arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.08882cs.CVcs.LG
收藏

用于视频对象分割的基于深度学习光流的运动对象提议

Moving Object Proposals with Deep Learned Optical Flow for Video Object Segmentation

Umass Amherst(马萨诸塞大学阿默斯特分校)

Ge Shi, Zhili Yang

AI总结:

提出一种结合无监督光流估计网络UnFlow和全卷积SegNet的神经网络架构,通过在DAVIS数据集上微调预训练模型,实现高效准确的视频运动对象分割。

摘要:

动态场景理解是计算机视觉界最受关注的领域之一。为了增强动态场景理解,采用神经网络进行像素级分割被广泛接受。最新的像素级分割研究结合了语义和运动信息,并取得了良好的性能。在本工作中,我们提出了一种最先进的神经网络架构,以准确高效地获取运动对象提议(MOP)。我们首先训练一个无监督卷积神经网络(UnFlow)来生成光流估计。然后,我们将光流网络的输出输入到一个全卷积SegNet模型中。我们工作的主要贡献是:(1)在全新的DAVIS数据集上微调预训练的光流模型;(2)利用具有编码器-解码器架构的全卷积神经网络来分割对象。我们使用TensorFlow开发了代码,并在AWS EC2实例上执行了训练和评估过程。

英文摘要:

Dynamic scene understanding is one of the most conspicuous field of interest among computer vision community. In order to enhance dynamic scene understanding, pixel-wise segmentation with neural networks is widely accepted. The latest researches on pixel-wise segmentation combined semantic and motion information and produced good performance. In this work, we propose a state of art architecture of neural networks to accurately and efficiently get the moving object proposals (MOP). We first train an unsupervised convolutional neural network (UnFlow) to generate optical flow estimation. Then we render the output of optical flow net to a fully convolutional SegNet model. The main contribution of our work is (1) Fine-tuning the pretrained optical flow model on the brand new DAVIS Dataset; (2) Leveraging fully convolutional neural networks with Encoder-Decoder architecture to segment objects. We developed the codes with TensorFlow, and executed the training and evaluation processes on an AWS EC2 instance.

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。

↑