arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.09609cs.CV
收藏

基于阴影去除的精细上下文阴影检测

Fine-Context Shadow Detection using Shadow Removal

Johns Hopkins University(约翰斯·霍普金斯大学)

Jeya Maria Jose Valanarasu, Vishal M. Patel

摘要:

当前的阴影检测方法在检测小的、不清楚的或具有模糊边缘的阴影区域时表现不佳。在这项工作中,我们试图从两个方面解决这个问题。首先,我们提出了一个精细的上下文感知阴影检测网络(FCSD-Net),在这里我们限制了感受野的大小,并专注于低级别的功能,以更好地学习精细的上下文特征。其次,我们提出了一种新的学习策略,称为恢复检测(R2 D),我们表明,当深度神经网络被训练用于恢复(阴影去除)时,它也会学习有意义的特征来描绘阴影掩模。为了利用这种互补性质的阴影检测和去除任务,我们训练辅助网络的阴影去除,并提出了一个互补的特征学习块(CFL)学习和融合有意义的功能,从阴影去除网络的阴影检测网络。我们使用跨多个数据集的R2 D学习策略训练所提出的网络FCSD-Net。三个公共阴影检测数据集(ISTD,SBU和UCF)的实验结果表明,我们的方法提高了阴影检测性能,同时能够检测到更好的上下文相比,最近的其他方法。

英文摘要:

Current shadow detection methods perform poorly when detecting shadow regions that are small, unclear or have blurry edges. In this work, we attempt to address this problem on two fronts. First, we propose a Fine Context-aware Shadow Detection Network (FCSD-Net), where we constraint the receptive field size and focus on low-level features to learn fine context features better. Second, we propose a new learning strategy, called Restore to Detect (R2D), where we show that when a deep neural network is trained for restoration (shadow removal), it learns meaningful features to delineate the shadow masks as well. To make use of this complementary nature of shadow detection and removal tasks, we train an auxiliary network for shadow removal and propose a complementary feature learning block (CFL) to learn and fuse meaningful features from shadow removal network to the shadow detection network. We train the proposed network, FCSD-Net, using the R2D learning strategy across multiple datasets. Experimental results on three public shadow detection datasets (ISTD, SBU and UCF) show that our method improves the shadow detection performance while being able to detect fine context better compared to the other recent methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