Longfei Wu

Mr. Longfei Wu

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 May 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
LWLongfei Wu
Longfei Wu
DWDan Wei
Dan Wei
Chang-An XuChang-An Xu
Chang-An Xu
Indoor image semantic segmentation technology is applied to fields such as smart homes and indoor security. The challenges faced by semantic segmentation techniques using RGB images and depth maps as data sources include the semantic gap between RGB images and depth maps and the loss of detailed information. To address these issues, a multi-head self-attention mechanism is adopted to adaptively align features of the two modalities and perform feature fusion in both spatial and channel dimensions. Appropriate feature extraction methods are designed according to the different characteristics of RGB images and depth maps. For RGB images, asymmetric convolution is introduced to capture features in the horizontal and vertical directions, enhance short-range information dependence, mitigate the gridding effect of dilated convolution, and introduce criss-cross attention to obtain contextual information from global dependency relationships. On the depth map, a strategy of extracting significant unimodal features from the channel and spatial dimensions is used. A lightweight skip connection module is designed to fuse low-level and high-level features. In addition, since the first layer contains the richest detailed information and the last layer contains rich semantic information, a feature refinement head is designed to fuse the two. The method achieves an mIoU of 53.86% and 51.85% on the NYUDv2 and SUN-RGBD datasets, which is superior to mainstream methods.

3 December 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
BLBjorn H Lambrigtsen
Bjorn H Lambrigtsen
PKPekka Kangaslahti
Pekka Kangaslahti
OMOliver Montes
Oliver Montes
NNNoppasin Niamsuwan
Noppasin Niamsuwan
DPDerek J. Posselt
Derek J. Posselt
IYIgor Yanovsky
Igor Yanovsky
A geostationary microwave sounder, capable of providing continuous monitoring of temperature, water vapor, clouds, precipitation, and wind in the presence of clouds and precipitation is now feasible. A design called the Geostationary Synthetic Thinned Aperture Radiometer (GeoSTAR) has been developed at the Jet Propulsion Laboratory, and the required new technology has been developed and is sufficiently mature that a space mission can be initiated. GeoSTAR can be thought of as AMSU in GEO, i.e. it has capabilities in geostationary earth orbit (GEO) similar to those of microwave sounders currently operating in low earth orbit (LEO). Having such a capability in GEO will add tremendously to our ability to observe dynamic atmospheric phenomena, such as hurricanes and severe storms, monsoonal moisture flow, atmospheric rivers, etc. GeoSTAR will make measurements every 15 minutes instead of every 12 hours and cover a large portion of the Earth continuously instead of snapshots in a narrow swath. By tracking water vapor patterns it is also possible to derive atmospheric wind speed and direction at altitudes from the surface to 10-15 km. All of this can be done regardless of cloud cover and weather conditions. During the latter half of 2020 a detailed study of GeoSTAR and its projected performance was undertaken as one of several such studies commissioned by NOAA for the purpose of configuring NOAAs next generation of earth environmental satellite systems. We present a summary of our findings, including instrument characteristics, measurement accuracy and precision, and expected impact on weather prediction and applications.

1 December 2021 in Journal of Applied Meteorology and Climatology
Verified
Journal Article
Open access
PDF file
AOAmir Ouyed
Amir Ouyed
Xubin ZengXubin Zeng
Xubin Zeng
LWLongfei Wu
Longfei Wu
DPDerek J. Posselt
Derek J. Posselt
HSHui Su
Hui Su
Much of the errors of atmospheric motion vectors (AMV) may be a consequence of algorithms not incorporating dynamical information. A physics-informed, artificial intelligence algorithm was developed that corrects errors of moisture tracking AMV (from the movement of water vapor) using numerical weather prediction (NWP) fields. The University of Arizona (UA) algorithm uses a variational method as a first step (fsUA); the second step then filters the first-stage AMVs using a random forest model that learns the error correction from NWP fields. The UA algorithm is compared with a traditional image feature tracking algorithm (JPL) using a global nature run as the “ground truth.” Experiments use global all-sky humidity fields at 500 and 850 hPa for 1–3 January 2006 and 1–3 July 2006. UA outputs AMVs with root-mean-square vector differences (RMSVDs) of 2 m s−1 for the tropics and ∼2–3 m s−1 for midlatitudes and the poles, whereas JPL outputs much higher RMSVDs of ∼3 m s−1 for the tropics and ∼3–9 m s−1 for the midlatitudes and poles. Although the algorithm fsUA produces approximately the same global RMSVDs as the JPL algorithm, fsUA has a higher resolution since it outputs an AMV per pixel, whereas the JPL algorithm uses a target box that effectively smooths the vectors. Furthermore, UA’s RMSVDs are lower than the intrinsic error (calculated from the differences between two reanalysis datasets). Even for error-prone regions with low moisture gradients and where winds are oriented along moisture isolines, UA’s absolute speed difference with “truth” stays within ∼3 m s−1.

21 April 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
LWLongfei Wu
Longfei Wu
DWDan Wei
Dan Wei
Chang-An XuChang-An Xu
Chang-An Xu
The indoor image semantic segmentation technology is applied to fields such as smart homes and indoor security. The challenges faced by semantic segmentation techniques using RGB images and depth maps as data sources include the semantic gap between RGB images and depth maps and the loss of detailed information. To address these issues, a multi-head self-attention mechanism is adopted to adaptively align features of the two modalities and perform feature fusion in both spatial and channel dimensions. Appropriate feature extraction methods are designed according to the different characteristics of RGB images and depth maps. For RGB images, asymmetric convolution is introduced to capture features in horizontal and vertical directions, enhance short-range information dependence, mitigate the gridding effect of dilated convolution, and introduce Criss-Cross Attention to obtain contextual information from global dependency relationships. On the depth map, a strategy of extracting significant unimodal features from the channel and spatial dimensions is used. A lightweight skip connection module is designed to fuse low-level and high-level features. In addition, since the first layer contains the richest detailed information and the last layer contains rich semantic information, a feature refinement head is designed to fuse the two. The method achieves mIoU of 53.86% and 51.85% on the NYUDv2 and SUN-RGBD datasets, which is superior to mainstream methods.

16 March 2024 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
DWDan Wei
Dan Wei
DLDanyang Liang
Danyang Liang
LWLongfei Wu
Longfei Wu
XWXiaolan Wang
Xiaolan Wang
LJLei Jiang
Lei Jiang
SLSuyun Luo
Suyun Luo