A deep convolutional neural network based approach for vehicle classification using large-scale GPS trajectory data

Dabiri, Sina; Marković, Nikola; Heaslip, Kevin; Reddy, Chandan K.

doi:10.1016/j.trc.2020.102644

Cited by 34 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Need for online VDCMost of the approaches reviewed in this paper worked on static images or videos previously captured by surveillance or aerial cameras, and less work has been done on real‐time videos. Research is necessary to extend online VDC systems and evaluate their performance according to the motion and dynamic characteristics of vehicles 40,41,75,86,125,167 Need for combining multiple types of sensorsMost of the research studies examined in this study only utilized vision sensors for detecting vehicles 44,67,71,102,138,161 .…”

Section: Discussionmentioning

confidence: 99%

“…However, VDC systems can be much more powerful if they use a combination of visual sensors and other types of sensors such as acoustic signal detection sensors. Identifying special types of vehiclesSome vehicles are built under specific conditions, customized for special use, or the owners of vehicles have made changes in the appearance of vehicles that will make them difficult to identify. Existing VDC systems can be strengthened to identify vehicles with special characteristics 29,40,161 Integrating different appearance‐based featuresIn the reviewed work, the detection was usually performed by one or eventually two features such as color, model, and type.…”

Section: Discussionmentioning

confidence: 99%

“… Light conditions: Lighting conditions mixed with glare on a vehicle, bright sunlight, shadows of objects upon a vehicle, and darkness of night have negative effects on the quality of images 13 Environmental conditions: Different weather conditions such as sunny, foggy, rainy, cloudy, and snowy weather diminish the quality of images 40,75 Delay in processing aerial imagesEvery pixel in an aerial image is a large area on the ground.…”

Section: Discussionmentioning

confidence: 99%

“…After all, the classified vehicles are ready to be used in different domains and applications such as VANETs, 7 IoV, 8 intelligent transportation, 10,36–38 traffic congestion avoidance, 4,32 navigation systems, 39–41 traffic/vehicular surveillance, 1,16 accident prevention, 33–35,37 insurance (rating), 2 unmanned aerial vehicle control, 4,10,36,38 and communication systems, 42–45 among others.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

See 3 more Smart Citations

A new comparison framework to survey neural networks‐based vehicle detection and classification approaches

Hashemi

Emami

Sangar

2021

Int J Communication

View full text Add to dashboard Cite

Summary The vehicle detection and classification (VDC) problem has received much attention recently due to the increased security threats and the need to develop intelligent transportation systems. A large number of approaches have been proposed for the VDC problem using neural networks. To determine how neural networks‐based approaches have developed for the VDC in recent years, this paper surveys the VDC approaches through a literature review with the range Jan. 2012 through Apr. 2021. To do this, we introduce a new comparison framework to classify and compare the VDC approaches. Our proposed framework is composed of nine comparison dimensions: input data type, vehicle type, scale, scope, dynamicity, vehicle detection method, vehicle classification method, application, and evaluation method. Next, using the proposed framework, we discuss the evolution of the VDC approaches and identify several open issues that have emerged in the field. This paper provides a guide for researchers to use or design robust VDC systems with proper characteristics based on their needs.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Theoretical Backgroundmentioning

confidence: 99%

See 2 more Smart Citations

A new comparison framework to survey neural networks‐based vehicle detection and classification approaches

Hashemi

Emami

Sangar

2021

Int J Communication

View full text Add to dashboard Cite

show abstract

“…The proposed method did follow this principle, that is, movement features including speed, acceleration, jerk, and bearing rate were calculated between every two consecutive points, and then using a specially designed network based on CNN to learn the highlevel features from point-level features for further predicting the classes. As an improvement, another study by Dabiri et al [34] introduced roadway features to combine with movement features, including the number of intersections, number of maneuvers, and road type. All features of a GPS leg (the route segment between two consecutive GPS points) were stacked into a vector for later input into the CNN network.…”

Section: Related Workmentioning

confidence: 99%

Dual Supervised Autoencoder Based Trajectory Classification Using Enhanced Spatio-Temporal Information

Xia

2020

IEEE Access

View full text Add to dashboard Cite

With the rapid development of mobile internet and location awareness techniques, massive spatio-temporal data is collected every day. Trajectory classification is critically important to many realworld applications such as human mobility understanding, urban planning, and intelligent transportation systems. A growing number of studies took advantage of the deep learning method to learn the high-level features of trajectory data for accurate estimation. However, some of these studies didn't interpret spatiotemporal information well, more importantly, they didn't fully utilize the high-level features extracted by neural networks. To overcome these drawbacks, this paper utilizes the proposed stop state and turn state to enhance spatial information, and at the same time, extracts stronger time information via Recurrence Plot (RP). Moreover, a novel Dual Convolutional neural networks based Supervised Autoencoder (Dual-CSA) is proposed by making the network aware of Predefined Class Centroids (PCC). Experiments conducted on two real-world datasets demonstrate that Dual-CSA can learn the high-level features well. The highest accuracy of the Geolife and SHL datasets are 89.475% and 89.602%, respectively, proving the superiority of our method.

show abstract

A deep semi-supervised machine learning algorithm for detecting transportation modes based on GPS tracking data

Sadeghian,

Golshan,

Zhao

et al. 2024

Transportation

View full text Add to dashboard Cite

Transportation research has benefited from GPS tracking devices since a higher volume of data can be acquired. Trip information such as travel speed, time, and most visited locations can be easily extracted from raw GPS tracking data. However, transportation modes cannot be extracted directly and require more complex analytical processes. Common approaches for detecting travel modes heavily depend on manual labelling of trajectories with accurate trip information, which is inefficient in many aspects. This paper proposes a method of semi-supervised machine learning by using minimal labelled data. The method can accept GPS trajectory with adjustable length and extract latent information with long short-term memory (LSTM) Autoencoder. The method adopts a deep neural network architecture with three hidden layers to map the latent information to detect transportation mode. The proposed method is assessed by applying it to the case study where an accuracy of 93.94% can be achieved, which significantly outperforms similar studies.

show abstract

A deep convolutional neural network based approach for vehicle classification using large-scale GPS trajectory data

Cited by 34 publications

References 12 publications

A new comparison framework to survey neural networks‐based vehicle detection and classification approaches

A new comparison framework to survey neural networks‐based vehicle detection and classification approaches

Dual Supervised Autoencoder Based Trajectory Classification Using Enhanced Spatio-Temporal Information

A deep semi-supervised machine learning algorithm for detecting transportation modes based on GPS tracking data

Contact Info

Product

Resources

About