first commit

.gitignore

@@ -0,0 +1,3 @@
+yolov3.weights
+yolov3-tiny.weights
+yolo_object.py

coco.names

@@ -0,0 +1,80 @@
+person
+bicycle
+car
+motorbike
+aeroplane
+bus
+train
+truck
+boat
+traffic light
+fire hydrant
+stop sign
+parking meter
+bench
+bird
+cat
+dog
+horse
+sheep
+cow
+elephant
+bear
+zebra
+giraffe
+backpack
+umbrella
+handbag
+tie
+suitcase
+frisbee
+skis
+snowboard
+sports ball
+kite
+baseball bat
+baseball glove
+skateboard
+surfboard
+tennis racket
+bottle
+wine glass
+cup
+fork
+knife
+spoon
+bowl
+banana
+apple
+sandwich
+orange
+broccoli
+carrot
+hot dog
+pizza
+donut
+cake
+chair
+sofa
+pottedplant
+bed
+diningtable
+toilet
+tvmonitor
+laptop
+mouse
+remote
+keyboard
+cell phone
+microwave
+oven
+toaster
+sink
+refrigerator
+book
+clock
+vase
+scissors
+teddy bear
+hair drier
+toothbrush

readme.md

@@ -0,0 +1,18 @@
+# Object Detection using Yolo and OpenCV
+
+### <b>Commands to execute the code:</b>
+
+If you want to perform object detection in a static image file,
+```
+python yolo.py --image=True --image_path="folder/imagename.jpg"
+```
+
+If you want to perform object detection in a video,
+```
+python yolo.py --play_video=True --video_path='folder/video.mp4"
+```
+
+If you want to start the webcam and perform real-time object detection,
+```
+python yolo.py --webcam=True
+```

