From 292e6083251cd8bdab5a315c413042f276af670f Mon Sep 17 00:00:00 2001
From: Edmond Yoo <hj3yoo@uwaterloo.ca>
Date: Fri, 14 Sep 2018 20:57:27 +0000
Subject: [PATCH] quick change on opencv_dnn

---
 opencv_dnn.py |   72 +++++++++++++++--------------------
 1 files changed, 31 insertions(+), 41 deletions(-)

diff --git a/opencv_dnn.py b/opencv_dnn.py
index 8746c84..d923fc2 100644
--- a/opencv_dnn.py
+++ b/opencv_dnn.py
@@ -2,6 +2,7 @@
 import numpy as np
 import os
 import sys
+from operator import itemgetter
 
 
 # Disclaimer: majority of the basic framework in this file is modified from the following tutorial:
@@ -17,7 +18,7 @@
 
 
 # Remove the bounding boxes with low confidence using non-maxima suppression
-def postprocess(frame, outs, classes, thresh_conf, thresh_nms):
+def post_process(frame, outs, thresh_conf, thresh_nms):
     frame_height = frame.shape[0]
     frame_width = frame.shape[1]
 
@@ -42,17 +43,11 @@
                 confidences.append(float(confidence))
                 boxes.append([left, top, width, height])
 
-    # Perform non maximum suppression to eliminate redundant overlapping boxes with
-    # lower confidences.
-    indices = cv2.dnn.NMSBoxes(boxes, confidences, thresh_conf, thresh_nms)
-    for i in indices:
-        i = i[0]
-        box = boxes[i]
-        left = box[0]
-        top = box[1]
-        width = box[2]
-        height = box[3]
-        draw_pred(frame, class_ids[i], classes, confidences[i], left, top, left + width, top + height)
+    # Perform non maximum suppression to eliminate redundant overlapping boxes with lower confidences.
+    indices = [ind[0] for ind in cv2.dnn.NMSBoxes(boxes, confidences, thresh_conf, thresh_nms)]
+    
+    ret = [[class_ids[i], confidences[i], boxes[i]] for i in indices]
+    return ret
 
 
 # Draw the predicted bounding box
@@ -73,7 +68,7 @@
     cv2.putText(frame, label, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255))
 
 
-def detect_frame(net, classes, img, thresh_conf=0.5, thresh_nms=0.4, in_dim=(416, 416), out_path=None):
+def detect_frame(net, classes, img, thresh_conf=0.5, thresh_nms=0.4, in_dim=(416, 416), display=True, out_path=None):
     # Create a 4D blob from a frame.
     blob = cv2.dnn.blobFromImage(img, 1 / 255, in_dim, [0, 0, 0], 1, crop=False)
 
@@ -84,7 +79,11 @@
     outs = net.forward(get_outputs_names(net))
 
     # Remove the bounding boxes with low confidence
-    postprocess(img, outs, classes, thresh_conf, thresh_nms)
+    obj_list = post_process(img, outs, thresh_conf, thresh_nms)
+    for obj in obj_list:
+        class_id, confidence, box = obj
+        left, top, width, height = box
+        draw_pred(img, class_id, classes, confidence, left, top, left + width, top + height)
 
     # Put efficiency information. The function getPerfProfile returns the
     # overall time for inference(t) and the timings for each of the layers(in layersTimes)
@@ -94,9 +93,14 @@
 
     if out_path is not None:
         cv2.imwrite(out_path, img.astype(np.uint8))
+    if display:
+        cv2.imshow('result', img)
+        cv2.waitKey(0)
+
+    return obj_list
 
 
-def detect_video(net, classes, capture, thresh_conf=0.5, thresh_nms=0.4, in_dim=(416, 416), out_path=None):
+def detect_video(net, classes, capture, thresh_conf=0.5, thresh_nms=0.4, in_dim=(416, 416), display=True, out_path=None):
     if out_path is not None:
         vid_writer = cv2.VideoWriter(out_path, cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'), 30,
                                      (round(capture.get(cv2.CAP_PROP_FRAME_WIDTH)),
@@ -108,28 +112,10 @@
             print("End of video. Press any key to exit")
             cv2.waitKey(0)
             break
-        '''
-        # Create a 4D blob from a frame.
-        blob = cv2.dnn.blobFromImage(frame, 1 / 255, in_dim, [0, 0, 0], 1, crop=False)
-
-        # Sets the input to the network
-        net.setInput(blob)
-
-        # Runs the forward pass to get output of the output layers
-        outs = net.forward(get_outputs_names(net))
-
-        # Remove the bounding boxes with low confidence
-        postprocess(frame, outs, classes, thresh_conf, thresh_nms)
-
-        # Put efficiency information. The function getPerfProfile returns the
-        # overall time for inference(t) and the timings for each of the layers(in layersTimes)
-        t, _ = net.getPerfProfile()
-        label = 'Inference time: %.2f ms' % (t * 1000.0 / cv2.getTickFrequency())
-        cv2.putText(frame, label, (0, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
-        '''
-        detect_frame(net, classes, frame,
-                     thresh_conf=thresh_conf, thresh_nms=thresh_nms, in_dim=in_dim, out_path=None)
-        cv2.imshow('result', frame)
+        obj_list = detect_frame(net, classes, frame, thresh_conf=thresh_conf, thresh_nms=thresh_nms, in_dim=in_dim,
+                                display=False, out_path=None)
+        if display:
+            cv2.imshow('result', frame)
         if out_path is not None:
             vid_writer.write(frame.astype(np.uint8))
         cv2.waitKey(1)
@@ -137,24 +123,27 @@
     if out_path is not None:
         vid_writer.release()
     cv2.destroyAllWindows()
-    pass
 
 
 def main():
     # Specify paths for all necessary files
-    test_path = '../data/test1.mp4'
+    test_path = os.path.abspath('../data/test1.mp4')
     weight_path = 'weights/second_general/tiny_yolo_final.weights'
     cfg_path = 'cfg/tiny_yolo.cfg'
     class_path = "data/obj.names"
     out_dir = 'out'
     if not os.path.isfile(test_path):
         print('The test file %s doesn\'t exist!' % os.path.abspath(test_path))
+        return
     if not os.path.isfile(weight_path):
         print('The weight file %s doesn\'t exist!' % os.path.abspath(test_path))
+        return
     if not os.path.isfile(cfg_path):
         print('The config file %s doesn\'t exist!' % os.path.abspath(test_path))
+        return
     if not os.path.isfile(class_path):
         print('The class file %s doesn\'t exist!' % os.path.abspath(test_path))
+        return
 
     # Setup
     # Read class names from text file
@@ -162,8 +151,8 @@
         classes = [line.strip() for line in f.readlines()]
     # Load up the neural net using the config and weights
     net = cv2.dnn.readNetFromDarknet(cfg_path, weight_path)
-    #net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
-    #net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+    net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
+    net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
 
     # Save the detection result if out_dir is provided
     if out_dir is None or out_dir == '':
@@ -172,6 +161,7 @@
         out_path = out_dir + '/' + os.path.split(test_path)[1]
     # Check if test file is image or video
     test_ext = test_path[test_path.find('.') + 1:]
+
     if test_ext in ['jpg', 'jpeg', 'bmp', 'png', 'tiff']:
         img = cv2.imread(test_path)
         detect_frame(net, classes, img, out_path=out_path)

--
Gitblit v1.10.0