Yolov5 crashes with RTSP stream analysis #2226

philippneugebauer · 2021-02-16T09:34:56Z

🐛 Bug

If I want to analyze an rtsp stream with Yolov5 in a docker container, regardless the latest or the v4.0 version, it crashes.

To Reproduce (REQUIRED)

Input:

docker run --rm -it -e RTSP_PROTOCOLS=tcp -p 8554:8554 aler9/rtsp-simple-server

ffmpeg -i video.mp4 -s 640x480 -c:v libx264 -f rtsp -rtsp_transport tcp rtsp://localhost:8554/analysis

docker run -it ultralytics/yolov5:latest

python3 detect.py --source rtsp://host.docker.internal:8554/analysis --weights yolov5s.pt --conf 0.25 --save-txt

Output:

Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.25, device='', exist_ok=False, img_size=640, iou_thres=0.45, name='exp', project='runs/detect', save_conf=False, save_txt=True, source='rtsp://host.docker.internal:8554/analysis', update=False, view_img=False, weights=['yolov5s.pt'])
/opt/conda/lib/python3.8/site-packages/torch/cuda/__init__.py:52: UserWarning: CUDA initialization: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx (Triggered internally at  ../c10/cuda/CUDAFunctions.cpp:100.)
  return torch._C._cuda_getDeviceCount() > 0
YOLOv5 v4.0-80-gf8464b4 torch 1.8.0a0+1606899 CPU

Fusing layers...
Model Summary: 224 layers, 7266973 parameters, 0 gradients, 17.0 GFLOPS
[h264 @ 0x55e674656100] co located POCs unavailable
[h264 @ 0x55e674656100] mmco: unref short failure
[h264 @ 0x55e675117cc0] co located POCs unavailable
[h264 @ 0x55e674dbb300] mmco: unref short failure
[h264 @ 0x55e674ec09c0] co located POCs unavailable
1/1: rtsp://host.docker.internal:8554/analysis...  success (640x480 at 30.00 FPS).

0: 480x640 13 persons, 1 tennis racket, Done. (2.089s)
qt.qpa.xcb: could not connect to display
qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/opt/conda/lib/python3.8/site-packages/cv2/qt/plugins" even though it was found.
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.

Available platform plugins are: xcb.

Aborted

Expected behavior

Doing the analysis

Environment

OS: Yolov5 docker container on macos Catalina
GPU none

The text was updated successfully, but these errors were encountered:

github-actions · 2021-02-16T09:35:40Z

👋 Hello @philippneugebauer, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

Google Colab and Kaggle notebooks with free GPU:
Google Cloud Deep Learning VM. See GCP Quickstart Guide
Amazon Deep Learning AMI. See AWS Quickstart Guide
Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

glenn-jocher · 2021-02-16T20:25:32Z

@philippneugebauer you may want to verify that publicly accessible streams are working for you, before trying custom container connections. This works locally for me for example:

python detect.py --source rtsp://wowzaec2demo.streamlock.net/vod/mp4:BigBuckBunny_115k.mov

Be aware this displays a live preview of detection results. You may need to disable the preview component in non-desktop environments by setting view_img = False:

yolov5/detect.py

Lines 45 to 54 in f8464b4

    
           # Set Dataloader 
        
           vid_path, vid_writer = None, None 
        
           if webcam: 
        
               view_img = True 
        
               cudnn.benchmark = True  # set True to speed up constant image size inference 
        
               dataset = LoadStreams(source, img_size=imgsz, stride=stride) 
        
           else: 
        
               save_img = True 
        
               dataset = LoadImages(source, img_size=imgsz, stride=stride)

philippneugebauer · 2021-02-16T20:35:08Z

Damit, yeah, you're right, the view_img = True was the problem. Sorry :/

glenn-jocher · 2021-02-16T20:43:57Z

@philippneugebauer I think we looked at automatically disabling this before but found no easy way to automatically detect non-desktop environments. If you think of any ideas for more robustly handling this please submit a PR!

philippneugebauer · 2021-02-16T20:47:26Z

I was confused because with the normal video analysis I had no trouble at all. Maybe it's an idea to manually enable the view_img option? It's even part of the arguments so I wouldn't expect this to be a default

glenn-jocher · 2021-02-16T20:59:33Z

@philippneugebauer yes that's true, that is confusing. We turn it on by default for streaming sources since the main use case is new users testing out a local webcam with detect.py --source 0, and they tend to raise issues if they don't see the video displayed.

