Combining invariant features and localization techniques for visual place classification: successful experiences in the robotVision@ImageCLEF competition

Gómez, Jesús Martínez; Picazo, Alejandro Jiménez; Gámez, José A.; Varea, Ismael García

doi:10.14198/jopha.2011.5.1.06

Cited by 4 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The similarity between images has been widely used for several robotic tasks such as object recognition [14], navigation [15] and semantic localization [16]. Regarding topological mapping, large image collections [5] are the traditional main source of information.…”

Section: Related Workmentioning

confidence: 99%

LexToMap: lexical-based topological mapping

et al. 2016

View full text Add to dashboard Cite

Any robot should be provided with a proper representation of its environment in order to perform navigation and other tasks. In addition to metrical approaches, topological mapping generates graph representations in which nodes and edges correspond to locations and transitions. In this article, we present LexToMap, a topological mapping procedure that relies on image annotations. These annotations, represented in this work by lexical labels, are obtained from pre-trained deep learning models, namely CNNs, and are used to estimate image similarities. Moreover, the lexical labels contribute to the descriptive capabilities of the topological maps. The proposal has been evaluated using the KTH-IDOL 2 dataset, which consists of image sequences acquired within an indoor environment under three different lighting conditions. The generality of the procedure as well as the descriptive capabilities of the generated maps validate the proposal.

show abstract

Section: Related Workmentioning

confidence: 99%

LexToMap: lexical-based topological mapping

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Grabbing objects requires a detailed visual inspection of the object along with its close environment in order to determine the best way to go near to the object and manipulate it. Besides, identifying objects is not only useful to interacting with them but also to solving other problems, such as place-classification (e.g., [6], [7], [8]). …”

Section: Why Incorporate a Vision System Into A Gmr?mentioning

confidence: 99%

“…This is clearly represented in the RobotVision@ImageCLEF competition [188], where participant proposals [7] have to deal with these conditions.…”

Section: Indoor Locationsmentioning

confidence: 99%

A Taxonomy of Vision Systems for Ground Mobile Robots

Gómez

Fernández-Caballero

García-Varea

et al. 2014

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This paper introduces a taxonomy of vision systems for ground mobile robots. In the last five years, a significant number of relevant papers have contributed to this subject. Firstly, a thorough review of the papers is proposed to discuss and classify both past and the most current approaches in the field. As a result, a global picture of the state of the art of the last five years is obtained. Moreover, the study of the articles is used to put forward a comprehensive taxonomy based on the most up-to-date research in ground mobile robotics. In this sense, the paper aims at being especially helpful to both budding and experienced researchers in the areas of vision systems and mobile ground robots. The taxonomy described is devised from a novel perspective, namely in order to respond to the main questions posed when designing robotic vision systems: why?, what for?, what with?, how?, and where? The answers are derived from the most relevant techniques described in the recent literature, leading in a natural way to a series of classifications that are discussed and contextualized. The article offers a global picture of the state of the art in the area and discovers some promising research lines.

show abstract

“…This procedure was successfully used in [13]. To demonstrate, key frames are images with a significant change between it and the previous accepted key frame, thus, eliminating the useless images and reducing the computation complexity without losing information.…”

Section: Preprocessingmentioning

confidence: 99%

Nested Graph Representation for Visual SLAM based on Local and Global Feature Processing

Elgayar¹,

Salem²,

Roushdy³

2013

IJCA

View full text Add to dashboard Cite

Self localization of mobile autonomous systems is fundamental step in various applications, such as assistant navigation systems for blind people or smart house appliances. This paper presents a novel framework for Vision-based Simultaneous Localization and Mapping which focuses on the class of indoor mobile robots using only a monocular camera. A method to combine local and global features mapping have been proposed in a nested graph representation, where the indoor environment is divided into locations which is then decomposed into different views. The Scale Invariant Feature Transform is used to extract and build up a global map which provide rough estimation of the robot position. Horizontal, vertical and diagonal details of the wavelet coefficients are then used to provide finer estimation of the robot position and pose. The output topological map is validated with the ground truth of the environment. Moreover, the number of decomposition levels of the wavelet transform is analysed. The results show high localization accuracy and low rate of matching time.

show abstract

Combining invariant features and localization techniques for visual place classification: successful experiences in the robotVision@ImageCLEF competition

Cited by 4 publications

References 16 publications

LexToMap: lexical-based topological mapping

LexToMap: lexical-based topological mapping

A Taxonomy of Vision Systems for Ground Mobile Robots

Nested Graph Representation for Visual SLAM based on Local and Global Feature Processing

Contact Info

Product

Resources

About