Vehicle classification and counting system

Chen, Chun-Yu; Liang, Yu-Ming; Chen, Sei-Wang

doi:10.1109/icalip.2014.7009841

Cited by 13 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [23], the generated TSI was processed by a self‐adaptive sample consensus background model and then counted vehicles. In [24], a method based on ROI accumulative curve method and the fuzzy constraints satisfaction propagation was designed to count vehicles in TSI. These processes on TSI are also based on BS methods; hence the performance of these methods may fall when dealing with serious occlusions or clustered scenes.…”

Section: Related Workmentioning

confidence: 99%

Vehicle counting and traffic flow parameter estimation for dense traffic scenes

Chang

Liu

et al. 2020

IET intell. transp. syst

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Vehicle counting and traffic flow parameter estimation for dense traffic scenes

Chang

Liu

et al. 2020

IET intell. transp. syst

View full text Add to dashboard Cite

“…Hasilnya, Algoritma yang digunakan berfungsi dengan baik untuk mengklasifikasi dan menghitung informasi setiap kategori kendaraan yang lewat. [5] Penelitian yang dilakukan (…”

Section: Pendahuluanunclassified

Pengenalan Dan Perhitungan Kendaraan Sepeda Motor Pada Video Lalu Lintas Menggunakan Teknik Background Subtraction

Suardi¹,

Setyanto²,

Kurniawan³

2020

jtir

View full text Add to dashboard Cite

INTISARIKlasifikasi kendaraan adalah bagian penting dari Sistem Smart Transportasi. Dalam penelitian ini, didedikasikan untuk presentasi sistem untuk penghitungan dan deteksi kendaraan bermotor. Pengolahan video digunakan untuk mengklasifikasikan kendaraan di jalur khusus. Dimana diharapkan dapat membantu mengurangi tingkat kecelakaan akibat pelanggaran lalu lintas yang disebabkan oleh pengendara yang melawan arus pada jalan satu arah. Kami mengusulkan algoritma background subtraction untuk mendeteksi piksel foreground sesuai dengan kendaraan yang bergerak. Prinsip sistem ini adalah menggunakan kamera statis, kondisi dimana kamera dalam keadaan stabil. Sistem ini mencakup proses pengambilan video, klasifikasi kendaraan dan penghitungan kendaraan. Kata kunci— deteksi kendaraan, traffic information, background subtraction, analisis video, klasifikasi. ABSTRACT Vehicle classification is an important part of the Smart Transportation System. In this study, it was challenging to present a system for counting and detection of transition vehicles. Processing video used to classify vehicles on a special lane. Which is expected to help reduce the level of traffic accidents passed by motorists who oppose the flow on one-way streets. We request a background reduction algorithm to move the foreground pixels according to the moving vehicle. The principle of this system uses a statistical camera, a condition where the camera is stable. This system regulates the process of video capture, vehicle classification and vehicle calculation. Kata kunci— vehicle detection, traffic information, background subtraction, video analytics, clasification.

show abstract

“…In [23], shape based multi-class classification model was developed where the concavity property of vehicles like buses and sedans were used for detection classification; however it could not address the issue of tracking under occlusion or dynamic background conditions. A DBN was designed in [24] where HOG features and Eigen features were used together to perform vehicle detection and tracking.Unlike single base classifier based approaches, authors applied ensemble classification with SVM, K-NN, random forest and multiple-layer perceptrons (MLPs) algorithms.In [25], vehicle morphology was used where to deal with occlusionROI accumulative curve method and Fuzzy Constraints Satisfaction Propagation (FCSP) were developed. Retrieving the Time-Spatial Images (TSI) from the surveillance video, they eliminated shadowed region using SVM and Deterministic Non-Model Scheme (DNMS).…”

Section: Related Workmentioning

confidence: 99%

Distinctly Trained Multi-Source CNN for Multi-Camera Based Vehicle Tracking System

Harsha¹,

Simhadri²,

Katragadda³

et al. 2019

IJRTE

View full text Add to dashboard Cite

In the last few years the exponential rise in the demands or robust surveillance systems have revitalized academia-industries to achieve more efficient vision based computing systems. Vision based computing methods have been found potential for the different surveillance purposes such as Intelligent Transport System (ITS), civil surveillance, defense and other public-private establishment security. However, computational complexities turn-out to be more complicate for ITS under occlusion where multiple cameras could be synchronized together to track certain target vehicle. Classical texture, color based approaches are confined and often leads false positive outcome thus impacting decision making efficiency. Considering this as motivation, in this paper a highly robust and novel Distinctly Trained Multi-Source Convolutional Neural Network (DCNN) has been developed that exhibits pre-training of the real-time traffic videos from multiple cameras to track certain targeted vehicle. Our proposed DCNNvehicle tracking model encompasses multiple shared layers with multiple branchesof the source-specific layers. In other words, DCNN is implemented on each camera or source where it performs feature learning and enables a set of features shared by each camera, which is then learnt to identify Region of Interest (ROI) signifying the “targeted vehicle”. Our proposed DCNNmodel trains each source input iteratively to achieve ROI representations in the shared layers. To perform tracking in a new sequence, DCNNforms a new network by combining the shared layers in the pre-trained DCNN with a new binary classification layer, which is updated online. This process enables online tracking by retrieving the ROI windows arbitrarily sampled near the previous ROI state. It helps achieving real-time vehicle tracking even under occlusion and dynamic background conditions.

show abstract

Vehicle classification and counting system

Cited by 13 publications

References 9 publications

Vehicle counting and traffic flow parameter estimation for dense traffic scenes

Vehicle counting and traffic flow parameter estimation for dense traffic scenes

Pengenalan Dan Perhitungan Kendaraan Sepeda Motor Pada Video Lalu Lintas Menggunakan Teknik Background Subtraction

Distinctly Trained Multi-Source CNN for Multi-Camera Based Vehicle Tracking System

Contact Info

Product

Resources

About