Live Object Detection in Python
Vložit
- čas přidán 19. 05. 2024
- Today we learn how to implement live object detection in Python, using machine learning and OpenCV.
Resources: github.com/chuanqi305/MobileN...
◾◾◾◾◾◾◾◾◾◾◾◾◾◾◾◾◾
📚 Programming Books & Merch 📚
🐍 The Python Bible Book: www.neuralnine.com/books/
💻 The Algorithm Bible Book: www.neuralnine.com/books/
👕 Programming Merch: www.neuralnine.com/shop
🌐 Social Media & Contact 🌐
📱 Website: www.neuralnine.com/
📷 Instagram: / neuralnine
🐦 Twitter: / neuralnine
🤵 LinkedIn: / neuralnine
📁 GitHub: github.com/NeuralNine
🎙 Discord: / discord
🎵 Outro Music From: www.bensound.com/
Timestamps:
(0:00) Intro
(0:15) Set Up & Resources
(3:15) Object Recognition on Images
(21:32) Live Object Recognition
(24:33) Outro - Věda a technologie
![[Vowel]물고기는 물에서 살아야 해🐟🤣Fish have to live in the water #funny](http://i.ytimg.com/vi/3G9MH063Cx4/mqdefault.jpg)
This is the best programming channel on youtube. It teaches well, clear and all in 1 part. Deserves 10 million subscribes atleast
Real true
Agree with you because akcent is understandable 👍
@@frettmann5317 do you have the code
Right
Greatly appreciate the content and the effort behind it :)
I found an opencv error in line 17 in the code. The error said "cv2.dnn has no attribute readNetFromCaffee". In case anyone else also has the same problem, changing the function from cv2.readNetFromCaffee to cv2.readNet helped solve this issue
thanks bro
@@ahmedachtibat8661 You're welcome :)
bro i got problem with it
still getting error sir
Great video thank you!
Where can I find different type of models?
in this case, the model does include bottles but i also need (in example) cans
Vielen Dank, bin sehr beeindruckt davon.
Thanks a million for your invaluable content... it's just wonderful
Wonderful content, I am a fan! Random question: how did you make the intro music?
Hey man a lot of thanks you explain very well i got a question i need to find an object that is not common where do i find the model for this object or how can i make my own model?????
Thank you for sharing content like this, I really appreciate this :)
How this channel haven't one million subscribers yet???
I N S A N E !
You are rocking bro🔥🔥🔥🔥.............. I am always fan for you✨
If I want to use a different model like yolo for example does it work the same way?
Hi Mr
That’s amazing tut 🥰✨♥️ i want to asked you
If i want to detect more object what can i do ?
Thanks you for every thing
As always, thank you very much!
Im not getting access to files you provided links in description. Please help
Gotta keep the notifications
This Works Beutifully!
Thanks a million, you rock!
It was very useful. And I had a question, can this program be used to confirm the "I'm not a robot" section in Selenium?
Translated by Google Translate
addition for the facecam part:
For me it only worked, when I moved following code out of the for-loop. Also added to exit the program when pressing 'q'.
cv2.imshow("Detected Objects", image)
key = cv2.waitKey(1)
if key == ord('q'):
break
files:
drive.google.com/drive/folders/13nAcSOx_S8QkbDw_oEimv0yRyfJazUNG
Thank you
our hero
cheers
thanks bhai thanks yaar
you are a legend
permission to learn sir. thank you
Nice video !!!
Keep it up bro !
Thanks man
How can we add new object category to the list?
I have done the whole code correct but still not getting the prediction in the image output, it's just the image gets opened without any prediction
Looks like good.
Your video ideas are very good
may i know sir what editor you have?
good learning, thanks a lot
Could you explain how to get that model on the computer? if i just use the files, nothing happens
It says I need access to google drive
Excellent video! Do you guys think technology is at that level where object recognition code can identify a e.g. crack on the wall as well?
i am making one
Hello, thank you so much for the video, I have a question, if i wanted to see the distance from the camera to the objects/person, what should i use ?
Almost impossible. Best way would be to use a rangefinder ofc.
i have completed python can i make these projects now
I can't access the links you provide
how do you create that file model and put caffemodel and prototxt.txt?
Thanks Bro but how can I use It to recognize a polygon
Thankyou sir
how can we catch a frame from video or online videos?
Can I use this for object detection on screen?
Bro please make a video on drone object detection of that contest by mutazas workshop.
i was working on that drone object detection. all were right but my program were not detecting cars properly so please make a video.
That contest is over right now
What & Where is the edition codes if I want Windows Notifications when the objects detected?
please can you tell me how do you make your intro
I'm not able to access caffe model
Please help if someone got access
Awesome!!! TQVM!!
I was wondering what studio it is that you use for python?
looks like pycharm
Hello Sir
I want to add one feature in this project
In case screen will empty NO Object are in the screen. So it will display "NO OBJECT DETECTED"
How we add this feature
I try some if statement code but it was not succes
Please help me to add this feature
Please provide code
where did the file mobilenetssd_deploy.caffemodel come from? It is not in the voc folder on the github site.
i too have the same dbt
Acces denied when i try to download mobilenet SSD
drive.google.com/drive/folders/13nAcSOx_S8QkbDw_oEimv0yRyfJazUNG
The same
How to solve these
1 more subs. Thanks for share this super useful vid.
