View Independent Vehicle Make, Model and Color Recognition Using Convolutional Neural Network

TL;DR

This paper presents a deep convolutional neural network-based system for vehicle make, model, and color recognition that is accurate, efficient, and tested on multiple datasets, outperforming existing methods.

Contribution

The paper introduces a novel, computationally inexpensive CNN architecture trained on a large semi-automatically labeled dataset for vehicle recognition.

Findings

Outperforms other methods on all benchmarks

Achieves state-of-the-art accuracy

Demonstrates robustness across datasets

Abstract

This paper describes the details of Sighthound's fully automated vehicle make, model and color recognition system. The backbone of our system is a deep convolutional neural network that is not only computationally inexpensive, but also provides state-of-the-art results on several competitive benchmarks. Additionally, our deep network is trained on a large dataset of several million images which are labeled through a semi-automated process. Finally we test our system on several public datasets as well as our own internal test dataset. Our results show that we outperform other methods on all benchmarks by significant margins. Our model is available to developers through the Sighthound Cloud API at https://www.sighthound.com/products/cloud