Claim Missing Document
Check
Articles

Found 5 Documents
Search

Online Digital Image Stabilization for an Unmanned Aerial Vehicle (UAV) Rahmaniar, Wahyu; Rakhmania, Amalia Eka
Journal of Robotics and Control (JRC) Vol 2, No 4 (2021): July (Forthcoming Issue)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The Unmanned Aerial Vehicle (UAV) video system uses a portable camera mounted on the robot to monitor scene activities. In general, UAVs have very little stabilization equipment, so getting good and stable images of UAVs in real-time is still a challenge. This paper presents a novel framework for digital image stabilization for online applications using a UAV. This idea aims to solve the problem of unwanted vibration and motion when recording video using a UAV. The proposed method is based on dense optical flow to select features representing the displacement of two consecutive frames. K-means clustering is used to find the cluster of the motion vector field that has the largest members. The centroid of the largest cluster was chosen to estimate the rigid transform motion that handles rotation and translation. Then, the trajectory is compensated using the Kalman filter. The experimental results show that the proposed method is suitable for online video stabilization and achieves an average computation time performance of 47.5 frames per second (fps).
Real-Time Human Detection Using Deep Learning on Embedded Platforms: A Review Rahmaniar, Wahyu; Hernawan, Ari
Journal of Robotics and Control (JRC) Vol 2, No 6 (2021): November (Forthcoming Issue)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The detection of an object such as a human is very important for image understanding in the field of computer vision. Human detection in images can provide essential information for a wide variety of applications in intelligent systems. In this paper, human detection is carried out using deep learning that has developed rapidly and achieved extraordinary success in various object detection implementations. Recently, several embedded systems have emerged as powerful computing boards to provide high processing capabilities using the graphics processing unit (GPU). This paper aims to provide a comprehensive survey of the latest achievements in this field brought about by deep learning techniques in the embedded platforms. NVIDIA Jetson was chosen as a low power system designed to accelerate deep learning applications. This review highlights the performance of human detection models such as PedNet, multiped, SSD MobileNet V1, SSD MobileNet V2, and SSD inception V2 on edge computing. This survey aims to provide an overview of these methods and compare their performance in accuracy and computation time for real-time applications. The experimental results show that the SSD MobileNet V2 model provides the highest accuracy with the fastest computation time compared to other models in our video datasets with several scenarios.
Design and Implementation of a Mobile Robot for Carbon Monoxide Monitoring Rahmaniar, Wahyu; Wicaksono, Ardhi
Journal of Robotics and Control (JRC) Vol 2, No 1 (2021): January
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.2143

Abstract

The gas detection problem is relevant to many real-world applications, such as leak detection in industrial settings and landfill monitoring. The mobile robot used for gas detection has several advantages and can reduce danger for humans. In this study, we proposed an integration system for a mobile robot that can be used for carbon monoxide (CO) monitoring with different operating temperatures. The design and implementation of a mobile robot system that proposed consists of the onboard and ground stations. The proposed system can read CO gas concentration and temperature then send it wirelessly using an XBee module to the ground station. This system was also able to receive the command from the ground station to move the robot. The system provided real-time acquisition data that believed can be a useful tool for monitoring and can be applied for various purposes. The experimental results show that a combination of a mobile robot and environmental sensors can be used for environmental monitoring.
Mobile Robot Path Planning in a Trajectory with Multiple Obstacles Using Genetic Algorithms Rahmaniar, Wahyu; Rakhmania, Amalia Eka
Journal of Robotics and Control (JRC) Vol 3, No 1 (2022): January
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v3i1.11024

Abstract

Path planning is an essential algorithm to help robots complete their task in the field quickly. However, some path planning algorithms are computationally expensive and cannot adapt to new environments with a distinctly different set of obstacles. This paper presents optimal path planning based on a genetic algorithm (GA) that is proposed to be carried out in a dynamic environment with various obstacles. First, the points of the feasible path are found by performing a local search procedure. Then, the points are optimized to find the shortest path. When the optimal path is calculated, the position of the points on the path is smoothed to avoid obstacles in the environment. Thus, the average fitness values and the GA generation are better than the traditional method. The simulation results show that the proposed algorithm successfully finds the optimal path in an environment with multiple obstacles. Compared to a traditional GA-based method, our proposed algorithm has a smoother route due to path optimization. Therefore, this makes the proposed method advantageous in a dynamic environment.
Understanding of Convolutional Neural Network (CNN): A Review Purwono, Purwono; Ma'arif, Alfian; Rahmaniar, Wahyu; Fathurrahman, Haris Imam Karim; Frisky, Aufaclav Zatu Kusuma; Haq, Qazi Mazhar ul
International Journal of Robotics and Control Systems Vol 2, No 4 (2022)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v2i4.888

Abstract

The application of deep learning technology has increased rapidly in recent years. Technologies in deep learning increasingly emulate natural human abilities, such as knowledge learning, problem-solving, and decision-making. In general, deep learning can carry out self-training without repetitive programming by humans. Convolutional neural networks (CNNs) are deep learning algorithms commonly used in wide applications. CNN is often used for image classification, segmentation, object detection, video processing, natural language processing, and speech recognition. CNN has four layers: convolution layer, pooling layer, fully connected layer, and non-linear layer. The convolutional layer uses kernel filters to calculate the convolution of the input image by extracting the fundamental features. The pooling layer combines two successive convolutional layers. The third layer is the fully connected layer, commonly called the convolutional output layer. The activation function defines the output of a neural network, such as 'yes' or 'no'. The most common and popular CNN activation functions are Sigmoid, Tanh, ReLU, Leaky ReLU, Noisy ReLU, and Parametric Linear Units. The organization and function of the visual cortex greatly influence CNN architecture because it is designed to resemble the neuronal connections in the human brain. Some of the popular CNN architectures are LeNet, AlexNet and VGGNet.