Flood extent mapping plays a crucial role in disaster management and national water forecasting. Unfortunately, traditional classification methods are often hampered by the existence of noise, obstacles and heterogeneity in spectral features as well as implicit anisotropic spatial dependency across class labels. In this paper, we propose geographical hidden Markov tree, a probabilistic graphical model that generalizes the common hidden Markov model from a one dimensional sequence to a two dimensional map. Anisotropic spatial dependency is incorporated in the hidden class layer with a reverse tree structure. We also investigate computational algorithms for reverse tree construction, model parameter learning and class inference. Extensive evaluations on both synthetic and real world datasets show that proposed model outperforms multiple baselines in flood mapping, and our algorithms are scalable on large data sizes.

No abstract

No abstract

No abstract

Each year, an average of around 6 million car accidents occur in the United States. Road safety features (e.g., concrete barriers, metal crash barriers, rumble strips) play an important role in preventing or mitigating vehicle crashes. Accurate maps of road safety features is an important component of safety management systems for federal or state transportation agencies, helping traffic engineers identify locations to invest in safety infrastructure. In current practice, mapping road safety features is largely done manually (e.g., observations on the road or visual interpretation of streetview imagery), which is both expensive and time consuming. In this article, we propose a deep learning approach to automatically map road safety features from streetview imagery. Unlike existing convolutional neural networks that classify each image individually, we propose to further add a recurrent neural network (long short-term memory) to capture geographic context of images (spatial autocorrelation effect along linear road network paths). Evaluations on real-world streetview imagery show that our proposed model outperforms several baseline methods.