add timing to person detection

camera/counter_people.py

@@ -1,11 +1,12 @@
 #!/usr/bin/env python
 
+import argparse
 import numpy as np
-import imutils
 import cv2
-import argparse
-from video_stream import imagezmq
+import imutils
 from imutils.object_detection import non_max_suppression
+from video_stream import imagezmq
+
 
 '''
 Usage:
@@ -25,7 +26,7 @@ def detector(image):
 
     clone = image.copy()
 
-    (rects, weights) = HOGCV.detectMultiScale(image, winStride=(4, 4), padding=(8, 8), scale=1.05)
+    (rects, _) = HOGCV.detectMultiScale(image, winStride=(4, 4), padding=(8, 8), scale=1.05)
 
     # draw the original bounding boxes
     for (x, y, w, h) in rects:

camera/person_detection.py

@@ -1,15 +1,26 @@
 #!/usr/bin/env python
 
-from imutils.video import VideoStream
-from imutils.video import FPS
 import argparse
+#from datetime import datetime, time
+import time
+from statistics import median
+
 import imutils
+from imutils.video import VideoStream
+#from imutils.video import FPS
+
 import cv2
-from datetime import datetime, time
 import numpy as np
-import time as time2
 
-VISUAL_DEBUG=True
+frame_timer = None
+contour_timer = None
+detection_timer = None
+
+frame_time = []
+contour_time = []
+detection_time = []
+
+VISUAL_DEBUG = True
 
 def getArgs():
     """ Arguments """
@@ -22,18 +33,20 @@ def getArgs():
 
 def main():
     args = getArgs()
+    timer = Timer()
 
     # if the video argument is None, then the code will read from webcam (work in progress)
     if args.get("video", None) is None:
         vs = VideoStream(src=0).start()
-        time2.sleep(2.0)
+        time.sleep(2.0)
     # otherwise, we are reading from a video file
     else:
         vs = cv2.VideoCapture(args["video"])
 
     cv2.namedWindow('Video stream', cv2.WINDOW_NORMAL)
-    detector = DetectionFromFrame(args["min_area"], 0.8)
+    detector = DetectionFromFrame(args["min_area"], 0.5)
     while True:
+        timer.start_frame_timer()
         detector.currentFrame = vs.read()
         detector.currentFrame = detector.currentFrame if args.get("video", None) is None else detector.currentFrame[1]
         # if the frame can not be grabbed, then we have reached the end of the video
@@ -42,12 +55,13 @@ def main():
 
         # resize the frame to 500
         detector.currentFrame = imutils.resize(detector.currentFrame, width=500)
-        detector.framecounter+=1
+        detector.framecounter += 1
         if detector.framecounter > 1:
             cnts = detector.prepareFrame()
-            
+
             for c in cnts:
-                boundRect = cv2.boundingRect(c)
+                timer.start_contour_timer()
+                bound_rect = cv2.boundingRect(c)
                 #(x, y, w, h) = cv2.boundingRect(c)
                 #initBB2 =(x,y,w,h)
 
@@ -56,19 +70,24 @@ def main():
                 net = cv2.dnn.readNetFromCaffe(prott1, prott2)
 
                 #trackbox = detector.currentFrame[y:y+h, x:x+w]boundRect[1]
-                trackbox = detector.currentFrame[boundRect[1]:boundRect[1]+boundRect[3], 
-                                                boundRect[0]:boundRect[0]+boundRect[2]]
+                trackbox = detector.currentFrame[bound_rect[1]:bound_rect[1]+bound_rect[3], 
+                                                bound_rect[0]:bound_rect[0]+bound_rect[2]]
                 trackbox = cv2.resize(trackbox, (224, 224))
                 #cv2.imshow('image',trackbox)
-                
+                timer.start_detection_timer()
                 blob = cv2.dnn.blobFromImage(cv2.resize(trackbox, (300, 300)),0.007843, (300, 300), 127.5)
                 net.setInput(blob)
                 detections = net.forward()
-
+                
                 for i in np.arange(0, detections.shape[2]):
-                    detector.detectConfidentiallyPeople(i, detections, boundRect)
-                cv2.rectangle(detector.currentFrame, (boundRect[0], boundRect[1]), 
-                                (boundRect[0] + boundRect[2], boundRect[1] + boundRect[3]), (255, 255, 0), 1)
+                    
+                    detector.detectConfidentiallyPeople(i, detections, bound_rect)
+                timer.stop_detection_timer()
+                
+                cv2.rectangle(detector.currentFrame, (bound_rect[0], bound_rect[1]), 
+                                (bound_rect[0] + bound_rect[2], bound_rect[1] + bound_rect[3]), (255, 255, 0), 1)
+
+                timer.stop_contour_timer()
 
