scholarly journals Exploiting Visibility Information in Surface Reconstruction to Preserve Weakly Supported Surfaces

2014 ◽  
Vol 2014 ◽  
pp. 1-20 ◽  
Author(s):  
Michal Jancosek ◽  
Tomas Pajdla
Keyword(s):  
Surface Reconstruction ◽  
Free Space ◽  
State Of The Art ◽  
The State ◽  
Real Object ◽  
Reconstruction Method ◽  
The Real ◽  
Model Free ◽  
Novel Method ◽  
Different Levels

We present a novel method for 3D surface reconstruction from an input cloud of 3D points augmented with visibility information. We observe that it is possible to reconstruct surfaces that do not contain input points. Instead of modeling the surface from input points, we model free space from visibility information of the input points. The complement of the modeled free space is considered full space. The surface occurs at interface between the free and the full space. We show that under certain conditions a part of the full space surrounded by the free space must contain a real object also when the real object does not contain any input points; that is, an occluder reveals itself through occlusion. Our key contribution is the proposal of a new interface classifier that can also detect the occluder interface just from the visibility of input points. We use the interface classifier to modify the state-of-the-art surface reconstruction method so that it gains the ability to reconstruct weakly supported surfaces. We evaluate proposed method on datasets augmented with different levels of noise, undersampling, and amount of outliers. We show that the proposed method outperforms other methods in accuracy and ability to reconstruct weakly supported surfaces.

A Survey of Real-Time Industrial Wireless LAN Research

2015 ◽  
Vol 738-739 ◽  
pp. 1105-1110 ◽  
Author(s):  
Yuan Qing Qin ◽  
Ying Jie Cheng ◽  
Chun Jie Zhou
Keyword(s):  
Real Time ◽  
Future Development ◽  
Wireless Lan ◽  
State Of The Art ◽  
The State ◽  
Local Networks ◽  
The Real ◽  
Time Requirements ◽  
And Performance ◽  
Fundamental Mechanism

This paper mainly surveys the state-of-the-art on real-time communicaton in industrial wireless local networks(WLANs), and also identifys the suitable approaches to deal with the real-time requirements in future. Firstly, this paper summarizes the features of industrial WLANs and the challenges it encounters. Then according to the real-time problems of industrial WLAN, the fundamental mechanism of each recent representative resolution is analyzed in detail. Meanwhile, the characteristics and performance of these resolutions are adequately compared. Finally, this paper concludes the current of the research and discusses the future development of industrial WLANs.

scholarly journals Graph Algorithms for Word Sense Disambiguation in Biomedicine

2015 ◽  
Author(s):  
Rodrigo Goulart ◽  
Juliano De Carvalho ◽  
Vera De Lima
Keyword(s):  
Text Mining ◽  
Graph Algorithms ◽  
State Of The Art ◽  
Word Sense Disambiguation ◽  
The State ◽  
Word Sense ◽  
New Approach ◽  
Similar Performance ◽  
Sense Disambiguation ◽  
Different Levels

Word Sense Disambiguation (WSD) is an important task for Biomedicine text-mining. Supervised WSD methods have the best results but they are complex and their cost for testing is too high. This work presents an experiment on WSD using graph-based approaches (unsupervised methods). Three algorithms were tested and compared to the state of the art. Results indicate that similar performance could be reached with different levels of complexity, what may point to a new approach to this problem.

Cloud Monitoring

2012 ◽  
pp. 97-116
Author(s):  
Peer Hasselmeyer ◽  
Gregory Katsaros ◽  
Bastian Koller ◽  
Philipp Wieder
Keyword(s):  
State Of The Art ◽  
The State ◽  
Cloud Environment ◽  
State Health ◽  
Cloud Monitoring ◽  
Cloud Environments ◽  
And Performance ◽  
Cloud Infrastructures ◽  
Different Levels ◽  
The Way

