Disease Detection in Cotton field using Deep Learning through UAV Imagery / (Record no. 615333)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02310nam a22001457a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 629.8 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Iqbal, Anwar |
| 245 ## - TITLE STATEMENT | |
| Title | Disease Detection in Cotton field using Deep Learning through UAV Imagery / |
| Statement of responsibility, etc. | Anwar Iqbal |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | Islamabad : |
| Name of producer, publisher, distributor, manufacturer | SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice | 2025. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 99p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | Cotton sustains the textile economies of 80+ countries with annual yield of 113 million<br/>bales, yet 30–60 % yield losses are still attributed to viral, bacterial and fungal diseases<br/>that remain undetected until manual field scouting. To address this critical issue, the<br/>use of Unmanned-aerial-vehicle (UAV) imagery combined with deep learning offers a<br/>scalable early-warning system, but existing models suffer from low early-stage<br/>accuracy, poor transferability and high computational cost. In this paper, we propose<br/>Cotton-Vision, a fully convolutional single-stage detector that synergizes three lightweight architectural innovations. The architectural changes include ghost bottleneck<br/>modules for 20 % parameter reduction, efficient channel-attention (ECA) for adaptive<br/>feature recalibration, and cross-stage partial (CSP) fusion for enriched gradient flow.<br/>The network is trained on local datasets of cotton collected from 7 different fields and<br/>comprised 2700+ drone images from local cotton farms in Punjab Province of Pakistan.<br/>Extensive augmentation (rotation, shear, exposure, saturation) yields 11704 training<br/>samples. On a held-out test set, Cotton-vision achieved a precision of 97.7%, a recall<br/>of 77.7%, a mAP@50 of 85.6%, and a mAP@50-95 of 76.6%. These results represent<br/>10-20% improvement in precision, recall and mAP over the leading models, including<br/>YOLOv5, YOLOv8, YOLOv11, YOLOv12, RT-DETR and RF-DTR. Through a<br/>comprehensive ablation study, we demonstrate that each of our proposed architectural<br/>enhancements contributes to the model's superior performance with 12%-16%<br/>improvement from the base model. Our findings confirm that this synergy of<br/>lightweight and attention-based modules provides a robust and computationally viable<br/>solution for early cotton disease detection. |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | MS Robotics and Intelligent Machine Engineering |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/56219">http://10.250.8.41:8080/xmlui/handle/123456789/56219</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Koha item type |
|---|---|---|---|---|---|---|---|
| School of Mechanical & Manufacturing Engineering (SMME) | School of Mechanical & Manufacturing Engineering (SMME) | E-Books | 11/12/2025 | 629.8 | SMME-TH-1194 | Thesis |