scholarly journals Estimating Weight of Unknown Objects Using Active Thermography

Robotics ◽  
2019 ◽  
Vol 8 (4) ◽  
pp. 92 ◽  
Author(s):  
Tamas Aujeszky ◽  
Georgios Korres ◽  
Mohamad Eid ◽  
Farshad Khorrami
Keyword(s):  
Neural Networks ◽  
Physical Properties ◽  
Infrared Thermography ◽  
Material Characterization ◽  
Autonomous Robots ◽  
Density Property ◽  
Active Thermography ◽  
Density Values ◽  
Unknown Objects ◽  
Unknown Object

Successful manipulation of unknown objects requires an understanding of their physical properties. Infrared thermography has the potential to provide real-time, contactless material characterization for unknown objects. In this paper, we propose an approach that utilizes active thermography and custom multi-channel neural networks to perform classification between samples and regression towards the density property. With the help of an off-the-shelf technology to estimate the volume of the object, the proposed approach is capable of estimating the weight of the unknown object. We show the efficacy of the infrared thermography approach to a set of ten commonly used materials to achieve a 99.1% R 2 -fit for predicted versus actual density values. The system can be used with tele-operated or autonomous robots to optimize grasping techniques for unknown objects without touching them.

Deep convolutional neural networks for classifying breast cancer using infrared thermography

2021 ◽  
pp. 1-12
Author(s):  
Juan Carlos Torres-Galván ◽  
Edgar Guevara ◽  
Eleazar Samuel Kolosovas-Machuca ◽  
Antonio Oceguera-Villanueva ◽  
Jorge L. Flores ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Infrared Thermography ◽  
Convolutional Neural Networks ◽  
Deep Convolutional Neural Networks

Reflection interference removal for infrared thermography images based on GAN

2021 ◽  
Vol 63 (9) ◽  
pp. 529-533
Author(s):  
Jiali Zhang ◽  
Yupeng Tian ◽  
LiPing Ren ◽  
Jiaheng Cheng ◽  
JinChen Shi
Keyword(s):  
Neural Networks ◽  
Infrared Thermography ◽  
Metal Surfaces ◽  
Infrared Image ◽  
Infrared Camera ◽  
Infrared Images ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Continuous Application ◽  
Visible Images

Reflection in images is common and the removal of complex noise such as image reflection is still being explored. The problem is difficult and ill-posed, not only because there is no mixing function but also because there are no constraints in the output space (the processed image). When it comes to detecting defects on metal surfaces using infrared thermography, reflection from smooth metal surfaces can easily affect the final detection results. Therefore, it is essential to remove the reflection interference in infrared images. With the continuous application and expansion of neural networks in the field of image processing, researchers have tried to apply neural networks to remove image reflection. However, they have mainly focused on reflection interference removal in visible images and it is believed that no researchers have applied neural networks to remove reflection interference in infrared images. In this paper, the authors introduce the concept of a conditional generative adversarial network (cGAN) and propose an end-to-end trained network based on this with two types of loss: perceptual loss and adversarial loss. A self-built infrared reflection image dataset from an infrared camera is used. The experimental results demonstrate the effectiveness of this GAN for removing infrared image reflection.

scholarly journals Using Deep Convolutional Neural Networks and Infrared Thermography to Identify Coal Quality and Gangue

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Refat Mohammed Abdullah Eshaq ◽  
Eryi Hu ◽  
Hamzah A.A.M. Qaid ◽  
Yao Zhang ◽  
Tonggang Liu
Keyword(s):  
Neural Networks ◽  
Infrared Thermography ◽  
Convolutional Neural Networks ◽  
Deep Convolutional Neural Networks ◽  
Coal Quality

scholarly journals CHARACTERISTICS OF PHYSICAL PROPERTIES OF WOOD POWDER COMPOSITES AND BAGASSEAS CONSTRUCTION MATERIALS OF SHIP

2019 ◽  
Vol 5 (1) ◽  
Author(s):  
Ersti Yulika Sari ◽  
Polaris Nasution ◽  
Fajri Ramdhan1
Keyword(s):  
Physical Properties ◽  
Water Absorption ◽  
Construction Materials ◽  
Absorption Test ◽  
Wood Powder ◽  
Powder Composites ◽  
Density Values ◽  
Water Absorption Test ◽  
Composite Wood

