面向复杂光照的舞台演员检测  

Actor Detection Method for Complex Lighting Stage

作　　者：赵国庆 董天阳[1] 童程凯 沈冰雁 Zhao Guoqing;Dong Tianyang;Tong Chengkai;Shen Bingyan(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310014)

机构地区：[1]浙江工业大学计算机学院,杭州310014

出　　处：《计算机辅助设计与图形学学报》2024年第4期565-574,共10页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(62072405);国家重点研发计划(2018YFB1404100);浙江省基础公益研究计划(LGF20F020017)。

摘　　要：复杂舞台场景存在多个光源产生的偏色和光照不均匀问题,严重影响了演员检测的精度.针对上述问题,提出一种基于伪多模态融合的演员检测方法.首先随机选取一种光照处理方法构建增强图像,与原图像构成伪多模态图像对;然后在增强图像中以演员关键点建立候选集合,从集合中随机选取部分关键点所在的区域构建增强补丁集合,并将补丁替换到原始图像中进行训练;最后在传统特征金字塔网络的基础上借鉴Transformer编码器的构建形式,利用视觉注意力模块构建视觉注意力编码器,强化多尺度特征的交互逻辑.在自建4543幅包含舞台演员的图像数据集上与3个模型进行组合,舞台演员检测的均值平均精度分别提升0.4%~2.9%,表明所提方法能够较好地降低偏色和不均匀光照的影响.In complex stage scenes,the accuracy of actor detection is severely affected by color bias and uneven illumination problems generated by multiple light sources.To solve these problems,an actor detection method based on pseudo-multimodal fusion is proposed.First,a random illumination method is used to construct an enhanced image to form a pseudo-multimodal image pair with the original image;second,an actor key point candidate set is created in the enhanced image,and some key points are randomly selected from the set to construct enhanced patches,and the patches are replaced into the original image for training.Then,based on the traditional feature pyramid network,the visual attention module is used to construct visual attention encoders to enhance the interaction logic of multi-scale features.On a self-constructed dataset of 4543 images which containing stage actors,the average accuracy of detection is improved 0.4% to 2.9% by combining the three models,and the results show that the proposed method can better reduce the effects of color bias and uneven illumination.

关 键 词：目标检测 光照处理 行人检测 数据增强 特征金字塔网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]