Small Object Detection with Multiscale Features
The existing object detection algorithm based on the deep convolution neural network needs to carry out multilevel convolution and pooling operations to the entire image in order to extract a deep semantic features of the image. The detection models can get better results for big object. However, th...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | International Journal of Digital Multimedia Broadcasting |
| Online Access: | http://dx.doi.org/10.1155/2018/4546896 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832566811756855296 |
|---|---|
| author | Guo X. Hu Zhong Yang Lei Hu Li Huang Jia M. Han |
| author_facet | Guo X. Hu Zhong Yang Lei Hu Li Huang Jia M. Han |
| author_sort | Guo X. Hu |
| collection | DOAJ |
| description | The existing object detection algorithm based on the deep convolution neural network needs to carry out multilevel convolution and pooling operations to the entire image in order to extract a deep semantic features of the image. The detection models can get better results for big object. However, those models fail to detect small objects that have low resolution and are greatly influenced by noise because the features after repeated convolution operations of existing models do not fully represent the essential characteristics of the small objects. In this paper, we can achieve good detection accuracy by extracting the features at different convolution levels of the object and using the multiscale features to detect small objects. For our detection model, we extract the features of the image from their third, fourth, and 5th convolutions, respectively, and then these three scales features are concatenated into a one-dimensional vector. The vector is used to classify objects by classifiers and locate position information of objects by regression of bounding box. Through testing, the detection accuracy of our model for small objects is 11% higher than the state-of-the-art models. In addition, we also used the model to detect aircraft in remote sensing images and achieved good results. |
| format | Article |
| id | doaj-art-40e7da4b37d2483cb40d69ace31ed124 |
| institution | Kabale University |
| issn | 1687-7578 1687-7586 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Digital Multimedia Broadcasting |
| spelling | doaj-art-40e7da4b37d2483cb40d69ace31ed1242025-02-03T01:03:11ZengWileyInternational Journal of Digital Multimedia Broadcasting1687-75781687-75862018-01-01201810.1155/2018/45468964546896Small Object Detection with Multiscale FeaturesGuo X. Hu0Zhong Yang1Lei Hu2Li Huang3Jia M. Han4College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaSchool of Computer Information Engineering, Jiangxi Normal University, Nanchang 330022, ChinaElementary Education College, Jiangxi Normal University, Nanchang 330022, ChinaCollege of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaThe existing object detection algorithm based on the deep convolution neural network needs to carry out multilevel convolution and pooling operations to the entire image in order to extract a deep semantic features of the image. The detection models can get better results for big object. However, those models fail to detect small objects that have low resolution and are greatly influenced by noise because the features after repeated convolution operations of existing models do not fully represent the essential characteristics of the small objects. In this paper, we can achieve good detection accuracy by extracting the features at different convolution levels of the object and using the multiscale features to detect small objects. For our detection model, we extract the features of the image from their third, fourth, and 5th convolutions, respectively, and then these three scales features are concatenated into a one-dimensional vector. The vector is used to classify objects by classifiers and locate position information of objects by regression of bounding box. Through testing, the detection accuracy of our model for small objects is 11% higher than the state-of-the-art models. In addition, we also used the model to detect aircraft in remote sensing images and achieved good results.http://dx.doi.org/10.1155/2018/4546896 |
| spellingShingle | Guo X. Hu Zhong Yang Lei Hu Li Huang Jia M. Han Small Object Detection with Multiscale Features International Journal of Digital Multimedia Broadcasting |
| title | Small Object Detection with Multiscale Features |
| title_full | Small Object Detection with Multiscale Features |
| title_fullStr | Small Object Detection with Multiscale Features |
| title_full_unstemmed | Small Object Detection with Multiscale Features |
| title_short | Small Object Detection with Multiscale Features |
| title_sort | small object detection with multiscale features |
| url | http://dx.doi.org/10.1155/2018/4546896 |
| work_keys_str_mv | AT guoxhu smallobjectdetectionwithmultiscalefeatures AT zhongyang smallobjectdetectionwithmultiscalefeatures AT leihu smallobjectdetectionwithmultiscalefeatures AT lihuang smallobjectdetectionwithmultiscalefeatures AT jiamhan smallobjectdetectionwithmultiscalefeatures |