EDGE20: A Cross Spectral Evaluation Dataset for Multiple Surveillance Problems

Le, Ha A.; Smailis, Christos; Shi, Lei; Kakadiaris, Ioannis A.

doi:10.1109/wacv45572.2020.9093573

Cited by 4 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the CASIA NIR-VIS 2.0 dataset is acquired in a lab-controlled environment, it is no longer a challenging dataset. Thus, in addition to CASIA NIR-VIS 2.0, the EDGE20 dataset [21] is used for testing. The images of EDGE20 are captured from trail cameras during both day and night in an unconstrained environment.…”

Section: Datasetsmentioning

confidence: 99%

DBLFace: Domain-Based Labels for NIR-VIS Heterogeneous Face Recognition

Kakadiaris

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning-based domain-invariant feature learning methods are advancing in near-infrared and visible (NIR-VIS) heterogeneous face recognition. However, these methods are prone to overfitting due to the large intra-class variation and the lack of NIR images for training. In this paper, we introduce Domain-Based Label Face (DBLFace), a learning approach based on the assumption that a subject is not represented by a single label but by a set of labels. Each label represents images of a specific domain. In particular, a set of two labels per subject, one for the NIR images and one for the VIS images, are used for training a NIR-VIS face recognition model. The classification of images into different domains reduces the intra-class variation and lessens the negative impact of data imbalance in training. To train a network with sets of labels, we introduce a domain-based angular margin loss and a maximum angular loss to maintain the inter-class discrepancy and to enforce the close relationship of labels in a set. Quantitative experiments confirm that DBLFace significantly improves the rank-1 identification rate by 6.7% on the EDGE20 dataset and achieves state-of-the-art performance on the CASIA NIR-VIS 2.0 dataset.

show abstract

Section: Datasetsmentioning

confidence: 99%

DBLFace: Domain-Based Labels for NIR-VIS Heterogeneous Face Recognition

Kakadiaris

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A color camera and human pose estimation model trained on color images are used in combination with an LFIR camera for automatic dataset annotation, where a person is recorded with both sensors in parallel, and an estimate of the human pose on the color image is mapped to the infrared image. In [ 16 ], a cross-spectral evaluation dataset, named EDGE20, for multiple surveillance problems was presented. The dataset is used in the problems of pedestrian and facial detection, as well as facial recognition in images captured using visible-light and near-infrared (NIR) cameras.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based SWIR Object Detection in Long-Range Surveillance Systems: An Automated Cross-Spectral Approach

Pavlović

Milanović

Stanković

et al. 2022

Sensors

View full text Add to dashboard Cite

SWIR imaging bears considerable advantages over visible-light (color) and thermal images in certain challenging propagation conditions. Thus, the SWIR imaging channel is frequently used in multi-spectral imaging systems (MSIS) for long-range surveillance in combination with color and thermal imaging to improve the probability of correct operation in various day, night and climate conditions. Integration of deep-learning (DL)-based real-time object detection in MSIS enables an increase in efficient utilization for complex long-range surveillance solutions such as border or critical assets control. Unfortunately, a lack of datasets for DL-based object detection models training for the SWIR channel limits their performance. To overcome this, by using the MSIS setting we propose a new cross-spectral automatic data annotation methodology for SWIR channel training dataset creation, in which the visible-light channel provides a source for detecting object types and bounding boxes which are then transformed to the SWIR channel. A mathematical image transformation that overcomes differences between the SWIR and color channel and their image distortion effects for various magnifications are explained in detail. With the proposed cross-spectral methodology, the goal of the paper is to improve object detection in SWIR images captured in challenging outdoor scenes. Experimental tests for two object types (cars and persons) using a state-of-the-art YOLOX model demonstrate that retraining with the proposed automatic cross-spectrally created SWIR image dataset significantly improves average detection precision. We achieved excellent improvements in detection performance in various variants of the YOLOX model (nano, tiny and x).

show abstract

A Convolutional Neural Network for Learning Local Feature Descriptors on Multispectral Images

Nunes

Pádua

2022

IEEE Latin Am. Trans.

View full text Add to dashboard Cite

EDGE20: A Cross Spectral Evaluation Dataset for Multiple Surveillance Problems

Cited by 4 publications

References 20 publications

DBLFace: Domain-Based Labels for NIR-VIS Heterogeneous Face Recognition

DBLFace: Domain-Based Labels for NIR-VIS Heterogeneous Face Recognition

Deep Learning Based SWIR Object Detection in Long-Range Surveillance Systems: An Automated Cross-Spectral Approach

A Convolutional Neural Network for Learning Local Feature Descriptors on Multispectral Images

Contact Info

Product

Resources

About