Exploratory Data Preparation and Model Training Process for Raspberry Pi-Based Object Detection Model Deployments
Most computer vision applications that use deep learning on constrained device come from the Internet of Things (IoT) or robotics fields, where low-quality cameras are used to capture input images in real time. Since most pretrained models typically undergo training on high-quality image datasets, t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10478903/ |
| _version_ | 1797231211719950336 |
|---|---|
| author | Vidya Kamath Renuka A. Vishwas G. Kini Shwetha Prabhu |
| author_facet | Vidya Kamath Renuka A. Vishwas G. Kini Shwetha Prabhu |
| author_sort | Vidya Kamath |
| collection | DOAJ |
| description | Most computer vision applications that use deep learning on constrained device come from the Internet of Things (IoT) or robotics fields, where low-quality cameras are used to capture input images in real time. Since most pretrained models typically undergo training on high-quality image datasets, the low-quality, noisy, or blurry images captured with these resource-constrained devices could possibly have a negative impact on the models’ performance. To determine if model performance is impacted by training models using low-quality data, a secondary image dataset named MOD-2022 was prepared for object detection and tracking tasks using an exploratory data preparation methodology. This dataset was primarily designed to include a wider range of classes with an adequate number of images per class while being free of errors due to inaccurate labelling or annotations. Additionally, a training approach is also proposed to support the model’s training when the dataset is considerably large. A VGG16-SSD model was trained with this approach on the prepared dataset and deployed on a Raspberry Pi and it showed that this approach is very useful in developing models for resource-constrained applications. Furthermore, this data preparation approach can be extended to prepare numerous other datasets required for training models designed to be deployed on constrained devices similar to the Raspberry Pi. |
| first_indexed | 2024-04-24T15:40:47Z |
| format | Article |
| id | doaj.art-7ff1a65fdb44456685a2eb97e53f5a94 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T15:40:47Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7ff1a65fdb44456685a2eb97e53f5a942024-04-01T23:00:34ZengIEEEIEEE Access2169-35362024-01-0112454234544110.1109/ACCESS.2024.338179810478903Exploratory Data Preparation and Model Training Process for Raspberry Pi-Based Object Detection Model DeploymentsVidya Kamath0https://orcid.org/0000-0002-7396-886XRenuka A.1https://orcid.org/0000-0001-6511-9780Vishwas G. Kini2https://orcid.org/0000-0002-5933-6655Shwetha Prabhu3Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaDepartment of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaDepartment of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaDepartment of Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaMost computer vision applications that use deep learning on constrained device come from the Internet of Things (IoT) or robotics fields, where low-quality cameras are used to capture input images in real time. Since most pretrained models typically undergo training on high-quality image datasets, the low-quality, noisy, or blurry images captured with these resource-constrained devices could possibly have a negative impact on the models’ performance. To determine if model performance is impacted by training models using low-quality data, a secondary image dataset named MOD-2022 was prepared for object detection and tracking tasks using an exploratory data preparation methodology. This dataset was primarily designed to include a wider range of classes with an adequate number of images per class while being free of errors due to inaccurate labelling or annotations. Additionally, a training approach is also proposed to support the model’s training when the dataset is considerably large. A VGG16-SSD model was trained with this approach on the prepared dataset and deployed on a Raspberry Pi and it showed that this approach is very useful in developing models for resource-constrained applications. Furthermore, this data preparation approach can be extended to prepare numerous other datasets required for training models designed to be deployed on constrained devices similar to the Raspberry Pi.https://ieeexplore.ieee.org/document/10478903/Dataset preparationdeep learningmodel trainingobject detectionRaspberry Piresource-constrained |
| spellingShingle | Vidya Kamath Renuka A. Vishwas G. Kini Shwetha Prabhu Exploratory Data Preparation and Model Training Process for Raspberry Pi-Based Object Detection Model Deployments IEEE Access Dataset preparation deep learning model training object detection Raspberry Pi resource-constrained |
| title | Exploratory Data Preparation and Model Training Process for Raspberry Pi-Based Object Detection Model Deployments |
| title_full | Exploratory Data Preparation and Model Training Process for Raspberry Pi-Based Object Detection Model Deployments |
| title_fullStr | Exploratory Data Preparation and Model Training Process for Raspberry Pi-Based Object Detection Model Deployments |
| title_full_unstemmed | Exploratory Data Preparation and Model Training Process for Raspberry Pi-Based Object Detection Model Deployments |
| title_short | Exploratory Data Preparation and Model Training Process for Raspberry Pi-Based Object Detection Model Deployments |
| title_sort | exploratory data preparation and model training process for raspberry pi based object detection model deployments |
| topic | Dataset preparation deep learning model training object detection Raspberry Pi resource-constrained |
| url | https://ieeexplore.ieee.org/document/10478903/ |
| work_keys_str_mv | AT vidyakamath exploratorydatapreparationandmodeltrainingprocessforraspberrypibasedobjectdetectionmodeldeployments AT renukaa exploratorydatapreparationandmodeltrainingprocessforraspberrypibasedobjectdetectionmodeldeployments AT vishwasgkini exploratorydatapreparationandmodeltrainingprocessforraspberrypibasedobjectdetectionmodeldeployments AT shwethaprabhu exploratorydatapreparationandmodeltrainingprocessforraspberrypibasedobjectdetectionmodeldeployments |