Cover Image

Effect of positive-negative image ratio on the performance of pedestrian detection model

Pedestrian detection holds significant importance in computer vision, finding applications in video surveillance, human-computer interaction, and autonomous vehicles. Surprisingly, there is a scarcity of research addressing the optimal ratio of positive to negative images for training detection mode...

Full description

Saved in:
Bibliographic Details
Main Authors: Yee, Lai Kok, Ken, Tan Lit, Choo, Hau Sim, Asako, Yutaka, Lee, Kee Quen, Kang, Hooi Siang, Gan, Yee Siang, Chuan, Zunliang, Tey, Wah Yen, Nor Azwadi, Che Sidik
Format: Article
Language:English
Published: Penerbit UTM Press 2024
Subjects:
HD Industries. Land use. Labor
Q Science (General)
T Technology (General)
Online Access:http://umpir.ump.edu.my/id/eprint/41516/1/Effect%20of%20positive-negative%20image%20ratio%20on%20the%20performance%20of%20pedestrian%20detection%20model.pdf
http://umpir.ump.edu.my/id/eprint/41516/
https://doi.org/10.11113/mjfas.v20n2.3300
https://doi.org/10.11113/mjfas.v20n2.3300
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ump.umpir.41516
record_format eprints
spelling my.ump.umpir.415162025-01-15T01:14:30Z http://umpir.ump.edu.my/id/eprint/41516/ Effect of positive-negative image ratio on the performance of pedestrian detection model Yee, Lai Kok Ken, Tan Lit Choo, Hau Sim Asako, Yutaka Lee, Kee Quen Kang, Hooi Siang Gan, Yee Siang Chuan, Zunliang Tey, Wah Yen Nor Azwadi, Che Sidik HD Industries. Land use. Labor Q Science (General) T Technology (General) Pedestrian detection holds significant importance in computer vision, finding applications in video surveillance, human-computer interaction, and autonomous vehicles. Surprisingly, there is a scarcity of research addressing the optimal ratio of positive to negative images for training detection models. This study endeavors to fill this research gap by exploring various detection models and determining the ideal ratio. Two distinct scenarios are investigated, each characterized by an equal total image count and an equivalent number of positive images sourced from CVC-14 night/visible, night/FIR, and INRIA databases. The study leverages the Histogram of Oriented Gradient, utilizing both Support Vector Machines and Medium Neural Networks to construct the detection models. Notably, the experiments reveal that the accuracy of the models remains relatively stable, even with an increase in the ratio of negative images. However, a noteworthy inverse relationship between sensitivity and specificity emerges as the ratio escalates. The findings, guided by the Youden Index, pinpoint the optimal training ratio for pedestrian detection models, falling within the range of 1:0.5 to 1:2. In the CVC-14 nighttime database, the Youden index reached 100% when the model was trained with a 1:0.5 ratio using SVM, and a total of 4500 images were employed in the training process. On the other hand, in the INRIA dataset, the Youden index exhibited its highest value at 98.50%. This occurred when both SVM and a Medium neural network were utilized to train the model with a ratio of 1:2, utilizing a total of 3000 images for the training phase. It's worth highlighting that the processing time for SVM models lags behind that of Medium Neural Networks. This disparity arises from the heightened computational complexity inherent to medium-sized neural networks, making them computationally demanding compared to SVMs. This study contributes valuable insights into the nuanced relationship between image ratios and the performance of pedestrian detection models. Penerbit UTM Press 2024-03 Article PeerReviewed pdf en cc_by_nc_4 http://umpir.ump.edu.my/id/eprint/41516/1/Effect%20of%20positive-negative%20image%20ratio%20on%20the%20performance%20of%20pedestrian%20detection%20model.pdf Yee, Lai Kok and Ken, Tan Lit and Choo, Hau Sim and Asako, Yutaka and Lee, Kee Quen and Kang, Hooi Siang and Gan, Yee Siang and Chuan, Zunliang and Tey, Wah Yen and Nor Azwadi, Che Sidik (2024) Effect of positive-negative image ratio on the performance of pedestrian detection model. Malaysian Journal of Fundamental and Applied Sciences, 20 (2). pp. 266-287. ISSN 2289-599X. (Published) https://doi.org/10.11113/mjfas.v20n2.3300 https://doi.org/10.11113/mjfas.v20n2.3300