The management of the entire service landscape comprising a Cloud environment is a complex and challenging venture. There, one task of utmost importance, is the generation and processing of information about the state, health, and performance of the various services and IT components, something which is generally referred to as monitoring. Such information is the foundation for proper assessment and management of the whole Cloud. This chapter pursues two objectives: first, to provide an overview of monitoring in Cloud environments and, second, to propose a solution for interoperable and vendor-independent Cloud monitoring. Along the way, the authors motivate the necessity of monitoring at the different levels of Cloud infrastructures, introduce selected state-of-the-art, and extract requirements for Cloud monitoring. Based on these requirements, the following sections depict a Cloud monitoring solution and describe current developments towards interoperable, open, and extensible Cloud monitoring frameworks.

scholarly journals Event Time Extraction with a Decision Tree of Neural Classifiers

2018 ◽  
Vol 6 ◽  
pp. 77-89 ◽  
Author(s):  
Nils Reimers ◽  
Nazanin Dehghani ◽  
Iryna Gurevych
Keyword(s):  
Decision Tree ◽  
State Of The Art ◽  
Time Frame ◽  
The State ◽  
Accuracy Improvement ◽  
Event Time ◽  
Current Events ◽  
Future Events ◽  
Novel Method ◽  
Time Information

Extracting the information from text when an event happened is challenging. Documents do not only report on current events, but also on past events as well as on future events. Often, the relevant time information for an event is scattered across the document. In this paper we present a novel method to automatically anchor events in time. To our knowledge it is the first approach that takes temporal information from the complete document into account. We created a decision tree that applies neural network based classifiers at its nodes. We use this tree to incrementally infer, in a stepwise manner, at which time frame an event happened. We evaluate the approach on the TimeBank-EventTime Corpus (Reimers et al., 2016) achieving an accuracy of 42.0% compared to an inter-annotator agreement (IAA) of 56.7%. For events that span over a single day we observe an accuracy improvement of 33.1 points compared to the state-of-the-art CAEVO system (Chambers et al., 2014). Without retraining, we apply this model to the SemEval-2015 Task 4 on automatic timeline generation and achieve an improvement of 4.01 points F1-score compared to the state-of-the-art. Our code is publically available.

scholarly journals Microscopic Structure from Motion (SfM) for Microscale 3D Surface Reconstruction

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5599
Author(s):  
Dugan Um ◽  
Sangsoo Lee
Keyword(s):  
Surface Reconstruction ◽  
Structure From Motion ◽  
Imaging Technique ◽  
Confocal Imaging ◽  
Reconstruction Method ◽  
Accuracy Analysis ◽  
Ambient Light ◽  
Solid Objects ◽  
Transparent Objects ◽  
Novel Method

In microscale photogrammetry, the confocal microscopic imaging technique has been the dominant trend. Unlike the confocal imaging mostly for transparent objects, we propose a novel method to construct a 3D shape in microscale for various micro-sized solid objects in a broad spectrµm of applications. Recently, the structure from motion (SfM) demonstrated reliable 3D reconstruction capability for macroscale objects. In this paper, we discuss the results of a novel micro-surface reconstruction method using the Structure from Motion in microscale. The proposed micro SfM technique utilizes the photometric stereovision via microscopic photogrammetry. The main challenges lie in the scanning methodology, ambient light control, and light conditioning for microscale object photography. Experimental results of the microscale SfM, as well as the modeling accuracy analysis of a reconstructed micro-object, are shared in the paper.

scholarly journals Computational Models of Narrative: Review of a Workshop

AI Magazine ◽  
2010 ◽  
Vol 31 (2) ◽  
pp. 97 ◽  
Author(s):  
Mark A. Finlayson ◽  
Whitman Richards ◽  
Patrick Henry Winston
Keyword(s):  
Computational Modeling ◽  
Computational Models ◽  
State Of The Art ◽  
Data Bank ◽  
The State ◽  
Narrative Review ◽  
Current Work ◽  
Standard Data ◽  
Abstract Level ◽  
Different Levels

On October 8-10, 2009 an interdisciplinary group met at the Wylie Center in Beverley, Massachusetts to evaluate the state of the art in the computational modeling of narrative. Three important findings emerged: (1) current work in computational modeling is described by three different levels of representation; (2) there is a paucity of studies at the highest, most abstract level aimed at inferring the meaning or message of the narrative; and (3) there is a need to establish a standard data bank of annotated narratives, analogous to the Penn Treebank.

