A neural network for mode space source depth estimation

2005 ◽  
Vol 117 (4) ◽  
pp. 2463-2464
Author(s):  
William Lee ◽  
Yung Lee
Keyword(s):  
Neural Network ◽  
Depth Estimation ◽  
Source Depth ◽  
Mode Space

scholarly journals Source depth estimation using spectral transformations and convolutional neural network in a deep-sea environment

2020 ◽  
Vol 148 (6) ◽  
pp. 3633-3644
Author(s):  
Wenbo Wang ◽  
Zhen Wang ◽  
Lin Su ◽  
Tao Hu ◽  
Qunyan Ren ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Deep Sea ◽  
Depth Estimation ◽  
Source Depth ◽  
Spectral Transformations

scholarly journals Time- and Resource-Efficient Time-to-Collision Forecasting for Indoor Pedestrian Obstacles Avoidance

2021 ◽  
Vol 7 (4) ◽  
pp. 61
Author(s):  
David Urban ◽  
Alice Caplier
Keyword(s):  
Neural Network ◽  
Autonomous Vehicles ◽  
Depth Estimation ◽  
Video Camera ◽  
Obstacle Detection ◽  
Navigation Systems ◽  
Time To Collision ◽  
Static Data ◽  
Monocular Depth ◽  
Fully Connected

As difficult vision-based tasks like object detection and monocular depth estimation are making their way in real-time applications and as more light weighted solutions for autonomous vehicles navigation systems are emerging, obstacle detection and collision prediction are two very challenging tasks for small embedded devices like drones. We propose a novel light weighted and time-efficient vision-based solution to predict Time-to-Collision from a monocular video camera embedded in a smartglasses device as a module of a navigation system for visually impaired pedestrians. It consists of two modules: a static data extractor made of a convolutional neural network to predict the obstacle position and distance and a dynamic data extractor that stacks the obstacle data from multiple frames and predicts the Time-to-Collision with a simple fully connected neural network. This paper focuses on the Time-to-Collision network’s ability to adapt to new sceneries with different types of obstacles with supervised learning.

Source depth estimation using multi-station waveform data

1984 ◽  
Vol 74 (5) ◽  
pp. 1623-1643
Author(s):  
Falguni Roy
Keyword(s):  
Depth Estimation ◽  
The United States ◽  
Digital Data ◽  
United States Geological Survey ◽  
Travel Times ◽  
Source Depth ◽  
Time Data ◽  
Waveform Data ◽  
Level Ii ◽  
Level I

Abstract A depth estimation procedure has been described which essentially attempts to identify depth phases by analyzing multi-station waveform data (hereafter called level II data) in various ways including deconvolution, prediction error filtering, and spectral analysis of the signals. In the absence of such observable phases, other methods based on S-P, ScS-P, and SKS-P travel times are tried to get an estimate of the source depth. The procedure was applied to waveform data collected from 31 globally distributed stations for the period between 1 and 15 October 1980. The digital data were analyzed at the temporary data center facilities of the National Defense Research Institute, Stockholm, Sweden. During this period, a total number of 162 events in the magnitude range 3.5 to 6.2 were defined by analyzing first arrival time data (hereafter called level I data) alone. For 120 of these events, it was possible to estimate depths using the present procedure. The applicability of the procedure was found to be 100 per cent for the events with mb > 4.8 and 88 per cent for the events with mb > 4. A comparison of level I depths and level II depths (the depths as obtained from level I and level II data, respectively) with that of the United States Geological Survey estimates indicated that it will be necessary to have at least one local station (Δ < 10°) among the level I data to obtain reasonable depth estimates from such data alone. Further, it has been shown that S wave travel times could be successfully utilized for the estimation of source depth.

A 3D Convolutional Neural Network for Light Field Depth Estimation

2019 ◽  
Author(s):  
Agota Faluvegi ◽  
Quentin Bolsee ◽  
Sergiu Nedevschi ◽  
Vasile-Teodor Dadarlat ◽  
Adrian Munteanu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Light Field ◽  
Depth Estimation

Formulas for Source Depth Estimation From Multipath Arrivals in Deep Water

2020 ◽  
Vol 56 (6) ◽  
pp. 4856-4871
Author(s):  
Rui Duan ◽  
Kunde Yang ◽  
Feiyun Wu ◽  
Yuanliang Ma
Keyword(s):  
Deep Water ◽  
Depth Estimation ◽  
Source Depth
Sign in / Sign up

Export Citation Format

Share Document