Vehicle Detection with HOG and Linear SVM
Journal
Journal of Emerging Computer Technologies
Date Issued
2021-02-16
Author(s)
Tomikj, Nikola
Abstract
In this paper, we present a vehicle detection system
by employing Histogram of Oriented Gradients (HOG) for
feature extraction and linear SVM for classification. We study the
influence of the color space on the performance of the detector,
concluding that decorrelated and perceptual color spaces give
the best results. An in-depth analysis is carried out on the
effects of the HOG and SVM parameters, the threshold for the
distance between features and the SVM classifying plane, and the
non-maximum suppression (NMS) threshold on the performance
of the detector, and we propose values that illustrate good
performance for vehicle detection on images. We also discuss
the issues of the approach and the reasons for its mediocre
performance on videos. Finally, we address these issues by
presenting ideas that can be considered for improving the system.
by employing Histogram of Oriented Gradients (HOG) for
feature extraction and linear SVM for classification. We study the
influence of the color space on the performance of the detector,
concluding that decorrelated and perceptual color spaces give
the best results. An in-depth analysis is carried out on the
effects of the HOG and SVM parameters, the threshold for the
distance between features and the SVM classifying plane, and the
non-maximum suppression (NMS) threshold on the performance
of the detector, and we propose values that illustrate good
performance for vehicle detection on images. We also discuss
the issues of the approach and the reasons for its mediocre
performance on videos. Finally, we address these issues by
presenting ideas that can be considered for improving the system.
Subjects
File(s)![Thumbnail Image]()
Loading...
Name
Vehicle Detection with HOG and Linear SVM[#980065]-1913733.pdf
Size
592.6 KB
Format
Adobe PDF
Checksum
(MD5):b0b7bd4e2b34225a34649eb703e56e40