State-of-the-Art Deep Learning Methods for Objects Detection in Remote Sensing Satellite Images
<b>Introduction:</b> Object detection in remotely sensed satellite images is critical to socio-economic, bio-physical, and environmental monitoring, necessary for the prevention of natural disasters such as flooding and fires, socio-economic service delivery, and general urban and rural...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/13/5849 |
| _version_ | 1797590890264395776 |
|---|---|
| author | Adekanmi Adeyinka Adegun Jean Vincent Fonou Dombeu Serestina Viriri John Odindi |
| author_facet | Adekanmi Adeyinka Adegun Jean Vincent Fonou Dombeu Serestina Viriri John Odindi |
| author_sort | Adekanmi Adeyinka Adegun |
| collection | DOAJ |
| description | <b>Introduction:</b> Object detection in remotely sensed satellite images is critical to socio-economic, bio-physical, and environmental monitoring, necessary for the prevention of natural disasters such as flooding and fires, socio-economic service delivery, and general urban and rural planning and management. Whereas deep learning approaches have recently gained popularity in remotely sensed image analysis, they have been unable to efficiently detect image objects due to complex landscape heterogeneity, high inter-class similarity and intra-class diversity, and difficulty in acquiring suitable training data that represents the complexities, among others. <b>Methods:</b> To address these challenges, this study employed multi-object detection deep learning algorithms with a transfer learning approach on remotely sensed satellite imagery captured on a heterogeneous landscape. In the study, a new dataset of diverse features with five object classes collected from Google Earth Engine in various locations in southern KwaZulu-Natal province in South Africa was used to evaluate the models. The dataset images were characterized with objects that have varying sizes and resolutions. Five (5) object detection methods based on R-CNN and YOLO architectures were investigated via experiments on our newly created dataset. <b>Conclusions:</b> This paper provides a comprehensive performance evaluation and analysis of the recent deep learning-based object detection methods for detecting objects in high-resolution remote sensing satellite images. The models were also evaluated on two publicly available datasets: Visdron and PASCAL VOC2007. Results showed that the highest detection accuracy of the vegetation and swimming pool instances was more than 90%, and the fastest detection speed 0.2 ms was observed in YOLOv8. |
| first_indexed | 2024-03-11T01:29:53Z |
| format | Article |
| id | doaj.art-f765facf69d345f4ad5d35c192509298 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:29:53Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f765facf69d345f4ad5d35c1925092982023-11-18T17:27:41ZengMDPI AGSensors1424-82202023-06-012313584910.3390/s23135849State-of-the-Art Deep Learning Methods for Objects Detection in Remote Sensing Satellite ImagesAdekanmi Adeyinka Adegun0Jean Vincent Fonou Dombeu1Serestina Viriri2John Odindi3School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Durban 4041, South AfricaSchool of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Pietermaritzburg 3209, South AfricaSchool of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Durban 4041, South AfricaSchool of Agricultural, Earth and Environmental Sciences, University of KwaZulu-Natal, Pietermaritzburg 3209, South Africa<b>Introduction:</b> Object detection in remotely sensed satellite images is critical to socio-economic, bio-physical, and environmental monitoring, necessary for the prevention of natural disasters such as flooding and fires, socio-economic service delivery, and general urban and rural planning and management. Whereas deep learning approaches have recently gained popularity in remotely sensed image analysis, they have been unable to efficiently detect image objects due to complex landscape heterogeneity, high inter-class similarity and intra-class diversity, and difficulty in acquiring suitable training data that represents the complexities, among others. <b>Methods:</b> To address these challenges, this study employed multi-object detection deep learning algorithms with a transfer learning approach on remotely sensed satellite imagery captured on a heterogeneous landscape. In the study, a new dataset of diverse features with five object classes collected from Google Earth Engine in various locations in southern KwaZulu-Natal province in South Africa was used to evaluate the models. The dataset images were characterized with objects that have varying sizes and resolutions. Five (5) object detection methods based on R-CNN and YOLO architectures were investigated via experiments on our newly created dataset. <b>Conclusions:</b> This paper provides a comprehensive performance evaluation and analysis of the recent deep learning-based object detection methods for detecting objects in high-resolution remote sensing satellite images. The models were also evaluated on two publicly available datasets: Visdron and PASCAL VOC2007. Results showed that the highest detection accuracy of the vegetation and swimming pool instances was more than 90%, and the fastest detection speed 0.2 ms was observed in YOLOv8.https://www.mdpi.com/1424-8220/23/13/5849remote sensingsatellite imagesobject detectionYOLOR-CNN |
| spellingShingle | Adekanmi Adeyinka Adegun Jean Vincent Fonou Dombeu Serestina Viriri John Odindi State-of-the-Art Deep Learning Methods for Objects Detection in Remote Sensing Satellite Images Sensors remote sensing satellite images object detection YOLO R-CNN |
| title | State-of-the-Art Deep Learning Methods for Objects Detection in Remote Sensing Satellite Images |
| title_full | State-of-the-Art Deep Learning Methods for Objects Detection in Remote Sensing Satellite Images |
| title_fullStr | State-of-the-Art Deep Learning Methods for Objects Detection in Remote Sensing Satellite Images |
| title_full_unstemmed | State-of-the-Art Deep Learning Methods for Objects Detection in Remote Sensing Satellite Images |
| title_short | State-of-the-Art Deep Learning Methods for Objects Detection in Remote Sensing Satellite Images |
| title_sort | state of the art deep learning methods for objects detection in remote sensing satellite images |
| topic | remote sensing satellite images object detection YOLO R-CNN |
| url | https://www.mdpi.com/1424-8220/23/13/5849 |
| work_keys_str_mv | AT adekanmiadeyinkaadegun stateoftheartdeeplearningmethodsforobjectsdetectioninremotesensingsatelliteimages AT jeanvincentfonoudombeu stateoftheartdeeplearningmethodsforobjectsdetectioninremotesensingsatelliteimages AT serestinaviriri stateoftheartdeeplearningmethodsforobjectsdetectioninremotesensingsatelliteimages AT johnodindi stateoftheartdeeplearningmethodsforobjectsdetectioninremotesensingsatelliteimages |