I think what we need is a line like view_img &= check_imshow() to check that the environment actually supports viewing images. I think this would cause an image to briefly appear for everyone during check_imshow() though.

import cv2
import numpy as np

def check_imshow():
    # Check if environment supports image display
    try:
        cv2.imshow('test', np.zeros((320, 320, 3)))
        cv2.waitKey(1)
        cv2.destroyAllWindows()
        cv2.waitKey(1)
        return True
    except:
        print('WARNING: Environment does not support cv2.imshow() or PIL Image.show() image previews')
        return False

print(check_imshow())

philippneugebauer · 2021-02-16T21:07:09Z

yeah, I see your point. So that would be the ideal solution.

Maybe adding a message to the exception that non-GUI environments should disable the view_img manually. It gives a nice hint for the user and is a simple workaround

glenn-jocher · 2021-02-16T21:33:14Z

@philippneugebauer good idea! I've created PR #2231 that should address this. Can you give it a quick lookover?

philippneugebauer · 2021-02-16T21:37:22Z

haha, so I meant the exception I encountered, but it obviously also fit your code :D. Your solution is more useful though. I am not a Python expert but it looks good to me. Let me know if I should test the code locally

glenn-jocher · 2021-02-16T21:48:40Z

@philippneugebauer yes good point. I've updated now. Looks good in Colab, the Exception actually provides meaningful info.

ozett · 2021-09-23T10:01:55Z

today i ran into this problem on cli-only

(y5) olaf@ub2004yolo5:~/yolov5$ python detect.py --source rtsp://192.168.14.108/axis-media/media.amp
detect: weights=yolov5s.pt, source=rtsp://192.168.14.108/axis-media/media.amp, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False
YOLOv5 🚀 v5.0-455-g59aae85 torch 1.9.1+cu102 CPU

Fusing layers...
Model Summary: 224 layers, 7266973 parameters, 0 gradients
qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/home/olaf/.virtualenvs/y5/lib/python3.8/site-packages/cv2/qt/plugins" even though it was found.
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.

Available platform plugins are: xcb.

Aborted (core dumped)
(y5) olaf@ub2004yolo5:~/yolov5$

i will try to fiddle with detect.py on streaming source while on commandLine-only

edit: surprise. the code-change is in, but the error still persits...

edit2: hmmm, where are the hints for correct options? in the code?

(y5) olaf@ub2004yolo5:~/yolov5$ python detect.py --view_img=false --source rtsp://192.168.14.108/axis-media/media.amp
usage: detect.py [-h] [--weights WEIGHTS [WEIGHTS ...]] [--source SOURCE] [--imgsz IMGSZ [IMGSZ ...]] [--conf-thres CONF_THRES] [--iou-thres IOU_THRES]
                 [--max-det MAX_DET] [--device DEVICE] [--view-img] [--save-txt] [--save-conf] [--save-crop] [--nosave] [--classes CLASSES [CLASSES ...]]
                 [--agnostic-nms] [--augment] [--visualize] [--update] [--project PROJECT] [--name NAME] [--exist-ok] [--line-thickness LINE_THICKNESS]
                 [--hide-labels] [--hide-conf] [--half]
detect.py: error: unrecognized arguments: --view_img=false
(y5) olaf@ub2004yolo5:~/yolov5$ ^C
(y5) olaf@ub2004yolo5:~/yolov5$ python detect.py --view_img False --source rtsp://192.168.14.108/axis-media/media.amp
usage: detect.py [-h] [--weights WEIGHTS [WEIGHTS ...]] [--source SOURCE] [--imgsz IMGSZ [IMGSZ ...]] [--conf-thres CONF_THRES] [--iou-thres IOU_THRES]
                 [--max-det MAX_DET] [--device DEVICE] [--view-img] [--save-txt] [--save-conf] [--save-crop] [--nosave] [--classes CLASSES [CLASSES ...]]
                 [--agnostic-nms] [--augment] [--visualize] [--update] [--project PROJECT] [--name NAME] [--exist-ok] [--line-thickness LINE_THICKNESS]
                 [--hide-labels] [--hide-conf] [--half]
detect.py: error: unrecognized arguments: --view_img False

glenn-jocher · 2021-09-24T15:43:02Z

@ozett YOLOv5 arguments don't use underscores, they use dashes: --view-img

About your original question I'm not able to reproduce your command as your stream is not available:
[tcp @ 0x7fe94801ee00] Connection to tcp://192.168.14.108:554?timeout=0 failed: Connection refused

