Vehicle 24-Color Long Tail Recognition Based on Smooth Modulation Neural Network with Multi-layer Feature Representation

TL;DR

This paper introduces a new neural network model, SMNN-MFR, for vehicle color recognition that handles 24 color categories with high accuracy, outperforming existing methods and providing a new benchmark dataset.

Contribution

The paper develops a novel Smooth Modulated Neural Network with Multi-layer Feature Representation for improved vehicle color recognition on a new 24-color dataset.

Findings

Achieved 94.96% average recognition accuracy on 24 vehicle colors.

Outperformed Faster RCNN by 33.47% in recognition accuracy.

Validated effectiveness of each network module through visualization and ablation studies.

Abstract

Vehicle color recognition plays an important role in intelligent traffic management and criminal investigation assistance. However, the current vehicle color recognition research involves at most 13 types of colors and the recognition accuracy is low, which is difficult to meet practical applications. To this end, this paper has built a benchmark dataset (Vehicle Color-24) that includes 24 types of vehicle colors, including 10091 vehicle pictures taken from 100 hours of urban road surveillance videos. In addition, in order to solve the problem of long tail distribution in Vehicle Color-24 dataset and low recognition rate of existing methods, this paper proposes a Smooth Modulated Neural Network with Multi-layer Feature Representation (SMNN-MFR) is used for 24 types of vehicle color recognition. SMNN-MFR includes four parts: feature extraction, multi-scale feature fusion, suggestion frame generation and smooth modulation. The model is trained and verified on the Vehicle Color-24 benchmark dataset. Comprehensive experiments show that the average recognition accuracy of the algorithm in the 24 categories of color benchmark databases is 94.96%, which is 33.47% higher than the Faster RCNN network. In addition, the average accuracy rate of the model when recognizing 8 types of colors is 97.25%, and the detection accuracy of algorithms in similar databases is improved. At the same time, visualization and ablation experiments also proved the rationality of our network settings and the effectiveness of each module. The code and database are published at: https://github.com/mendy-2013.