scholarly journals Large-scale, real-time visual–inertial localization revisited

2020 ◽  
Vol 39 (9) ◽  
pp. 1061-1084
Author(s):  
Simon Lynen ◽  
Bernhard Zeisl ◽  
Dror Aiger ◽  
Michael Bosse ◽  
Joel Hesch ◽  
...  
Keyword(s):  
Real Time ◽  
Large Scale ◽  
Model Building ◽  
Nearest Neighbor ◽  
Local Features ◽  
Nearest Neighbor Search ◽  
Small Scale ◽  
Concept System ◽  
Pose Tracking ◽  
Cloud Models

The overarching goals in image-based localization are scale, robustness, and speed. In recent years, approaches based on local features and sparse 3D point-cloud models have both dominated the benchmarks and seen successful real-world deployment. They enable applications ranging from robot navigation, autonomous driving, virtual and augmented reality to device geo-localization. Recently, end-to-end learned localization approaches have been proposed which show promising results on small-scale datasets. However, the positioning accuracy, scalability, latency, and compute and storage requirements of these approaches remain open challenges. We aim to deploy localization at a global scale where one thus relies on methods using local features and sparse 3D models. Our approach spans from offline model building to real-time client-side pose fusion. The system compresses the appearance and geometry of the scene for efficient model storage and lookup leading to scalability beyond what has been demonstrated previously. It allows for low-latency localization queries and efficient fusion to be run in real-time on mobile platforms by combining server-side localization with real-time visual–inertial-based camera pose tracking. In order to further improve efficiency, we leverage a combination of priors, nearest-neighbor search, geometric match culling, and a cascaded pose candidate refinement step. This combination outperforms previous approaches when working with large-scale models and allows deployment at unprecedented scale. We demonstrate the effectiveness of our approach on a proof-of-concept system localizing 2.5 million images against models from four cities in different regions of the world achieving query latencies in the 200 ms range.

A Meta-Algorithm for Improving Top-N Prediction Efficiency of Matrix Factorization Models in Collaborative Filtering

2019 ◽  
Vol 34 (03) ◽  
pp. 2059007
Author(s):  
A. Murat Yagci ◽  
Tevfik Aytekin ◽  
Fikret S. Gurgen
Keyword(s):  
Collaborative Filtering ◽  
Matrix Factorization ◽  
Large Scale ◽  
Nearest Neighbor ◽  
Nearest Neighbor Search ◽  
Space Efficiency ◽  
Neighbor Search ◽  
Prediction Time ◽  
Low Dimensional ◽  
Prediction Efficiency

Matrix factorization models often reveal the low-dimensional latent structure in high-dimensional spaces while bringing space efficiency to large-scale collaborative filtering problems. Improving training and prediction time efficiencies of these models are also important since an accurate model may raise practical concerns if it is slow to capture the changing dynamics of the system. For the training task, powerful improvements have been proposed especially using SGD, ALS, and their parallel versions. In this paper, we focus on the prediction task and combine matrix factorization with approximate nearest neighbor search methods to improve the efficiency of top-N prediction queries. Our efforts result in a meta-algorithm, MMFNN, which can employ various common matrix factorization models, drastically improve their prediction efficiency, and still perform comparably to standard prediction approaches or sometimes even better in terms of predictive power. Using various batch, online, and incremental matrix factorization models, we present detailed empirical analysis results on many large implicit feedback datasets from different application domains.

Real-Time Public Transport Operations: Library of Control Strategies

2017 ◽  
Vol 2647 (1) ◽  
pp. 26-32 ◽  
Author(s):  
Mahmood Mahmoodi Nesheli ◽  
Avishai (Avi) Ceder
Keyword(s):  
Real Time ◽  
Public Transport ◽  
Large Scale ◽  
Real Life ◽  
Small Scale ◽  
Control Procedure ◽  
Service Reliability ◽  
Real Time Control ◽  
Time Control ◽  
Control Actions

Modern public transport (PT) operations have evolved into a complex multimodal system in which small-scale disorder can propagate. Large-scale disruptions to passengers and PT agencies result. Various studies have been developed to model PT control at the operational level; however, the main downside of possible real-time control actions is the lack of intelligent modeling and a systematic process that can activate such actions immediately. This study presents a real-time control procedure to increase service reliability and to improve successful coordinated transfers in a complex PT system. The developed method aims at minimizing total travel time for passengers and reducing the uncertainty of meetings between PT vehicles. A library of operational tactics is first built to serve as a basis of the real-time decision-making process. The methodology developed is applied to a real-life case study in Auckland, New Zealand. The results showed improvements in system performance and confirmed the use of real-time control actions to maintain reliable PT service.

