Unsupervised image transformation for outdoor semantic labelling
Unsupervised image transformation for outdoor semantic labelling
复制标题
DOI：
10.1109/ivs.2015.7225740
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
G. Ros;J. Álvarez
中科院分区：
文献类型：
--
作者：
G. Ros;J. Álvarez
城市图像的语义标记是自动驾驶的关键组成部分。当前方法的准确性高度依赖于所使用的训练集，并且当测试图像中的分布与训练集的预期分布不匹配时，准确性急剧下降。这种情况将不可避免地发生，例如，当照明从白天变为黄昏时。为了解决这个问题，我们提出了一种快速的无监督图像变换方法，遵循全局颜色转移策略。我们的建议将经典的一对一颜色转移方案推广到更合适的一对多方案。此外，我们的方法可以自然地处理视频流的时间一致性，以执行一致的变换。我们在两个公开的数据集中使用不同的最先进的语义标签框架展示了我们的建议的好处。
Semantic labelling of urban images is a crucial component towards autonomous driving. The accuracy of current methods is highly dependent on the training set being used and drops drastically when the distribution in the test image does not match the expected distribution of the training set. This situation will inevitably occur, as for instance, when the illumination changes from daytime to dusk. To address this problem we propose a fast unsupervised image transformation approach following a global color transfer strategy. Our proposal generalizes classical one-to-one color transfer schemes to the more suitable one-to-many scheme. In addition, our approach can naturally deal with the temporal consistency of video streams to perform a coherent transformation. We demonstrate the benefits of our proposal in two publicly available datasets using different state-of-the-art semantic labelling frameworks.