             
         # show the frame and record if the user presses a key
@@ -82,10 +101,55 @@ def main():
             detector.firstFrame = None
         #detector.lastFrame = detector.currentFrame
 
+        timer.print_time()
+
     # finally, stop the camera/stream and close any open windows
     vs.stop() if args.get("video", None) is None else vs.release()
     cv2.destroyAllWindows()
 
+class Timer:
+    def __init__(self):
+        self.frame_timer = None
+        self.contour_timer = None
+        self.detection_timer = None
+
+        self.contour_time = []
+        self.detection_time = []
+
+    def start_frame_timer(self):
+        self.frame_timer = time.time()
+
+    def get_frame_time(self):
+        return time.time() - self.frame_timer
+
+    def start_contour_timer(self):
+        self.contour_timer = time.time()
+
+    def stop_contour_timer(self):
+        self.contour_time.append(time.time() - self.contour_timer)
+
+    def start_detection_timer(self):
+        self.detection_timer = time.time()
+
+    def stop_detection_timer(self):
+        self.detection_time.append(time.time() - self.detection_timer)
+
+    def print_time(self):
+        average_contour = 0 if not self.contour_time else sum(self.contour_time)/float(len(self.contour_time))
+        average_detection = 0 if not self.detection_time else sum(self.detection_time)/float(len(self.detection_time))
+
+        median_contour = 0 if not self.contour_time else median(self.contour_time)
+        median_detection = 0 if not self.detection_time else median(self.detection_time)
+
+        total_contour = sum(self.contour_time)
+        total_detection = sum(self.detection_time)
+
+        print("Time for Frame: {:.2f}. Contour Total: {:.2f}. Contour Median: {:.2f}. Contour Average: {:.2f}. Detection Total: {:.2f}. Detection Median: {:.2f}. Detection Average: {:.2f}. ".format(
+            self.get_frame_time(), total_contour, median_contour, average_contour, total_detection, median_detection, average_detection))
+        #print("Contour Times:" + str(timer.contour_time))
+        #print("Detection Times:" + str(timer.detection_time))
+        self.contour_time = []
+        self.detection_time = []
 
 class DetectionFromFrame:
     def __init__(self, min_size, confidence):
@@ -132,10 +196,10 @@ class DetectionFromFrame:
 
         return cnts
 
-    def detectConfidentiallyPeople(self, i, detections, boundRect):
-        CLASSES = ["person"]
+    def detectConfidentiallyPeople(self, i, detections, bound_rect):
+        #CLASSES = ["person"]
 
-        COLORS = [0,255,0]
+        detected_color = (0, 255, 0)
         #COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
 
         confidence = detections[0, 0, i, 2]
@@ -144,21 +208,21 @@ class DetectionFromFrame:
             # extract the index of the class label from the `detections`, then compute the (x, y)-coordinates of
             # the bounding box for the object
             #idx = int(detections[0, 0, i, 1])
-            box = detections[0, 0, i, 3:7] * np.array([boundRect[2], boundRect[3], boundRect[2], boundRect[3]])
-            (startX, startY, endX, endY) = box.astype("int")
+            #box = detections[0, 0, i, 3:7] * np.array([bound_rect[2], bound_rect[3], bound_rect[2], bound_rect[3]])
+            #(startX, startY, endX, endY) = box.astype("int")
             # draw the prediction on the frame
             
             #label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
-            label = "{}: {:.2f}%".format(CLASSES[0], confidence * 100)
+            label = "{:.2f}%".format(confidence * 100)
             
             #cv2.rectangle(frame, (startX, startY), (endX, endY), COLORS[idx], 2)
-            cv2.rectangle(self.currentFrame, (boundRect[0], boundRect[1]), 
-                                (boundRect[0] + boundRect[2], boundRect[1] + boundRect[3]), (0,255,  0), 3)
+            cv2.rectangle(self.currentFrame, (bound_rect[0], bound_rect[1]),
+                                (bound_rect[0] + bound_rect[2], bound_rect[1] + bound_rect[3]), detected_color, 3)
             
-            y = boundRect[1] - 15 if boundRect[1] - 15 > 15 else boundRect[1] + 15
+            y = bound_rect[1] - 15 if bound_rect[1] - 15 > 15 else bound_rect[1] + 15
 
             #cv2.putText(frame, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)
-            cv2.putText(self.currentFrame, label, (0, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,0,0), 1)
+            cv2.putText(self.currentFrame, label, (bound_rect[0], bound_rect[1]-5), cv2.FONT_HERSHEY_SIMPLEX, 0.3, detected_color, 1)
             #cv2.imshow("Video stream", self.currentFrame)
             #print("Person found")