Efficient Object Detection Based on Masking Semantic Segmentation Region for Lightweight Embedded Processors
Because of the development of image processing using cameras and the subsequent development of artificial intelligence technology, various fields have begun to develop. However, it is difficult to implement an image processing algorithm that requires a lot of calculations on a light board. This pape...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/22/8890 |
| _version_ | 1797463976905277440 |
|---|---|
| author | Heuijee Yun Daejin Park |
| author_facet | Heuijee Yun Daejin Park |
| author_sort | Heuijee Yun |
| collection | DOAJ |
| description | Because of the development of image processing using cameras and the subsequent development of artificial intelligence technology, various fields have begun to develop. However, it is difficult to implement an image processing algorithm that requires a lot of calculations on a light board. This paper proposes a method using real-time deep learning object recognition algorithms in lightweight embedded boards. We have developed an algorithm suitable for lightweight embedded boards by appropriately using two deep neural network architectures. The first architecture requires small computational volumes, although it provides low accuracy. The second architecture uses large computational volumes and provides high accuracy. The area is determined using the first architecture, which processes semantic segmentation with relatively little computation. After masking the area using the more accurate deep learning architecture, object detection is implemented with improved accuracy, as the image is filtered by segmentation and the cases that have not been recognized by various variables, such as differentiation from the background, are excluded. OpenCV (Open source Computer Vision) is used to process input images in Python, and images are processed using an efficient neural network (ENet) and You Only Look Once (YOLO). By running this algorithm, the average error can be reduced by approximately 2.4 times, allowing for more accurate object detection. In addition, object recognition can be performed in real time for lightweight embedded boards, as a rate of about 4 FPS (frames per second) is achieved. |
| first_indexed | 2024-03-09T18:00:22Z |
| format | Article |
| id | doaj.art-b9a805c489334896b274e0f1e2605f13 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:00:22Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b9a805c489334896b274e0f1e2605f132023-11-24T09:57:24ZengMDPI AGSensors1424-82202022-11-012222889010.3390/s22228890Efficient Object Detection Based on Masking Semantic Segmentation Region for Lightweight Embedded ProcessorsHeuijee Yun0Daejin Park1School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of KoreaSchool of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of KoreaBecause of the development of image processing using cameras and the subsequent development of artificial intelligence technology, various fields have begun to develop. However, it is difficult to implement an image processing algorithm that requires a lot of calculations on a light board. This paper proposes a method using real-time deep learning object recognition algorithms in lightweight embedded boards. We have developed an algorithm suitable for lightweight embedded boards by appropriately using two deep neural network architectures. The first architecture requires small computational volumes, although it provides low accuracy. The second architecture uses large computational volumes and provides high accuracy. The area is determined using the first architecture, which processes semantic segmentation with relatively little computation. After masking the area using the more accurate deep learning architecture, object detection is implemented with improved accuracy, as the image is filtered by segmentation and the cases that have not been recognized by various variables, such as differentiation from the background, are excluded. OpenCV (Open source Computer Vision) is used to process input images in Python, and images are processed using an efficient neural network (ENet) and You Only Look Once (YOLO). By running this algorithm, the average error can be reduced by approximately 2.4 times, allowing for more accurate object detection. In addition, object recognition can be performed in real time for lightweight embedded boards, as a rate of about 4 FPS (frames per second) is achieved.https://www.mdpi.com/1424-8220/22/22/8890autonomous drivingobject detectionOpenCVENetYOLOdeep learning |
| spellingShingle | Heuijee Yun Daejin Park Efficient Object Detection Based on Masking Semantic Segmentation Region for Lightweight Embedded Processors Sensors autonomous driving object detection OpenCV ENet YOLO deep learning |
| title | Efficient Object Detection Based on Masking Semantic Segmentation Region for Lightweight Embedded Processors |
| title_full | Efficient Object Detection Based on Masking Semantic Segmentation Region for Lightweight Embedded Processors |
| title_fullStr | Efficient Object Detection Based on Masking Semantic Segmentation Region for Lightweight Embedded Processors |
| title_full_unstemmed | Efficient Object Detection Based on Masking Semantic Segmentation Region for Lightweight Embedded Processors |
| title_short | Efficient Object Detection Based on Masking Semantic Segmentation Region for Lightweight Embedded Processors |
| title_sort | efficient object detection based on masking semantic segmentation region for lightweight embedded processors |
| topic | autonomous driving object detection OpenCV ENet YOLO deep learning |
| url | https://www.mdpi.com/1424-8220/22/22/8890 |
| work_keys_str_mv | AT heuijeeyun efficientobjectdetectionbasedonmaskingsemanticsegmentationregionforlightweightembeddedprocessors AT daejinpark efficientobjectdetectionbasedonmaskingsemanticsegmentationregionforlightweightembeddedprocessors |