Dhaivat Bhatt*1 Danish Sodhi*1 Arghya Pal2 Vineeth Balasubramanian2 K. Madhava Krishna1
Long-short term memory networks(LSTM) mod- els have shown considerable performance on variety of prob- lems dealing with sequential data. In this paper, we pro- pose a variant of Long-Term Recurrent Convolutional Net- work(LRCN) to detect road intersection. We call this network as IntersectNet. We pose road intersection detection as binary classification task over sequence of frames. The model combines deep hierarchical visual feature extractor with recurrent se- quence model. The model is end to end trainable with capability of capturing the temporal dynamics of the system. We exploit this capability to identify road intersection in a sequence of temporally consistent images. The model has been rigorously trained and tested on various different datasets. We think that our findings could be useful to model behavior of autonomous agent in the real-world.