Create Social Distance Detection

The Social Distance Detection system is a Python application that uses OpenCV and deep learning techniques to monitor and determine whether individuals in a specified area are maintaining appropriate social distancing. This tool is particularly useful in public spaces to promote safety during health crises.

Author: Kirti-Pant

Diff for: Social Distance Detection

@@ -0,0 +1,67 @@
+import cv2
+import numpy as np
+net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
+layer_names = net.getLayerNames()
+output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
+def calculate_distance(point1, point2):
+    return np.linalg.norm(np.array(point1) - np.array(point2))
+def social_distance_detection(video_source=0):
+    cap = cv2.VideoCapture(video_source)
+
+    while True:
+        # Read frame from the video source
+        ret, frame = cap.read()
+        height, width, _ = frame.shape
+        
+        # Detecting objects
+        blob = cv2.dnn.blobFromImage(frame, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
+        net.setInput(blob)
+        outputs = net.forward(output_layers)
+
+        boxes = []
+        confidences = []
+        class_ids = []
+        for output in outputs:
+            for detection in output:
+                scores = detection[5:]
+                class_id = np.argmax(scores)
+                confidence = scores[class_id]
+                
+                # Filter only person class (ID 0 for COCO dataset)
+                if confidence > 0.5 and class_id == 0:
+                    center_x = int(detection[0] * width)
+                    center_y = int(detection[1] * height)
+                    w = int(detection[2] * width)
+                    h = int(detection[3] * height)
+                    # Rectangle coordinates
+                    x = int(center_x - w / 2)
+                    y = int(center_y - h / 2)
+
+                    boxes.append([x, y, w, h])
+                    confidences.append(float(confidence))
+                    class_ids.append(class_id)
+
+        indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
+        detected_points = []
+        for i in range(len(boxes)):
+            if i in indexes:
+                x, y, w, h = boxes[i]
+                cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
+                cx, cy = x + w // 2, y + h // 2
+                detected_points.append((cx, cy))
+                cv2.putText(frame, "Person", (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+
+        for i in range(len(detected_points)):
+            for j in range(i + 1, len(detected_points)):
+                dist = calculate_distance(detected_points[i], detected_points[j])
+                if dist < 100:  # Distance threshold (e.g., 100 pixels)
+                    cv2.putText(frame, "Maintain distance!", (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
+        cv2.imshow("Social Distance Detection", frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+if __name__ == "__main__":
+    social_distance_detection()