Yu-Shiuan Tsai^*, Yuk-Hang Sit

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.3, pp. 3065-3090, 2025, DOI:10.32604/cmes.2025.064783 - 30 June 2025

Abstract To improve small object detection and trajectory estimation from an aerial moving perspective, we propose the Aerial View Attention-PRB (AVA-PRB) model. AVA-PRB integrates two attention mechanisms—Coordinate Attention (CA) and the Convolutional Block Attention Module (CBAM)—to enhance detection accuracy. Additionally, Shape-IoU is employed as the loss function to refine localization precision. Our model further incorporates an adaptive feature fusion mechanism, which optimizes multi-scale object representation, ensuring robust tracking in complex aerial environments. We evaluate the performance of AVA-PRB on two benchmark datasets: Aerial Person Detection and VisDrone2019-Det. The model achieves 60.9% mAP@0.5 on the Aerial Person… More >

Murat Yavuz Koparal¹, Burak Elmas^2,*, Serhat Gurocak¹, Cihat Aytekin¹, Mustafa Ozgur Tan¹

Canadian Journal of Urology, Vol.32, No.3, pp. 199-207, 2025, DOI:10.32604/cju.2025.063616 - 27 June 2025

Abstract Aim: The aim of this study was to investigate the factors affecting treatment success in children that got either pyeloplasty or J stent placement in ureteropelvic junction obstruction (UPJO). Patients and Methods: The study comprised 126 patients who either J stent placement or pyeloplasty performed by the same physician for UPJO from 2012 to 2022. The criteria for surgical intervention adhered to the European Association of Urology (EAU) recommendations. Symptomatic patients with verified obstruction, with a split renal function (SRF) over 40%, low-grade hydronephrosis (Society of Fetal Urology grade 2), and an obstructive segment measuring less… More >

Mohammad Barr^*

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.1, pp. 593-616, 2025, DOI:10.32604/cmes.2025.062264 - 11 April 2025

Abstract Recent years have seen a surge in interest in object detection on remote sensing images for applications such as surveillance and management. However, challenges like small object detection, scale variation, and the presence of closely packed objects in these images hinder accurate detection. Additionally, the motion blur effect further complicates the identification of such objects. To address these issues, we propose enhanced YOLOv9 with a transformer head (YOLOv9-TH). The model introduces an additional prediction head for detecting objects of varying sizes and swaps the original prediction heads for transformer heads to leverage self-attention mechanisms. We… More >

Yawar Abbas¹, Aisha Ahmed Alarfaj², Ebtisam Abdullah Alabdulqader³, Asaad Algarni⁴, Ahmad Jalal^1,5, Hui Liu^6,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4759-4776, 2025, DOI:10.32604/cmc.2025.059224 - 06 March 2025

Abstract Human Activity Recognition (HAR) in drone-captured videos has become popular because of the interest in various fields such as video surveillance, sports analysis, and human-robot interaction. However, recognizing actions from such videos poses the following challenges: variations of human motion, the complexity of backdrops, motion blurs, occlusions, and restricted camera angles. This research presents a human activity recognition system to address these challenges by working with drones’ red-green-blue (RGB) videos. The first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while… More >

Liang Mao^1,2, Yue Li^1,2, Linlin Wang^1,*, Jie Li¹, Jiajun Tan¹, Yang Meng¹, Cheng Xiong¹

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 1985-1999, 2025, DOI:10.32604/cmc.2024.058409 - 17 February 2025

Abstract This paper introduces an advanced and efficient method for distributed drone-based fruit recognition and localization, tailored to satisfy the precision and security requirements of autonomous agricultural operations. Our method incorporates depth information to ensure precise localization and utilizes a streamlined detection network centered on the RepVGG module. This module replaces the traditional C2f module, enhancing detection performance while maintaining speed. To bolster the detection of small, distant fruits in complex settings, we integrate Selective Kernel Attention (SKAttention) and a specialized small-target detection layer. This adaptation allows the system to manage difficult conditions, such as variable… More >

Ibrahim Akinjobi Aromoye¹, Hai Hiung Lo¹, Patrick Sebastian¹, Ghulam E Mustafa Abro^2,*, Shehu Lukman Ayinla^1,3

