transmission powers to increase the performance of a wireless localization system. To this extent, we have designed a robot positioning system based on wireless motes. Our motes use an inexpensive, low-power sub-1-GHz system-on-chip (CC1110) working in the 433-MHz ISM band. Our localization algorithm is based on a particle filter and infers the robot position by: (1) comparing the power received with the expected one; and (2) integrating the robot displacement. We demonstrate that the use of transmitters that vary their transmission power over time improves the performance of the wireless positioning system significantly, with respect to a system that uses fixed power transmitters. This opens the door for applications where the robot can localize itself actively by requesting the transmitters to change their power in real time.

show abstract

Omnidirectional visual SLAM under severe occlusions

Cited by 19 publications

References 27 publications

Spherical-Model-Based SLAM on Full-View Images for Indoor Environments

Spherical-Model-Based SLAM on Full-View Images for Indoor Environments

Particle filter robot localisation through robust fusion of laser, WiFi, compass, and a network of external cameras

Mobile Robot Positioning with 433-MHz Wireless Motes with Varying Transmission Powers and a Particle Filter

Contact Info

Product

Resources

About