Create common_detection.py

common_detection.py

@@ -0,0 +1,41 @@
+# common_detection.py
+import cv2
+import numpy as np
+from PIL import Image
+
+def perform_detection(image, interpreter, labels, input_details, output_details, height, width, floating_model):
+    imH, imW, _ = image.shape
+    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    image_resized = cv2.resize(image_rgb, (width, height))
+    input_data = np.expand_dims(image_resized, axis=0)
+
+    input_mean = 127.5
+    input_std = 127.5
+    if floating_model:
+        input_data = (np.float32(input_data) - input_mean) / input_std
+
+    interpreter.set_tensor(input_details[0]['index'], input_data)
+    interpreter.invoke()
+
+    boxes = interpreter.get_tensor(output_details[0]['index'])[0]
+    classes = interpreter.get_tensor(output_details[1]['index'])[0]
+    scores = interpreter.get_tensor(output_details[2]['index'])[0]
+
+    detections = []
+    for i in range(len(scores)):
+        if (scores[i] > 0.5):
+            ymin = int(max(1, (boxes[i][0] * imH)))
+            xmin = int(max(1, (boxes[i][1] * imW)))
+            ymax = int(min(imH, (boxes[i][2] * imH)))
+            xmax = int(min(imW, (boxes[i][3] * imW)))
+            
+            cv2.rectangle(image, (xmin, ymin), (xmax, ymax), (10, 255, 0), 2)
+            object_name = labels[int(classes[i])]
+            label = f'{object_name}: {int(scores[i] * 100)}%'
+            labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2)
+            label_ymin = max(ymin, labelSize[1] + 10)
+            cv2.rectangle(image, (xmin, label_ymin - labelSize[1] - 10), (xmin + labelSize[0], label_ymin + baseLine - 10), (255, 255, 255), cv2.FILLED)
+            cv2.putText(image, label, (xmin, label_ymin - 7), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 0), 2)
+
+            detections.append([object_name, scores[i], xmin, ymin, xmax, ymax])
+    return image