We've created a few short guidelines below to help users provide what we need in order to get started investigating a possible problem.

How to create a Minimal, Reproducible Example

When asking a question, people will be better able to provide help if you provide code that they can easily understand and use to reproduce the problem. This is referred to by community members as creating a minimum reproducible example. Your code that reproduces the problem should be:

✅ Minimal – Use as little code as possible that still produces the same problem
✅ Complete – Provide all parts someone else needs to reproduce your problem in the question itself
✅ Reproducible – Test the code you're about to provide to make sure it reproduces the problem

In addition to the above requirements, for Ultralytics to provide assistance your code should be:

✅ Current – Verify that your code is up-to-date with current GitHub master, and if necessary git pull or git clone a new copy to ensure your problem has not already been resolved by previous commits.
✅ Unmodified – Your problem must be reproducible without any modifications to the codebase in this repository. Ultralytics does not provide support for custom code ⚠️.

If you believe your problem meets all of the above criteria, please close this issue and raise a new one using the 🐛 Bug Report template and providing a minimum reproducible example to help us better understand and diagnose your problem.

Thank you! 😃

ozett · 2021-09-25T14:59:22Z

Hi thanks for looking into this.
i did the dashes wrong. but even without options i cannot do inference on the cli.
the stream seams not the problem, because i do this without a graphical environment on ssh-cli.
should that work, or is it intended not to?

detect: weights=yolov5s.pt, source=rtsp://192.168.14.108/axis-media/media.amp, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False
YOLOv5 🚀 v5.0-455-g59aae85 torch 1.9.1+cu102 CPU

Fusing layers...
Model Summary: 224 layers, 7266973 parameters, 0 gradients
qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/home/olaf/.virtualenvs/y5/lib/python3.8/site-packages/cv2/qt/plugins" even though it was found.
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.

Available platform plugins are: xcb.

Aborted (core dumped)
(y5) olaf@ub2004yolo5:~/yolov5$

glenn-jocher · 2021-09-25T16:15:36Z

@ozett seems like you are missing some cv2 dependencies. You may want to use one of our verified environments while you debug your local environment.

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

Google Colab and Kaggle notebooks with free GPU:
Google Cloud Deep Learning VM. See GCP Quickstart Guide
Amazon Deep Learning AMI. See AWS Quickstart Guide
Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

jjqoie · 2021-11-14T23:34:03Z

Hi all
I just run into the same error message qt.qpa.plugin: "Could not load the Qt platform plugin xcb" but triggered in a slightly different way
I run YoloV5 on my home iot server which doesn't have a Monitor. For testing I'm using a jupyterlab in a docker container
To fix this I installed opencv headless - see link
https://forum.qt.io/topic/119109/using-pyqt5-with-opencv-python-cv2-causes-error-could-not-load-qt-platform-plugin-xcb-even-though-it-was-found/7
Seems that the cv2 import itself is causing it?

After installing pip install opencv-python-headless a problem in the datasets.py line 350 with cv2.waitkey appeared
if not all(x.is_alive() for x in self.threads): # or cv2.waitKey(1) == ord('q'): # q to quit
After commenting this part out yolov5 start processing frames

PS: YoloV5 correctly detected imshow is not supported and print it out
WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays

andiandhika · 2022-05-26T18:02:57Z

https://user-images.githubusercontent.com/62016426/170547790-2e7bb51d-bfea-4384-a7e0-452d071f69b7.PNG

hi , what should I do if something like this happens?

afrahthahir · 2022-05-28T03:32:39Z

https://user-images.githubusercontent.com/55926806/170808240-284a1835-ffc1-47b7-96b5-758813116c8b.png
hii, I am working yolov5 on google colab. When I use the rtsp link which is valid, Could not get the results as expected.
Pls help me on this.

glenn-jocher · 2022-05-28T08:45:01Z

@afrahthahir 👋 hi, thanks for letting us know about this possible problem with YOLOv5 🚀. We've created a few short guidelines below to help users provide what we need in order to start investigating a possible problem.