yolo.py

@@ -0,0 +1,150 @@
+import cv2
+import numpy as np
+import argparse
+import time
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--webcam', help="True/False", default=False)
+parser.add_argument('--play_video', help="Tue/False", default=False)
+parser.add_argument('--image', help="Tue/False", default=False)
+parser.add_argument('--video_path', help="Path of video file", default="videos/car_on_road.mp4")
+parser.add_argument('--image_path', help="Path of image to detect objects", default="Images/bicycle.jpg")
+parser.add_argument('--verbose', help="To print statements", default=True)
+args = parser.parse_args()
+
+#Load yolo
+def load_yolo():
+    #net = cv2.dnn.readNet("yolov3-tiny.weights", "yolov3-tiny.cfg")
+    net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
+    classes = []
+    with open("coco.names", "r") as f:
+        classes = [line.strip() for line in f.readlines()]
+
+    output_layers = [layer_name for layer_name in net.getUnconnectedOutLayersNames()]
+    colors = np.random.uniform(0, 255, size=(len(classes), 3))
+    return net, classes, colors, output_layers
+
+def load_image(img_path):
+    # image loading
+    img = cv2.imread(img_path)
+    img = cv2.resize(img, None, fx=0.4, fy=0.4)
+    height, width, channels = img.shape
+    return img, height, width, channels
+
+def start_webcam():
+    cap = cv2.VideoCapture(0)
+
+    return cap
+
+
+def display_blob(blob):
+    '''
+    Three images each for RED, GREEN, BLUE channel
+    '''
+    for b in blob:
+        for n, imgb in enumerate(b):
+            cv2.imshow(str(n), imgb)
+
+def detect_objects(img, net, outputLayers):
+    blob = cv2.dnn.blobFromImage(img, scalefactor=0.00392, size=(320, 320), mean=(0, 0, 0), swapRB=True, crop=False)
+    net.setInput(blob)
+    outputs = net.forward(outputLayers)
+    return blob, outputs
+
+def get_box_dimensions(outputs, height, width):
+    boxes = []
+    confs = []
+    class_ids = []
+    for output in outputs:
+        for detect in output:
+            scores = detect[5:]
+            class_id = np.argmax(scores)
+            conf = scores[class_id]
+            if conf > 0.3:
+                center_x = int(detect[0] * width)
+                center_y = int(detect[1] * height)
+                w = int(detect[2] * width)
+                h = int(detect[3] * height)
+                x = int(center_x - w/2)
+                y = int(center_y - h / 2)
+                boxes.append([x, y, w, h])
+                confs.append(float(conf))
+                class_ids.append(class_id)
+    return boxes, confs, class_ids
+
+def draw_labels(boxes, confs, colors, class_ids, classes, img):
+    indexes = cv2.dnn.NMSBoxes(boxes, confs, 0.5, 0.4)
+    font = cv2.FONT_HERSHEY_PLAIN
+    for i in range(len(boxes)):
+        if i in indexes:
+            x, y, w, h = boxes[i]
+            label = str(classes[class_ids[i]])
+            color = colors[i]
+            cv2.rectangle(img, (x,y), (x+w, y+h), color, 2)
+            cv2.putText(img, label, (x, y - 5), font, 3, color, 3)
+    cv2.imshow("Image", img)
+
+def image_detect(img_path):
+    model, classes, colors, output_layers = load_yolo()
+    image, height, width, channels = load_image(img_path)
+    blob, outputs = detect_objects(image, model, output_layers)
+    boxes, confs, class_ids = get_box_dimensions(outputs, height, width)
+    draw_labels(boxes, confs, colors, class_ids, classes, image)
+    while True:
+        key = cv2.waitKey(1)
+        if key == 27:
+            break
+
+def webcam_detect():
+    model, classes, colors, output_layers = load_yolo()
+    cap = start_webcam()
+    while True:
+        _, frame = cap.read()
+        height, width, channels = frame.shape
+        blob, outputs = detect_objects(frame, model, output_layers)
+        boxes, confs, class_ids = get_box_dimensions(outputs, height, width)
+        draw_labels(boxes, confs, colors, class_ids, classes, frame)
+        key = cv2.waitKey(1)
+        if key == 27:
+            break
+    cap.release()
+
+
+def start_video(video_path):
+    model, classes, colors, output_layers = load_yolo()
+    cap = cv2.VideoCapture(video_path)
+    while True:
+        _, frame = cap.read()
+        height, width, channels = frame.shape
+        blob, outputs = detect_objects(frame, model, output_layers)
+        boxes, confs, class_ids = get_box_dimensions(outputs, height, width)
+        draw_labels(boxes, confs, colors, class_ids, classes, frame)
+        k = cv2.waitKey(1) & 0xFF
+        if k == 27:
+            cv2.destroyAllWindows()
+            break
+    cap.release()
+
+
+
+if __name__ == '__main__':
+    webcam = args.webcam
+    video_play = args.play_video
+    image = args.image
+    if webcam:
+        if args.verbose:
+            print('---- Starting Web Cam object detection ----')
+        webcam_detect()
+    if video_play:
+        video_path = args.video_path
+        if args.verbose:
+            print('Opening '+video_path+" .... ")
+        start_video(video_path)
+    if image:
+        image_path = args.image_path
+        if args.verbose:
+            print("Opening "+image_path+" .... ")
+        image_detect(image_path)
+
+
+    cv2.destroyAllWindows()

yolov3-tiny.cfg

@@ -0,0 +1,182 @@
+[net]
+# Testing
+batch=1
+subdivisions=1
+# Training
+# batch=64
+# subdivisions=2
+width=416
+height=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 500200
+policy=steps
+steps=400000,450000
+scales=.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=16
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=1
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+###########
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+
+[yolo]
+mask = 3,4,5
+anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
+classes=80
+num=6
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 8
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+[yolo]
+mask = 0,1,2
+anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
+classes=80
+num=6
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1

yolov3.cfg

@@ -0,0 +1,788 @@
+[net]
+# Testing
+# batch=1
+# subdivisions=1
+# Training
+batch=64
+subdivisions=16
+width=608
+height=608
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 500200
+policy=steps
+steps=400000,450000
+scales=.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+######################
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 6,7,8
+anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
+classes=80
+num=9
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1
+
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 61
+
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 3,4,5
+anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
+classes=80
+num=9
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1
+
+
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 36
+
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 0,1,2
+anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
+classes=80
+num=9
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1