遥感图像目标检测的相似目标替换增广算法OA北大核心CSTPCD
Similar target replacement for remote sensing object detection data augmentation
现今主流遥感图像目标检测算法依赖于深度学习技术的发展.在模型训练时,对训练集数据进行增广处理是增强模型泛化能力的重要方法.当前遥感图像目标检测算法的图像增广方法主要沿用通用的目标检测增广方法,亟需发展针对遥感目标特点的增广方法.本文提出基于遥感图像的相似目标替换增广方法,设计了相似目标替换的增广流程,即通过建立样本库、划分相似类、查询相似样本及替换样本预处理等步骤对数据集中的目标进行相似目标分类.首先,建立所有训练集样本的样本库,统计样本类别信息;其次,对训练集中的目标类别划分相似类;然后,针对数据集中样本数量不均衡的问题,设计了少数样本补偿机制,通过控制采样样本的概率平衡样本数据的训练比例;最后,设计了替换样本预处理机制,针对不同目标类别的特点,使用适宜的变换方法作为样本预处理方法.在 DOTA 数据集上的实验表明,使用相似目标替换增广算法的DCL检测算法检测结果的mAP值相较于baseline提高了1.34,模型对相似类别的预测准确率上升,对样本数量较少类别的目标检测能力得到提高.
Nowadays remote sensing image object detection algorithms are highly relied on the development of deep learning technology.Data augmentation to dataset images is an important way to enhance model's generalization ability.Current augmentation methods of remote sensing object detection algorithms still use general object detection methods.There is an urge need to develop methods that focus on the properties of remote sensing objects.This paper raised a data augmentation method named Similar Targets Replacement(STR)that based on remote sensing images and designed the STR process.First,the sample library is built to collect statistics of samples'categories.Second,categories of the dataset is divided into several similar target categories.Then,to solve the problem of disbalanced sample amounts,minority sample compensation is designed to balance the proportion of samples from different categories by controlling the probability of input samples.Finally,sample replacing preprocess mechanics is designed by using appropriate transforms for each different categories as the preprocess methods.Experiments on DOTA dataset shows the mAP of DCL detection algorithm using STR augmentation raises 1.34 compared to baseline.Model's detection accuracy to similar categories raises and ability to categories with fewer number of samples is strengthened.
孙得耀;朱明;王佳荣
中国科学院 长春光学精密机械与物理研究所,吉林 长春 130033||中国科学院大学,北京 100049中国科学院 长春光学精密机械与物理研究所,吉林 长春 130033
计算机与自动化
遥感图像目标检测数据增广相似目标替换
remote sensing imagesobject detectiondata augmentationsimilar target replacement
《液晶与显示》 2024 (006)
813-821 / 9
吉林省科技厅重点研发项目(No.20210201137GX)Supported by Science and Technology Department of Jilin Province,China(No.20210201137GX)
评论