Update services/thermal_service.py

services/thermal_service.py

@@ -1,23 +1,23 @@
-import cv2
+from transformers import DetrImageProcessor, DetrForObjectDetection
+import torch
 from PIL import Image
-from transformers import pipeline
+import cv2
 
-thermal_detector = pipeline("object-detection", model="facebook/detr-resnet-50")
+# Load model
+processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
+model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
 
 def detect_thermal_anomalies(frame):
-    pil_img = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
-    results = thermal_detector(pil_img)
-    boxes = []
+    image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+    inputs = processor(images=image, return_tensors="pt")
+    outputs = model(**inputs)
 
-    for result in results:
-        box = result["box"]
-        boxes.append((
-            int(box["xmin"]),
-            int(box["ymin"]),
-            int(box["xmax"]),
-            int(box["ymax"]),
-            result["score"],
-            result["label"],
-        ))
+    target_sizes = torch.tensor([image.size[::-1]])
+    results = processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[0]
+
+    boxes = []
+    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+        if score >= 0.9:
+            boxes.append(box.tolist())
 
     return boxes