A Semantic Relation Graph Reasoning Network for Object Detection

2021 ◽  
Author(s):  
Xiao Shu ◽  
Rui Liu ◽  
Jun Xu
Keyword(s):  
Object Detection ◽  
Semantic Relation ◽  
Relation Graph

scholarly journals Relation Graph Network for 3D Object Detection in Point Clouds

2021 ◽  
Vol 30 ◽  
pp. 92-107
Author(s):  
Mingtao Feng ◽  
Syed Zulqarnain Gilani ◽  
Yaonan Wang ◽  
Liang Zhang ◽  
Ajmal Mian
Keyword(s):  
Object Detection ◽  
Point Clouds ◽  
3D Object ◽  
Relation Graph ◽  
3D Object Detection

Assembly Unit Division Method Based on Connection Strength

2013 ◽  
Vol 427-429 ◽  
pp. 2118-2121
Author(s):  
Chang Chun Liu ◽  
Shu Jian Zhang ◽  
Zhong Qi Sheng
Keyword(s):  
Graph Model ◽  
Semantic Relation ◽  
Connection Strength ◽  
Assembly Time ◽  
Assembly Unit ◽  
Relation Graph ◽  
Division Number

Through analysing the assembly relation between the product parts, this paper divided the product parts into function parts and the connectors. Then the simplified assembly semantic relation graph model was established in this paper. The concept of assembly connection strength was introduced to express the complexity of assembly between the parts. Using the least assembly time as the goal to determine the optimal unit division number, the assembly unit division was accomplished based on the connection strength. Finally using the spindle box of HTC2500hs as an example to check this division method, the results show that this method has applicability and effectiveness.

Automatic accounting of Baikal diatomic algae: approaches and prospects

2019 ◽  
pp. 295-299
Author(s):  
Кonstantin А. Elshin ◽  
Еlena I. Molchanova ◽  
Мarina V. Usoltseva ◽  
Yelena V. Likhoshway
Keyword(s):  
Object Detection ◽  
Loss Function ◽  
Classification Accuracy ◽  
Diatom Species ◽  
Bounding Box ◽  
Synedra Acus ◽  
And Training

Using the TensorFlow Object Detection API, an approach to identifying and registering Baikal diatom species Synedra acus subsp. radians has been tested. As a result, a set of images was formed and training was conducted. It is shown that аfter 15000 training iterations, the total value of the loss function was obtained equal to 0,04. At the same time, the classification accuracy is equal to 95%, and the accuracy of construction of the bounding box is also equal to 95%.

Object Detection in Cluttered Range Images Using Edgel Geometry

2010 ◽  
Vol 130 (9) ◽  
pp. 1572-1580
Author(s):  
Dipankar Das ◽  
Yoshinori Kobayashi ◽  
Yoshinori Kuno
Keyword(s):  
Object Detection ◽  
Range Images
Sign in / Sign up

Export Citation Format

Share Document