Road Traffic Conditions Classification Based on Multilevel Filtering of Image Content Using Convolutional Neural Networks

Pamuła, T.

doi:10.1109/mits.2018.2842040

Cited by 46 publications

(20 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A deep CNN that collectively counts the number of vehicles on a road segment based solely on video images, without special attention to an individual vehicle as an object to be detected separately, is proposed in [35]. A further CNN approach is proposed in [36] for classification of road traffic conditions based on video surveillance data, to establish measures of congestion of observed traffic. In [37], authors propose a unified online and offline learning framework for traffic sign detection, tracking, and recognition task using a mono-camera mounted on a moving vehicle.…”

Section: B Transportmentioning

confidence: 99%

Toward Intelligent Industrial Informatics: A Review of Current Developments and Future Directions of Artificial Intelligence in Industrial Applications

Silva

Sierla

Alahakoon

et al. 2020

EEE Ind. Electron. Mag.

View full text Add to dashboard Cite

Research, the universal pursuit of new knowledge, is embarking on a fresh journey into Artificial Intelligence (AI). Nature reports that AI arose nine places to fourth most popular search-term, and that search-terms machine-learning and deep-learning appeared in the top-20 search for the first time in 2018. It is pertinent for Industrial Informatics to embrace this renewed surge of interest in AI with clear direction and purpose that engages scholars, practitioners and professionals alike. This article aims to

show abstract

Section: B Transportmentioning

confidence: 99%

Toward Intelligent Industrial Informatics: A Review of Current Developments and Future Directions of Artificial Intelligence in Industrial Applications

Silva

Sierla

Alahakoon

et al. 2020

EEE Ind. Electron. Mag.

View full text Add to dashboard Cite

show abstract

“…Recently, Deep Learning (DL) models have achieved great success to overcome the complex problems of road traffic datasets [4]. Specifically, well-known DL models such as Deep Neural Network (DNN) [5], Recurrent Neural Network (RNN) [6], Convolutional Neural Network (CNN) [7], and Deep Reinforcement Learning (DQN) [8], [9] have been adopted for various applications in ITS as shown in Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

Traffic Density Classification Using Sound Datasets: An Empirical Study on Traffic Flow at Asymmetric Roads

Bui

2020

IEEE Access

View full text Add to dashboard Cite

Recently, with the rapid growth of Deep Learning models for solving complicated classification problems, urban sound classification techniques have been attracted more attention. In this paper, we take an investigation on how to apply this approach for the transportation domain. Specifically, traffic density classification based on the road sound datasets, which have been recorded and preprocessed on the urban road network, is taken into account. In particular, state-of-the-art methods for analyzing and extracting sound datasets have taken into account for the classification problem of traffic flow. Consequently, this study focuses on three main processes which are: i) generating image representation for the sequences of the road sound datasets; ii) proposing a convolutional neural network model for the feature extraction; iii) adopting a hybrid approach for the classification stage by combining convolutional neural network with other machine learning models. Regarding the experiment, the road sound dataset has been collected at an urban asymmetric road with different time periods (e.g., morning and evening) in order to evaluate our proposed method. Specifically, the implementations show promising results in which the accuracies are able to achieve from 92% to 95% for classifying traffic densities with different time periods. INDEX TERMS Intelligent transportation system, traffic density classification, urban sound classification, deep learning, convolutional neural network VOLUME 4, 2016 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.

show abstract

“…A classificação do fluxo de carros consiste em rotular a condição do trânsito de veículos na via, considerando algumas variáveis como o número de carros em um curto espaço de tempo e a velocidade média deles [10]. Em geral, na literatura há trabalhos classificando o trânsito em duas, três ou quatro classes distintas [11] [12] [13].…”

unclassified

“…Com o recente avanço do poder computacional para o processamento e armazenamento de dados, o uso das CNNs melhorou o rendimento em diversos campos de aplicação [21]. Por conseguinte, o emprego dessas técnicas nas abordagens holísticas envolvendo classificação e previsão do trânsito recebeu grande atenção nosúltimos anos [13] Luo et al [19] investigaram um método que não utiliza informações de movimento na cena. Para adquirir uma representação global do tráfego, os autores testaram quatro descritores visuais e dois modelos de CNN treinados no banco de dados ImageNet [23].…”

unclassified

See 1 more Smart Citation

Traffic Flow Classification using a Video Descriptor and a Convolutional Neural Network

Ribeiro

Samatelo

2019

Anais Do XV Workshop De Visão Computacional (WVC 2019)

View full text Add to dashboard Cite

Trafﬁc congestion is a signiﬁcant problem in urban cities and affects economic, health, and social questions. Although many works have been published in the last years to trafﬁc applications based on video data, different techniques of computer vision can be explored in this area. In this work, we proposed a method for trafﬁc ﬂow classiﬁcation using StarRGB and Convolutional Neural Networks (CNN). The StarRGB describes a global representation of the trafﬁc video into a colored image based on motion elements in the scene. Then, the generated image passed as input to a pre-trained CNN to extract the features and classify the trafﬁc video activity in three classes: LIGHT, MEDIUM, and HEAVY. In our experiments using a trafﬁc video database, the proposed method reached an accuracy of 96.47%. Also, the results suggest that StarRGB is a good descriptor for trafﬁc video applications.

show abstract

Road Traffic Conditions Classification Based on Multilevel Filtering of Image Content Using Convolutional Neural Networks

Cited by 46 publications

References 20 publications

Toward Intelligent Industrial Informatics: A Review of Current Developments and Future Directions of Artificial Intelligence in Industrial Applications

Toward Intelligent Industrial Informatics: A Review of Current Developments and Future Directions of Artificial Intelligence in Industrial Applications

Traffic Density Classification Using Sound Datasets: An Empirical Study on Traffic Flow at Asymmetric Roads

Traffic Flow Classification using a Video Descriptor and a Convolutional Neural Network

Contact Info

Product

Resources

About