Crop Loss Evaluation Using Digital Surface Models from Unmanned Aerial Vehicles Data
Bibliographic record
Abstract
Precision agriculture and Unmanned Aerial Vehicles (UAV) are revolutionizing agriculture management methods. Remote sensing data, image analysis and Digital Surface Models derived from Structure from Motion and Multi-View Stereopsis offer new and fast methods to detect the needs of crops, greatly improving crops efficiency. In this study, we present a tool to detect and estimate crop damage after a disturbance (i.e., weather event, wildlife attacks or fires). The types of damage that are addressed in this study affect crop structure (i.e., plants are bent or gone), in the shape of depressions in the crop canopy. The aim of this study was to evaluate the performance of four unsupervised methods based on terrain analyses, for the detection of damaged crops in UAV 3D models: slope detection, variance analysis, geomorphology classification and cloth simulation filter. A full workflow was designed and described in this article that involves the postprocessing of the raw results from the terrain analyses, for a refinement in the detection of damages. Our results show that all four methods performed similarly well after postprocessing––reaching an accuracy above to 90%––in the detection of severe crop damage, without the need of training data. The results of this study suggest that the used methods are effective and independent of the crop type, crop damage and growth stage. However, only severe damages were detected with this workflow. Other factors such as data volume, processing time, number of processing steps and spatial distribution of targets and errors are discussed in this article for the selection of the most appropriate method. Among the four tested methods, slope analysis involves less processing steps, generates the smallest data volume, is the fastest of methods and resulted in best spatial distribution of matches. Thus, it was selected as the most efficient method for crop damage detection.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".