Image Caption Description of Traffic Scene Based on Deep Learning
Shiru Qu, Yuling Xi, Songtao Ding · Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University · 2018
It is a hard issue to describe the complex traffic scene accurately in computer vision. The traffic scene is changeable, which causes image captioning easily interfered by light changes and object occlusion. To solve this problem, we propose an image caption generation model based on attention mechanism. Combining convolutional neural network (CNN) and recurrent neural network (RNN) to generate an end-to-end description for traffic images. To generate a semantic description with distinct degree of discrimination, the attention mechanism is applied to language model. Using Flickr8K、Flickr30K and MS COCO benchmark datasets to validate the effectiveness of our method. The accuracy is promoted maximally by 8.6%, 12.4%, 19.3% and 21.5% in different evaluation metrics. Experiments show that our algorithm has good robustness in four different complex traffic scenarios, such as light change, abnormal weather environment, road marked target and various kinds of transportation tools.