Abstract
This paper presents a novel approach for segmenting moving objects in unconstrained environments using guided convolutional neural networks. This guiding process relies on foreground masks from independent algorithms (i.e. state-of-the-art algorithms) to implement an attention mechanism that incorporates the spatial location of foreground and background to compute their separated representations. Our approach initially extracts two kinds of features for each frame using colour and optical flow information. Such features are combined following a multiplicative scheme to benefit from their complementarity. These unified colour and motion features are later processed to obtain the separated foreground and background representations. Then, both independent representations are concatenated and decoded to perform foreground segmentation. Experiments conducted on the challenging DAVIS 2016 dataset demonstrate that our guided representations not only outperform non-guided, but also recent and top-performing video object segmentation algorithms.
Abstract (translated)
本文提出了一种新的无约束环境下运动目标分割方法。这一指导过程依赖于来自独立算法(即最先进的算法)的前景遮罩来实现一种注意力机制,该机制结合前景和背景的空间位置来计算它们的分离表示。我们的方法首先使用颜色和光流信息为每个帧提取两种特征。这些特征结合在一个乘法方案之后,以得益于它们的互补性。这些统一的颜色和运动特征随后被处理,以获得分离的前景和背景表示。然后,将两个独立的表示连接起来并解码,以执行前景分割。对具有挑战性的Davis 2016数据集进行的实验表明,我们的引导表示不仅优于非引导表示,而且优于最新和最先进的视频对象分割算法。
URL
https://arxiv.org/abs/1904.11256