Video-Based Detection, Counting and Classification of Vehicles Using OpenCV

Veni, Shriharsha S.; Hiremath, Ananda S.; Patil, Mahalakshmi; Shinde, Mayuri; Teli, Aishwarya

doi:10.2139/ssrn.3769139

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In deep neural networks, standard short-cut connections between layers are connections that bypass at least one intermediate layer. The author in [44] classify the vehicles using blob tracking technologies.The author in [45] proposed a model to count the vehicles in the congested scene using multiple fully convolutional sub-networks to predict the density map for a given static image. In [46], the author introduced an online-update mechanism during training; an online updating technique is employed to update the pseudo ground truth, while a locally constrained regression loss is used to place further constraints on the projected box sizes in a local area by relocating high-level shallow layers features and emphasizing their low-level features.…”

Section: Cnn-based Methodsmentioning

confidence: 99%

Deep Neural Network-based Approach for Accurate Vehicle Counting

2023

IJIES

View full text Add to dashboard Cite

In highway management, intelligent vehicle detection and counting are becoming increasingly important as an accurate estimation of traffic density on road congestion reduction. Traffic density estimation is affected by the difficulties of perspective distortion, size change, significant occlusion, and background interference in traffic images. To address the previous issues, this article develops a novel model that enhances the quality of estimating traffic density. The efficientNet fine-tuning architecture is used then, followed by the development of seven dilated convolutional layers to extract the deeper features in the images that maintain the output's resolution to generate a high-quality density map. Finally, the vehicle count will be calculated from the high-quality density map. The experimental results indicate that the suggested approach significantly enhances the accuracy of traffic density estimation compared to the existing ones. It achieves 5.23 as a mean absolute error (MAE) on the TRANCOS dataset.

show abstract

Section: Cnn-based Methodsmentioning

confidence: 99%