docs

README.md

@@ -31,3 +31,5 @@ Pfad | Beschreibung
 ### Architektur
 
 ![Architektur Übersicht](arch.png)
+
+Es wurden nur die Komponenten mit einer soliden Umrandung umgesetzt.

server/app.py

@@ -13,6 +13,7 @@ from flask import Flask, jsonify, Response, send_file
 
 application = Flask(__name__)
 
+# init the "database"
 clients = []
 cams = []
 lastImages = list(range(0,10))
@@ -22,6 +23,7 @@ with open("./clients.json", 'r', encoding='utf-8') as f:
 with open("./cams.json", 'r', encoding='utf-8') as f:
     cams = json.loads(f.read())
 
+# provides th function used for the live streams
 class VideoCamera(object):
     """Video stream object"""
     def __init__(self, url):
@@ -60,6 +62,7 @@ def main():
     for cam in cams:
         cam["last_detection"] = 0
 
+    # check all camers sequentially while the server is running
     while True:
         for cam in cams:
             stream = cam["ip"]
@@ -126,11 +129,8 @@ def cam_stream(num):
 
 @application.route('/cam/<num>/processed')
 def cam_stream_processed(num):
-    #frame = cv2.imencode('.jpg', lastImages[int(num)])[1]
-    #return send_file(io.BytesIO(frame), mimetype='image/jpeg')
     return Response(gen_processed(num), mimetype='multipart/x-mixed-replace; boundary=frame')
 
-
 #########           ###########
 ###         Start           ###
 #########           ###########
@@ -138,5 +138,4 @@ def cam_stream_processed(num):
 if __name__ == '__main__':
 
     _thread.start_new_thread(main, () )
-
     application.run(host='0.0.0.0', port=5000, threaded=True)

server/detector.py

@@ -6,7 +6,8 @@ import numpy as np
 import tensorflow as tf
 import cv2
 
-
+# Detector API can be changed out given the I/O remains the same
+# this way you can use a different N-Net if you like to
 class DetectorAPI:
     def __init__(self, path_to_ckpt):
         self.path_to_ckpt = path_to_ckpt
@@ -70,7 +71,7 @@ class Detector:
         r, img = cap.read()
         if img is None:
             return img
-
+        # scale the image down for faster processing
         scale_percent = 60 # percent of original size
         width = int(img.shape[1] * scale_percent / 100)
         height = int(img.shape[0] * scale_percent / 100)
@@ -78,10 +79,12 @@ class Detector:
 
         img = cv2.resize(img, dim)
 
+        # get the results from the net
         boxes, scores, classes, num = self.odapi.process_frame(img)
         res = False
         for i in range(len(boxes)):
             # Class 1 represents human
+            # draw recogniction boxes and return resulting image + true/false
             if classes[i] == 1:
                 if scores[i] > self.threshold:
                     box = boxes[i]
@@ -92,10 +95,3 @@ class Detector:
                     res = False
                     return img, res
 
-        
-            
-    #def __del__(self):
-
-        #self.cap.release()
-        #cv2.destroyAllWindows()
-        #requests.get("http://192.168.178.53/stop")