institution Universiti Malaysia Pahang Al-Sultan Abdullah
building UMPSA Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Pahang Al-Sultan Abdullah
content_source UMPSA Institutional Repository
url_provider http://umpir.ump.edu.my/
language English
topic HD Industries. Land use. Labor
Q Science (General)
T Technology (General)
spellingShingle HD Industries. Land use. Labor
Q Science (General)
T Technology (General)
Yee, Lai Kok
Ken, Tan Lit
Choo, Hau Sim
Asako, Yutaka
Lee, Kee Quen
Kang, Hooi Siang
Gan, Yee Siang
Chuan, Zunliang
Tey, Wah Yen
Nor Azwadi, Che Sidik
Effect of positive-negative image ratio on the performance of pedestrian detection model
description Pedestrian detection holds significant importance in computer vision, finding applications in video surveillance, human-computer interaction, and autonomous vehicles. Surprisingly, there is a scarcity of research addressing the optimal ratio of positive to negative images for training detection models. This study endeavors to fill this research gap by exploring various detection models and determining the ideal ratio. Two distinct scenarios are investigated, each characterized by an equal total image count and an equivalent number of positive images sourced from CVC-14 night/visible, night/FIR, and INRIA databases. The study leverages the Histogram of Oriented Gradient, utilizing both Support Vector Machines and Medium Neural Networks to construct the detection models. Notably, the experiments reveal that the accuracy of the models remains relatively stable, even with an increase in the ratio of negative images. However, a noteworthy inverse relationship between sensitivity and specificity emerges as the ratio escalates. The findings, guided by the Youden Index, pinpoint the optimal training ratio for pedestrian detection models, falling within the range of 1:0.5 to 1:2. In the CVC-14 nighttime database, the Youden index reached 100% when the model was trained with a 1:0.5 ratio using SVM, and a total of 4500 images were employed in the training process. On the other hand, in the INRIA dataset, the Youden index exhibited its highest value at 98.50%. This occurred when both SVM and a Medium neural network were utilized to train the model with a ratio of 1:2, utilizing a total of 3000 images for the training phase. It's worth highlighting that the processing time for SVM models lags behind that of Medium Neural Networks. This disparity arises from the heightened computational complexity inherent to medium-sized neural networks, making them computationally demanding compared to SVMs. This study contributes valuable insights into the nuanced relationship between image ratios and the performance of pedestrian detection models.
format Article
author Yee, Lai Kok
Ken, Tan Lit
Choo, Hau Sim
Asako, Yutaka
Lee, Kee Quen
Kang, Hooi Siang
Gan, Yee Siang
Chuan, Zunliang
Tey, Wah Yen
Nor Azwadi, Che Sidik
author_facet Yee, Lai Kok
Ken, Tan Lit
Choo, Hau Sim
Asako, Yutaka
Lee, Kee Quen
Kang, Hooi Siang
Gan, Yee Siang
Chuan, Zunliang
Tey, Wah Yen
Nor Azwadi, Che Sidik
author_sort Yee, Lai Kok
title Effect of positive-negative image ratio on the performance of pedestrian detection model
title_short Effect of positive-negative image ratio on the performance of pedestrian detection model
title_full Effect of positive-negative image ratio on the performance of pedestrian detection model
title_fullStr Effect of positive-negative image ratio on the performance of pedestrian detection model
title_full_unstemmed Effect of positive-negative image ratio on the performance of pedestrian detection model
title_sort effect of positive-negative image ratio on the performance of pedestrian detection model
publisher Penerbit UTM Press
publishDate 2024
url http://umpir.ump.edu.my/id/eprint/41516/1/Effect%20of%20positive-negative%20image%20ratio%20on%20the%20performance%20of%20pedestrian%20detection%20model.pdf
http://umpir.ump.edu.my/id/eprint/41516/
https://doi.org/10.11113/mjfas.v20n2.3300
https://doi.org/10.11113/mjfas.v20n2.3300
_version_ 1822924942729019392
score 13.239859

Similar Items