Classification from Sky: A Robust Remote Sensing Time Series Image Classification Using Spatial Encoder and Multi-Fast Channel Attention
The unparalleled availability of Satellite Image Time Series (SITS) for crop phenology classification unravels agricultural parcel observation and monitoring with applications of both economic and ecological importance. Moreover, the need for distinct classification of agricultural parcels into indi...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-11-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157822003962 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849316097281490944 |
|---|---|
| author | Kwabena Sarpong Jehoiada Kofi Jackson Derrick Effah Daniel Addo Sophyani Banaamwini Yussif Mohammad Awrangjeb Rutherford Agbeshi Patamia Juliana Mantebea Danso Zhiguang Qin |
| author_facet | Kwabena Sarpong Jehoiada Kofi Jackson Derrick Effah Daniel Addo Sophyani Banaamwini Yussif Mohammad Awrangjeb Rutherford Agbeshi Patamia Juliana Mantebea Danso Zhiguang Qin |
| author_sort | Kwabena Sarpong |
| collection | DOAJ |
| description | The unparalleled availability of Satellite Image Time Series (SITS) for crop phenology classification unravels agricultural parcel observation and monitoring with applications of both economic and ecological importance. Moreover, the need for distinct classification of agricultural parcels into individual crop types falls on state-of-the-art deep learning models for this extrinsic task. However, most existing approaches implemented are complex and ineffective attention incorporated models, which in turn lack the resilience to recognize useful bands in achieving greater accuracy. We propose a Multi-Fast Channel Attention module for deep CNNs based on a Spatial Encoder (SE-MFCA) that requires a few parameters while enhancing the performance-complexity trade-off dilemma. Hence, we leverage on spatial encoder module to extract the images as disorderly sets of pixels to enhance the coarse spatial resolution features. We empirically show that appropriate parameter sharing in the cross channel interaction can preserve performance while significantly reducing model complexity. The proposed multi-channel attention module can efficiently be implemented via an encoder-decoder network to prevent the loss of detailed spatial information. Again, we parallelly distributed the input channel into multiple heads in our network to recover the specialized input features, which will concatenate with the residual to form a rich single feature representation. The extensive experiment has shown that our model SE-MFCA is efficient and effective compared with the previous state-of-the-art time series classification algorithm on a publicly available dataset of Sentinel-2 images for agricultural parcels. Performance-wise SE-MFCA achieves the highest overall accuracy of 94.50% and the highest mean intersection over union score of 51.92%, besides the least trainable params of 131 K and fewer floating point operations of 0.16 M. |
| format | Article |
| id | doaj-art-e2fb174522614245b4c9132a87d52aba |
| institution | Kabale University |
| issn | 1319-1578 |
| language | English |
| publishDate | 2022-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj-art-e2fb174522614245b4c9132a87d52aba2025-08-20T03:51:58ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782022-11-013410104051042210.1016/j.jksuci.2022.10.029Classification from Sky: A Robust Remote Sensing Time Series Image Classification Using Spatial Encoder and Multi-Fast Channel AttentionKwabena Sarpong0Jehoiada Kofi Jackson1Derrick Effah2Daniel Addo3Sophyani Banaamwini Yussif4Mohammad Awrangjeb5Rutherford Agbeshi Patamia6Juliana Mantebea Danso7Zhiguang Qin8School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, Sichuan, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, Sichuan, ChinaSchool of Management Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, Sichuan, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, Sichuan, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, Sichuan, ChinaSchool of Information and Communication Technology, Griffith University, Nathan QLD 4111, Queensland, AustraliaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, Sichuan, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, Sichuan, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, Sichuan, China; Corresponding author at: Network and Data Security Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 610054, China.The unparalleled availability of Satellite Image Time Series (SITS) for crop phenology classification unravels agricultural parcel observation and monitoring with applications of both economic and ecological