Last active
November 2, 2023 10:50
-
-
Save imvickykumar999/6da98e00e7a4b8b932222fce7f38926d to your computer and use it in GitHub Desktop.
Object Detection of Public Live Camera using YOLOv3
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # https://screenrec.com/share/sca8wgJKrU | |
| import numpy as np | |
| import time | |
| import cv2 | |
| import sys | |
| port = '8080' | |
| ip = '80.32.125.254' | |
| try: url = sys.argv[1] | |
| except: url = f'http://{ip}:{port}/cgi-bin/faststream.jpg' | |
| if url == '0': url = 0 | |
| video_capture = cv2.VideoCapture(url) | |
| file = time.strftime("%Y-%m-%d %H-%M-%S", time.gmtime()) | |
| fourcc = cv2.VideoWriter_fourcc(*'mp4v') | |
| out = cv2.VideoWriter(f'Recorded/{file} yolo.mp4', fourcc, 20.0, (640, 480)) | |
| confidenceThreshold = 0.5 | |
| NMSThreshold = 0.3 | |
| modelWeights = 'YOLO/yolov3.weights' # download weights file (236 MB) | |
| modelConfiguration = 'YOLO/yolov3.cfg' | |
| labelsPath = 'YOLO/coco.names' | |
| labels = open(labelsPath).read().strip().split('\n') | |
| np.random.seed(10) | |
| COLORS = np.random.randint(0, 255, size=(len(labels), 3), dtype="uint8") | |
| net = cv2.dnn.readNetFromDarknet(modelConfiguration, modelWeights) | |
| outputLayer = net.getLayerNames() | |
| outputLayer = [outputLayer[i - 1] for i in net.getUnconnectedOutLayers()] | |
| (W, H) = (None, None) | |
| while True: | |
| ret, frame = video_capture.read() | |
| if W is None or H is None: | |
| (H,W) = frame.shape[:2] | |
| blob = cv2.dnn.blobFromImage(frame, 1 / 255.0, (416, 416), swapRB = True, crop = False) | |
| net.setInput(blob) | |
| layersOutputs = net.forward(outputLayer) | |
| boxes = [] | |
| confidences = [] | |
| classIDs = [] | |
| for output in layersOutputs: | |
| for detection in output: | |
| scores = detection[5:] | |
| classID = np.argmax(scores) | |
| confidence = scores[classID] | |
| if confidence > confidenceThreshold: | |
| box = detection[0:4] * np.array([W, H, W, H]) | |
| (centerX, centerY, width, height) = box.astype('int') | |
| x = int(centerX - (width/2)) | |
| y = int(centerY - (height/2)) | |
| boxes.append([x, y, int(width), int(height)]) | |
| confidences.append(float(confidence)) | |
| classIDs.append(classID) | |
| detectionNMS = cv2.dnn.NMSBoxes(boxes, confidences, confidenceThreshold, NMSThreshold) | |
| if(len(detectionNMS) > 0): | |
| for i in detectionNMS.flatten(): | |
| (x, y) = (boxes[i][0], boxes[i][1]) | |
| (w, h) = (boxes[i][2], boxes[i][3]) | |
| color = [int(c) for c in COLORS[classIDs[i]]] | |
| cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2) | |
| text = '{}: {:.4f}'.format(labels[classIDs[i]], confidences[i]) | |
| cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2) | |
| out.write(frame) | |
| cv2.imshow('YOLO - ESC to Quit', frame) | |
| if cv2.waitKey(1) & 0xFF == 27: | |
| break | |
| video_capture.release() | |
| cv2.destroyAllWindows() | |
| out.release() | |
| '''How to run file... | |
| >>> python yolo.py http://212.26.235.210/mjpg/video.mjpg | |
| >>> python yolo.py http://80.32.125.254:8080/cgi-bin/faststream.jpg | |
| >>> python yolo.py http://212.147.38.3/mjpg/video.mjpg | |
| >>> python yolo.py http://imvickykumar999:[email protected]:8080/video | |
| >>> python yolo.py 0 | |
| ''' |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| [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 | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| [InternetShortcut] | |
| URL=https://pjreddie.com/media/files/yolov3.weights |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment