Automatic Construction of a Recurrent Neural Network based Classifier for Vehicle Passage Detection

TL;DR

This paper presents an automated method for constructing LSTM-based RNN classifiers to detect vehicle passages using sensor data, replacing traditional handcrafted rule-based systems with learned models.

Contribution

It introduces an automatic approach for building RNN classifiers for vehicle detection, leveraging sensor data and eliminating manual rule crafting.

Findings

RNN classifiers outperform rule-based systems.

Automatic training achieves high detection accuracy.

Sensor data effectively informs the RNN model.

Abstract

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.