Results 31 to 40 of about 15,951 (227)
International Journal of Ambient Computing and IntelligenceThe power construction industry's growth demands efficient monitoring of high-risk worker behaviors, yet traditional methods are inefficient and existing models face false alarms in complex scenes. This study proposes DSR-YOLOv8, an improved YOLOv8 algorithm integrating three modules: (1) DSRAB using deep separable convolution and global pooling to ...
Lingwen Meng +4 more
openaire +1 more source
Advanced Robotics Research, EarlyView.An AI‐powered, robot‐assisted framework automatically produces, images, and analyzes 3D tumor spheroids to evaluate drug efficacy. Integrated modules handle spheroid formation, live/dead staining, brightfield imaging, and automated image analysis, including spheroid segmentation, viability and metrics to assess the drug treatment efficacy. The workflow
Dalia Mahdy +13 more
wiley +1 more source
智能科学与技术学报针对无人机航拍图像目标检测效果差的问题，提出改进的UAVAI-YOLO模型。首先，为使模型获得更加丰富的语义信息，使用改进可变形卷积网络（deformable convolutional networks，DCN）替换原骨干（backbone）网络部分通道到像素（channel-to-pixel，C2f）模块原始卷积。其次，为增加P2特征层而不增加模型参数量，提出Conv_C模块将骨干网络输出通道降维，同时避免通道降维导致的语义信息丢失，使用改进ODConv卷积替换颈部（neck）部分C2f模块原始卷积。
何植仟, 曹立杰
doaj +1 more source
C4D-YOLOv8: improved YOLOv8 for object detection on drone-captured images
Signal, Image and Video ProcessingAbstract Unmanned aerial vehicles (UAVs), as an emerging technology with vast application prospects, produce distinctive images due to factors, such as their shooting environment, altitude, and equipment. These UAV-captured images possess unique characteristics compared with traditional pictures, including high resolution, abundant presence of ...
Weihui Zeng +4 more
openaire +1 more source
Advanced Science, EarlyView.A functionally biomimetic design methodology is presented, enabling a single robot to perform eight distinct functions and manipulate objects across a size range exceeding 2300‐fold. The robot exceeds basic human hand functions and demonstrates remote operation, multi‐object manipulation, humanoid‐robot hand interaction, and narrow‐space inspection ...
Xin Tong +7 more
wiley +1 more source
Object Detection Based on You Look Only Once Version 8 for Real-Time Applications
IJCCS (Indonesian Journal of Computing and Cybernetics Systems)This research focus to involves human detection in crowded situations, especially in the lecturer's room. The lecturer's room is very vulnerable because it can be accessed by anyone with only one entry and exit to the lecturer's room, so it would be ...
Gede Agus Santiago +2 more
doaj +1 more source
Model predictive control with inline parameter adaptation for direct crystal growth rate regulation
AIChE Journal, EarlyView.Abstract In batch cooling crystallization, many interactive factors, including supersaturation, reactor dimensions, and operating conditions, govern crystal growth and significantly influence product properties. Variables such as temperature or refractive index are used as surrogate control variables but have limitations in capturing growth rate ...
Huitian Yu, Jiewen Zhao, Heiko Briesen
wiley +1 more source
Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation System
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)This study addresses the critical need for enhanced accuracy in YOLOv8 models designed for visually impaired navigation systems. Existing models often struggle with consistency in object detection and distance estimation under varying environmental ...
Erwin Syahrudin +2 more
doaj +1 more source
Advanced Intelligent Discovery, EarlyView.This paper presents a computer vision (deep learning) pipeline integrating YOLOv8 and YOLOv9 for automated detection, segmentation, and analysis of rosette cellulose synthase complexes in freeze‐fracture electron microscopy images. The study explores curated dataset expansion for model improvement and highlights pipeline accuracy, speed ...
Siri Mudunuri +6 more
wiley +1 more source
FB-YOLOv8s: A fire detection algorithm based on YOLOv8s
Cognitive RoboticsThe significance of fire detection lies in protecting public safety and safeguarding the lives and property of people. However, there exist some problems in traditional detection algorithms of fire, such as low accuracy, high miss rate, and low detection rate of small targets.
Yuhang Liu, Chunjuan Bo, Chong Feng
openaire +2 more sources