Results 61 to 70 of about 2,448 (190)

Leaf Segmentation Using Modified YOLOv8-Seg Models

Life
Computer-vision-based plant leaf segmentation technology is of great significance for plant classification, monitoring of plant growth, precision agriculture, and other scientific research.
Peng Wang, Hong Deng, Jiaxu Guo, Siqi Ji, Dan Meng, Jun Bao, Peng Zuo   +6 more
doaj   +1 more source

FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection

Sensors, 2022
UAV-based object detection has recently attracted a lot of attention due to its diverse applications. Most of the existing convolution neural network based object detection models can perform well in common object detection cases.
Wenyu Xu, Chaofan Zhang, Qi Wang, Pangda Dai   +3 more
doaj   +1 more source

Million-scale Object Detection with Large Vision Model

, 2023
Over the past few years, there has been growing interest in developing a broad, universal, and general-purpose computer vision system. Such a system would have the potential to solve a wide range of vision tasks simultaneously, without being restricted ...
Chen, Fanglin, Hu, Wenze, Lin, Feng, Lu, Guangming, Tian, Yonghong, Wang, Xiaoyu, Wang, Yaowei, Xu, Yong   +7 more
core  

USIF‐Net: U‐Shaped Symmetrical Interactive Fusion Network for Industrial Surface Defect Detection

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This paper proposes USIF‐Net to address challenges in industrial defect detection such as inter‐defect similarity, weak small‐target semantics, and multi‐scale variations. The model incorporates LGFE‐Net for local‐global feature extraction, a U‐shaped PIC‐Net for cross‐level interactive fusion, and AFFM for adaptive feature integration to mitigate ...
Laomo Zhang, Zeyu Yang, Ying Ma, Guowei Li   +3 more
wiley   +1 more source

BGF-YOLO: Enhanced YOLOv8 with Multiscale Attentional Feature Fusion for Brain Tumor Detection

, 2023
You Only Look Once (YOLO)-based object detectors have shown remarkable accuracy for automated brain tumor detection. In this paper, we develop a novel BGF-YOLO architecture by incorporating Bi-level Routing Attention (BRA), Generalized feature pyramid ...
Kang, Ming, Phan, Raphaël C. -W., Ting, Chee-Ming, Ting, Fung Fung   +3 more
core  

A Highway Litter Detection Method Based on Multi‐scale Feature Fusion and Dynamic Feature Enhancement

IET Intelligent Transport Systems, Volume 20, Issue 1, January/December 2026.
To address missed detections and false positives in highway litter detection caused by small target sizes and feature degradation, this study proposes a novel framework integrating multi‐scale feature fusion and dynamic feature enhancement mechanisms, which includes a contextual anchor attention module, an improved spatial pyramid pooling module, a ...
Changlu Guo, Yecai Guo, Songbin Li
wiley   +1 more source

Transmission Line Defect Detection in Low‐Light Environments Using Image Adversarial Synthesis and the LCDD‐YOLO Algorithm

International Journal of Intelligent Systems, Volume 2026, Issue 1, 2026.
To address the requirements for high‐precision detection of transmission line defects by inspection drones in low‐light environments such as cloudy days and to overcome the problem of significant accuracy degradation in current defect detection algorithms under low‐light conditions, this paper uses YOLOv8 as the baseline algorithm.
Yuxin Zhu, Shaotong Pei, Floriano Cuccureddu   +2 more
wiley   +1 more source

Rock Surface Crack Recognition Based on Improved Mask R-CNN with CBAM and BiFPN

Buildings
To address the challenges of multi-scale distribution, low contrast and background interference in rock crack identification, this paper proposes an improved Mask R-CNN model (CBAM-BiFPN-Mask R-CNN) that integrates the convolutional block attention ...
Yu Hu, Naifu Deng, Fan Ye, Qinglong Zhang, Yuchen Yan   +4 more
doaj   +1 more source

Dataset Construction and Real‐Time Monitoring for Developing an Intelligent Drowning Warning Algorithm by the CamTra System

International Journal of Intelligent Systems, Volume 2026, Issue 1, 2026.
To solve the problem of sparse images in real‐world drowning datasets, this study aims to create an intelligent system that can generate a large number of drowning datasets by optimizing AI image generation algorithms. The system will gradually be used to make up for the shortage of rare real‐world drowning datasets based on the CamTra (camera tracking)
Bing Bai, Chen Chuan Yu, Yan Wu, Sinuo Hou, Wang Qin, Litao Zhou, Xiaozheng Li, Richard Murray   +7 more
wiley   +1 more source

CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction

, 2023
Multi-scale features are essential for dense prediction tasks, such as object detection, instance segmentation, and semantic segmentation. The prevailing methods usually utilize a classification backbone to extract multi-scale features and then fuse ...
Hu, Xiaolin, Li, Jianmin, Li, Ziyi, Tang, Chufeng, Zhang, Gang   +4 more
core