update readme

README.md

@@ -3,7 +3,7 @@ title: horizon-metrics
 tags:
   - evaluate
   - metric
-description: "TODO: add a description here"
+description: "This huggingface metric calculates horizon evaluation metrics using `seametrics.horizon.HorizonMetrics`."
 sdk: gradio
 sdk_version: 3.19.1
 app_file: app.py
@@ -25,7 +25,7 @@ To get started with horizon-metrics, make sure you have the necessary dependenci
 
 ### Installation
 
-```bash
+```sh
   pip install evaluate git+https://github.com/SEA-AI/seametrics@develop
 ```
 
@@ -52,23 +52,25 @@ prediction_points = [[[0.0, 0.5428930956049597], [1.0, 0.4642497615378973]],
 ##### Load data from fiftyone
 
 ```python
-sequence = "Sentry_2023_02_Portugal_2023_01_24_19_15_17"
+# Load data from fiftyone
+sequence = "Sentry_2022_11_PROACT_CELADON_7.5M_MOB_2022_11_25_12_29_48"
 dataset_name = "SENTRY_VIDEOS_DATASET_QA"
 sequence_view = fo.load_dataset(dataset_name).match(F("sequence") == sequence)
 sequence_view = sequence_view.select_group_slices("thermal_wide")
 
+# Get the ground truth points
 polylines_gt = sequence_view.values("frames.ground_truth_pl")
 ground_truth_points = [
-    line["polylines"][0]["points"][0] for line in polylines_gt[0]
-    if line is not None
+    line["polylines"][0]["points"][0] if line is not None else None
+    for line in polylines_gt[0]
 ]
 
+# Get the predicted points
 polylines_pred = sequence_view.values(
-    "frames.ahoy-IR-b2-whales__XAVIER-AGX-JP46_pl")
+    "frames.ahoy-IR-b2-whales__XAVIER-AGX-JP46_pl_TnFoV")
 prediction_points = [
-    line["polylines"][0]["points"][0] for line in polylines_pred[0]
-    if line is not None
-]
+    line["polylines"][0]["points"][0] if line is not None else None
+    for line in polylines_pred[0]
 ```
 
 ##### Calculate horizon metrics
@@ -76,38 +78,45 @@ prediction_points = [
 ```python
 import evaluate
 
-module = evaluate.load("SEA-AI/horizon-metrics")
-module.add(predictions=ground_truth_points, references=prediction_points)
+module = evaluate.load("SEA-AI/horizon-metrics", roll_threshold=0.5, pitch_threshold=0.1, vertical_fov_degrees=25.6, height=512)
+module.add(predictions=prediction_points, references=ground_truth_points)
 module.compute()
+
 ```
 
 This is output the evalutaion metrics for your horizon prediciton model:
 
-```python
-{
-  'average_slope_error': 0.014823194839790999,
-  'average_midpoint_error': 0.014285714285714301,
-  'stddev_slope_error': 0.01519178791378349,
-  'stddev_midpoint_error': 0.0022661781575342445,
-  'max_slope_error': 0.033526146567062376,
-  'max_midpoint_error': 0.018161272321428612,
-  'num_slope_error_jumps': 1,
-  'num_midpoint_error_jumps': 1
-}
+```console
+{'average_slope_error': 0.39394822776758726,
+ 'average_midpoint_error': 0.0935801366906932,
+ 'average_midpoint_error_px': 1.871602733813864,
+ 'stddev_slope_error': 0.3809031270343266,
+ 'stddev_midpoint_error': 0.23003871087476538,
+ 'stddev_midpoint_error_px': 4.6007742174953075,
+ 'max_slope_error': 3.5549008029526132,
+ 'max_midpoint_error': 2.515424321301225,
+ 'max_midpoint_error_px': 50.3084864260245,
+ 'num_slope_error_jumps': 173,
+ 'num_midpoint_error_jumps': 205,
+ 'detection_rate': 0.2606486908948808}
 ```
 
 ### Output Values
 
 SEA-AI/horizon-metrics provides the following performance metrics for horizon prediction:
 
-- **average_slope_error**: Measures the average difference in slope between the predicted and ground truth horizon.
-- **average_midpoint_error**: Calculates the average difference in midpoint position between the predicted and ground truth horizon.
-- **stddev_slope_error**: Indicates the variability of errors in slope between the predicted and ground truth horizon.
-- **stddev_midpoint_error**: Quantifies the variability of errors in midpoint position between the predicted and ground truth horizon.
-- **max_slope_error**: Represents the maximum difference in slope between the predicted and ground truth horizon.
-- **max_midpoint_error**: Indicates the maximum difference in midpoint position between the predicted and ground truth horizon.
+- **average_slope_error**: Measures the average difference in slope between the predicted and ground truth horizon in degree.
+- **average_midpoint_error**: Represents the average difference in midpoint position between the predicted and ground truth horizon.
+- **average_midpoint_error_px**: Represents the average difference in midpoint position between the predicted and ground truth horizon, measured in pixels.
+- **stddev_slope_error**: Indicates the variability of errors in slope between the predicted and ground truth horizon in degree.
+- **stddev_midpoint_error**: Quantifies the variability of errors in midpoint position between the predicted and ground truth horizon in degree.
+- **stddev_midpoint_error_px**: Quantifies the variability of errors in midpoint position between the predicted and ground truth horizon, measured in pixels.
+- **max_slope_error**: Represents the maximum difference in slope between the predicted and ground truth horizon in degree.
+- **max_midpoint_error**: Indicates the maximum difference in midpoint position between the predicted and ground truth horizon in degree.
+- **max_midpoint_error_px**: Indicates the maximum difference in midpoint position between the predicted and ground truth horizon, measured in pixels.
 - **num_slope_error_jumps**: Calculates the differences between errors in successive frames for the slope. It then counts the number of jumps in these errors by comparing the absolute differences to a specified threshold.
 - **num_midpoint_error_jumps**: Calculates the differences between errors in successive frames for the midpoint. It then counts the number of jumps in these errors by comparing the absolute differences to a specified threshold.
+- **detection_rate**: Measures the proportion of frames in which the horizon is successfully detected out of the total number of frames.
 
 ## Further References