Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes
In complex scenes, dynamic background, illumination variation, and shadow are important factors, which make conventional moving object detection algorithms suffer from poor performance. To solve this problem, a moving object detection method via ResNet-18 with encoder-decoder structure is proposed t...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8781779/ |
| _version_ | 1831686211775758336 |
|---|---|
| author | Xianfeng Ou Pengcheng Yan Yiming Zhang Bing Tu Guoyun Zhang Jianhui Wu Wujing Li |
| author_facet | Xianfeng Ou Pengcheng Yan Yiming Zhang Bing Tu Guoyun Zhang Jianhui Wu Wujing Li |
| author_sort | Xianfeng Ou |
| collection | DOAJ |
| description | In complex scenes, dynamic background, illumination variation, and shadow are important factors, which make conventional moving object detection algorithms suffer from poor performance. To solve this problem, a moving object detection method via ResNet-18 with encoder-decoder structure is proposed to segment moving objects from complex scenes. ResNet-18 with encoder-decoder structure possesses pixel-level classification capability to divide pixels into foreground and background, and it performs well in feature extraction because of its layers are so shallow that many more low-scale features will be retained. First, the object frames and their corresponding artificial labels are input to the network. Then, feature vectors will be generated by the encoder, and they are converted into segmentation maps by the decoder through deconvolution processing. Third, a rough matching of the moving object regions will be obtained, and finally, the Euclidean distance is used to match the moving object regions accurately. The proposed method is suitable for the scenes where dynamic background, illumination variation, and shadow exist, and experimental results on the public standard CDnet2014 and I2R datasets, from both qualitative and quantitative comparison aspects, demonstrate that the proposed method outperforms state-of-the-art algorithms significantly, and its mean F-measure increased by 1.99%~29.17%. |
| first_indexed | 2024-12-20T08:35:22Z |
| format | Article |
| id | doaj.art-720fcceaf0c841a49c6036c108eb0122 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T08:35:22Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-720fcceaf0c841a49c6036c108eb01222022-12-21T19:46:35ZengIEEEIEEE Access2169-35362019-01-01710815210816010.1109/ACCESS.2019.29319228781779Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex ScenesXianfeng Ou0https://orcid.org/0000-0003-4419-7362Pengcheng Yan1Yiming Zhang2Bing Tu3Guoyun Zhang4Jianhui Wu5Wujing Li6School of Information Science and Engineering, Hunan Institute of Science and Technology, Yueyang, ChinaSchool of Information Science and Engineering, Hunan Institute of Science and Technology, Yueyang, ChinaSchool of Information Science and Engineering, Hunan Institute of Science and Technology, Yueyang, ChinaSchool of Information Science and Engineering, Hunan Institute of Science and Technology, Yueyang, ChinaSchool of Information Science and Engineering, Hunan Institute of Science and Technology, Yueyang, ChinaSchool of Information Science and Engineering, Hunan Institute of Science and Technology, Yueyang, ChinaSchool of Information Science and Engineering, Hunan Institute of Science and Technology, Yueyang, ChinaIn complex scenes, dynamic background, illumination variation, and shadow are important factors, which make conventional moving object detection algorithms suffer from poor performance. To solve this problem, a moving object detection method via ResNet-18 with encoder-decoder structure is proposed to segment moving objects from complex scenes. ResNet-18 with encoder-decoder structure possesses pixel-level classification capability to divide pixels into foreground and background, and it performs well in feature extraction because of its layers are so shallow that many more low-scale features will be retained. First, the object frames and their corresponding artificial labels are input to the network. Then, feature vectors will be generated by the encoder, and they are converted into segmentation maps by the decoder through deconvolution processing. Third, a rough matching of the moving object regions will be obtained, and finally, the Euclidean distance is used to match the moving object regions accurately. The proposed method is suitable for the scenes where dynamic background, illumination variation, and shadow exist, and experimental results on the public standard CDnet2014 and I2R datasets, from both qualitative and quantitative comparison aspects, demonstrate that the proposed method outperforms state-of-the-art algorithms significantly, and its mean F-measure increased by 1.99%~29.17%.https://ieeexplore.ieee.org/document/8781779/Complex scenesmoving object detectionResNet-18encoder-decoder networkbackground subtraction |
| spellingShingle | Xianfeng Ou Pengcheng Yan Yiming Zhang Bing Tu Guoyun Zhang Jianhui Wu Wujing Li Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes IEEE Access Complex scenes moving object detection ResNet-18 encoder-decoder network background subtraction |
| title | Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes |
| title_full | Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes |
| title_fullStr | Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes |
| title_full_unstemmed | Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes |
| title_short | Moving Object Detection Method via ResNet-18 With Encoder–Decoder Structure in Complex Scenes |
| title_sort | moving object detection method via resnet 18 with encoder x2013 decoder structure in complex scenes |
| topic | Complex scenes moving object detection ResNet-18 encoder-decoder network background subtraction |
| url | https://ieeexplore.ieee.org/document/8781779/ |
| work_keys_str_mv | AT xianfengou movingobjectdetectionmethodviaresnet18withencoderx2013decoderstructureincomplexscenes AT pengchengyan movingobjectdetectionmethodviaresnet18withencoderx2013decoderstructureincomplexscenes AT yimingzhang movingobjectdetectionmethodviaresnet18withencoderx2013decoderstructureincomplexscenes AT bingtu movingobjectdetectionmethodviaresnet18withencoderx2013decoderstructureincomplexscenes AT guoyunzhang movingobjectdetectionmethodviaresnet18withencoderx2013decoderstructureincomplexscenes AT jianhuiwu movingobjectdetectionmethodviaresnet18withencoderx2013decoderstructureincomplexscenes AT wujingli movingobjectdetectionmethodviaresnet18withencoderx2013decoderstructureincomplexscenes |