Gaussian Mixture Models optimization for counting the numbers of vehicle by adjusting the Region of Interest under heavy traffic condition

Basri, Basri; Indrabayu, -; Achmad, Andani

doi:10.1109/isitia.2015.7219986

Cited by 12 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas the type of motorbike vehicle (Roda 2) uses a contour with a width < 221 and height > 100. area < 5000. Based on the equation in [6], the accuracy value of the type of vehicle can be seen in Table 1. Table 1 has an average value of detection of motorbike and car type detection is 91%.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Tracking of Vehicle Tax Violations Using Vehicle Type and Plate Number Identification

Jaya¹,

Zainuddin²,

Syarif³

2019

Proceedings of the 1st International Conference on Science and Technology, ICOST 2019, 2-3 May, Makassar, Indonesia

View full text Add to dashboard Cite

This paper describes tracking violations of vehicle tax using the identification of type and number plates on vehicles. The case study of this research is in Sulawesi Selatan (Indonesia). The Gaussian Mixture Model (GMM) algorithm is used to detect vehicle types and the Automatic Number Plate Recognition (ANPR) algorithm for detecting vehicle license numbers. The proposed system uses a digital camera with a camera height of 250 cm and a camera tilt angle of 55 degrees. The proposed system design is the stages of preprocessing, feature extraction, feature selection, model selection, and database. For the introduction of types of vehicles are classified based on predetermined ROI while the introduction of vehicle numbers is trained using k-Nearest Neighbor (KNN). The results of the proposed system accuracy are 91% for vehicle type detection and 70% for vehicle license number detection.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Research related to the detection of vehicle types has been carried out by researchers. In [6], Indrabayu et al used the Gaussian Mixture Model (GMM) method for vehicle detection and Kalman Filter for object tracking. Researchers used the Region of Interest (ROI) from vehicle features for car and motorbike classifications.…”

Section: Introductionmentioning

confidence: 99%

Tracking of Vehicle Tax Violations Using Vehicle Type and Plate Number Identification

Jaya¹,

Zainuddin²,

Syarif³

2019

Proceedings of the 1st International Conference on Science and Technology, ICOST 2019, 2-3 May, Makassar, Indonesia

View full text Add to dashboard Cite

show abstract

“…GMM for multimodal background model is an effective method [8]. Modelling each pixel with GMM that being considered as one of the best models can describe the scene properly.…”

Section: Foreground Segmentation and The Flight Block Trackingmentioning

confidence: 99%

A Robust Vision-based Method for Real-time Flight Parking Bays Monitoring

Shen¹,

Dong²,

Mao³

2016

Proceedings of the 2015 International Conference on Mechanical Science and Engineering

View full text Add to dashboard Cite

The arrival and departure time sampling of the flight is one of the key information for parking bays monitoring to avoid conflict. Nowadays the time is reported and recorded by hand in many airports, which fault and delay reports may happen. Safety risks and lower efficiency cannot be neglected. This paper presents a robust vision-based method to automatically sample the arrival and departure time on the bays by flight move tracking and keep the flight under intelligent surveillance with the camera in the ramp. Based on the Gaussian Mixture Model algorithm, the improved method provided successfully solves the light changing disturbance and other moving object influence with Optical Flow Methods, which has been applied in the eighty seven bays of Shanghai Hongqiao International Airport that is one of the major airports in China. The practical result shows that the accuracy rate is above 90% and the missed alarm rate below 1%.

show abstract

“…The method involves dividing each frame into several pixels and modeling each pixel based on certain rules. A single Gaussian is used for a pixel having a single lighting surface, whereas an adaptive Gaussian is used to approximate multiple surfaces and changing lighting conditions [14]. Objects are detected by grouping Gaussian values that do not match those of the previous frame using connected components.…”

Section: Introductionmentioning

confidence: 99%

Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model

Majumder

Wilmot

2023

J. Imaging

View full text Add to dashboard Cite

Different techniques are being applied for automated vehicle counting from video footage, which is a significant subject of interest to many researchers. In this context, the You Only Look Once (YOLO) object detection model, which has been developed recently, has emerged as a promising tool. In terms of accuracy and flexible interval counting, the adequacy of existing research on employing the model for vehicle counting from video footage is unlikely sufficient. The present study endeavors to develop computer algorithms for automated traffic counting from pre-recorded videos using the YOLO model with flexible interval counting. The study involves the development of algorithms aimed at detecting, tracking, and counting vehicles from pre-recorded videos. The YOLO model was applied in TensorFlow API with the assistance of OpenCV. The developed algorithms implement the YOLO model for counting vehicles in two-way directions in an efficient way. The accuracy of the automated counting was evaluated compared to the manual counts, and was found to be about 90 percent. The accuracy comparison also shows that the error of automated counting consistently occurs due to undercounting from unsuitable videos. In addition, a benefit–cost (B/C) analysis shows that implementing the automated counting method returns 1.76 times the investment.

show abstract

Gaussian Mixture Models optimization for counting the numbers of vehicle by adjusting the Region of Interest under heavy traffic condition

Cited by 12 publications

References 5 publications

Tracking of Vehicle Tax Violations Using Vehicle Type and Plate Number Identification

Tracking of Vehicle Tax Violations Using Vehicle Type and Plate Number Identification

A Robust Vision-based Method for Real-time Flight Parking Bays Monitoring

Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model

Contact Info

Product

Resources

About