Research on Recognition of Fly Species Based on Improved RetinaNet and CBAM
Flies carry pathogens that endanger the health of humans and animals. The color and shape of the fly species are very similar, which is difficult to recognize. This paper proposes a fly species recognition method based on improved RetinaNet and convolutional block attention module (CBAM). Firstly, t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9099571/ |
| _version_ | 1818557902182416384 |
|---|---|
| author | Yantong Chen Xianzhong Zhang Weinan Chen Yuyang Li Junsheng Wang |
| author_facet | Yantong Chen Xianzhong Zhang Weinan Chen Yuyang Li Junsheng Wang |
| author_sort | Yantong Chen |
| collection | DOAJ |
| description | Flies carry pathogens that endanger the health of humans and animals. The color and shape of the fly species are very similar, which is difficult to recognize. This paper proposes a fly species recognition method based on improved RetinaNet and convolutional block attention module (CBAM). Firstly, the proposed method used ResNeXt101 as a feature extraction network, and the improved CBAM called Stochastic-CBAM was added. Then, we built a multi-scale feature pyramid through an improved feature pyramid network (FPN) and integrated multi-level feature information. Finally, the small full convolutional network (FCN) was used as the classification subnet and the bounding box regression subnet. The Kullback-Leibler (KL) loss replaced smooth L1 loss as a bounding box regression loss function for learning bounding box regression and positioning uncertainty at the same time. We experimentally compared the proposed method with other the state-of-the-art methods on the established dataset. Experimental results showed that the mean Average Precision (mAP) of this method reached 90.38%, which was better than the state-of-the-art methods. The average time to recognize a single image was 0.131s. This method has a good detection effect on the fly species recognition. |
| first_indexed | 2024-12-14T00:05:46Z |
| format | Article |
| id | doaj.art-da31ec3e867a4c78a58200d1f4edae87 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T00:05:46Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-da31ec3e867a4c78a58200d1f4edae872022-12-21T23:26:02ZengIEEEIEEE Access2169-35362020-01-01810290710291910.1109/ACCESS.2020.29974669099571Research on Recognition of Fly Species Based on Improved RetinaNet and CBAMYantong Chen0Xianzhong Zhang1https://orcid.org/0000-0002-1984-9704Weinan Chen2Yuyang Li3Junsheng Wang4Department of Information Science and Technology, Dalian Maritime University, Dalian, ChinaDepartment of Information Science and Technology, Dalian Maritime University, Dalian, ChinaDepartment of Information Science and Technology, Dalian Maritime University, Dalian, ChinaDepartment of Information Science and Technology, Dalian Maritime University, Dalian, ChinaDepartment of Information Science and Technology, Dalian Maritime University, Dalian, ChinaFlies carry pathogens that endanger the health of humans and animals. The color and shape of the fly species are very similar, which is difficult to recognize. This paper proposes a fly species recognition method based on improved RetinaNet and convolutional block attention module (CBAM). Firstly, the proposed method used ResNeXt101 as a feature extraction network, and the improved CBAM called Stochastic-CBAM was added. Then, we built a multi-scale feature pyramid through an improved feature pyramid network (FPN) and integrated multi-level feature information. Finally, the small full convolutional network (FCN) was used as the classification subnet and the bounding box regression subnet. The Kullback-Leibler (KL) loss replaced smooth L1 loss as a bounding box regression loss function for learning bounding box regression and positioning uncertainty at the same time. We experimentally compared the proposed method with other the state-of-the-art methods on the established dataset. Experimental results showed that the mean Average Precision (mAP) of this method reached 90.38%, which was better than the state-of-the-art methods. The average time to recognize a single image was 0.131s. This method has a good detection effect on the fly species recognition.https://ieeexplore.ieee.org/document/9099571/Fly species recognitionRetinaNet algorithmattention convolution moduleconvolutional neural network |
| spellingShingle | Yantong Chen Xianzhong Zhang Weinan Chen Yuyang Li Junsheng Wang Research on Recognition of Fly Species Based on Improved RetinaNet and CBAM IEEE Access Fly species recognition RetinaNet algorithm attention convolution module convolutional neural network |
| title | Research on Recognition of Fly Species Based on Improved RetinaNet and CBAM |
| title_full | Research on Recognition of Fly Species Based on Improved RetinaNet and CBAM |
| title_fullStr | Research on Recognition of Fly Species Based on Improved RetinaNet and CBAM |
| title_full_unstemmed | Research on Recognition of Fly Species Based on Improved RetinaNet and CBAM |
| title_short | Research on Recognition of Fly Species Based on Improved RetinaNet and CBAM |
| title_sort | research on recognition of fly species based on improved retinanet and cbam |
| topic | Fly species recognition RetinaNet algorithm attention convolution module convolutional neural network |
| url | https://ieeexplore.ieee.org/document/9099571/ |
| work_keys_str_mv | AT yantongchen researchonrecognitionofflyspeciesbasedonimprovedretinanetandcbam AT xianzhongzhang researchonrecognitionofflyspeciesbasedonimprovedretinanetandcbam AT weinanchen researchonrecognitionofflyspeciesbasedonimprovedretinanetandcbam AT yuyangli researchonrecognitionofflyspeciesbasedonimprovedretinanetandcbam AT junshengwang researchonrecognitionofflyspeciesbasedonimprovedretinanetandcbam |