scholarly journals Pedestrian Gender Recognition by Style Transfer of Visible-Light Image to Infrared-Light Image Based on an Attention-Guided Generative Adversarial Network

Mathematics ◽  
2021 ◽  
Vol 9 (20) ◽  
pp. 2535
Author(s):  
Na Rae Baek ◽  
Se Woon Cho ◽  
Ja Hyung Koo ◽  
Kang Ryoung Park
Keyword(s):  
Visible Light ◽  
Recognition Performance ◽  
Image Resolution ◽  
Infrared Light ◽  
Gender Recognition ◽  
Ir Camera ◽  
Style Transfer ◽  
Light Image ◽  
Outdoor Environments ◽  
Optical Blur

Gender recognition of pedestrians in uncontrolled outdoor environments, such as intelligent surveillance scenarios, involves various problems in terms of performance degradation. Most previous studies on gender recognition examined recognition methods involving faces, full body images, or gaits. However, the recognition performance is degraded in uncontrolled outdoor environments due to various factors, including motion and optical blur, low image resolution, occlusion, pose variation, and changes in lighting. In previous studies, a visible-light image in which image restoration was performed and infrared-light (IR) image, which is robust to the type of clothes, accessories, and lighting changes, were combined to improve recognition performance. However, a near-IR (NIR) image requires a separate NIR camera and NIR illuminator, because of which challenges are faced in providing uniform illumination to the object depending on the distance to the object. A thermal camera, which is also called far-IR (FIR), is not widely used in a surveillance camera environment because of expensive equipment. Therefore, this study proposes an attention-guided GAN for synthesizing infrared image (SI-AGAN) for style transfer of visible-light image to IR image. Gender recognition performance was improved by using only a visible-light camera without an additional IR camera by combining the synthesized IR image obtained by the proposed method with the visible-light image. In the experiments conducted using open databases—RegDB database and SYSU-MM01 database—the equal error rate (EER) of gender recognition of the proposed method in each database was 9.05 and 12.95%, which is higher than that of state-of-the-art methods.

A Non-Intrusive Particle Temperature Measurement Methodology Using Thermogram and Visible-Light Image Sets

2021 ◽  
Author(s):  
Jesus D. Ortega ◽  
Clifford K. Ho ◽  
Guillermo Anaya ◽  
Peter Vorobieff ◽  
Gowtham Mohan
Keyword(s):  
Visible Light ◽  
High Speed ◽  
Particle Temperature ◽  
Apparent Temperature ◽  
Unique Challenge ◽  
Ir Camera ◽  
Temperature Function ◽  
Light Image ◽  
Radiation Theory ◽  
Measurement Methodology

Abstract The measurement of particle plume and curtain temperatures in particle-laden gravity-driven flows presents a unique challenge to thermometry due to the flow’s transient and stochastic nature. Earlier attempts to assess the bulk particle temperature of a plume using intrusive and non-intrusive methods have produced very limited success. Here we describe a non-intrusive method using a high-speed IR camera (ImageI8300 from Infratec) and a visible-light camera (Nikon D3500) to produce indirect particle temperature measurements. The IR camera produces thermogram sets mapping the apparent particle temperature, while the visible-light image sets allow for the calculation of the plume opacity as a function of flow discharge position. An in-house post-processing algorithm based on Planck’s radiation theory was developed to compute the true particle temperature which is a function of the apparent temperature (thermograms) and the plume opacity obtained from the visible-light images. To validate these results, a series of lab-scale tests generating particle curtains of known dimensions at various temperatures were performed. The lab-scale tests were conducted using a small particle receiver which is equipped with thermocouples to measure the temperature directly. Using the recorded thermocouple data, a particle temperature function can be derived empirically, based on the lumped capacitance model for a free-falling sphere. The empirical particle temperature function is then compared with the temperature data measured using the methodology outlined in this work yielding agreement of the bulk particle temperature of the plume. The methods described here will be developed further to estimate the heat losses from the falling particle receiver at Sandia National Labs.

Metalorganic Molecular Beam Epitaxy of GaAsP for Visible Light-Emitting Devices on Si

1998 ◽  
Vol 535 ◽  
Author(s):  
M. Yoshimoto ◽  
J. Saraie ◽  
T. Yasui ◽  
S. HA ◽  
H. Matsunami
Keyword(s):  
Molecular Beam Epitaxy ◽  
Visible Light ◽  
Buffer Layer ◽  
Molecular Beam ◽  
Infrared Light ◽  
Light Emitting ◽  
Light Emitting Devices ◽  
Good Crystallinity ◽  
Metalorganic Molecular Beam Epitaxy ◽  
Pre Treatment

AbstractGaAs1–xPx (0.2 <; x < 0.7) was grown by metalorganic molecular beam epitaxy with a GaP buffer layer on Si for visible light-emitting devices. Insertion of the GaP buffer layer resulted in bright photoluminescence of the GaAsP epilayer. Pre-treatment of the Si substrate to avoid SiC formation was also critical to obtain good crystallinity of GaAsP. Dislocation formation, microstructure and photoluminescence in GaAsP grown layer are described. A GaAsP pn junction fabricated on GaP emitted visible light (˜1.86 eV). An initial GaAsP pn diode fabricated on Si emitted infrared light.

Infrared and Visible Image Registration Base on SIFT Features

2012 ◽  
Vol 500 ◽  
pp. 383-389 ◽  
Author(s):  
Kai Wei Yang ◽  
Tian Hua Chen ◽  
Su Xia Xing ◽  
Jing Xian Li
Keyword(s):  
Visible Light ◽  
Infrared Image ◽  
Infrared Light ◽  
Infrared Sensors ◽  
Visible Image ◽  
Sift Algorithm ◽  
Image Histogram ◽  
Visible Images ◽  
Sensors Fusion ◽  
Establishment Process

In the System of Target Tracking Recognition, infrared sensors and visible light sensors are two kinds of the most commonly used sensors; fusion effectively for these two images can greatly enhance the accuracy and reliability of identification. Improving the accuracy of registration in infrared light and visible light images by modifying the SIFT algorithm, allowing infrared images and visible images more quickly and accurately register. The method can produce good results for registration by infrared image histogram equa-lization, reasonable to reduce the level of Gaussian blur in the pyramid establishment process of sift algorithm, appropriate adjustments to thresholds and limits the scope of direction of sub-gradient descriptor. The features are invariant to rotation, image scale and change in illumination.

Sign in / Sign up

Export Citation Format

Share Document