Automatic Construction of a Recurrent Neural Network based Classifier for Vehicle Passage Detection
This work addresses vehicle detection for checkpoint monitoring, but it is incremental as it applies an existing RNN method to a specific sensor data task.
The authors tackled the problem of vehicle passage detection at checkpoints by proposing an automatic LSTM-RNN classifier that replaces handcrafted deterministic rules, achieving successful detection as demonstrated in their results.
Recurrent Neural Networks (RNNs) are extensively used for time-series modeling and prediction. We propose an approach for automatic construction of a binary classifier based on Long Short-Term Memory RNNs (LSTM-RNNs) for detection of a vehicle passage through a checkpoint. As an input to the classifier we use multidimensional signals of various sensors that are installed on the checkpoint. Obtained results demonstrate that the previous approach to handcrafting a classifier, consisting of a set of deterministic rules, can be successfully replaced by an automatic RNN training on an appropriately labelled data.