modified nms implementation using Adrians code

chapter6/flann.py

@@ -2,8 +2,8 @@
 import cv2
 from matplotlib import pyplot as plt
 
-queryImage = cv2.imread('images/bathory_album.jpg',0)
-trainingImage = cv2.imread('images/vinyls.jpg',0)
+queryImage = cv2.imread('../images/bathory_album.jpg',0)
+trainingImage = cv2.imread('../images/bathory_vinyls.jpg',0)
 
 # create SIFT and detect/compute
 sift = cv2.xfeatures2d.SIFT_create()

chapter7/car_detector/non_maximum.py

@@ -1,50 +1,60 @@
 # import the necessary packages
 import numpy as np
 
-def area(box):
-  return (abs(box[2] - box[0])) * (abs(box[3] - box[1]))
-
-def overlaps(a, b, thresh=0.5):
-  print "checking overlap "
-  print a, b
-  x1 = np.maximum(a[0], b[0])
-  x2 = np.minimum(a[2], b[2])
-  y1 = np.maximum(a[1], b[1])
-  y2 = np.minimum(a[3], b[3])
-  intersect = float(area([x1, y1, x2, y2]))
-  return intersect / np.minimum(area(a), area(b)) >= thresh
-
-def is_inside(rec1, rec2):
-  def inside(a,b):
-    if (a[0] >= b[0]) and (a[2] <= b[0]):
-      return (a[1] >= b[1]) and (a[3] <= b[3])
-    else:
-      return False
-
-  return (inside(rec1, rec2) or inside(rec2, rec1))
-
-def non_max_suppression(boxes, overlap_thresh = 0.5):
+# Malisiewicz et al.
+# Python port by Adrian Rosebrock
+def non_max_suppression_fast(boxes, overlapThresh):
   # if there are no boxes, return an empty list
   if len(boxes) == 0:
     return []
 
+  # if the bounding boxes integers, convert them to floats --
+  # this is important since we'll be doing a bunch of divisions
+  if boxes.dtype.kind == "i":
+    boxes = boxes.astype("float")
+
+  # initialize the list of picked indexes 
+  pick = []
+
+  # grab the coordinates of the bounding boxes
+  x1 = boxes[:,0]
+  y1 = boxes[:,1]
+  x2 = boxes[:,2]
+  y2 = boxes[:,3]
   scores = boxes[:,4]
-  score_idx = np.argsort(scores)
-
-  while len(score_idx) > 0:
-    box = scores[score_idx[0]]
-    print "checking box"
-    for s in score_idx:
-      to_delete = []
-      if s == 0:
-        continue
-      try:
-        if (overlaps(boxes[s], boxes[box], overlap_thresh)):
-          to_delete.append(box)
-          score_idx = np.delete(score_idx, [s], 0)
-      except:
-        pass
-    boxes = np.delete(boxes, to_delete, 0)
-    score_idx = np.delete(score_idx, 0, 0)
-
-  return boxes
+  # compute the area of the bounding boxes and sort the bounding
+  # boxes by the score/probability of the bounding box
+  area = (x2 - x1 + 1) * (y2 - y1 + 1)
+  idxs = np.argsort(scores)[::-1]
+
+  # keep looping while some indexes still remain in the indexes
+  # list
+  while len(idxs) > 0:
+    # grab the last index in the indexes list and add the
+    # index value to the list of picked indexes
+    last = len(idxs) - 1
+    i = idxs[last]
+    pick.append(i)
+
+    # find the largest (x, y) coordinates for the start of
+    # the bounding box and the smallest (x, y) coordinates
+    # for the end of the bounding box
+    xx1 = np.maximum(x1[i], x1[idxs[:last]])
+    yy1 = np.maximum(y1[i], y1[idxs[:last]])
+    xx2 = np.minimum(x2[i], x2[idxs[:last]])
+    yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+    # compute the width and height of the bounding box
+    w = np.maximum(0, xx2 - xx1 + 1)
+    h = np.maximum(0, yy2 - yy1 + 1)
+
+    # compute the ratio of overlap
+    overlap = (w * h) / area[idxs[:last]]
+
+    # delete all indexes from the index list that have
+    idxs = np.delete(idxs, np.concatenate(([last],
+      np.where(overlap > overlapThresh)[0])))
+
+  # return only the bounding boxes that were picked using the
+  # integer data type
+  return boxes[pick].astype("int")

chapter7/car_sliding_windows.py

@@ -9,9 +9,9 @@
 def in_range(number, test, thresh=0.2):
   return abs(number - test) < thresh
 
-test_image = "/home/d3athmast3r/dev/python/study/images/cars.jpg"
-img_path = "/home/d3athmast3r/dev/python/study/images/test.jpg"
-# remote = "http://previews.123rf.com/images/aremac/aremac0903/aremac090300044/4545419-Lonely-car-on-an-empty-parking-lot-Stock-Photo.jpg"
+test_image = "/home/d3athmast3r/dev/python/pycv/images/cars.jpg"
+img_path = "/home/d3athmast3r/dev/python/pycv/images/test.jpg"
+
 urllib.urlretrieve(test_image, img_path)
 
 svm, extractor = car_detector()

chapter8/surveillance_demo/main.py

@@ -96,8 +96,8 @@ def update(self, frame):
         cv2.LINE_AA)
 
 def main():
-  camera = cv2.VideoCapture(path.join(path.dirname(__file__), "traffic.flv"))
-  # camera = cv2.VideoCapture(path.join(path.dirname(__file__), "768x576.avi"))
+  # camera = cv2.VideoCapture(path.join(path.dirname(__file__), "traffic.flv"))
+  camera = cv2.VideoCapture(path.join(path.dirname(__file__), "768x576.avi"))
   # camera = cv2.VideoCapture(path.join(path.dirname(__file__), "..", "movie.mpg"))
   # camera = cv2.VideoCapture(0)
   history = 20
@@ -115,8 +115,8 @@ def main():
   pedestrians = {}
   firstFrame = True
   frames = 0
-
-
+  fourcc = cv2.VideoWriter_fourcc(*'XVID')
+  out = cv2.VideoWriter('output.avi',fourcc, 20.0, (640,480))
   while True:
     print " -------------------- FRAME %d --------------------" % frames
     grabbed, frane = camera.read()
@@ -156,8 +156,11 @@ def main():
     frames += 1
 
     cv2.imshow("surveillance", frame)
+    out.write(frame)
     if cv2.waitKey(110) & 0xff == 27:
         break
+  out.release()
+  camera.release()
 
 if __name__ == "__main__":
   main()