Natural gas and oil are one of the mainstays of the global economy. However, many issues surround the pipelines that transport these resources, including aging infrastructure, environmental impacts, and vulnerability to sabotage operations. Such issues can result in leakages in these pipelines, requiring significant effort to detect and pinpoint their locations. The objective of this project is to develop and implement a method for detecting oil spills caused by leaking oil pipelines using aerial images captured by a drone equipped with a Raspberry Pi 4. Using the message queuing telemetry transport Internet of Things (MQTT IoT) protocol, the acquired images and the global positioning system (GPS) coordinates of the images' acquisition are sent to the base station. Using deep learning approaches such as holistically-nested edge detection (HED) and extreme inception (Xception) networks, images are analyzed at the base station to identify contours using dense extreme inception networks for edge detection (DexiNed). This algorithm is capable of finding many contours in images. Moreover, the CIELAB color space (LAB) is employed to locate black-colored contours, which may indicate oil spills. The suggested method involves eliminating smaller contours to calculate the area of larger contours. If the contour's area exceeds a certain threshold, it is classified as a spill; otherwise, it is stored in a database for further review. In the experiments, spill sizes of 1m2, 2m2, and 3m2 were established at three separate test locations. The drone was operated at three different heights (5 m, 10 m, and 15 m) to capture the scenes. The results show that efficient detection can be achieved at a height of 10 meters using the DexiNed algorithm. Statistical comparison with other edge detection methods using basic metrics, such as perimage best threshold (OIS = 0.867), fixed contour threshold (ODS = 0.859), and average precision (AP = 0.905), validates the effectiveness of the DexiNed algorithm in generating thin edge maps and identifying oil slicks. © 2023 Lavoisier. All rights reserved.
There continues to be a need for an in-situ sensor system to monitor the engine oil of internal combustion engines. Engine oil needs to be monitored for contaminants and depletion of additives. While various sensor systems have been designed and evaluated, there is still a need to develop and evaluate new sensing technologies. This study evaluated Terahertz time-domain spectroscopy (THz-TDS) for the identification and estimation of the glycol contamination of automotive engine oil. Glycol contamination is a result of a gasket or seal leak allowing coolant to enter an engine and mix with the engine oil. An engine oil intended for use in both diesel and gasoline engines was obtained. Fresh engine oil samples were contaminated with fou
... Show MoreThe accuracy of the Moment Method for imposing no-slip boundary conditions in the lattice Boltzmann algorithm is investigated numerically using lid-driven cavity flow. Boundary conditions are imposed directly upon the hydrodynamic moments of the lattice Boltzmann equations, rather than the distribution functions, to ensure the constraints are satisfied precisely at grid points. Both single and multiple relaxation time models are applied. The results are in excellent agreement with data obtained from state-of-the-art numerical methods and are shown to converge with second order accuracy in grid spacing.
Drones play a vital role in the fundamental aspects of Industry 4.0 by converting conventional warehouses into intelligent ones, particularly in the realm of barcode scanning. Various potential issues frequently arise during barcode scanning by drones, specifically when the drone camera has difficulty obtaining distinct images due to certain factors, such as distance, capturing the image whilst flying, noise in the environment and different barcode dimensions. In addressing these challenges, this study proposes an approach that combines a proportional–integral–derivative (PID) controller with image processing techniques. The PID controller is responsible for continuously monitoring the camera’s input, detecting the difference
... Show MoreThe objective of this work is to study the influence of end milling cutting process parameters, tool material and geometry on multi-response outputs for 4032 Al-alloy. This can be done by proposing an approach that combines Taguchi method with grey relational analysis. Three cutting parameters have been selected (spindle speed, feed rate and cut depth) with three levels for each parameter. Three tools with different materials and geometry have been also used to design the experimental tests and runs based on matrix L9. The end milling process with several output characteristics is solved using a grey relational analysis. The results of analysis of variance (ANOVA) showed that the major influencing parameters on multi-objective response w
... Show MoreData <span>transmission in orthogonal frequency division multiplexing (OFDM) system needs source and channel coding, the transmitted data suffers from the bad effect of large peak to average power ratio (PAPR). Source code and channel codes can be joined using different joined codes. Variable length error correcting code (VLEC) is one of these joined codes. VLEC is used in mat lab simulation for image transmission in OFDM system, different VLEC code length is used and compared to find that the PAPR decreased with increasing the code length. Several techniques are used and compared for PAPR reduction. The PAPR of OFDM signal is measured for image coding with VLEC and compared with image coded by Huffman source coding and Bose-
... Show MoreThe Internet image retrieval is an interesting task that needs efforts from image processing and relationship structure analysis. In this paper, has been proposed compressed method when you need to send more than a photo via the internet based on image retrieval. First, face detection is implemented based on local binary patterns. The background is notice based on matching global self-similarities and compared it with the rest of the image backgrounds. The propose algorithm are link the gap between the present image indexing technology, developed in the pixel domain, and the fact that an increasing number of images stored on the computer are previously compressed by JPEG at the source. The similar images are found and send a few images inst
... Show MoreThe digital camera which contain light unit inside it is useful with low illumination but not for high. For different intensity; the quality of the image will not stay good but it will have dark or low intensity so we can not change the contrast and the intensity in order to increase the losses information in the bright and the dark regions. . In this search we study the regular illumination on the images using the tungsten light by changing the intensities. The result appears that the tungsten light gives nearly far intensity for the three color bands(RGB) and the illuminated band(L).the result depend on the statistical properties which represented by the voltage ,power and intensities and the effect of this parameter on the digital
... Show MoreCyber-attacks keep growing. Because of that, we need stronger ways to protect pictures. This paper talks about DGEN, a Dynamic Generative Encryption Network. It mixes Generative Adversarial Networks with a key system that can change with context. The method may potentially mean it can adjust itself when new threats appear, instead of a fixed lock like AES. It tries to block brute‑force, statistical tricks, or quantum attacks. The design adds randomness, uses learning, and makes keys that depend on each image. That should give very good security, some flexibility, and keep compute cost low. Tests still ran on several public image sets. Results show DGEN beats AES, chaos tricks, and other GAN ideas. Entropy reached 7.99 bits per pix
... Show MoreDBN Rashid, INTERNATIONAL JOURNAL OF DEVELOPMENT IN SOCIAL SCIENCE AND HUMANITIES, 2021