importance. Moreover, the need for distinct classification of agricultural parcels into individual crop types falls on state-of-the-art deep learning models for this extrinsic task. However, most existing approaches implemented are complex and ineffective attention incorporated models, which in turn lack the resilience to recognize useful bands in achieving greater accuracy. We propose a Multi-Fast Channel Attention module for deep CNNs based on a Spatial Encoder (SE-MFCA) that requires a few parameters while enhancing the performance-complexity trade-off dilemma. Hence, we leverage on spatial encoder module to extract the images as disorderly sets of pixels to enhance the coarse spatial resolution features. We empirically show that appropriate parameter sharing in the cross channel interaction can preserve performance while significantly reducing model complexity. The proposed multi-channel attention module can efficiently be implemented via an encoder-decoder network to prevent the loss of detailed spatial information. Again, we parallelly distributed the input channel into multiple heads in our network to recover the specialized input features, which will concatenate with the residual to form a rich single feature representation. The extensive experiment has shown that our model SE-MFCA is efficient and effective compared with the previous state-of-the-art time series classification algorithm on a publicly available dataset of Sentinel-2 images for agricultural parcels. Performance-wise SE-MFCA achieves the highest overall accuracy of 94.50% and the highest mean intersection over union score of 51.92%, besides the least trainable params of 131 K and fewer floating point operations of 0.16 M.http://www.sciencedirect.com/science/article/pii/S1319157822003962Agricultural parcelSatellite time seriesPhenologyDeep learningChannel attention |
| spellingShingle | Kwabena Sarpong Jehoiada Kofi Jackson Derrick Effah Daniel Addo Sophyani Banaamwini Yussif Mohammad Awrangjeb Rutherford Agbeshi Patamia Juliana Mantebea Danso Zhiguang Qin Classification from Sky: A Robust Remote Sensing Time Series Image Classification Using Spatial Encoder and Multi-Fast Channel Attention Journal of King Saud University: Computer and Information Sciences Agricultural parcel Satellite time series Phenology Deep learning Channel attention |
| title | Classification from Sky: A Robust Remote Sensing Time Series Image Classification Using Spatial Encoder and Multi-Fast Channel Attention |
| title_full | Classification from Sky: A Robust Remote Sensing Time Series Image Classification Using Spatial Encoder and Multi-Fast Channel Attention |
| title_fullStr | Classification from Sky: A Robust Remote Sensing Time Series Image Classification Using Spatial Encoder and Multi-Fast Channel Attention |
| title_full_unstemmed | Classification from Sky: A Robust Remote Sensing Time Series Image Classification Using Spatial Encoder and Multi-Fast Channel Attention |
| title_short | Classification from Sky: A Robust Remote Sensing Time Series Image Classification Using Spatial Encoder and Multi-Fast Channel Attention |
| title_sort | classification from sky a robust remote sensing time series image classification using spatial encoder and multi fast channel attention |
| topic | Agricultural parcel Satellite time series Phenology Deep learning Channel attention |
| url | http://www.sciencedirect.com/science/article/pii/S1319157822003962 |
| work_keys_str_mv | AT kwabenasarpong classificationfromskyarobustremotesensingtimeseriesimageclassificationusingspatialencoderandmultifastchannelattention AT jehoiadakofijackson classificationfromskyarobustremotesensingtimeseriesimageclassificationusingspatialencoderandmultifastchannelattention AT derrickeffah classificationfromskyarobustremotesensingtimeseriesimageclassificationusingspatialencoderandmultifastchannelattention AT danieladdo classificationfromskyarobustremotesensingtimeseriesimageclassificationusingspatialencoderandmultifastchannelattention AT sophyanibanaamwiniyussif classificationfromskyarobustremotesensingtimeseriesimageclassificationusingspatialencoderandmultifastchannelattention AT mohammadawrangjeb classificationfromskyarobustremotesensingtimeseriesimageclassificationusingspatialencoderandmultifastchannelattention AT rutherfordagbeshipatamia classificationfromskyarobustremotesensingtimeseriesimageclassificationusingspatialencoderandmultifastchannelattention AT julianamantebeadanso classificationfromskyarobustremotesensingtimeseriesimageclassificationusingspatialencoderandmultifastchannelattention AT zhiguangqin classificationfromskyarobustremotesensingtimeseriesimageclassificationusingspatialencoderandmultifastchannelattention |