Results 61 to 70 of about 1,087,010 (389)

An Enhanced Deep Convolutional Model for Spatiotemporal Image Fusion [PDF]

Remote Sensing, 2019
Earth observation data with high spatiotemporal resolution are critical for dynamic monitoring and prediction in geoscience applications, however, due to some technique and budget limitations, it is not easy to acquire satellite images with both high spatial and high temporal resolutions.
Zhenyu Tan, Liping Di, Mingda Zhang, Liying Guo, Meiling Gao   +4 more
openaire   +2 more sources

Incorporating Environmental Variables Into Spatiotemporal Fusion Model to Reconstruct High-Quality Vegetation Index Data

IEEE Transactions on Geoscience and Remote Sensing
Restricted by the design of satellite sensors, the existing satellite-based normalized difference vegetation index (NDVI) cannot simultaneously have a high temporal resolution and spatial resolution, which substantially limits its applications. In recent
Xiangqiang Li, Qiongyan Peng, Yi Zheng, Shangrong Lin, Bin He, Yuean Qiu, Jin Chen, Yang Chen, Wenping Yuan   +8 more
semanticscholar   +1 more source

Fully-Coupled Two-Stream Spatiotemporal Networks for Extremely Low Resolution Action Recognition

, 2018
A major emerging challenge is how to protect people's privacy as cameras and computer vision are increasingly integrated into our daily lives, including in smart devices inside homes.
Chen, Xin, Crandall, David J, Sharghi, Aidean, Xu, Mingze   +3 more
core   +1 more source

Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition [PDF]

arXiv, 2021
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognition methods have achieved promising performance through the tightly coupled multi-modal spatiotemporal representation, they still suffer from (i) optimization difficulty under ...
arxiv  

Exploiting Image-trained CNN Architectures for Unconstrained Video Classification

, 2015
We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification.
Andrews, Walter, Luisier, Florian, Salakhutdinov, Ruslan, Srivastava, Nitish, Zha, Shengxin   +4 more
core   +1 more source

Enblending Mosaicked Remote Sensing Images With Spatiotemporal Fusion of Convolutional Neural Networks

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
Mosaicking of remote sensing images stitches images of different moments or sensors to produce a new image under a uniform geographic coordinate system.
Jingbo Wei, Wenchao Tang, Chaoqi He
doaj   +1 more source

Reconstructing the Traffic State by Fusion of Heterogeneous Data

, 2009
We present an advanced interpolation method for estimating smooth spatiotemporal profiles for local highway traffic variables such as flow, speed and density.
Bertini, Bertini, Caceres, Cassidy, Cassidy, Chen, Fastenrath, Helbing, Helbing, Herrera, Ivan, Kerner, Kerner, Kesting, Newell, Schönhof, Treiber, Treiber, Treiber, Treiber, van Lint, Zielke   +21 more
core   +1 more source

Multisensory Fusion for Unsupervised Spatiotemporal Speaker Diarization

Sensors
Speaker diarization consists of answering the question of “who spoke when” in audio recordings. In meeting scenarios, the task of labeling audio with the corresponding speaker identities can be further assisted by the exploitation of spatial features.
Paris Xylogiannis, Nikolaos Vryzas, Lazaros Vrysis, Charalampos Dimoulas   +3 more
openaire   +3 more sources

Spatiotemporal Registration for Multi-sensor Fusion Systems

DEStech Transactions on Computer Science and Engineering, 2017
A method of online sensor fusion with spatially and temporally misaligned sensors is considered in this paper. A spatiotemporal registration mode is developed for sensor alignment, and augment the target state vector with spatiotemporal bias. An unscented Kalman filter (UKF) is used to fuse and register these sensors, then the target state estimation ...
Gong-jian Zhou, Shi-zhe Bu
openaire   +2 more sources

An Acceleration Based Fusion of Multiple Spatiotemporal Networks for Gait Phase Detection [PDF]

International Journal of Environmental Research and Public Health, 2020
Human-gait-phase-recognition is an important technology in the field of exoskeleton robot control and medical rehabilitation. Inertial sensors with accelerometers and gyroscopes are easy to wear, inexpensive and have great potential for analyzing gait dynamics.
Zhen, Tao, Yan, Lei, Kong, Jian-lei
openaire   +2 more sources