Results 1 - 10 of 143

Learning Deep Features for Scene Recognition using Places Database

by Bolei Zhou, Agata Lapedriza, Jianxiong Xiao, Antonio Torralba, Aude Oliva
"... Scene recognition is one of the hallmark tasks of computer vision, allowing defi-nition of a context for object recognition. Whereas the tremendous recent progress in object recognition tasks is due to the availability of large datasets like ImageNet and the rise of Convolutional Neural Networks (CN ..."
Abstract - Cited by 46 (4 self) - Add to MetaCart
million labeled pictures of scenes. We propose new methods to compare the density and diversity of image datasets and show that Places is as dense as other scene datasets and has more diversity. Using CNN, we learn deep features for scene recognition tasks, and establish new state-of-the-art results

Off-road Place Recognition using Fused Image Features

by Tobias Föhst, Michael Arndt, Karsten Berns, Christiano Couto Gava, Raquel Frizera Vassallo
"... This paper presents a method of image-based localization in rough off-road terrain. It assumes an underlying topological map of the environment modeling places that are relevant for navigation as nodes in a graph. Hence, localization is reduced to the coarse recognition of previously visited places. ..."
Abstract - Add to MetaCart
This paper presents a method of image-based localization in rough off-road terrain. It assumes an underlying topological map of the environment modeling places that are relevant for navigation as nodes in a graph. Hence, localization is reduced to the coarse recognition of previously visited places

How to learn an illumination robust image feature for place recognition

by Henning Lategahn, Johannes Beck, Bernd Kitt, Christoph Stiller - In IEEE Intelligent Vehicles Symposium, Gold , 2013
"... Abstract—Place recognition for loop closure detection lies at the heart of every Simultaneous Localization and Mapping (SLAM) method. Recently methods that use cameras and describe the entire image by one holistic feature vector have experienced a resurgence. Despite the success of these methods, it ..."
Abstract - Cited by 7 (2 self) - Add to MetaCart
Abstract—Place recognition for loop closure detection lies at the heart of every Simultaneous Localization and Mapping (SLAM) method. Recently methods that use cameras and describe the entire image by one holistic feature vector have experienced a resurgence. Despite the success of these methods

Graph-based multiple panorama extraction from unordered image sets”, Computational Imaging V. Edited by C.Bouman, E.Miller, I.Pollak

by Er Sibiryakov, Miroslaw Bober - Proceedings of the SPIE, Volume 6498 , 2007
"... This paper presents a multi-image registration method, which aims at recognizing and extracting multiple panoramas from an unordered set of images without user input. A method for panorama recognition introduced by Lowe and Brown [1] is based on extraction of a full set of scale invariant image feat ..."
Abstract - Cited by 2 (1 self) - Add to MetaCart
This paper presents a multi-image registration method, which aims at recognizing and extracting multiple panoramas from an unordered set of images without user input. A method for panorama recognition introduced by Lowe and Brown [1] is based on extraction of a full set of scale invariant image

Object Recognition in Image Sequences with Cellular Neural Networks

by Mariofanna Milanova, Ulrich Büker, Heinz Nixdorf
"... In this paper, the application of CNN associative memories for 3D object recognition is presented. The main idea is to analyse the optical flow in an image sequence of an object. Several features of the optical flow between two succeeding images are calculated and merged to a time series of features ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
In this paper, the application of CNN associative memories for 3D object recognition is presented. The main idea is to analyse the optical flow in an image sequence of an object. Several features of the optical flow between two succeeding images are calculated and merged to a time series

Graph Similarity Features for HMM-Based Handwriting Recognition in Historical Documents

by Andreas Fischer, Kaspar Riesen, Horst Bunke
"... Abstract—Automatic transcription of historical documents is vital for the creation of digital libraries. In this paper we propose graph similarity features as a novel descriptor for handwriting recognition in historical documents based on Hidden Markov Models. Using a structural graph-based represen ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
Abstract—Automatic transcription of historical documents is vital for the creation of digital libraries. In this paper we propose graph similarity features as a novel descriptor for handwriting recognition in historical documents based on Hidden Markov Models. Using a structural graph-based

Location Graphs for Visual Place Recognition

by Elena Stumm, Christopher Mei, Simon Lacroix, Margarita Chli
"... Abstract — With the growing demand for deployment of robots in real scenarios, robustness in the perception capabilities for navigation lies at the forefront of research interest, as this forms the backbone of robotic autonomy. Existing place recognition approaches traditionally follow the feature-b ..."
Abstract - Add to MetaCart
Abstract — With the growing demand for deployment of robots in real scenarios, robustness in the perception capabilities for navigation lies at the forefront of research interest, as this forms the backbone of robotic autonomy. Existing place recognition approaches traditionally follow the feature-based

Towards Robust Place Recognition for Robot Localization

by M. M. Ullah, A. Pronobis, B. Caputo, J. Luo, P. Jensfelt, H. I. Christensen
"... Abstract — Localization and context interpretation are two key competences for mobile robot systems. Visual place recognition, as opposed to purely geometrical models, holds promise of higher flexibility and association of semantics to the model. Ideally, a place recognition algorithm should be robu ..."
Abstract - Cited by 18 (2 self) - Add to MetaCart
of visual recognition algorithms for these tasks, this paper presents a new database, acquired in three different labs across Europe. It contains image sequences of several rooms under dynamic changes, acquired at the same time with a perspective and omnidirectional camera, mounted on a socket. We assess

Visual Hand Posture Recognition in Monocular Image Sequences

by Thorsten Dick, Jörg Zieren, Karl-friedrich Kraiss
"... Abstract. We present a model-based method for hand posture recognition in monocular image sequences that measures joint angles, viewing angle, and position in space. Visual markers in form of a colored cotton glove are used to extract descriptive and stable 2D features. Searching a synthetically gen ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
Abstract. We present a model-based method for hand posture recognition in monocular image sequences that measures joint angles, viewing angle, and position in space. Visual markers in form of a colored cotton glove are used to extract descriptive and stable 2D features. Searching a synthetically

Speech recognition based on phonetic features and acoustic landmarks

by Amit Juneja , 2004
"... A probabilistic and statistical framework is presented for automatic speech recognition based on a phonetic feature representation of speech sounds. In this acoustic-phonetic approach, the speech recognition problem is hypothesized as a maximization of the joint posterior probability of a set of pho ..."
Abstract - Cited by 20 (2 self) - Add to MetaCart
onsets and offsets, and sonorant consonant onsets and offsets. The classifiers use automatically extracted knowledge based acoustic param-eters (APs) that are acoustic correlates of those phonetic features. For isolated word recognition with known and limited vocabulary, the landmark sequences are con
Results 1 - 10 of 143