NICUface: Robust Neonatal Face Detection in Complex NICU Scenes

Dosso, Yasmina Souley; Kyrollos, Daniel G.; Greenwood, Kim; Harrold, JoAnn; Green, James R.

doi:10.1109/access.2022.3181167

Cited by 21 publications

(31 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, represents the distance loss, including the angle, is the shape loss, L box is the bounding box regression loss, L cls is the classification loss, here we use focal Loss, and W box and W cls are the box and classification loss weights, respectively [24].…”

Section: Label Assignment Strategymentioning

confidence: 99%

PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection

et al. 2023

View full text Add to dashboard Cite

The rapid development of the photovoltaic industry in recent years has made the efficient and accurate completion of photovoltaic operation and maintenance a major focus in recent studies. The key to photovoltaic operation and maintenance is the accurate multifault identification of photovoltaic panel images collected using drones. In this paper, PV-YOLO is proposed to replace YOLOX's backbone network, CSPDarknet53, with a transformer-based PVTv2 network to obtain local connections between images and feature maps to extract more edge-detail features of similar faults. The CBAM attention mechanism is added to enhance the effective features and improve the detection accuracy of small objects. The label assignment mechanism is optimized, and the SIoU loss functionis used to improve the uneven distribution of samples and accelerate network convergence. Experiments on the dataset prove that this method is superior to the existing technology, as the highest mAP value is 92.56%. This value is 10.46% higher than that of YOLOX, and the mAP is optimal under the same parameter magnitude,proving the model's effectiveness.Moreover, mAP is increased by over 10%, especially for small targets. In this paper, we implemented a lightweight design for the model, and proposes four models of different sizes to be-sized models that are suitable for different detection scenarios.

show abstract

Section: Label Assignment Strategymentioning

confidence: 99%

PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Video monitoring using face ROIs has received increasing interest for infant cardio-respiratory monitoring recently [1]- [3]. Cardio-respiratory monitoring is crucial for early detection, prediction of prognosis, and continued monitoring of major complications during the neonatal period [4].…”

Section: Introductionmentioning

confidence: 99%

“…This monitoring allows for treatment to prevent long-term effects on neurological and behavioural development [5]. Additionally, facial video monitoring for the detection of jaundice [1] and sleepwake classification [6] has been investigated in newborns.…”

Section: Introductionmentioning

confidence: 99%

“…Face and facial landmark detection for neonates, especially in clinical environments, has proven difficult [1], [7]- [9]. Neonates have less well-defined facial features compared to adults [7], poses/postures are more varied, and common obstructions, such as bottle feeding and pacifiers are prevalent [7]- [9].…”

Section: Introductionmentioning

confidence: 99%

“…Neonates have less well-defined facial features compared to adults [7], poses/postures are more varied, and common obstructions, such as bottle feeding and pacifiers are prevalent [7]- [9]. Additionally, in the clinical environment, background scenes are complicated, medical devices and interventions may be involved, and varying lighting conditions pose additional challenges [1], [9]. Additionally, many face and facial landmark detectors have been trained on predominantly adult data [1], [7].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neonatal Face and Facial Landmark Detection from Video Recordings

Grooby¹,

Sitaula²,

Ahani³

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper explores automated face and facial landmark detection of neonates, which is an important first step in many video-based neonatal health applications, such as vital sign estimation, pain assessment, sleep-wake classification, and jaundice detection. Utilising three publicly available datasets of neonates in the clinical environment, 366 images (258 subjects) and 89 (66 subjects) were annotated for training and testing, respectively. Transfer learning was applied to two YOLO-based models, with input training images augmented with random horizontal flipping, photo-metric colour distortion, translation and scaling during each training epoch. Additionally, the re-orientation of input images and fusion of trained deep learning models was explored. Our proposed model based on YOLOv7Face outperformed existing methods with a mean average precision of 84.8% for face detection, and a normalised mean error of 0.072 for facial landmark detection. Overall, this will assist in the development of fully automated neonatal health assessment algorithms.Clinical relevance-Accurate face and facial landmark detection provides an automated and non-contact option to assist in video-based neonatal health applications.

show abstract