Predicting Deeper into the Future of Semantic Segmentation

2017 IEEE International Conference on Computer Vision (ICCV)(2017)

引用 38|浏览203
暂无评分
摘要
The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene understanding for decision making. While prediction of the raw RGB pixel values in future video frames has been studied in previous work, here we introduce the novel task of predicting semantic segmentations of future frames. Given a sequence of video frames, our goal is to predict segmentation maps of not yet observed video frames that lie up to a second or further in the future. We develop an autoregressive convolutional neural network that learns to iteratively generate multiple frames. Our results on the Cityscapes dataset show that directly predicting future segmentations is substantially better than predicting and then segmenting future RGB frames. Prediction results up to half a second in the future are visually convincing and are much more accurate than those of a baseline based on warping semantic segmentations using optical flow.
更多
查看译文
关键词
semantic segmentation,utmost importance,autonomous driving,visual scene understanding,decision making,raw RGB pixel values,future video frames,predicting semantic segmentations,future frames,segmentation maps,autoregressive convolutional neural network,multiple frames,predicting future segmentations,future RGB frames,prediction results,Cityscapes dataset,optical flow
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要