Soybean Weed Detection Based on RT-DETR with Enhanced Multiscale Channel Features

To solve the missed and wrong detection problems of the object detection model in identifying soybean companion weeds, this paper proposes an enhanced multi-scale channel feature model based on RT-DETR (EMCF-RTDETR). First, we designed a lightweight hybrid-channel feature extraction backbone network...

Full description

Bibliographic Details

Published in:	Applied Sciences
Main Authors:	Hua Yang, Yanjie Lyu, Yunpeng Jiang, Feng Jiang, Taiyong Deng, Lihao Yu, Yuanhao Qiu, Hao Xue, Junying Guo, Zhaoqi Meng
Format:	Article
Language:	English
Published:	MDPI AG 2025-04-01
Subjects:	RT-DETR weed detection FasterNet EA attention feature fusion
Online Access:	https://www.mdpi.com/2076-3417/15/9/4812