Region-of-Interest Extraction Method to Increase Object-Detection Performance in Remote Monitoring System
This study proposes an image data preprocessing method to improve the efficiency of transmitting and processing images for object detection in distributed IoT systems such as digital CCTV. The proposed method prepares a background image using Gaussian Mixture-based modeling with a series of continuo...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/10/5328 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850128082620383232 |
|---|---|
| author | Hyeong-GI Jeon Kyoung-Hee Lee |
| author_facet | Hyeong-GI Jeon Kyoung-Hee Lee |
| author_sort | Hyeong-GI Jeon |
| collection | DOAJ |
| description | This study proposes an image data preprocessing method to improve the efficiency of transmitting and processing images for object detection in distributed IoT systems such as digital CCTV. The proposed method prepares a background image using Gaussian Mixture-based modeling with a series of continuous images in the video. Then it is used as the reference to be compared with a target image to extract the ROIs by our DSSIM-based area filtering algorithm. The background areas beside the ROIs in the image are filled with a single color—either black or white to reduce data size, or a highly saturated color to improve object detection performance. Our implementation results confirm that the proposed method can considerably reduce the network overhead and the processing time at the server side. From additional experiments, we found that the model’s inference time and accuracy for object detection can be significantly improved when our two new ideas are applied: expanding ROI areas to improve the objectness of each object in the image and filling the background with a highly saturated color. |
| format | Article |
| id | doaj-art-fb0dd7e31aad4f6cab52d9e1f7bd3544 |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-fb0dd7e31aad4f6cab52d9e1f7bd35442025-08-20T02:33:30ZengMDPI AGApplied Sciences2076-34172025-05-011510532810.3390/app15105328Region-of-Interest Extraction Method to Increase Object-Detection Performance in Remote Monitoring SystemHyeong-GI Jeon0Kyoung-Hee Lee1Smart ICT Convergence HRD Center, Pai-Chai University, Daejeon 35345, Republic of KoreaDepartment of Software Engineering, Pai-Chai University, Daejeon 35345, Republic of KoreaThis study proposes an image data preprocessing method to improve the efficiency of transmitting and processing images for object detection in distributed IoT systems such as digital CCTV. The proposed method prepares a background image using Gaussian Mixture-based modeling with a series of continuous images in the video. Then it is used as the reference to be compared with a target image to extract the ROIs by our DSSIM-based area filtering algorithm. The background areas beside the ROIs in the image are filled with a single color—either black or white to reduce data size, or a highly saturated color to improve object detection performance. Our implementation results confirm that the proposed method can considerably reduce the network overhead and the processing time at the server side. From additional experiments, we found that the model’s inference time and accuracy for object detection can be significantly improved when our two new ideas are applied: expanding ROI areas to improve the objectness of each object in the image and filling the background with a highly saturated color.https://www.mdpi.com/2076-3417/15/10/5328intelligent traffic monitoring systemobject detectioninterest point detectionstreaming media |
| spellingShingle | Hyeong-GI Jeon Kyoung-Hee Lee Region-of-Interest Extraction Method to Increase Object-Detection Performance in Remote Monitoring System Applied Sciences intelligent traffic monitoring system object detection interest point detection streaming media |
| title | Region-of-Interest Extraction Method to Increase Object-Detection Performance in Remote Monitoring System |
| title_full | Region-of-Interest Extraction Method to Increase Object-Detection Performance in Remote Monitoring System |
| title_fullStr | Region-of-Interest Extraction Method to Increase Object-Detection Performance in Remote Monitoring System |
| title_full_unstemmed | Region-of-Interest Extraction Method to Increase Object-Detection Performance in Remote Monitoring System |
| title_short | Region-of-Interest Extraction Method to Increase Object-Detection Performance in Remote Monitoring System |
| title_sort | region of interest extraction method to increase object detection performance in remote monitoring system |
| topic | intelligent traffic monitoring system object detection interest point detection streaming media |
| url | https://www.mdpi.com/2076-3417/15/10/5328 |
| work_keys_str_mv | AT hyeonggijeon regionofinterestextractionmethodtoincreaseobjectdetectionperformanceinremotemonitoringsystem AT kyoungheelee regionofinterestextractionmethodtoincreaseobjectdetectionperformanceinremotemonitoringsystem |