Helipad Pose Estimation Using Intelligent Helipad and LiDAR Camera Fusion (IHLCF)
Mohammad Sefidgar,
Rene Jr. Landry
Issue:
Volume 10, Issue 2, December 2022
Pages:
16-24
Received:
28 May 2022
Accepted:
15 June 2022
Published:
19 September 2022
DOI:
10.11648/j.ijssn.20221002.11
Downloads:
Views:
Abstract: Pose estimation has evolved into a beneficial concept in autonomous systems. It refers to the techniques used by computers to detect and quantify certain features in an image. The present work proposes modified helipad intelligent detection and pose estimation, using a fusion of camera and LiDAR. The image data are first collected using Otsu thresholding through the downward drone camera and converted to a binary image. Next, Boundary Parametric Ellipse Fitting (BPEF) algorithm is employed to detect circles, which will turn into ellipses when there is a tangential distortion in an image. Then, Ellipses Region of Interest (EROI) is extracted from the images via the potential circles. The algorithm uses a modified version of the helipad with an arrow sign located outside of the helipad’s circle. The arrow’s centroid point is located on the axial line, which horizontally splits the word “H” and passes the word’s centroid. Hence, using the proffering over-the-line-and-between-ellipses-check technique, potential arrows are extracted. A Support Vector Machine (SVM) is then trained to detect the helipad over 400 images of the word “H” and Arrow patterns. The “H” and the Arrow corners are detected and localized in the following phase. The projected LiDAR data is followingly utilized to find the corners depth information. Finally, the translational and rotational pose components are projected to obtain the corners’ coordinates and the rigid body transformation. Software-in-the-Loop (SIL) is used to assess the method accurately. The experimental setup is tuned so that the drone stays motionless over the landing platform and conducts the pose estimation. The method was compared with the AprilTag Detection Algorithm (ATDA). A statistical Root Mean Square Error (RMS) is also used to gauge the accuracy of the proffered method. The analysis results confirmed a notable improvement in rotational and translational estimations.
Abstract: Pose estimation has evolved into a beneficial concept in autonomous systems. It refers to the techniques used by computers to detect and quantify certain features in an image. The present work proposes modified helipad intelligent detection and pose estimation, using a fusion of camera and LiDAR. The image data are first collected using Otsu thresh...
Show More
Improving of Characteristics of Rotary Angular Sensor Using Nonlinear Transparent Disc
Nam Chol Yu,
Myong Jin Jo,
Chol Sun Kim
Issue:
Volume 10, Issue 2, December 2022
Pages:
25-32
Received:
28 June 2022
Accepted:
3 August 2022
Published:
28 September 2022
DOI:
10.11648/j.ijssn.20221002.12
Downloads:
Views:
Abstract: As the angular position sensor is a main sensor to measure an accurate position and direction, it plays an important role in various applications such as robotic controller, camera and industrial machines. Recently, lots of angular position sensors such as simple resistive potentiometer, capacitive potentiometer, optical sensor and magnetic sensor are described in several literatures. This paper has described a simple absolute rotary angular sensor with a nonlinear transparent disc. This sensor consists of five elements such as light-source, a shaft coupled nonlinear transparent optical disc, lens, a pair of light dependent resistor (LDR) and a signal processing circuit. This absolute rotary angular sensor is one of non-contact potentiometer based on characteristic of resistance via irradiance and has an advantage to fabricate easily as disc is made with fiber glass and a self-adhesive tape of which transparency is nonlinearly changed in a range of 0-360°. Also this sensor has a good linearity of R2 = 0.99999, a good repeatability of maximum characteristic drift around ±0.1° and measurement error below ±0.5°. And measurement stability is ±0.1° within its full operating range from 0° to 360°. The proposed disc assembly and overall results can be helpful to design absolute rotary angular sensor for performance improvement of it. It seems that the proposed method has important practical significance for the development of optical absolute rotary angular sensor.
Abstract: As the angular position sensor is a main sensor to measure an accurate position and direction, it plays an important role in various applications such as robotic controller, camera and industrial machines. Recently, lots of angular position sensors such as simple resistive potentiometer, capacitive potentiometer, optical sensor and magnetic sensor ...
Show More
Research Status and Prospects of Generative Adversarial Networks in Seismic Data Denoising
Yuan Xu,
Qing Wang,
Shiguang Guo
Issue:
Volume 10, Issue 2, December 2022
Pages:
33-50
Received:
13 September 2022
Accepted:
29 September 2022
Published:
17 October 2022
DOI:
10.11648/j.ijssn.20221002.13
Downloads:
Views:
Abstract: Efficient and high-quality processing of seismic data collected by geophone sensors is the core of successful seismic exploration. Seismic denoising is a key step in seismic data processing. Traditional seismic denoising relies on manual empirical parameter selection and comparative analysis, which is time-consuming and limited by subjective errors. Deep learning methods based on convolutional neural networks (CNN) have improved the efficiency of denoising massive amounts of seismic data and reduced the manual errors of traditional methods. However, most CNN methods only consider data loss and are weak in recovering the structure of seismic signals, resulting in severe attenuation of some seismic traces in the recovered effective signals, reducing the continuity of seismic events and the quality of seismic data. Generative adversarial networks (GAN), a popular method for deep learning with unique adversarial ideas and powerful feature extraction capabilities, can overcome the limitations of CNN methods in the field of seismic data denoising. This paper firstly introduces the classification and development process of seismic denoising. Then, starting from the principle of GAN, it introduces the workflow of the original GAN, the objective function in the training process, the existing problems of the original GAN and some mainstream solutions to these problems, and introduces the commonly used model of GAN in the field of earthquake denoising. besides, it summarizes and analyzes the current application and improvement innovation of GAN in the field of seismic denoising, and analyzes the application of GAN in the field of seismic denoising from two aspects of supervised learning and unsupervised learning with examples. Finally, the prospect of GAN for seismic denoising in the future is prospected.
Abstract: Efficient and high-quality processing of seismic data collected by geophone sensors is the core of successful seismic exploration. Seismic denoising is a key step in seismic data processing. Traditional seismic denoising relies on manual empirical parameter selection and comparative analysis, which is time-consuming and limited by subjective errors...
Show More