scholarly journals Terminal-Area Aircraft Intent Inference Approach Based on Online Trajectory Clustering

2015 ◽  
Vol 2015 ◽  
pp. 1-11
Author(s):  
Yang Yang ◽  
Jun Zhang ◽  
Kai-quan Cai
Keyword(s):  
Real Time ◽  
State Of The Art ◽  
Air Traffic ◽  
The State ◽  
Traffic Situation ◽  
Trajectory Clustering ◽  
The Real ◽  
Preliminary Results ◽  
Intent Modeling ◽  
Terminal Area

Terminal-area aircraft intent inference (T-AII) is a prerequisite to detect and avoid potential aircraft conflict in the terminal airspace. T-AII challenges the state-of-the-art AII approaches due to the uncertainties of air traffic situation, in particular due to the undefined flight routes and frequent maneuvers. In this paper, a novel T-AII approach is introduced to address the limitations by solving the problem with two steps that are intent modeling and intent inference. In the modeling step, an online trajectory clustering procedure is designed for recognizing the real-time available routes in replacing of the missed plan routes. In the inference step, we then present a probabilistic T-AII approach based on the multiple flight attributes to improve the inference performance in maneuvering scenarios. The proposed approach is validated with real radar trajectory and flight attributes data of 34 days collected from Chengdu terminal area in China. Preliminary results show the efficacy of the presented approach.

scholarly journals A protection method of trained CNN model with a secret key from unauthorized access

2021 ◽  
Vol 10 ◽  
Author(s):  
AprilPyone Maungmaung ◽  
Hitoshi Kiya
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Network Models ◽  
The State ◽  
Secret Key ◽  
Neural Network Models ◽  
Unauthorized Access ◽  
Protection Method ◽  
Novel Method

In this paper, we propose a novel method for protecting convolutional neural network models with a secret key set so that unauthorized users without the correct key set cannot access trained models. The method enables us to protect not only from copyright infringement but also the functionality of a model from unauthorized access without any noticeable overhead. We introduce three block-wise transformations with a secret key set to generate learnable transformed images: pixel shuffling, negative/positive transformation, and format-preserving Feistel-based encryption. Protected models are trained by using transformed images. The results of experiments with the CIFAR and ImageNet datasets show that the performance of a protected model was close to that of non-protected models when the key set was correct, while the accuracy severely dropped when an incorrect key set was given. The protected model was also demonstrated to be robust against various attacks. Compared with the state-of-the-art model protection with passports, the proposed method does not have any additional layers in the network, and therefore, there is no overhead during training and inference processes.

Visual Tracking with Multilevel Sparse Representation and Metric Learning

2018 ◽  
Vol 11 (2) ◽  
pp. 1-12 ◽  
Author(s):  
Baifan Chen ◽  
Meng Peng ◽  
Lijue Liu ◽  
Tao Lu
Keyword(s):  
Sparse Representation ◽  
Visual Tracking ◽  
Hierarchical Structure ◽  
Real World ◽  
State Of The Art ◽  
Metric Learning ◽  
The State ◽  
Discriminative Ability ◽  
The Real ◽  
The Hierarchical Structure

Visual tracking arises in various real-world tasks where an object should be located in a video. Sparse representation can implement tracking problems by linearly representing object with a few templates. However, this approach has two main shortcomings. Namely, setting the templates updating frequency is difficult and meanwhile it is relatively weak in distinguishing the object from the background. For solving these problems, the author models a multilevel object template set that can be stratified by different updating time spans. The hierarchical structure and updating strategy promise the real-timeness, stability, and diversity of object template. Additionally, metric learning is combined to evaluate the object candidates and thereby improve the discriminative ability. Experiments on well-known visual tracking datasets demonstrate that the proposed method can track an object more robustly and accurately compared to the state-of-the-art approaches.

Sign in / Sign up

Export Citation Format

Share Document