Loading

Estimation and Analysis of Highway Traffic
G. Poorani1, G.Nivedhitha2, S.Padmavathi3

1G. Poorani, Assistant. Professor, Department. of CSE, Sri Krishna College of Technology, Coimbatore (Tamil Nadu), India.
2G.Nivedhitha, Assistant. Professor, Department. of CSE, Sri Krishna College of Technology, Coimbatore (Tamil Nadu), India.
3S.Padmavathi, Assistant. Professor, Department. of CSE, Sri Krishna College of Technology, Coimbatore (Tamil Nadu), India.

Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 1743-1747 | Volume-8 Issue-7, May 2019 | Retrieval Number: F3895048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Based on multivariate analysis, that directly counts and classifies vehicles. a number of the present algorithms are inaccurate in poor quality videos and additionally fail to extract the reliable options. Here, we tend to propose a regression formula, that is helpful even once the vehicle resolution is low and when there are severe occlusions. In our planned formula, there are 2 contributions, First, to observe the foreground segments, a deformation technique is developed, that contain unclassified vehicles. throughout the deformation method, there’s some vehicle distortion, that is caused by foreshortening impact. A projective transformation and estimating and applying the heterogeneous mesh grid to scale back the vehicle distortion. Second, for every of the foreground segments, a group of lowlevel options is extracted and a cascaded regression approach is developed to count and classify the vehicles. Our planned regression primarily based formula are sturdy and correct, even in poor quality videos.
Keyword: Warping Method, Projective Transformation, a Nonuniform Mesh grid, Cascaded Regression.
Scope of the Article: Software Domain Modelling and Analysis.