Deep features class activation map for thermal face detection and tracking

Kwaśniewska, Alicja; Rumiński, Jacek; Rad, Paul

doi:10.1109/hsi.2017.8004993

Cited by 40 publications

(19 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Class activation maps (CAMs) 28 were output to determine which features our network were weighting as important for this task, ensuring that the machine learning algorithm was pinpointing image regions for classification that are believed to be critical such as the calcium burden and coronary artery geometry. It is accepted that calcium scoring 29 might be correlated with CAD severity; however, it is not sensitive to other features like coronary artery vessel narrowing due to soft noncalcified plaques.…”

Section: Methodsmentioning

confidence: 99%

Initial evaluation of a convolutional neural network used for noninvasive assessment of coronary artery disease severity from coronary computed tomography angiography data

et al. 2020

View full text Add to dashboard Cite

Purpose: Coronary computed tomography angiography (CTA) has one of the highest diagnostic sensitivities for detection of the significance of coronary artery disease (CAD); however, sensitivity is moderate and may result in increased catheterization rates. We performed an efficacy study to determine whether a trained machine learning algorithm that uses coronary CTA data may improve CAD diagnosis accuracy. Methods: Sixty-four-patient image datasets based on coronary CTA were retrospectively collected to generate eight views considering 45°increments around the coronary artery centerline. The dataset was randomly split into training and testing cohorts. Invasive FFR measurements were used as ground truth labels. A convolutional neural network (CNN) was trained and the model's capacity to predict severity of CAD was assessed on the testing cohort. Classification accuracy and area under the receiver operating characteristic curve (AUROC) analysis were performed. Similar CAD severity classification accuracy and AUROC analyses were performed using only percent diameter stenosis (%DS) and CT-derived FFR performed by 13 operators with various levels of expertise. Results: Classification accuracy over the test cohort was 80.9% using the trained network and 72.4% using the user-operated CT-derived FFR software. AUROC over the test cohort was 0.862 using the trained network, 0.807 using %DS, and 0.758 using the human-operated CT-derived FFR software. Conclusions: A trained neural network compared noninferiorly in-terms of classification accuracy and AUROC with human operators of a CT-derived FFR software, and in-terms of AUROC with clinical decision-making using %DS.

show abstract

Section: Methodsmentioning

confidence: 99%

Initial evaluation of a convolutional neural network used for noninvasive assessment of coronary artery disease severity from coronary computed tomography angiography data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Kwasniewska and Ruminski [100] demonstrated how CNNs can be efficiently utilized for face detection from low resolution thermal images, embedded in wearable devices or indoor monitoring solutions for non-intrusive remote diagnostics. Using the concept of transfer learning [101,102], they fine-tuned the Inception v3 [103] model with set of 86k thermal images and modified the final part of the network to enhance it with localization capabilities.…”

Section: Thermal Sensormentioning

confidence: 99%

Deep Learning on Multi Sensor Data for Counter UAV Applications—A Systematic Review

Samaras

Diamantidou

Ataloglou

et al. 2019

Sensors

156

View full text Add to dashboard Cite

Usage of Unmanned Aerial Vehicles (UAVs) is growing rapidly in a wide range of consumer applications, as they prove to be both autonomous and flexible in a variety of environments and tasks. However, this versatility and ease of use also brings a rapid evolution of threats by malicious actors that can use UAVs for criminal activities, converting them to passive or active threats. The need to protect critical infrastructures and important events from such threats has brought advances in counter UAV (c-UAV) applications. Nowadays, c-UAV applications offer systems that comprise a multi-sensory arsenal often including electro-optical, thermal, acoustic, radar and radio frequency sensors, whose information can be fused to increase the confidence of threat’s identification. Nevertheless, real-time surveillance is a cumbersome process, but it is absolutely essential to detect promptly the occurrence of adverse events or conditions. To that end, many challenging tasks arise such as object detection, classification, multi-object tracking and multi-sensor information fusion. In recent years, researchers have utilized deep learning based methodologies to tackle these tasks for generic objects and made noteworthy progress, yet applying deep learning for UAV detection and classification is considered a novel concept. Therefore, the need to present a complete overview of deep learning technologies applied to c-UAV related tasks on multi-sensor data has emerged. The aim of this paper is to describe deep learning advances on c-UAV related tasks when applied to data originating from many different sensors as well as multi-sensor information fusion. This survey may help in making recommendations and improvements of c-UAV applications for the future.

show abstract

“…In more recent papers, deep learning approach is used for facial features recognition. Kwasniewska et al [19] proposed a system based on the modified Inception v2 [38] neural network that was able to detect and track selected facial-feature in low resolution thermal images with accuracy close to 90%. Performance of their approach was close to real-time, although this was obtained on a high-end workstation equipped with powerful GPU.…”

Section: Features Acquisition and Object Detectionmentioning

confidence: 99%

Fast eyes detection in thermal images

Knapik

Cyganek

2020

Multimed Tools Appl

View full text Add to dashboard Cite

In recent years many methods have been proposed for eye detection. In some cases however, such as driver drowsiness detection, lighting conditions are so challenging that only the thermal imaging is a robust alternative to the visible light sensors. However, thermal images suffer from poor contrast and high noise, which arise due to the physical properties of the long waves processing. In this paper we propose an efficient method for eyes detection based on thermal image processing which can be successfully used in challenging environments. Image pre-processing with novel virtual high dynamic range procedure is proposed, which greatly enhances thermal image contrast and allows for more reliable computation of sparse image descriptors. The bag-of-visual-words approach with clustering was selected for final detections. We compare our method with the YOLOv3 deep learning model. Our method attains high accuracy and fast response in real conditions without computational complexity and requirement of a big dataset associated with the deep neural networks. For quantitative analysis a series of thermal video sequences were recorded in which eye locations were manually annotated. Created dataset was made publicly available on our website.

show abstract

Deep features class activation map for thermal face detection and tracking

Cited by 40 publications

References 17 publications

Initial evaluation of a convolutional neural network used for noninvasive assessment of coronary artery disease severity from coronary computed tomography angiography data

Initial evaluation of a convolutional neural network used for noninvasive assessment of coronary artery disease severity from coronary computed tomography angiography data

Deep Learning on Multi Sensor Data for Counter UAV Applications—A Systematic Review

Fast eyes detection in thermal images

Contact Info

Product

Resources

About