Research on object detection based on circular polarization property

A new kind of circular polarization leaky-wave antenna with N-shaped slots cut in the upper side of substrate integrated waveguide (SIW) is investigated and presented. The radiation pattern and polarization axial ratio of the leaky-wave antenna are studied. The results show that the width of N-shaped slots has significant effect on the circular polarization property of the antenna. By properly choosing structural parameters, the SIW based leaky-wave antenna can realize circular polarization with excellent axial ratio in 8 GHz satellite band.

Download Full-text

Automatic As-Built BIM with 3D Object Detection by Learning Building Structure Knowledge

Construction Research Congress 2020 ◽

10.1061/9780784482865.059 ◽

2020 ◽

Author(s):

Yongzhi Xu ◽

Xuesong Shen

Keyword(s):

Object Detection ◽

Building Structure ◽

3D Object ◽

Structure Knowledge ◽

3D Object Detection

Download Full-text

Visual Odometry with Dynamic Object Detection by Complementary Integration of Optical Flows and Pattern Recognition

Proceedings of the 30th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2017) ◽

10.33012/2017.15316 ◽

2017 ◽

Author(s):

Kojiro Takeyama ◽

Takashi Machida ◽

Yoshiko Kojima ◽

Nobuaki Kubo

Keyword(s):

Pattern Recognition ◽

Object Detection ◽

Visual Odometry ◽

Dynamic Object ◽

Optical Flows

Download Full-text

Automatic accounting of Baikal diatomic algae: approaches and prospects

Issues of modern algology (Вопросы современной альгологии) ◽

10.33624/2311-0147-2019-2(20)-295-299 ◽

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%.

Download Full-text