How to create a Minimal, Reproducible Example

When asking a question, people will be better able to provide help if you provide code that they can easily understand and use to reproduce the problem. This is referred to by community members as creating a minimum reproducible example. Your code that reproduces the problem should be:

✅ Minimal – Use as little code as possible to produce the problem
✅ Complete – Provide all parts someone else needs to reproduce the problem
✅ Reproducible – Test the code you're about to provide to make sure it reproduces the problem

For Ultralytics to provide assistance your code should also be:

✅ Current – Verify that your code is up-to-date with GitHub master, and if necessary git pull or git clone a new copy to ensure your problem has not already been solved in master.
✅ Unmodified – Your problem must be reproducible using official YOLOv5 code without changes. Ultralytics does not provide support for custom code ⚠️.

If you believe your problem meets all the above criteria, please close this issue and raise a new one using the 🐛 Bug Report template with a minimum reproducible example to help us better understand and diagnose your problem.

Thank you! 😃

andiandhika · 2022-05-28T09:53:50Z

okay thanks for the explanation, I'll try to explain again, I use google colab to run the code, when I want to run !python detect.py --source 0 to run using the webcam there is a notification WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays cv2.imshow() is disabled in Google Colab environments

I don't know how to fix it, Pls help me on this thanks

glenn-jocher · 2022-05-28T10:18:44Z

@andiandhika local webcams are only available in local environments, assuming you have one on your computer.

andiandhika · 2022-05-28T10:46:25Z

@andiandhika local webcams are only available in local environments, assuming you have one on your computer.

Thank you, I want to try again

andiandhika · 2022-05-29T14:57:24Z

hi i have tried again but the result is the same , i have used local camera, with command !python detect.py --source 0 but still there is a notification WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays cv2.imshow() is disabled in Google Colab environments

glenn-jocher · 2022-05-29T16:49:17Z

@andiandhika colab is not a local environment. Local means right there in front of you, i.e. YOUR computer.

andiandhika · 2022-05-29T17:11:41Z

@andiandhika colab is not a local environment. Local means right there in front of you, i.e. YOUR computer.

I don't think so, I tried using this code and it worked only to open the webcam

start streaming video from webcam

video_stream()

label for video

label_html = 'Capturing...'

initialze bounding box to empty

bbox = ''
count = 0
while True:
js_reply = video_frame(label_html, bbox)
if not js_reply:
break

# convert JS response to OpenCV Image
img = js_to_image(js_reply["img"])

# create transparent overlay for bounding box
bbox_array = np.zeros([480,640,4], dtype=np.uint8)

# grayscale image for face detection
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)

# get face region coordinates
faces = face_cascade.detectMultiScale(gray)
# get face bounding box for overlay
for (x,y,w,h) in faces:
  bbox_array = cv2.rectangle(bbox_array,(x,y),(x+w,y+h),(255,0,0),2)

bbox_array[:,:,3] = (bbox_array.max(axis = 2) > 0 ).astype(int) * 255
# convert overlay of bbox into bytes
bbox_bytes = bbox_to_bytes(bbox_array)
# update bbox so next frame gets new overlay
bbox = bbox_bytes

andiandhika · 2022-05-29T17:14:04Z

@andiandhika colab is not a local environment. Local means right there in front of you, i.e. YOUR computer.

