TY - JOUR
T1 - A W-shaped convolutional network for robust crop and weed classification in agriculture
AU - Moazzam, Syed Imran
AU - Nawaz, Tahir
AU - Qureshi, Waqar S.
AU - Khan, Umar S.
AU - Tiwana, Mohsin Islam
N1 - Publisher Copyright:
© 2023, The Author(s).
PY - 2023/10
Y1 - 2023/10
N2 - Agricultural image and vision computing are significantly different from other object classification-based methods because two base classes in agriculture, crops and weeds, have many common traits. Efficient crop, weeds, and soil classification are required to perform autonomous (spraying, harvesting, etc.) activities in agricultural fields. In a three-class (crop–weed–background) agricultural classification scenario, it is usually easier to accurately classify the background class than the crop and weed classes because the background class appears significantly different feature-wise than the crop and weed classes. However, robustly distinguishing between the crop and weed classes is challenging because their appearance features generally look very similar. To address this problem, we propose a framework based on a convolutional W-shaped network with two encoder–decoder structures of different sizes. The first encoder–decoder structure differentiates between background and vegetation (crop and weed), and the second encoder–decoder structure learns discriminating features to classify crop and weed classes efficiently. The proposed W network is generalizable for different crop types. The effectiveness of the proposed network is demonstrated on two crop datasets—a tobacco dataset and a sesame dataset, both collected in this study and made available publicly online for use by the community—by evaluating and comparing the performance with existing related methods. The proposed method consistently outperforms existing related methods on both datasets.
AB - Agricultural image and vision computing are significantly different from other object classification-based methods because two base classes in agriculture, crops and weeds, have many common traits. Efficient crop, weeds, and soil classification are required to perform autonomous (spraying, harvesting, etc.) activities in agricultural fields. In a three-class (crop–weed–background) agricultural classification scenario, it is usually easier to accurately classify the background class than the crop and weed classes because the background class appears significantly different feature-wise than the crop and weed classes. However, robustly distinguishing between the crop and weed classes is challenging because their appearance features generally look very similar. To address this problem, we propose a framework based on a convolutional W-shaped network with two encoder–decoder structures of different sizes. The first encoder–decoder structure differentiates between background and vegetation (crop and weed), and the second encoder–decoder structure learns discriminating features to classify crop and weed classes efficiently. The proposed W network is generalizable for different crop types. The effectiveness of the proposed network is demonstrated on two crop datasets—a tobacco dataset and a sesame dataset, both collected in this study and made available publicly online for use by the community—by evaluating and comparing the performance with existing related methods. The proposed method consistently outperforms existing related methods on both datasets.
KW - Crops and weeds
KW - Pixel-level classification
KW - Semantic segmentation
KW - Weed detection
UR - http://www.scopus.com/inward/record.url?scp=85159049000&partnerID=8YFLogxK
U2 - 10.1007/s11119-023-10027-7
DO - 10.1007/s11119-023-10027-7
M3 - Article
SN - 1385-2256
VL - 24
SP - 2002
EP - 2018
JO - Precision Agriculture
JF - Precision Agriculture
IS - 5
ER -