
V. Geethalakshmi
Ex-Vice ChancellorTamil Nadu Agricultural University Coimbatore, INDIA

Submitted
2026/07/17First Online
2026/09/11doi
10.18805/IJARe.A-6640Cite article - Deekshitha Arasa, S. Sivaramakrishnan, Sneha Sharma. (2026). AgriVision: Recognition-oriented Video Super-resolution for Weed Classification in Precision Agriculture. Indian Journal of Agricultural Research. 60: 49–57. doi: 10.18805/IJARe.A-6640
Background: Accurate weed identification is essential for precision agriculture, but low-resolution field images reduce recognition accuracy. This study proposes AgriVision, a lightweight task-aware video super-resolution framework for improving weed classification.
Methods: Five-frame pseudo-video sequences were generated from the DeepWeeds dataset. A lightweight video super-resolution network with HR-faithful and task-aware learning modes was developed and evaluated using PSNR, SSIM and weed classification accuracy.
Result: The HR-faithful model achieved 29.34 dB PSNR while the task-aware model achieved 0.8623 SSIM and improved classification accuracy from 70.33% to 84.17%, approaching the HR upper bound of 87.50%.
Distinguished scholars and subject experts committed to editorial excellence, scientific integrity and rigorous peer review.
View Full Board