scholarly journals A Filter of Minhash for Image Similarity Measures

2018 ◽  
Vol 22 (5) ◽  
pp. 689-698
Author(s):  
Jun Long ◽  
Qunfeng Liu ◽  
Xinpan Yuan ◽  
Chengyuan Zhang ◽  
Junfeng Liu ◽  
...  
Keyword(s):  
Large Scale ◽  
Nearest Neighbor ◽  
Similarity Measures ◽  
Computation Time ◽  
Image Features ◽  
Nearest Neighbor Search ◽  
Image Similarity ◽  
Scale Invariant ◽  
Minwise Hashing ◽  
Image Datasets

Image similarity measures play an important role in nearest neighbor search and duplicate detection for large-scale image datasets. Recently, Minwise Hashing (or Minhash) and its related hashing algorithms have achieved great performances in large-scale image retrieval systems. However, there are a large number of comparisons for image pairs in these applications, which may spend a lot of computation time and affect the performance. In order to quickly obtain the pairwise images that theirs similarities are higher than the specific thresholdT(e.g., 0.5), we propose a dynamic threshold filter of Minwise Hashing for image similarity measures. It greatly reduces the calculation time by terminating the unnecessary comparisons in advance. We also find that the filter can be extended to other hashing algorithms, on when the estimator satisfies the binomial distribution, such as b-Bit Minwise Hashing, One Permutation Hashing, etc. In this pager, we use the Bag-of-Visual-Words (BoVW) model based on the Scale Invariant Feature Transform (SIFT) to represent the image features. We have proved that the filter is correct and effective through the experiment on real image datasets.

IMPLEMENTING BACK-PROPAGATION- THROUGH-TIME LEARNING ALGORITHM USING CELLULAR NEURAL NETWORKS

1999 ◽  
Vol 09 (06) ◽  
pp. 1041-1074 ◽  
Author(s):  
TAO YANG ◽  
LEON O. CHUA
Keyword(s):  
Real Time ◽  
Time Complexity ◽  
Large Scale ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Back Propagation ◽  
Cellular Neural Network ◽  
Small Scale ◽  
Von Neumann ◽  
On Line

In a programmable (multistage) cellular neural network (CNN) structure, the CPU is a CNN universal chip which supports massively parallel computations on patterns and images, including videos. In this paper, we decompose the structure of a class of simultaneous recurrent networks (SRN) into a CNN program and run it on a von Neumann-like stored program CNN structure. To train the SRN, we map the back-propagation-through-time (BTT) learning algorithm into a sequence of CNN subroutines to achieve real-time performance via a CNN universal chip. By computing in parallel, the CNN universal chip can be programmed to implement in real time the BTT learning algorithm, which has a very high time complexity. An estimate of the time complexity of the BTT learning algorithm based on the CNN universal chip is presented. For small-scale problems, our simulation results show that a CNN implementation of the BTT learning algorithm for a two-dimensional SRN is at least 10,000 times faster than that based on state-of-the-art sequential workstations. For the few large-scale problems which we have so far simulated, the CNN implemented BTT learning algorithm maintained virtually the same time complexity with a learning time of a few seconds, while those implemented on state-of-the-art sequential workstations dramatically increased their time complexity, often requiring several days of running time. Several examples are presented to demonstrate how efficiently a CNN universal chip can speed up the learning algorithm for both off-line and on-line applications.

scholarly journals Log Data Real Time Analysis Using Big Data Analytic Framework with Storm and Hadoop

2018 ◽  
Vol 246 ◽  
pp. 03009
Author(s):  
Jia-Ke Lv ◽  
Yang Li ◽  
Xuan Wang
Keyword(s):  
Real Time ◽  
Large Scale ◽  
Knowledge Extraction ◽  
Streaming Data ◽  
Small Scale ◽  
Global Knowledge ◽  
Data Set ◽  
Log Data ◽  
Real Time Processing ◽  
Real Time Analysis

The log data real-time processing platform which is built using Storm On YARN integrated MapReduce and Storm that use MapReduce to complete large-scale off-line data global knowledge extraction, sudden knowledge extraction of small-scale data in Kafka buffers through Storm, and continuous real-time calculation of streaming data in combination with global knowledge. We tested our technique with the well-known KDD99 CUP data set. The experimentation results prove the system to be effective and efficient.

Sign in / Sign up

Export Citation Format

Share Document