Quasi-Equilibrium Feature Pyramid Network for Salient Object Detection

Song, Yue; Tang, Hao; Zhao, Mengyi; Sebe, Nicu; Wang, Wei

doi:10.1109/tip.2022.3220058

Cited by 5 publications

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KAPAO changes the output of yolov5 to suit the human posture estimation task. First, the input image is passed through the backbone network for feature extraction, and then four feature layers of different scales are obtained using Feature Pyramid Networks (FPN) [37] . Second, KAPAO decodes the human bounding box and its keypoints.…”

Section: Methodsmentioning

confidence: 99%

Clinical reliability and validity of a video-based markerless gait evaluation method

Lin¹,

Wang

Sha³

et al. 2023

Preprint

View full text Add to dashboard Cite

This study explored the reliability and validity of gait parameters obtained from gait assessment system software employing a human posture estimation algorithm based on markerless videos of children walking in clinical practice. Eighteen healthy children were recruited to walk along a designated sidewalk at a comfortable walking speed. A 3-dimensional gait analysis (3D GA) and a 2-dimensional markerless (2D ML) gait evaluation system were used to extract the gait kinematics parameters twice at an interval of 2 h. The two measurements of the children’s kinematic gait parameters revealed no significant differences (P > 0.05). Intra-class correlation coefficients(ICCs) were generally high(ICC>0.7), showing moderate to good relative reliability. The standard error of measurement (SEM) values of all gait parameters measured by the two walks were 1.26°– 2.91°. The system software had good to excellent validity compared to the 3D GA, with ICC values between 0.835 and 0.957 and SEM values of 0.87° to 1.71° for the gait parameters measured by both methods. The Bland-Altman plot analysis indicated no significant systematic errors. The results suggest that the markerless gait assessment method using the human posture estimation-based algorithm may provide reliable and valid gait analysis results for practical clinical applications.

show abstract

Section: Methodsmentioning

confidence: 99%

Clinical reliability and validity of a video-based markerless gait evaluation method

Lin¹,

Wang

Sha³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Initially, the input image undergoes feature extraction through a backbone network. Subsequently, four feature layers extracted from the backbone network are passed to Feature Pyramid Network (FPN) and Path Aggregation Network (PAN) for multi-scale fusion ( 26 ). Next, KAPAO decodes bounding boxes and their keypoints.…”

Section: Methodsmentioning

confidence: 99%

Clinical reliability and validity of a video-based markerless gait evaluation method

Lin,

Wang,

Sha

et al. 2023

Front. Pediatr.

View full text Add to dashboard Cite

ObjectiveTo explore the reliability and validity of gait parameters obtained from gait assessment system software employing a human posture estimation algorithm based on markerless videos of children walking in clinical practice.MethodsEighteen typical developmental (TD) children and ten children with developmental dysplasia of the hip (DDH) were recruited to walk along a designated sidewalk at a comfortable walking speed. A 3-dimensional gait analysis (3D GA) and a 2-dimensional markerless (2D ML) gait evaluation system were used to extract the gait kinematics parameters twice at an interval of 2 h.ResultsThe two measurements of the children's kinematic gait parameters revealed no significant differences (P > 0.05). Intra-class correlation coefficients (ICC) were generally high (ICC >0.7), showing moderate to good relative reliability. The standard error of measurement (SEM) values of all gait parameters measured by the two walks were 1.26°–2.91°. The system software had good to excellent validity compared to the 3D GA, with ICC values between 0.835 and 0.957 and SEM values of 0.87°–1.71° for the gait parameters measured by both methods. The Bland–Altman plot analysis indicated no significant systematic errors.ConclusionsThe feasibility of the markerless gait assessment method using the human posture estimation-based algorithm may provide reliable and valid gait analysis results for practical clinical applications.

show abstract

Invisible gas detection: An RGB-thermal cross attention network and a new benchmark

Wang,

Lin,

Zhao

et al. 2024

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Quasi-Equilibrium Feature Pyramid Network for Salient Object Detection

Cited by 5 publications

References 51 publications

Clinical reliability and validity of a video-based markerless gait evaluation method

Clinical reliability and validity of a video-based markerless gait evaluation method

Clinical reliability and validity of a video-based markerless gait evaluation method

Invisible gas detection: An RGB-thermal cross attention network and a new benchmark

Contact Info

Product

Resources

About