液晶与显示2025，Vol.40Issue(3)：472-480,9.DOI:10.37188/CJLCD.2024-0225
基于自适应切片辅助推理的航拍图像目标检测方法
Object detection method for aerial images based on adaptive slicing aided inference
摘要
Abstract
In order to address the problem of missed and false detections caused by different object scales,densities,unclear details and especially numerous small objects in drone aerial images,a novel object detection method based on Adaptive Slicing Aided Inference(ASAI)is proposed.Firstly,an aerial image is input into an object detection network for initial inference.With the initial inference results,a window scoring mechanism is designed to locate the ambiguous targets in the input image,and the effective image regions are selected automatically for slicing to adapt to objects with different scales and densities.Then,the sliced images are sent to the object detection network for secondary inference.Finally,the two inference results are processed by an improved non-maximum suppression(NMS)algorithm to obtain the final detection result.Experimental results on typical datasets of VisDrone2019 and AI-TOD indicate that the proposed method improves the mAP metrics of typical lightweight object detection models including YOLOv7-tiny,YOLOv8n,YOLOv8s and YOLOv9-C,effectively improving the performance of object detection for aerial images.关键词
小目标检测/自适应切片辅助推理/不确定目标定位/非极大值抑制Key words
small object detection/adaptive slicing aided inference/ambiguous target localization/non-maximum suppression分类
计算机与自动化引用本文复制引用
金黎威,徐望明,李垚翔..基于自适应切片辅助推理的航拍图像目标检测方法[J].液晶与显示,2025,40(3):472-480,9.基金项目
国家自然科学基金(No.51805386) （No.51805386）
冶金自动化与检测技术教育部工程研究中心开放课题(No.MADTOF2021B02) Supported by National Natural Science Foundation of China(No.51805386) （No.MADTOF2021B02）
Open Project of Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education(No.MADTOF2021B02) （No.MADTOF2021B02）
