Singular value decomposition in image processing
The rapid advancement of object detection models in recent years has provided fast and accurate object detections on critical applications such as autonomous driving and healthcare services. While current-state-of-the art object detection models have achieved remarkable accuracy, it is at the exp...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156165 |
| _version_ | 1826114466171846656 |
|---|---|
| author | Goh, Raymond Kang Sheng |
| author2 | Deepu Rajan |
| author_facet | Deepu Rajan Goh, Raymond Kang Sheng |
| author_sort | Goh, Raymond Kang Sheng |
| collection | NTU |
| description | The rapid advancement of object detection models in recent years has provided fast
and accurate object detections on critical applications such as autonomous driving
and healthcare services. While current-state-of-the art object detection models have
achieved remarkable accuracy, it is at the expense of high computational cost and a
significant amount of training time and data. In this project, we investigate various
compressive sensing techniques, such as applying SVD compression and SVD
background subtraction on the training images with the YOLOv5 object detection
model in an attempt to investigate the benefit of compressive sensing on object
detection tasks. The SVD-IC dataset, with SVD compression applied on the training
dataset, outperformed the original dataset by achieving 7.9% higher mAP and 3.1%
higher precision accuracy during testing. When SVD compression and SVD
background subtraction were applied to the training dataset, it was observed that it
enhances performance during the early stage of training. Systems with lower
computational resources are able to benefit from SVD compression, where
compressed training images would result in lower storage usage, as well as obtaining
object detection models with better performance when trained with low number of
epochs. |
| first_indexed | 2024-10-01T03:39:38Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/156165 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:39:38Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1561652022-04-05T08:21:29Z Singular value decomposition in image processing Goh, Raymond Kang Sheng Deepu Rajan School of Computer Science and Engineering ASDRajan@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision The rapid advancement of object detection models in recent years has provided fast and accurate object detections on critical applications such as autonomous driving and healthcare services. While current-state-of-the art object detection models have achieved remarkable accuracy, it is at the expense of high computational cost and a significant amount of training time and data. In this project, we investigate various compressive sensing techniques, such as applying SVD compression and SVD background subtraction on the training images with the YOLOv5 object detection model in an attempt to investigate the benefit of compressive sensing on object detection tasks. The SVD-IC dataset, with SVD compression applied on the training dataset, outperformed the original dataset by achieving 7.9% higher mAP and 3.1% higher precision accuracy during testing. When SVD compression and SVD background subtraction were applied to the training dataset, it was observed that it enhances performance during the early stage of training. Systems with lower computational resources are able to benefit from SVD compression, where compressed training images would result in lower storage usage, as well as obtaining object detection models with better performance when trained with low number of epochs. Bachelor of Engineering (Computer Science) 2022-04-05T08:21:29Z 2022-04-05T08:21:29Z 2022 Final Year Project (FYP) Goh, R. K. S. (2022). Singular value decomposition in image processing. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156165 https://hdl.handle.net/10356/156165 en SCSE21-0313 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Goh, Raymond Kang Sheng Singular value decomposition in image processing |
| title | Singular value decomposition in image processing |
| title_full | Singular value decomposition in image processing |
| title_fullStr | Singular value decomposition in image processing |
| title_full_unstemmed | Singular value decomposition in image processing |
| title_short | Singular value decomposition in image processing |
| title_sort | singular value decomposition in image processing |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | https://hdl.handle.net/10356/156165 |
| work_keys_str_mv | AT gohraymondkangsheng singularvaluedecompositioninimageprocessing |