Parameters for measuring the physical properties on this research are divided into three elements, including measurement of weight, water absorption, and density. This research was conducted from January to March 2018 to determine the physical properties of wood powder composites and bagasse. The manufacturing and testing process refers to the ASTM and JIS standards. Weight and density testing refer to the ASTM D 792 standard while the water absorption test refers to the JIS A5908 standard. The results showed that the density of wood powder was 0.4175 gr / cm3, and the bagasse was 0.3125 gr / cm3. Then, fiber absorption in units of volume to water and resin were 16.88% and 13.75% respectively. The results showed that the largest water absorption was found in composite wood powder 60% and bagasse 40%, which was 13.47%, and for the highest density values found in wood powder composites as much as 80% or 1,078.29 kg / m3

scholarly journals Ketahanan Papan Partikel Terhadap Suhu Tinggi, Serapan Air dan Perilaku Patah

2019 ◽  
Vol 2 (3) ◽  
pp. 230
Author(s):  
Dian Sestining Ayu ◽  
Edi Kurniadi
Keyword(s):  
Physical Properties ◽  
Water Absorption ◽  
Particle Density ◽  
Flexural Modulus ◽  
Wood Powder ◽  
Wood Floor ◽  
Structural Purpose ◽  
Density Values ◽  
Shell Particles ◽  
Coconut Shells

Wood is widely used for structural and non-structural purposes. In non-structural purpose, wood is used, among others, as furniture, parquet (wood floor), partitions and so on. In line with the decreasing availability of wood, the price of wood is becoming increasingly expensive. In certain uses, substitute materials such as particle boards have been started to use. Particle boards are generally composed of certain wood powder wastes. This study aimed to look for alternative materials for building particle boards from coconut shells. The particle boards to be tested were composed of coconut shells with the addition of certain wood powder which is added with certain percentage. Particle boards were printed with a certain size, given certain pressure and tested for their physical properties. The physical properties of the particle boards tested included particle density, water absorption, dry flexural modulus, and dry bending fracture modulus. The results showed that the best mixture composition capable of producing density values, water absorption, fracture modulus and optimum modulus of elasticity were found in the proportion of mixtures of 70-90% coconut shell particles and 30-10% wood particles.

scholarly journals Ponding time in infiltration process for different land use

2021 ◽  
Vol 930 (1) ◽  
pp. 012054
Author(s):  
I K Hidayati ◽  
Suhardjono ◽  
D Harisuseno ◽  
A Suharyanto
Keyword(s):  
Land Use ◽  
Physical Properties ◽  
River Basin ◽  
Sugar Cane ◽  
Infiltration Rate ◽  
Soil Types ◽  
Land Uses ◽  
Infiltration Process ◽  
Double Ring ◽  
Density Values

Abstract Ponding time is the period from the beginning of rainfall/infiltration until the occurrence of ponding. This paper aims to determine the infiltration rate and ponding time on different land uses, such as open fields, residential, agriculture, and vegetation. This research was conducted in one of the watersheds in the Brantas River Basin, namely the Lesti River Basin, which is administratively included in the Malang Regency, East Java. The Lesti River is one of the tributaries of the Brantas River, which originates around Mount Semeru, a very intensive area for planting rice, sugar cane, and coffee. Infiltration data were collected at 35 points using a double-ring infiltrometer spread across the Lesti watershed with Andosol, Mediterranean, and Regosol soil types. At the same time, ponding time was obtained from infiltration measurements in the field using the flooding method. The physical properties of the soils were tested in the laboratory to obtain water content, porosity, and bulk density values. This study resulted in the infiltration rate and ponding time for each land use and shows how the physical properties of the soil affect the ponding time.

Prediction of Chemical-Physical Properties by Neural Networks for Structures

2006 ◽  
Vol 234 (1) ◽  
pp. 13-19 ◽  
Author(s):  
Celia Duce ◽  
Alessio Micheli ◽  
Roberto Solaro ◽  
Antonina Starita ◽  
Maria Rosaria Tiné
Keyword(s):  
Neural Networks ◽  
Physical Properties
Sign in / Sign up

Export Citation Format

Share Document