A traffic sign detection method based on deep attribute learning was proposed.To make up the gap between raw image and high level semantics,three visual attributes,including shape,color and pattern,were introduced.Attribute learning was added to train Convolutional Neural Network(CNN), where attribute learning and classification learning were carried out simultaneously.Experimental results on datasets Sweden Traffic Sign Detection Dataset(STSD)and German Traffic Sign Detection Dataset(GTSD)show that the pro...
| 
推荐 
点击下列相关研究机构和相关文献作者，可以直接查到这些机构和作者被《中国知识资源总库》收录的其它文献，使您全面了解该机构和该作者的研究动态和历史。
