Realtime Object Detection Using OpenCV Python ON CPU | OpenCV Object Detection Tutorial

Object detection with OpenCV Python in real-time on modern CPUs is possible. In this object detection tutorial, we use the OpenCV to implement a real-time object detector using the CPU. We have found that using the OpenCV object detection method, we were able to achieve 20-22 FPS (without screen recording) on the CPU. We use pretrained Object Detection model SSD Mobilenet.

** Code is available for our Patreon Supporters**
---------------------------------------------
► Time Stamps:
Introduction: (0:00)
Downloading Object Detection Model: (0:21)
Object Detection Class: (01:04)
Beautify Bounding Boxes: (11:30)
Display FPS: (15:32)
Object Detection on Webcam: (16:43)
---------------------------------------------
► Links:
---------------------------------------------
Want to discuss more?

#TheCodingBug
---------------------------------------------
► My Other Tutorials:
○ Install TensorFlow Under 90 Seconds
○ Install PyTorch Under 90 Seconds
---------------------------------------------
---------------------------------------------
DISCLAIMER: Links included in this description might be affiliate links. If you purchase a product or service with the links that I provide I may receive a small commission. There is no additional charge to you!

[TheCodingBug]

► My Other Tutorials:
Object Detection with OpenCV

DETECTRON2 Custom Object Detection, Custom Instance Segmentation Tutorial: Part 2 (Training Models)

DETECTRON2 Custom Object Detection, Custom Instance Segmentation Tutorial: Part 1 (Preparing Data)

Detectron2 on Colab

Instance Segmentation as Rendering

Detectron2 Complete Tutorial

Colorize Black and White Images and Videos using Python OpenCV

Build and Install OpenCV 4.5.1 With CUDA GPU Support on Windows 10

Face Detection Using OpenCV Python with CUDA GPU Acceleration

YOLOv4 On Android Using TFLite

Install TensorFlow GPU Under 90 Seconds

Install PyTorch GPU Under 90 Seconds

Custom YOLOv4 Object Detection with TensorFlow and TFLite

Darknet YOLOv4 Custom Object Detection: Part 2 (Training YOLOv4 Darknet)

Darknet YOLOv4 Custom Object Detection: Part 1 (Preparing Custom Dataset)

YOLOv4 Object Detection with TensorFlow, TFLite and TensorRT

Darknet YOLOv4 Object Detection for Windows 10 on Images, Videos, and Webcams

Real Time Object Detection on Webcam and Videos Using OpenCV With YOLOv3 and YOLOv4 | Windows Linux

Build and Install OpenCV 4.4.0 with CUDA (GPU) Support on Windows 10

Install TensorFlow GPU and PyTorch with CUDA on Windows 10 Anaconda | CUDA 10.1 cuDNN 7.6

Real-time Multiple Object Tracking with YOLOv4 TensorFlow and Deep Sort | Linux, Windows

[cyberhard]

Excellent tutorial. You have a new subscriber.

[stevi]

Very very good content. Very well explain !!!! thanks a lot

[raymondmichael]

New here but I like it, sadly you don't upload often.

Greetings from Tanzania 🇹🇿

Subed

[mtasalloti]

Hi - Great video and nice contrast to the TensorFlow one you have. Very clear, concise and to the point. Question - would you be able to recommend where I could get a similar overview of how to train / add / remove items into your model? Many Thanks again

[johnmelbolaybolay]

why do i get this error
SystemError: <class 'cv2.dnn.DetectionModel'> returned a result with an exception set

[yopijulia]

Hello, I don't have videos in the "test_videos" folder. Where can I get the "street1" and "street2" videos?

[YbborNetsrek]

Hi i keep getting an error with: def__init__ (self, vdeoPath, configPath, modelPath, classesPath):
SyntaxError: invalid syntax

Any suggestions?

[padmavathynarasareddygari]

Hi- I have to say, a great video. It really helped me with my project. I made sure to recommend it to my friends. But I have a small doubt. Is opencv-contrib required to do it? Like can the project work without installing it? Thank you :)

[stevi]

Amazing content, are you planing to make more tutorial like this in the
future ? I watched a lot of tutorial video about object detection and I
can tell you it's one of the best. Thank you

[jhoanrodrigoperezvargas]

Hi, great video tutorial.
is it possible to implement tracking?

[maulanamahmuddin]

Amazing content and really inspired me, permission to ask, is the difference between labelmap.pbtxt and coco.name the same or different? What I know is that a labelmap is a set of names that are used as json, if coco.name is just a list of names, right? If it's the same, can classesPath also use a labelmap?

Please help and thank you

[amansinghal]

Hi please make tutorial on human pose detection

[panzznine]

Hi, is there a way to change vid source instead from recorded video, i want to direct it on my camera feed

[opensourcethings]

heyy great video... but what if i want to add weapons in the object detection ... is there any method to modify your given model or let me know from where i can get this type of model which detect weapons also

[raghulprasanth]

How can I use Efficienet instead of SSD mobilenet. Will it work if I use pbtxt of SSD for efficientdet. I'm facing trouble finding pbtxt for Efficientdet. Can you please help me sir

[RethanyaS]

Output Virtual window ie.Result window is not showing but the code runs successfully
What should I miss?

[aslanserafimov]

Can you recognize the picture? If yes, what needs to be done?

[pypoornith]

Hey, great video. Your script runs perfectly runs for me. But I wanted to change it up a little bit. Instead of showing it on the video using imshow(), it should print the name and confidence in the console. so I did something like this:

displaytext = "{}:{:.2f}".format(classLabel, classConfidence*100)
print(displaytext)


but it is not printing the names of all the objects, its only printing the name of the first object it sees(I think). Can you please help me to modify this code so that it works the way I intended it to? Thanks again for the video 😀

[dzulgonzalezmarcosadalbert]

any tutorial to generate the .pb and .pbtxt files of the video in yolov4?please