Human Detection in Thermal Imaging Using YOLO

Ivašić-Kos, Marina; Krišto, Mate; Pobar, Miran

doi:10.1145/3323933.3324076

Cited by 84 publications

(50 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, the proposed model was compared to other related methods to measure the performance of human detection and recognition at night depending on the fusion of the face and gait method, as shown in Table 5 . The results of the YOLOv3-Human model based on the fusion of face and gait biometrics were outperformed by other related results obtained by the individual biometrics recognition models, e.g., TIRFaceNet model [ 66 ], YOLO model [ 69 ], and MMTOD model [ 28 ] on the same night databases. The YOLOv3-Human model achieved an accuracy rate of 99% for face and gender recognition, which exceeds the accuracy (89.7%) achieved by the TIRFaceNet model for individual facial recognition evaluated on the same DHU Night dataset, in addition to achieving an accuracy of 90% for gait recognition with large-size subjects.…”

Section: Results and Analysismentioning

confidence: 89%

Real-Time Human Recognition at Night via Integrated Face and Gait Recognition Technologies

Manssor

Sun

Elhassan

2021

Sensors

View full text Add to dashboard Cite

Human recognition technology is a task that determines the people existing in images with the purpose of identifying them. However, automatic human recognition at night is still a challenge because of its need to align requirements with a high accuracy rate and speed. This article aims to design a novel approach that applies integrated face and gait analyses to enhance the performance of real-time human recognition in TIR images at night under various walking conditions. Therefore, a new network is proposed to improve the YOLOv3 model by fusing face and gait classifiers to identify individuals automatically. This network optimizes the TIR images, provides more accurate features (face, gait, and body segment) of the person, and possesses it through the PDM-Net to detect the person class; then, PRM-Net classifies the images for human recognition. The proposed methodology uses accurate features to form the face and gait signatures by applying the YOLO-face algorithm and YOLO algorithm. This approach was pre-trained on three night (DHU Night, FLIR, and KAIST) databases to simulate realistic conditions during the surveillance-protecting areas. The experimental results determined that the proposed method is superior to other results-related methods in the same night databases in accuracy and detection time.

show abstract

Section: Results and Analysismentioning

confidence: 89%

Real-Time Human Recognition at Night via Integrated Face and Gait Recognition Technologies

Manssor

Sun

Elhassan

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…They integrate a hardwired adaptive Boolean-map-based saliency (ABMS) kernel with the YOLO detector, to generate a saliency feature map that boosts the pedestrian from the background based on the particular season. In [23,24] YOLO detector was trained on a thermal image dataset for person detection. This paper greatly extends the scope of that work by analyzing different weather conditions separately, by testing on other datasets and including possibly confusing objects such as animals in the test.…”

Section: Related Workmentioning

confidence: 99%

“…Weather conditions are another major factor that affects the recording quality and thus the detection performance. With the deterioration of weather conditions, the distance at which it is possible to make a successful object or person detection is reduced [23]. For example, somebody parts that may be important for object recognition, such as human leg, are tiny in the case of long-distance shooting and are represented with only a few pixels in the image.…”

Section: A Thermal Camera Characteristic For Surveillance Applicationsmentioning

confidence: 99%

Thermal Object Detection in Difficult Weather Conditions Using YOLO

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…All other methods that we found in the available literature are dealing with single-class (mostly pedestrians) detections [ 29 , 30 , 31 , 32 ] and do not scale the training dataset above the limit of several hundreds or a few thousand images.…”

Section: Introductionmentioning

confidence: 99%

Fully Automated DCNN-Based Thermal Images Annotation Using Neural Network Pretrained on RGB Data

Ligocki

Jelinek

Žalud

et al. 2021

Sensors

View full text Add to dashboard Cite

One of the biggest challenges of training deep neural network is the need for massive data annotation. To train the neural network for object detection, millions of annotated training images are required. However, currently, there are no large-scale thermal image datasets that could be used to train the state of the art neural networks, while voluminous RGB image datasets are available. This paper presents a method that allows to create hundreds of thousands of annotated thermal images using the RGB pre-trained object detector. A dataset created in this way can be used to train object detectors with improved performance. The main gain of this work is the novel method for fully automatic thermal image labeling. The proposed system uses the RGB camera, thermal camera, 3D LiDAR, and the pre-trained neural network that detects objects in the RGB domain. Using this setup, it is possible to run the fully automated process that annotates the thermal images and creates the automatically annotated thermal training dataset. As the result, we created a dataset containing hundreds of thousands of annotated objects. This approach allows to train deep learning models with similar performance as the common human-annotation-based methods do. This paper also proposes several improvements to fine-tune the results with minimal human intervention. Finally, the evaluation of the proposed solution shows that the method gives significantly better results than training the neural network with standard small-scale hand-annotated thermal image datasets.

show abstract

Human Detection in Thermal Imaging Using YOLO

Cited by 84 publications

References 14 publications

Real-Time Human Recognition at Night via Integrated Face and Gait Recognition Technologies

Real-Time Human Recognition at Night via Integrated Face and Gait Recognition Technologies

Thermal Object Detection in Difficult Weather Conditions Using YOLO

Fully Automated DCNN-Based Thermal Images Annotation Using Neural Network Pretrained on RGB Data

Contact Info

Product

Resources

About