Fix webp animation link to point to main branch; bump citation example to v1.3.0

README.md

@@ -2,15 +2,12 @@
 license: cc-by-4.0
 base_model:
 - Ultralytics/YOLOv8
-base_model_relation: finetune
 pipeline_tag: object-detection
 library_name: ultralytics
-num_parameters: 11137922
 github: https://github.com/rfonod/geo-trax
 language:
 - en
 tags:
-- ultralytics
 - yolov8
 - object-detection
 - aerial-imagery
@@ -68,7 +65,7 @@ comprehensive pipeline for extracting georeferenced vehicle trajectories from hi
 (bird's-eye view) video footage. The model detects vehicles in aerial imagery and underpins the
 results reported in the associated [publication](https://doi.org/10.1016/j.trc.2025.105205).
 
-![Geo-trax Output Visualization](https://raw.githubusercontent.com/rfonod/geo-trax/v1.0.0/assets/geo-trax_visualization.webp)
+![Geo-trax Output Visualization](https://raw.githubusercontent.com/rfonod/geo-trax/main/assets/geo-trax_visualization.webp)
 
 🎬 This accelerated animation previews some of the capabilities of Geo-trax. Watch the full
 demonstration (~4 min) on [YouTube](https://youtu.be/gOGivL9FFLk).
@@ -80,7 +77,7 @@ demonstration (~4 min) on [YouTube](https://youtu.be/gOGivL9FFLk).
 | Architecture | YOLOv8s (HBB, horizontal bounding boxes) |
 | Input resolution | 1920 × 1920 px |
 | Classes | 6 trained (4 primary + 2 auxiliary; see below) |
-| Parameters | 11.1 M (11,137,922) |
+| Parameters | ~11 M |
 | Framework | [Ultralytics](https://github.com/ultralytics/ultralytics) ≥ 8.4.64 |
 | Trained on | 19,339 annotated aerial images (679,306 labeled instances); multi-stage, see [publication](https://doi.org/10.1016/j.trc.2025.105205) |
 | Validated on | [Songdo Vision](https://doi.org/10.5281/zenodo.13828407) test set (1,084 images, 55,124 vehicle instances) |
@@ -140,7 +137,7 @@ geotrax batch   video.mp4           # full pipeline including georeferencing (re
 See the Geo-trax [GitHub README](https://github.com/rfonod/geo-trax) for the full pipeline,
 configuration options, and georeferencing.
 
-### Direct Ultralytics inference (PyTorch)
+### Direct Ultralytics inference
 
 ```python
 from ultralytics import YOLO
@@ -158,24 +155,6 @@ results[0].show()
 > detection of small vehicles (motorcycles, distant cars). Pass `classes=[0, 1, 2, 3]` to
 > restrict inference to the four evaluated classes and suppress unreliable predictions.
 
-### ONNX inference
-
-An ONNX export (opset 12, static 1920 × 1920 input) is available for deployment without a PyTorch dependency:
-
-```python
-import numpy as np
-import onnxruntime as ort
-from huggingface_hub import hf_hub_download
-
-onnx_path = hf_hub_download(repo_id="rfonod/geo-trax", filename="geotrax_hbb_yolov8s_1920_v1.onnx")
-session = ort.InferenceSession(onnx_path, providers=["CPUExecutionProvider"])
-
-# Prepare input: BGR image resized/padded to 1920×1920, normalized to [0, 1]
-img = np.random.rand(1, 3, 1920, 1920).astype(np.float32)  # replace with real image
-outputs = session.run(None, {"images": img})
-# outputs[0] shape: (1, 10, 75600) — 10 = 4 bbox coords + 6 class scores
-```
-
 ## Training Data
 
 Training followed a multi-stage strategy starting from **YOLOv8s weights pretrained on COCO**
@@ -270,7 +249,7 @@ If you use this model, please cite the associated publication:
 ```
 
 If you additionally use the [Geo-trax software](https://github.com/rfonod/geo-trax), please
-also cite the specific version you used via its Zenodo record. For example, for version 1.0.0:
+also cite the specific version you used via its Zenodo record. For example, for version 1.3.0:
 
 ```bibtex
 @software{fonod2026geo-trax,
@@ -278,7 +257,7 @@ also cite the specific version you used via its Zenodo record. For example, for
   title   = {Geo-trax: A Comprehensive Framework for Georeferenced Vehicle Trajectory Extraction from Drone Imagery},
   url     = {https://github.com/rfonod/geo-trax},
   doi     = {10.5281/zenodo.12119542},
-  version = {1.0.0},
+  version = {1.3.0},
   year    = {2026}
 }
 ```