Untitled

Sun, Changming

doi:10.1023/a:1014585622703

Cited by 180 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sandbar algorithm was initialized using a manual identification of the location of the sandbar crest every 10-m in the alongshore in both vesselbased and cBathy bathymetries from 15 Sep. This approximate crest location was used to define a Gaussian-shaped region AE200 m crossshore from the initial estimate, from which the cross-shore crest location x SB was identified using a two-stage dynamic programming (TSDP) technique (Sun, 2002). Subsequent sandbar positions were determined by applying the TSDP to the Gaussian region centered at the previous survey's sandbar position.…”

Section: Sandbar Position Extraction From Surveysmentioning

confidence: 99%

Evaluation of video-based linear depth inversion performance and applications using altimeters and hydrographic surveys in a wide range of environmental conditions

Brodie

Palmsten

Hesser

et al. 2018

Coastal Engineering

View full text Add to dashboard Cite

The performance of a linear depth inversion algorithm, cBathy, applied to coastal video imagery was assessed using observations of water depth from vessel-based hydrographic surveys and in-situ altimeters for a wide range of wave conditions (0.3 < significant wave height < 4.3 m) on a sandy Atlantic Ocean beach near Duck, North Carolina. Comparisons of video-based cBathy bathymetry with surveyed bathymetry were similar to previous studies (root mean square error (RMSE) ¼ 0.75 m, bias ¼ À0.26 m). However, the cross-shore locations of the surfzone sandbar in video-derived bathymetry were biased onshore 18-40 m relative to the survey when offshore wave heights exceeded 1.2 m or were greater than half of the bar crest depth, and broke over the sandbar. The onshore bias was 3-4 m when wave heights were less than 0.8 m and were not breaking over the sandbar. Comparisons of video-derived seafloor elevations with in-situ altimeter data at three locations onshore of, near, and offshore of the surfzone sandbar over~1 year provide the first assessment of the cBathy technique over a wide range of wave conditions. In the outer surf zone, video-derived results were consistent with long-term patterns of bathymetric change (r 2 ¼ 0.64, RMSE ¼ 0.26 m, bias ¼ À0.01 m), particularly when wave heights were less than 1.2 m (r 2 ¼ 0.83). However, during storms when wave heights exceeded 3 m, video-based cBathy overestimated the depth by up to 2 m. Near the sandbar, the sign of depth errors depended on the location relative to wave breaking, with video-based depths overestimated (underestimated) offshore (onshore) of wave breaking in the surfzone. Wave speeds estimated by video-based cBathy at the initiation of wave breaking often were twice the speeds predicted by linear theory, and up to three times faster than linear theory during storms. Estimated wave speeds were half as fast as linear theory predictions at the termination of wave breaking shoreward of the sandbar. These results suggest that video-based cBathy should not be used to track the migration of the surfzone sandbar using data when waves are breaking over the bar nor to quantify morphological evolution during storms. However, these results show that during low energy conditions, cBathy estimates could be used to quantify seasonal patterns of seafloor evolution.

show abstract

Section: Sandbar Position Extraction From Surveysmentioning

confidence: 99%

Evaluation of video-based linear depth inversion performance and applications using altimeters and hydrographic surveys in a wide range of environmental conditions

Brodie

Palmsten

Hesser

et al. 2018

Coastal Engineering

View full text Add to dashboard Cite

show abstract

“…Traditional geometry-based methods [8][9][10][11][12][13][14] and learning-based methods [12,[15][16][17]] can predict depth from images but encounter formidable challenges in implementation. Factors such as high computational costs, the limited availability of remote sensing images for a specific area, and other constraints pose significant obstacles.…”

Section: Introductionmentioning

confidence: 99%

Attention-Based Monocular Depth Estimation Considering Global and Local Information in Remote Sensing Images

Lv,

Zhang,

Guo

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Monocular depth estimation using a single remote sensing image has emerged as a focal point in both remote sensing and computer vision research, proving crucial in tasks such as 3D reconstruction and target instance segmentation. Monocular depth estimation does not require multiple views as references, leading to significant improvements in both time and efficiency. Due to the complexity, occlusion, and uneven depth distribution of remote sensing images, there are currently few monocular depth estimation methods for remote sensing images. This paper proposes an approach to remote sensing monocular depth estimation that integrates an attention mechanism while considering global and local feature information. Leveraging a single remote sensing image as input, the method outputs end-to-end depth estimation for the corresponding area. In the encoder, the proposed method employs a dense neural network (DenseNet) feature extraction module with efficient channel attention (ECA), enhancing the capture of local information and details in remote sensing images. In the decoder stage, this paper proposes a dense atrous spatial pyramid pooling (DenseASPP) module with channel and spatial attention modules, effectively mitigating information loss and strengthening the relationship between the target’s position and the background in the image. Additionally, weighted global guidance plane modules are introduced to fuse comprehensive features from different scales and receptive fields, finally predicting monocular depth for remote sensing images. Extensive experiments on the publicly available WHU-OMVS dataset demonstrate that our method yields better depth results in both qualitative and quantitative metrics.

show abstract