Identifying and Counting Vehicles in Multiple Lanes by Using a Low-Cost Vehicle-Mounted Sensor for Intelligent Traffic Management Systems

Namazi, Elnaz; Li, Jingyue; Mester, Rudolf; Lu, Chaoru

doi:10.1007/978-3-030-61705-9_49

Cited by 4 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our recent studies [9], [10], data were collected with a vehicle equipped with a monocular camera with a built-in GPS receiver. The purposes of those studies were to use the ego-vehicle as a mobile sensor, estimating traffic data for surrounding vehicles, in order to share them with ITMS.…”

Section: Methodsmentioning

confidence: 99%

Improving Vehicle Localization with Two Low-Cost GPS Receivers

Namazi

Mester

et al. 2022

Lecture Notes in Networks and Systems

Self Cite

View full text Add to dashboard Cite

A primary concern of intelligent traffic management systems (ITMS) is to collect necessary traffic data. Vehicle position is one of the most important data types to manage traffic effectively. Most current approaches to localize modern vehicles (MVs) fall into three categories. The first category uses standalone reference stations, such as the wide-area augmentation system (WAAS), which are expensive modules. The second category uses multiple expensive localization sensors such as the global positioning system (GPS), global navigation satellite system (GNSS), and inertial measurement unit (IMU). However, such expensive solutions may not be applicable in all vehicles, impacting generalizability. The third category is a software-based approach. As opposed to the abovementioned approaches using expensive hardware, the third category uses software, such as map-matching techniques, to augment noisy localization sensors. In this study, we investigated map-matching software in some case studies and found that it cannot locate the vehicle effectively if the positional data are collected by a low-cost and too noisy GPS receiver. Therefore, this paper analyzes and highlights the impact of GPS receiver's noise in applying self-localization. It also proposes a new methodology by integrating cross-GPS validation, interpolation/best fit, and map-matching techniques to localize a vehicle in the presence of GPS signal noise and investigate it in real traffic data from a metropolitan area. Our proposed methodology is able to identify the more accurate GPS receiver dynamically, by considering the fixed distance between the two GPS receivers. Our evaluations indicate that the proposed methodology can significantly improve vehicle self-localization performance.

show abstract

Section: Methodsmentioning

confidence: 99%

Improving Vehicle Localization with Two Low-Cost GPS Receivers

Namazi

Mester

et al. 2022

Lecture Notes in Networks and Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…To detect lanes, as we presented in [8] and [9], we used canny edge detection [27] and the progressive probabilistic Hough transform [28][29].…”

Section: Ii) Approach 2: Geometric Computationmentioning

confidence: 99%

“…Therefore, in this paper, we go beyond the lane-level target-vehicle localization presented in [9] and find the latitude and longitude of a target vehicle in a GPS coordinate system dynamically while both the ego vehicle and the target vehicle are moving in a metropolitan area. Although some research has been carried out on utilizing an ego vehicle as a mobile sensor to estimate traffic data of the target vehicle, there is still very little scientific understanding of estimating the geolocation of HDVs based on ego-vehicle self-localization, image-based estimated distance to the target vehicle, and the relative angle between them by using a monocular camera with a built-in GPS receiver mounted on a mobile ego vehicle.…”

Section: Introductionmentioning

confidence: 99%

“…To address this research question, we proposed two approaches based on (1) object detection and image processing and (2) geometric computation by considering the camera's pitch angle and height from the road surface. In this regard, we extended the proposed algorithms presented in [9] by including the estimation of the distance and angle between the ego vehicle and the target vehicle.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Geolocation estimation of target vehicles using image processing and geometric computation

Namazi¹,

Mester²,

Lu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Estimating vehicles' locations is one of the key components in intelligent traffic management systems (ITMSs) for increasing traffic scene awareness. Traditionally, stationary sensors have been employed in this regard. The development of advanced sensing and communication technologies on modern vehicles (MVs) makes it feasible to use such vehicles as mobile sensors to estimate the traffic data of observed vehicles. This study aims to explore the capabilities of a monocular camera mounted on an MV in order to estimate the geolocation of the observed vehicle in a global positioning system (GPS) coordinate system.We proposed a new methodology by integrating deep learning, image processing, and geometric computation to address the observed-vehicle localization problem. To evaluate our proposed methodology, we developed new algorithms and tested them using real-world traffic data. The results indicated that our proposed methodology and algorithms could effectively estimate the observed vehicle's latitude and longitude dynamically.

show abstract

“…The proposed technique outperformed the conventional CNN in-vehicle image analysis, according to experimental observations. Furthermore, Namazi et al [15] invented different methods to enhance a traffic control system when there is a mix of modern vehicles and human-driven vehicles with varying degrees of autonomy. The results indicated that the algorithms can correctly determine the type of detected vehicle in the widely researched scenarios 95.21% of the time.…”

Section: Literature Reviewmentioning

confidence: 99%

Effective Two-Lane Traffic Management at the University of Ibadan, Nigeria Main Gate Using Multiple Vehicle Recognition Systems

Adebayo¹,

Olusola²,

Kazeem³

et al. 2022

IJSSE

View full text Add to dashboard Cite

Traffic congestion and management have posed a major challenge to many cities in the world. Intelligent traffic management system plays an important role in monitoring and enforcing traffic laws with reduced labor. This paper uses vehicle information recognition to identify unpermitted lane shunting at the University of Ibadan main gate. The vehicle recognition system captures three main details of the vehicle; its license plate, make, and colour to ensure the system, which is named UiScope, is robust enough. Machine learning and deep learning algorithms including Convolutional Neural Network (CNN), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms are used to train classifiers for vehicle make, license plate, and colour recognition. The captured details are uploaded on a Structured Query Language (SQL) database to create a blacklist of vehicles that are shunted. The querying of the database is used to determine the shunted vehicle. The success rate for plate identification is 92%, character segmentation is 87%, character recognition is 75%, and vehicle colour recognition is 78%.

show abstract

Identifying and Counting Vehicles in Multiple Lanes by Using a Low-Cost Vehicle-Mounted Sensor for Intelligent Traffic Management Systems

Cited by 4 publications

References 18 publications

Improving Vehicle Localization with Two Low-Cost GPS Receivers

Improving Vehicle Localization with Two Low-Cost GPS Receivers

Geolocation estimation of target vehicles using image processing and geometric computation

Effective Two-Lane Traffic Management at the University of Ibadan, Nigeria Main Gate Using Multiple Vehicle Recognition Systems

Contact Info

Product

Resources

About