Evaluation of egohumans dataset.

scripts/test_skelda_dataset.py

@@ -25,6 +25,7 @@ dataset_use = "human36m"
 # dataset_use = "ikeaasm"
 # dataset_use = "tsinghua"
 # dataset_use = "human36m_wb"
+# dataset_use = "egohumans"
 datasets = {
     "panoptic": {
         "path": "/datasets/panoptic/skelda/test.json",
@@ -63,6 +64,17 @@ datasets = {
         "path": "/datasets/human36m/skelda/wb/test.json",
         "take_interval": 100,
     },
+    "egohumans": {
+        "path": "/datasets/egohumans/skelda/all.json",
+        "take_interval": 2,
+        # "subset": "tagging",
+        "subset": "legoassemble",
+        # "subset": "fencing",
+        # "subset": "basketball",
+        # "subset": "volleyball",
+        # "subset": "badminton",
+        # "subset": "tennis",
+    },
 }
 
 joint_names_2d = test_triangulate.joint_names_2d
@@ -169,6 +181,13 @@ def load_labels(dataset: dict):
     elif "human36m_wb" in dataset:
         labels = load_json(dataset["human36m_wb"]["path"])
 
+    elif "egohumans" in dataset:
+        labels = load_json(dataset["egohumans"]["path"])
+        labels = [lb for lb in labels if "test" in lb["splits"]]
+        labels = [lb for lb in labels if dataset["egohumans"]["subset"] in lb["seq"]]
+        if dataset["egohumans"]["subset"] in ["volleyball", "tennis"]:
+            labels = [lb for i, lb in enumerate(labels) if i % 150 < 60]
+
     else:
         raise ValueError("Dataset not available")
 
@@ -215,8 +234,8 @@ def main():
     print(labels[0])
 
     minscores = {
-        # Choose this depending on the fraction of invalid/missing persons
-        # A higher value reduces the number of proposals
+        # Describes how good two 2D poses need to match each other to create a valid triangulation
+        # If the quality of the 2D detections is poor, use a lower value
         "panoptic": 0.94,
         "human36m": 0.94,
         "mvor": 0.86,
@@ -224,19 +243,32 @@ def main():
         "shelf": 0.96,
         "ikeaasm": 0.89,
         "tsinghua": 0.96,
+        "egohumans": 0.95,
         "human36m_wb": 0.94,
         "koarob": 0.91,
     }
     minscore = minscores.get(dataset_use, 0.95)
     min_group_sizes = {
+        # Describes the minimum number of camera pairs that need to detect the same person
         # If the number of cameras is high, and the views are not occluded, use a higher value
         "panoptic": 1,
         "shelf": 2,
         "tsinghua": 2,
+        "egohumans": 4,
     }
     min_group_size = min_group_sizes.get(dataset_use, 1)
     if dataset_use == "panoptic" and len(datasets["panoptic"]["cams"]) == 10:
         min_group_size = 4
+    if dataset_use == "egohumans" and (
+        "lego" in labels[0]["seq"] or "tagging" in labels[0]["seq"]
+    ):
+        min_group_size = 2
+    if dataset_use == "egohumans" and (
+        "volleyball" in labels[0]["seq"] or "badminton" in labels[0]["seq"]
+    ):
+        min_group_size = 7
+    if dataset_use == "egohumans" and "tennis" in labels[0]["seq"]:
+        min_group_size = 11
 
     print("\nRunning predictions ...")
     all_poses = []