Object class segmentation of RGB-D video using recurrent convolutional neural networks
Object class segmentation of RGB-D video using recurrent convolutional neural networks
复制标题
DOI：
10.1016/j.neunet.2017.01.003
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
M. Pavel;Hannes Schulz;Sven Behnke
中科院分区：
文献类型：
--
作者：
M. Pavel;Hannes Schulz;Sven Behnke
对象分类分割是一项计算机视觉任务，它需要将图像的每个像素标记为其所属的对象类别。深度卷积神经网络（DNN）能够学习并利用该任务所需的局部空间相关性。然而，它们受到固定大小的小过滤器的限制，这限制了它们学习长期依赖关系的能力。另一方面，循环神经网络（RNN）不受这种限制。他们的迭代解释允许他们通过传播活动来建模远程依赖关系。这个属性在标记视频序列时特别有用，其中空间和时间的长期依赖关系都发生了。在这项工作中，提出了一种新的用于对象类分割的RNN架构。我们研究了几种训练这种网络的方法。我们在具有挑战性的NYU Depth v2数据集上评估了我们的模型，并获得了具有竞争力的结果。
Object class segmentation is a computer vision task which requires labeling each pixel of an image with the class of the object it belongs to. Deep convolutional neural networks (DNN) are able to learn and take advantage of local spatial correlations required for this task. They are, however, restricted by their small, fixed-sized filters, which limits their ability to learn long-range dependencies. Recurrent Neural Networks (RNN), on the other hand, do not suffer from this restriction. Their iterative interpretation allows them to model long-range dependencies by propagating activity. This property is especially useful when labeling video sequences, where both spatial and temporal long-range dependencies occur. In this work, a novel RNN architecture for object class segmentation is presented. We investigate several ways to train such a network. We evaluate our models on the challenging NYU Depth v2 dataset for object class segmentation and obtain competitive results.