Refining Yolov4 for Vehicle Detection

International Journal of Advanced Research in Engineering and Technology (IJARET), 11(5), 2020, pp. 409-419.

11 Pages Posted: 9 Jul 2020

See all articles by Pooja Mahto

Pooja Mahto

Department of Electronics & Communication Engineering, Delhi Technological University, India

Priyamm Garg

Department of Electronics & Communication Engineering, Delhi Technological University, India

Pranav Seth

Department of Electronics & Communication Engineering, Delhi Technological University, India

J Panda

Department of Electronics & Communication Engineering, Delhi Technological University, India

Date Written: June 16, 2020

Abstract

Real-time vehicle detection is a technology employed in applications like selfdriving cars, traffic camera surveillance. Every year we see better and updated stateof-the-art (SOTA) object detectors, but as those are trained on general-purpose datasets (like MS COCO), we miss out on targeted model improvements for vehicular data. The aim of this paper is to improve the newly released, YOLOv4 detector, specifically, for vehicle tracking applications using some existing methods such as optimising anchor box predictions by using k-means clustering. We also carefully hand-pick and verify some key techniques mentioned in the original paper, to optimise YOLOv4 as per the requirements of our dataset (UA-DETRAC).

Our fine-tuned model is also compared with the existing models on a number of performance metrics such as - precision, recall, F1 score, mean average precision, and the average IoU. Our experimental results show that the SOTA model which already has real-time object detection capabilities can be further improved for highly targeted use cases. We urge the readers to expand the scope of the paper (and the original model) to other specific situations as well.

Keywords: object detection, convolutional neural network (CNN), YOLOv4, vehicle detection, k-means clustering

Suggested Citation

Mahto, Pooja and Garg, Priyamm and Seth, Pranav and Panda, J, Refining Yolov4 for Vehicle Detection (June 16, 2020). International Journal of Advanced Research in Engineering and Technology (IJARET), 11(5), 2020, pp. 409-419., Available at SSRN: https://ssrn.com/abstract=3628439

Pooja Mahto (Contact Author)

Department of Electronics & Communication Engineering, Delhi Technological University, India ( email )

Bawana Road
Main Bawana Road,
Delhi, Delhi 110042
India

Priyamm Garg

Department of Electronics & Communication Engineering, Delhi Technological University, India ( email )

Bawana Road
Main Bawana Road,
Delhi, Delhi 110042
India

Pranav Seth

Department of Electronics & Communication Engineering, Delhi Technological University, India ( email )

Bawana Road
Main Bawana Road,
Delhi, Delhi 110042
India

J Panda

Department of Electronics & Communication Engineering, Delhi Technological University, India ( email )

Bawana Road
Main Bawana Road,
Delhi, Delhi 110042
India

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
2,068
Abstract Views
5,943
rank
11,295
PlumX Metrics