A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning

TL;DR

This paper introduces a large, diverse dataset of overhead car images for training deep learning models to classify, detect, and count cars, along with a novel counting method that is fast, accurate, and adaptable to different objects and scenes.

Contribution

The paper presents a new large dataset for car classification, detection, and counting, and proposes a novel counting approach using ResCeption that is scene-agnostic and easy to implement.

Findings

ResCeption achieves accurate car counting in overhead images.

The dataset improves training for classification and detection tasks.

Counting method generalizes to different objects and scenes.

Abstract

We have created a large diverse set of cars from overhead images, which are useful for training a deep learner to binary classify, detect and count them. The dataset and all related material will be made publically available. The set contains contextual matter to aid in identification of difficult targets. We demonstrate classification and detection on this dataset using a neural network we call ResCeption. This network combines residual learning with Inception-style layers and is used to count cars in one look. This is a new way to count objects rather than by localization or density estimation. It is fairly accurate, fast and easy to implement. Additionally, the counting method is not car or scene specific. It would be easy to train this method to count other kinds of objects and counting over new scenes requires no extra set up or assumptions about object locations.