Dense Optical Flow and Residual Network-Based Human Activity Recognition

Sultana, Negar; Mridula, Danastan Tasaouf; Sheikh, Zahid; Iffath, Fariha; Shopon,

doi:10.1007/978-981-16-8558-3_12

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are commonly used in computer vision and image processing tasks (Kumar, 2023;Barcelos et al, 2024) as an intermediate representation of an image, which is more perceptually meaningful than individual pixels. Superpixel segmentation is a computer vision technique that involves grouping pixels with color, texture, and other low-level properties into regions or clusters that perceptually belong together while drastically lowering the number of primitives for downstream tasks, such as saliency (Cong et al, 2017a(Cong et al, , b, 2019, object tracking (Kim et al, 2019), image enhancement (Fan et al, 2017;Subudhi et al, 2021), image reconstruction (Fan et al, 2018b;Li et al, 2020), and optical flow (Sultana et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

USNet: underwater image superpixel segmentation via multi-scale water-net

Wang,

Duan,

Luan

et al. 2024

Front. Mar. Sci.

View full text Add to dashboard Cite

Underwater images commonly suffer from a variety of quality degradations, such as color casts, low contrast, blurring details, and limited visibility. Existing superpixel segmentation algorithms face challenges in achieving superior performance when directly applied to underwater images with quality degradation. In this paper, to alleviate the limitations of superpixel segmentation when applied to underwater scenes, we propose the first underwater superpixel segmentation network (USNet), specifically designed according to the intrinsic characteristics of underwater images. Considering the quality degradation, we propose a multi-scale water-net module (MWM) aimed at enhancing the quality of underwater images before superpixel segmentation. The degradation-aware attention (DA) mechanism is then created and incorporated into MWM to solve light scattering and absorption, which can decrease object visibility and cause blurred edges. By effectively directing the network to prioritize locations that exhibit a considerable decrease in quality, this method enhances the visibility of those specific areas. Additionally, we extract the deep spatial features using the coordinate attention method. Finally, these features are fused with the shallow spatial information using the dynamic spatiality embedding module to embed comprehensive spatial features. Training and testing were conducted on the SUIM dataset, the underwater change detection dataset, and UIEB dataset. Experimental results show that our method achieves the best scores in terms of achievable segmentation accuracy, undersegmentation error, and boundary recall evaluation metrics compared to other methods. Both quantitative and qualitative evaluations demonstrate that our method can handle complicated underwater scenes and outperform existing state-of-the-art segmentation methods.

show abstract