scholarly journals DETECTION OF OBJECTS IN IMAGES USING AREA SELECTION

2020 ◽  
pp. 6-11
Author(s):  
V. Yu. Volkov
Keyword(s):  
Area Selection ◽  
Detection Of Objects

USE OF SIMILARITY METRICS IN TEMPLATE-BASED DETECTION OF OBJECTS IN IMAGES

2019 ◽  
Vol 78 (14) ◽  
pp. 1249-1261
Author(s):  
O. Rubel ◽  
S. K. Abramov ◽  
V. V. Abramova ◽  
V. V. Lukin
Keyword(s):  
Similarity Metrics ◽  
Detection Of Objects

Detection of Objects in Underwater Images Based on the Two-Dimensional Tsallis Entropy

ROBOT ◽  
2010 ◽  
Vol 32 (3) ◽  
pp. 289-297
Author(s):  
Xudong TANG ◽  
Yongjie PANG ◽  
Tiedong ZHANG ◽  
Ye LI
Keyword(s):  
Tsallis Entropy ◽  
Two Dimensional ◽  
Detection Of Objects

scholarly journals Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing

2021 ◽  
Vol 11 (13) ◽  
pp. 5931
Author(s):  
Ji’an You ◽  
Zhaozheng Hu ◽  
Chao Peng ◽  
Zhiqiang Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Image Annotation ◽  
Three Dimensional ◽  
Image Data ◽  
Detection Algorithm ◽  
Simulation Software ◽  
High Quality ◽  
Annotation Method ◽  
Detection Of Objects

Large amounts of high-quality image data are the basis and premise of the high accuracy detection of objects in the field of convolutional neural networks (CNN). It is challenging to collect various high-quality ship image data based on the marine environment. A novel method based on CNN is proposed to generate a large number of high-quality ship images to address this. We obtained ship images with different perspectives and different sizes by adjusting the ships’ postures and sizes in three-dimensional (3D) simulation software, then 3D ship data were transformed into 2D ship image according to the principle of pinhole imaging. We selected specific experimental scenes as background images, and the target ships of the 2D ship images were superimposed onto the background images to generate “Simulation–Real” ship images (named SRS images hereafter). Additionally, an image annotation method based on SRS images was designed. Finally, the target detection algorithm based on CNN was used to train and test the generated SRS images. The proposed method is suitable for generating a large number of high-quality ship image samples and annotation data of corresponding ship images quickly to significantly improve the accuracy of ship detection. The annotation method proposed is superior to the annotation methods that label images with the image annotation software of Label-me and Label-img in terms of labeling the SRS images.

Metamorphic Gradient: A Regional-Scale Area Selection Criterion for Gold in the Northeastern Superior Province, Eastern Canadian Shield

SEG Discovery ◽  
2007 ◽  
pp. 1-15
Author(s):  
Michel Gauthier ◽  
Sylvain Trépanier ◽  
Stephen Gardoll
Keyword(s):  
Regional Scale ◽  
Selection Criterion ◽  
Superior Province ◽  
James Bay ◽  
Area Selection ◽  
The North ◽  
First Pass ◽  
Abitibi Subprovince ◽  
Frontier Region ◽  
Metamorphic Gradient

ABSTRACT One hundred years after the first gold discoveries in the Abitibi subprovince, the Archean James Bay region to the north is experiencing a major exploration boom. Poor geologic coverage in this part of the northeastern Superior province has hindered the application of traditional Abitibi exploration criteria such as crustal-scale faults and “Timiskaming-type” sedimentary rocks. New area selection criteria are needed for successful greenfield exploration in this frontier region, and the use of steep metamorphic gradients is presented as a possible alternative. The statistical robustness of the metamorphic gradient area selection criterion was confirmed by using the curve of the receiver operating characteristic (ROC) to estimate the correlation between metamorphic fronts and the distribution of known Abitibi orogenic gold producers. The criterion was then applied to the James Bay region during a first-pass craton-scale exploration program. This was part of the strategy that led to the discovery of the Eleonore multimillion-ounce gold deposit in 2004.

The series elastic gripper design, object detection and recognition by touch

2021 ◽  
pp. 1-33
Author(s):  
Ozan Kaya ◽  
Gokce Burak Taglioglu ◽  
Seniz Ertugrul
Keyword(s):  
Synthetic Data ◽  
Estimation Algorithm ◽  
Robot Arm ◽  
Force Estimation ◽  
Tactile Sensors ◽  
Stl File ◽  
Detection Of Objects ◽  
Set Up ◽  
Force Calculation ◽  
Series Elastic

Abstract In recent years, robotic applications have been improved for better object manipulation and collaboration with human. With this motivation, the detection of objects has been studied with serial elastic parallel gripper by simple touching in case of no visual data available. A series elastic gripper, capable of detecting geometric properties of objects is designed using only elastic elements and absolute encoders instead of tactile or force/torque sensors. The external force calculation is achieved by employing an estimation algorithm. Different objects are selected for trials for recognition. A Deep Neural Network model is trained by synthetic data extracted from STL file of selected objects . For experimental set-up, the series elastic parallel gripper is mounted on a Staubli RX160 robot arm and objects are placed in pre-determined locations in the workspace. All objects are successfully recognized using the gripper, force estimation and the DNN model. The best DNN model capable of recognizing different objects with the average prediction value ranging from 71% to 98%. Hence the proposed design of gripper and the algorithm achieved the recognition of selected objects without need for additional force/torque or tactile sensors.

scholarly journals REMOTE DETECTION OF OBJECTS IN THE PRESENCE OF INTERFERENCE IN IR-THZ WAVELENGTH RANGE

2021 ◽  
Vol 8 ◽  
pp. 254-261
Author(s):  
Valerik S. Ayrapetyan
Keyword(s):  
Object Detection ◽  
Wavelength Range ◽  
High Accuracy ◽  
Remote Detection ◽  
Movement Direction ◽  
Experimental Measurements ◽  
Detection Of Objects

The paper deals with issues of object detection in conditions of smoke, dust curtains and fog in the IR-THz ranges of electromagnetic wavelengths. It is shown that remote detection of objects and determination of their movement direction under conditions of real interference in the atmosphere is provided with high accuracy and reliability in the IR-THz ranges. The results of experimental measurements and the performed calculations show that to reduce the attenuation of the signal received from the object under conditions of smoke, dust curtains and fog, it is necessary to use IR and THz methods together.

Sign in / Sign up

Export Citation Format

Share Document