How to detect other objects ??
How can i get the code you wrote?
Please tell me the name of intro music.
Amazing
Hi, Could You share me MobileNet-SSD deploy ? I can't dowload this. :(
Where can i find the code source pls :')
Hello sir
Nice project but I am having a problem with saving and using the prototxt file
It is showing a problem that
Can't open "MobileSSD_deploy.prototxt.txt" in function 'cv:dnn:ReadProtoFromTextFile'
I think it's the problem with the extension
Because I can't save it with extension prototxt
Please help sir I see your every video and also I make the fantastic project's
Please help
i cand deploy the model can you help?
Not able to access the deploy file from chuanqi , asks for access request...somebody help me with this
I have the same problem
Did you find a solution?
drive.google.com/drive/folders/13nAcSOx_S8QkbDw_oEimv0yRyfJazUNG@@mhteach3120
Hey, i have cv2.error: OpenCV(4.5.5) :-1: error: (-5:Bad argument) in function 'putText'
> Overload resolution failed:
> - Can't parse 'org'. Input argument doesn't provide sequence protocol
> - Can't parse 'org'. Input argument doesn't provide sequence protocol
what is solutions ? please help
your line is 41
how to get the model
Nice.
hey anyone have the cafe model drive link ? pls share
Sir please help I am not able to download the caffe model
drive.google.com/drive/folders/13nAcSOx_S8QkbDw_oEimv0yRyfJazUNG
why drive is close ?
Instead of np.random.whatever you could import random and use random.whatever, don't you?
Well explained and interesting demo but it seems there is a long way to go to detect all persons and objects as good and as fast as we do....
Hi, can you link code ???
Hi, im getting a unexpected type error when I try to resize the image. The project is working, but makes the image extremely zoomed in, any tips on how to solve this ?
Resolved this by adding image = cv2.resize(image, (600, 600) to the code. But how can I find out all the possibilities of items in the class to see what else can be detected as well ?
not working netssd link
i am not able to access caffemodel in github can anyone resolve this please urgent...
Hey,i am not able to get the access for caffemodel , can u please help me with that
me too i can't access it
@@Sulltan-al me too bro
here u can find the files: drive.google.com/drive/folders/13nAcSOx_S8QkbDw_oEimv0yRyfJazUNG
@@rolandkiraly2138 Many thanks for the link. Köszi a segítséget, sikerült innen letölteni 👍
@@dosaimre anytime😁
Where is the code to copy 😅
Hello, how long does it take to get permission for the ‘MobileNet-SSD’ file?
Did you get
I was having trouble with this too... I requested permission but I'm not sure if that's how to go about it. I know you commented 5 months ago but did you ever get it?
@@jaysee_6292 did you get the model?
can you make a video on custom object detection.
With this Video you could do it yourself.
@@wz_lx24 Maybe he would like to recognize unicorns, so he has to train a model to do that ^^
Custom object detection sir next time
not able to download files please allow me to dowmload
Can you share the code
Hello, how do I get access to download deploy?
just search the file name, there are other deploy out there you can download and no need access
cv2.dnn and cv2.imread not working..How to fix it?
have you fixed it?
When I click deploy, it says I have not access.
Please help me!
from @KamehlionHD: drive.google.com/drive/folders/13nAcSOx_S8QkbDw_oEimv0yRyfJazUNG
@@untoastedbread0 but how can I the file caffemodel, plz help me. It says "The file is not displayed in the text editor because it is either binary or uses an unsupported text encoding." on my visual studio code
Where can I find the source code?
4 legs and long thing definitely a giraffe and not a chair
am i the only one that cant not download the files from git?
yes its says i need access
edit: drive.google.com/drive/folders/13nAcSOx_S8QkbDw_oEimv0yRyfJazUNG
@@KamehlionHD omg thank you so much
@@KamehlionHD thanks
@@KamehlionHD I appreciate that thank you
fucking cool
it says I need access to download deploy?
same maybe the user changed access
error: (-2:Unspecified error) FAILED: fs.is_open(). Can't open "/MobileNetSSD_deploy.prototxt"
in function 'cv::dnn::ReadProtoFromTextFile'
I am getting this error .... can anyone help me, please..
did u know the solution??
why do I get this error
net = cv2.dnn.readNetFromCaffe(prototxt_path, model_path)
cv2.error: OpenCV(4.7.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\caffe\caffe_io.cpp:1126: error: (-2:Unspecified error) FAILED: fs.is_open(). Can't open "models\MobileNetSSD_deploy.prototxt" in function 'cv::dnn::ReadProtoFromTextFile'
Gee yeah I wonder why
not able to get that MobileNetSSD_deploy.caffemodel
Anyone else having trouble downloading the "MobileNetSSD_deploy.caffemodel"? When I click the link it says that I don't have permission and that I have to ask for it. I asked permission a couple hours ago and still don't got it.
drive.google.com/drive/folders/13nAcSOx_S8QkbDw_oEimv0yRyfJazUNG
drive.google.com/drive/folders/13nAcSOx_S8QkbDw_oEimv0yRyfJazUNG
I have the file right here but I don't know how to open it. It says: "The file is not displayed in the text editor because it is either binary or uses an unsupported text encoding."