Better structure

Author: Vaibhav

Readme.md

@@ -1,4 +1,4 @@
-# VideoStabilization 
+# VideoStabilization
 
 ## Description
 
@@ -20,13 +20,16 @@ Finally a cropped region of the video is outputted where the cropped region box
 
 ## How To
 
-* Run the webapp: 	
-```console
-	bar@foo:~/VideoStabilization$ python3 preproc.py <video_file>
-	bar@foo:~/VideoStabilization$ python3 stabilize.py
-	bar@foo:~/VideoStabilization$ python3 generate.py <video_file>	
+* Run:
+
+```bash
+bar@foo:~/VideoStabilization$ python3 src/preproc.py <video_file_path>
+bar@foo:~/VideoStabilization$ python3 src/stabilize.py <Displacement_threshold_pixels>
+bar@foo:~/VideoStabilization$ python3 src/generate.py <video_file_path> <Displacement_threshold_pixels>
 ```
 
+Note: This will create some temporary pickle files, please ignore them.
+
 ## Built With
 
 * [Python3](https://www.python.org/download/releases/3.0/)

sampleVideos/vid1.mp4

@@ -4,6 +4,7 @@
 import sys
 
 sift = cv2.xfeatures2d.SIFT_create(200)
+
 def getAffMat(I1, I2):
     I1 = cv2.cvtColor(I1, cv2.COLOR_BGR2GRAY)
     I2 = cv2.cvtColor(I2, cv2.COLOR_BGR2GRAY)
@@ -15,12 +16,12 @@ def getAffMat(I1, I2):
     # Finding good matches using ratio testing
     bf = cv2.BFMatcher()
     matches = bf.knnMatch(desc1, desc2, k=2)
-    print('Before filtering->', len(matches))
+    
     good = []
     for m,n in matches:
         if m.distance < 0.7*n.distance:
             good.append(m)
-    print('After filtering->', len(good))
+
     pts_src = []
     pts_dst = []
     for i in range(len(good)):
@@ -35,27 +36,37 @@ def getAffMat(I1, I2):
 
 v = cv2.VideoCapture(sys.argv[1])
 n_frames = int(v.get(cv2.CAP_PROP_FRAME_COUNT))
+
 # Generating the Xdata and Ydata
 transforms = [[], [], [], []]
 count = 0
 while v.isOpened():
+    
     ret, frame = v.read()
+
     if ret == True:
+
         if count > 0:
             transMat = getAffMat(prev, frame)
-            transforms[0].append(transMat[0][2])
-            transforms[1].append(transMat[1][2])
-            transforms[2].append(np.arctan2(transMat[1][0], transMat[0][0]))
-            transforms[3].append(np.sqrt(transMat[1][0]**2 + transMat[0][0]**2))
-
+            try:
+                transforms[0].append(transMat[0][2])
+                transforms[1].append(transMat[1][2])
+                transforms[2].append(np.arctan2(transMat[1][0], transMat[0][0]))
+                transforms[3].append(np.sqrt(transMat[1][0]**2 + transMat[0][0]**2))
+            except:
+            	transforms[0].append(0)
+            	transforms[1].append(0)
+            	transforms[2].append(0)
+            	transforms[3].append(1)
+            
         count += 1
         prev = frame
-        print((count/n_frames)*100, '%')
+        print( str((count/n_frames)*100) + "% completed")
     else:
     	break
 
 v.release()
 
 # Storing the data
 with open('transforms.pkl', 'wb') as f:
-	pickle.dump(transforms, f)
+	pickle.dump(transforms, f)

shakey2.mp4 renamed to sampleVideos/vid2.mp4

@@ -51,21 +51,27 @@
 	obj += lbd3*(cp.abs(fx[i+3]-3*fx[i+2] + 3*fx[i+1]-fx[i]) + cp.abs(fy[i+3]-3*fy[i+2]+3*fy[i+1]-fy[i]) + cp.abs(fth[i+3]-3*fth[i+2]+3*fth[i+1]-fth[i]) + cp.abs(fs[i+3]-3*fs[i+2]+3*fs[i+1]-fs[i]))
 
 prob = cp.Problem(cp.Minimize(obj), constraints)
-prob.solve()
+print("Started Solving the optimization using ECOS")
+prob.solve(solver=cp.ECOS)
+print("Optimization solved")
 
 # Results
 plt.subplot(2, 2, 1)
 plt.plot(trajectory[0])
 plt.plot(fx.value)
+plt.title("Horizontal trajectory")
 plt.subplot(2, 2, 2)
 plt.plot(trajectory[1])
 plt.plot(fy.value)
+plt.title("Verical trajectory")
 plt.subplot(2, 2, 3)
 plt.plot(trajectory[2])
 plt.plot(fth.value)
+plt.title("Angle of rotn. trajectory")
 plt.subplot(2, 2, 4)
 plt.plot(trajectory[3])
 plt.plot(fs.value)
+plt.title("Scale trajectory")
 plt.show()
 
 smoothTrajectory = np.array([fx.value, fy.value, fth.value, fs.value])