摘要
已有基于卷积神经网络的目标检测算法倾向于提取目标纹理特征,而非结构特征;因此,已有方法不能实现变纹理目标的可靠检测。针对此问题,提出基于纹理随机化的结构主导目标检测方法,采用仿真纹理随机化方法减弱网络模型对纹理特征的拟合,实现基于结构特征的变纹理目标可靠检测。利用目标的三维模型,借助Blender渲染引擎,完成纹理随机化仿真训练数据集的生成。仿真及真实图像实验测试结果表明:该方法能够实现基于目标结构特征的变纹理目标可靠检测。
Region-based detectors with convolutional neural networks tend to learn textural rather structural feature and thus face substantial difficulties in detecting objects with various textures.To tackle this problem,the texture randomization to augment the synthetic training image dataset was employed and a novel method for structure-aware object detection was proposed.The texture-randomized simulation data were generated by rendering 3D model with varied textures using Blender.Experiments on synthetic and real images indicate that the proposed method is capable of robustly detecting texture-varied objects based on structural information.
作者
王梓
毕道明
周颉鑫
孙晓亮
于起峰
WANG Zi;BI Daoming;ZHOU Jiexin;SUN Xiaoliang;YU Qifeng(College of Aerospace Science and Engineering,National University of Defense Technology,Changsha 410073,China;Hunan Key Laboratory of Videometrics and Vision Navigation,National University of Defense Technology,Changsha 410073,China;Shenyang Aircraft Design&Research Institute,Shenyang 110035,China)
出处
《国防科技大学学报》
EI
CAS
CSCD
北大核心
2021年第4期24-30,共7页
Journal of National University of Defense Technology
基金
湖南省自然科学基金资助项目(2019JJ50732)。
关键词
纹理随机化
仿真数据
目标检测
三维模型
texture randomization
simulation data
object detection
3D model