CMES-Computer Modeling in Engineering & Sciences, Vol.142, No.2, pp. 1155-1197, 2025, DOI:10.32604/cmes.2025.058598 - 27 January 2025

Abstract Unmanned aerial vehicles (UAVs) technology is rapidly advancing, offering innovative solutions for various industries, including the critical task of oil and gas pipeline surveillance. However, the limited flight time of conventional UAVs presents a significant challenge to comprehensive and continuous monitoring, which is crucial for maintaining the integrity of pipeline infrastructure. This review paper evaluates methods for extending UAV flight endurance, focusing on their potential application in pipeline inspection. Through an extensive literature review, this study identifies the latest advancements in UAV technology, evaluates their effectiveness, and highlights the existing gaps in achieving prolonged flight… More > Graphic Abstract

Yong Beom Park, Jian Kim, BeomKyu Suh, Ismatov Akobir, Ki-Il Kim^*

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 4727-4742, 2024, DOI:10.32604/cmc.2024.058512 - 19 December 2024

Abstract Content delivery networks (CDNs) lead to fast content distribution through content caching at specific CDN servers near end users. However, existing CDNs based on infrastructure cannot be employed in special cases, such as military operations. Thus, a temporary CDN without an existing infrastructure is required. To achieve this goal, we introduce a new CDN for drone-aided ad hoc networks, whereby multiple drones form ad hoc networks and quickly store specific content according to new caching algorithms. Unlike the typical CDN server, the content-caching algorithm in the proposed architecture considers the limited storage capacity of the… More >

Ahamad B. Alkodre¹, Nour Mahmoud Bahbouh², Sandra Sendra³, Adnan Ahmed Abi Sen^4,*, Yazed Alsaawy¹, Saad Said Alqahtany¹, Abdallah Namoun¹, Hani Almoamari¹

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2727-2751, 2024, DOI:10.32604/cmc.2024.053706 - 18 November 2024

Abstract In Saudi Arabia, drones are increasingly used in different sensitive domains like military, health, and agriculture to name a few. Typically, drone cameras capture aerial images of objects and convert them into crucial data, alongside collecting data from distributed sensors supplemented by location data. The interception of the data sent from the drone to the station can lead to substantial threats. To address this issue, highly confidential protection methods must be employed. This paper introduces a novel steganography approach called the Shuffling Steganography Approach (SSA). SSA encompasses five fundamental stages and three proposed algorithms, designed… More >

Wenxia Wang, Jinchen Xu, Xiaodong Ding, Zhihui Song, Yizhen Huang, Xin Zhou, Zheng Shan^*

CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 1363-1390, 2024, DOI:10.32604/cmc.2024.054055 - 15 October 2024

Abstract With the wide application of drone technology, there is an increasing demand for the detection of radar return signals from drones. Existing detection methods mainly rely on time-frequency domain feature extraction and classical machine learning algorithms for image recognition. This method suffers from the problem of large dimensionality of image features, which leads to large input data size and noise affecting learning. Therefore, this paper proposes to extract signal time-domain statistical features for radar return signals from drones and reduce the feature dimension from 512 × 4 to 16 dimensions. However, the downscaled feature data… More >

Oumaima Ameslek^1,*, Hafida Zahir², Soukaina Mitro², El Mostafa Bachaoui¹

Revue Internationale de Géomatique, Vol.33, pp. 321-340, 2024, DOI:10.32604/rig.2024.054838 - 03 September 2024

Abstract L’agriculture de précision (AP) est une stratégie de gestion agricole fondée sur l’observation, la mesure et la réponse à la variabilité des cultures inter/intra-champ. Il comprend des avancées en matière de collecte, d’analyse et de gestion des données, ainsi que des développements technologiques en matière de stockage et de récupération de données, de positionnement précis, de surveillance des rendements et de télédétection. Cette dernière offre une résolution spatiale, spectrale et temporelle sans précédent, mais peut également fournir des informations détaillées sur la hauteur de la végétation et diverses observations. Aujourd’hui, le succès des nouvelles technologies… More >