Real-Time Object Detection OpenCV Python With Source Code

Real Time Object Detection OpenCV Python With Source Code

The Real-Time Object Detection OpenCV Python was developed using Python OpenCV, This opencv realtime object detection script is a simple experimental tool to detect common objects (COCO) easily with your built-in webcam.

It uses opencv’s readNet method and uses the external yolov3-tiny model (which can be upgraded to the full sized model).

Opencv’s readNet method only runs on CPU (and not GPU), is very intensive, and therefore, it will be not be optimal for big AI projects.

A Object Detection OpenCV Python implements an image and video object detection classifier using pretrained yolov3 models.

The yolov3 models are taken from the official yolov3 paper which was released in 2018. The yolov3 implementation is from darknet. Also, this project implements an option to perform classification real-time using the webcam.

Project Information’s

Project Name:	Real Time Object Detection OpenCV Python With Source Code
Language/s Used:	Python (OpenCV)
Python version (Recommended):	2.x or 3.x
Database:	None
Type:	Deep Learning Project
Developer:	IT SOURCECODE
Updates:	0

About The Project

In this Python OpenCV Project also includes a downloadable Python Project With Source Code for free, just find the downloadable source code below and click to start downloading.

By the way if you are new to python programming and you don’t know what would be the the Python IDE to use, I have here a list of Best Python IDE for Windows, Linux, Mac OS that will suit for you. I also have here How to Download and Install Latest Version of Python on Windows.

To start executing Real-Time Object Detection OpenCV Python With Source Code, make sure that you have installed Python 3.9 and PyCharm in your computer.

Steps On How To Run The Real Time Object Detection OpenCV Python With Source Code

Installed Libraries

import cv2
import numpy as np
import time

Complete Source Code

import cv2
import numpy as np
import time

# Load the YOLO model
net = cv2.dnn.readNet("./weights/yolov3-tiny.weights", "./configuration/yolov3-tiny.cfg")
classes = []
with open("./configuration/coco.names", "r") as f:
    classes = [line.strip() for line in f.readlines()]
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
colors = np.random.uniform(0, 255, size=(len(classes), 3))

# Load webcam
cap = cv2.VideoCapture(0)
font = cv2.FONT_HERSHEY_SIMPLEX
starting_time = time.time()
frame_id = 0

while True:
    # Read webcam
    _, frame = cap.read()
    frame_id += 1
    height, width, channels = frame.shape

    # Detecting objects
    blob = cv2.dnn.blobFromImage(frame, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
    net.setInput(blob)
    outs = net.forward(output_layers)

    # Visualising data
    class_ids = []
    confidences = []
    boxes = []
    for out in outs:
        for detection in out:
            scores = detection[5:]
            class_id = np.argmax(scores)
            confidence = scores[class_id]
            if confidence > 0.1:
                # Object detected
                center_x = int(detection[0] * width)
                center_y = int(detection[1] * height)
                w = int(detection[2] * width)
                h = int(detection[3] * height)

                # Rectangle coordinates
                x = int(center_x - w / 2)
                y = int(center_y - h / 2)

                boxes.append([x, y, w, h])
                confidences.append(float(confidence))
                class_ids.append(class_id)

    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.8, 0.3)

    for i in range(len(boxes)):
        if i in indexes:
            x, y, w, h = boxes[i]
            label = str(classes[class_ids[i]])
            confidence = confidences[i]
            color = colors[class_ids[i]]
            cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
            cv2.putText(frame, label + " " + str(round(confidence, 2)), (x, y + 30), font, 3, color, 3)

    elapsed_time = time.time() - starting_time
    fps = frame_id / elapsed_time
    cv2.putText(frame, "FPS: " + str(round(fps, 2)), (40, 670), font, .7, (0, 255, 255), 1)
    cv2.putText(frame, "press [esc] to exit", (40, 690), font, .45, (0, 255, 255), 1)
    cv2.imshow("Image", frame)
    key = cv2.waitKey(1)
    if key == 27:
        print("[button pressed] ///// [esc].")
        print("[feedback] ///// Videocapturing succesfully stopped")
        break

cap.release()
cv2.destroyAllWindows()

Output

Download Source Code below

Summary

This project implements an image and video object detection classifier using pretrained yolov3 models. The yolov3 models are taken from the official yolov3 paper which was released in 2018. The yolov3 implementation is from darknet. Also, this project implements an option to perform classification real-time using the webcam.

Related Articles

• Code For Game in Python: Python Game Projects With Source Code
• Best Python Projects With Source Code 2020 FREE DOWNLOAD
• How to Make a Point of Sale In Python With Source Code 2021
• Python Code For Food Ordering System | FREE DOWNLOAD | 2020
• Inventory Management System Project in Python With Source Code

Inquiries

If you have any questions or suggestions about Real-Time Object Detection OpenCV Python With Source Code, please feel free to leave a comment below.