An Evaluation of Deep Learning Methods for Small Object Detection
Small object detection is an interesting topic in computer vision. With the rapid development in deep learning, it has drawn attention of several researchers with innovations in approaches to join a race. These innovations proposed comprise region proposals, divided grid cell, multiscale feature map...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Journal of Electrical and Computer Engineering |
| Online Access: | http://dx.doi.org/10.1155/2020/3189691 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832554582230695936 |
|---|---|
| author | Nhat-Duy Nguyen Tien Do Thanh Duc Ngo Duy-Dinh Le |
| author_facet | Nhat-Duy Nguyen Tien Do Thanh Duc Ngo Duy-Dinh Le |
| author_sort | Nhat-Duy Nguyen |
| collection | DOAJ |
| description | Small object detection is an interesting topic in computer vision. With the rapid development in deep learning, it has drawn attention of several researchers with innovations in approaches to join a race. These innovations proposed comprise region proposals, divided grid cell, multiscale feature maps, and new loss function. As a result, performance of object detection has recently had significant improvements. However, most of the state-of-the-art detectors, both in one-stage and two-stage approaches, have struggled with detecting small objects. In this study, we evaluate current state-of-the-art models based on deep learning in both approaches such as Fast RCNN, Faster RCNN, RetinaNet, and YOLOv3. We provide a profound assessment of the advantages and limitations of models. Specifically, we run models with different backbones on different datasets with multiscale objects to find out what types of objects are suitable for each model along with backbones. Extensive empirical evaluation was conducted on 2 standard datasets, namely, a small object dataset and a filtered dataset from PASCAL VOC 2007. Finally, comparative results and analyses are then presented. |
| format | Article |
| id | doaj-art-960c05452e414574881e1a51e1538917 |
| institution | Kabale University |
| issn | 2090-0147 2090-0155 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Electrical and Computer Engineering |
| spelling | doaj-art-960c05452e414574881e1a51e15389172025-02-03T05:51:13ZengWileyJournal of Electrical and Computer Engineering2090-01472090-01552020-01-01202010.1155/2020/31896913189691An Evaluation of Deep Learning Methods for Small Object DetectionNhat-Duy Nguyen0Tien Do1Thanh Duc Ngo2Duy-Dinh Le3University of Information Technology, Vietnam National University, Ho Chi Minh City, VietnamUniversity of Information Technology, Vietnam National University, Ho Chi Minh City, VietnamUniversity of Information Technology, Vietnam National University, Ho Chi Minh City, VietnamUniversity of Information Technology, Vietnam National University, Ho Chi Minh City, VietnamSmall object detection is an interesting topic in computer vision. With the rapid development in deep learning, it has drawn attention of several researchers with innovations in approaches to join a race. These innovations proposed comprise region proposals, divided grid cell, multiscale feature maps, and new loss function. As a result, performance of object detection has recently had significant improvements. However, most of the state-of-the-art detectors, both in one-stage and two-stage approaches, have struggled with detecting small objects. In this study, we evaluate current state-of-the-art models based on deep learning in both approaches such as Fast RCNN, Faster RCNN, RetinaNet, and YOLOv3. We provide a profound assessment of the advantages and limitations of models. Specifically, we run models with different backbones on different datasets with multiscale objects to find out what types of objects are suitable for each model along with backbones. Extensive empirical evaluation was conducted on 2 standard datasets, namely, a small object dataset and a filtered dataset from PASCAL VOC 2007. Finally, comparative results and analyses are then presented.http://dx.doi.org/10.1155/2020/3189691 |
| spellingShingle | Nhat-Duy Nguyen Tien Do Thanh Duc Ngo Duy-Dinh Le An Evaluation of Deep Learning Methods for Small Object Detection Journal of Electrical and Computer Engineering |
| title | An Evaluation of Deep Learning Methods for Small Object Detection |
| title_full | An Evaluation of Deep Learning Methods for Small Object Detection |
| title_fullStr | An Evaluation of Deep Learning Methods for Small Object Detection |
| title_full_unstemmed | An Evaluation of Deep Learning Methods for Small Object Detection |
| title_short | An Evaluation of Deep Learning Methods for Small Object Detection |
| title_sort | evaluation of deep learning methods for small object detection |
| url | http://dx.doi.org/10.1155/2020/3189691 |
| work_keys_str_mv | AT nhatduynguyen anevaluationofdeeplearningmethodsforsmallobjectdetection AT tiendo anevaluationofdeeplearningmethodsforsmallobjectdetection AT thanhducngo anevaluationofdeeplearningmethodsforsmallobjectdetection AT duydinhle anevaluationofdeeplearningmethodsforsmallobjectdetection AT nhatduynguyen evaluationofdeeplearningmethodsforsmallobjectdetection AT tiendo evaluationofdeeplearningmethodsforsmallobjectdetection AT thanhducngo evaluationofdeeplearningmethodsforsmallobjectdetection AT duydinhle evaluationofdeeplearningmethodsforsmallobjectdetection |