I don't think so, I tried using this code and it worked only to open the webcam

start streaming video from webcam

video_stream()

label for video

label_html = 'Capturing...'

initialze bounding box to empty

bbox = '' count = 0 while True: js_reply = video_frame(label_html, bbox) if not js_reply: break
# convert JS response to OpenCV Image
img = js_to_image(js_reply["img"])

# create transparent overlay for bounding box
bbox_array = np.zeros([480,640,4], dtype=np.uint8)

# grayscale image for face detection
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)

# get face region coordinates
faces = face_cascade.detectMultiScale(gray)
# get face bounding box for overlay
for (x,y,w,h) in faces:
  bbox_array = cv2.rectangle(bbox_array,(x,y),(x+w,y+h),(255,0,0),2)

bbox_array[:,:,3] = (bbox_array.max(axis = 2) > 0 ).astype(int) * 255
# convert overlay of bbox into bytes
bbox_bytes = bbox_to_bytes(bbox_array)
# update bbox so next frame gets new overlay
bbox = bbox_bytes

it would be better to make changes to the code so that it can be run using a webcam, thank you in advance

glenn-jocher · 2022-05-29T17:45:48Z

@andiandhika hi, thank you for your feature suggestion on how to improve YOLOv5 🚀!

The fastest and easiest way to incorporate your ideas into the official codebase is to submit a Pull Request (PR) implementing your idea, and if applicable providing before and after profiling/inference/training results to help us understand the improvement your feature provides. This allows us to directly see the changes in the code and to understand how they affect workflows and performance.

Please see our ✅ Contributing Guide to get started.

andiandhika · 2022-05-29T18:02:35Z

@andiandhika hi, thank you for your feature suggestion on how to improve YOLOv5 🚀!

The fastest and easiest way to incorporate your ideas into the official codebase is to submit a Pull Request (PR) implementing your idea, and if applicable providing before and after profiling/inference/training results to help us understand the improvement your feature provides. This allows us to directly see the changes in the code and to understand how they affect workflows and performance.

Please see our ✅ Contributing Guide to get started.

ok thanks in advance, definitely when i know more about it

andiandhika · 2022-06-03T16:38:02Z

hi, i have done training i want to ask what is the difference between these two mAP@? which I marked in red

afrahthahir · 2022-10-11T08:00:17Z

I think yolov5 has no test.py May be ur command is for detect.py or train.py

…

On Wed, 1 Jun 2022, 00:36 andiandhika, ***@***.***> wrote: hi I'm trying to calculate the map on the test dataset with the command !python test.py --weights yolov5s.pt runs/train/yolo_road_det/weights/ best.pt --data road_sign_data.yaml --task test --name yolo_det , but getting a notification: python3: can't open file 'test.py': [Errno 2] No such file or directory this makes sense to me , since I also can't find the test.py file, is the test.py file really not available? — Reply to this email directly, view it on GitHub <#2226 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ANKWAFWKBVEWWPY4A5VT74LVMZPJ7ANCNFSM4XWDWPHQ> . You are receiving this because you were mentioned.Message ID: ***@***.***>

afrahthahir · 2022-10-11T08:22:40Z

In YouTube, for yolov5 realtime object detection code is shown for only webcam as the source. If u want to use your source as webcam, u should try at the system directly and don't opt for cloud GPUs such as colab. Colab doesnot support webcam as source. It is possible but it is complicated than trying in the system directly. Hope it helps..

…

On Sun, 29 May 2022, 20:27 andiandhika, ***@***.***> wrote: hi i have tried again but the result is the same , i have used local camera, with command !python detect.py --source 0 but still there is a notification WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays cv2.imshow() is disabled in Google Colab environment [image: Capture] <https://user-images.githubusercontent.com/62016426/170875951-a47ddb3f-951c-42d8-a74f-59dbaa547930.PNG> s — Reply to this email directly, view it on GitHub <#2226 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ANKWAFRT6CDPWXGV7RU6RW3VMOAV7ANCNFSM4XWDWPHQ> . You are receiving this because you were mentioned.Message ID: ***@***.***>

mansi733 · 2023-05-12T16:47:59Z

Hi,
I am using torch.hub.load and I want to access CCTV camera with the IP address, please check the screenshot is the correct way to connect CCTV camera.

glenn-jocher · 2023-05-12T19:21:04Z

@mansi733 hello,

Thank you for reaching out. Unfortunately, we cannot see the screenshot that you mentioned in your message. Can you please try to attach it again or provide more details on how you are trying to access the CCTV camera with the IP address? This information will help us better understand your issue and provide you with the appropriate solution.

Thank you.

mansi733 · 2023-05-13T03:26:44Z

@mansi733 hello,

Thank you for reaching out. Unfortunately, we cannot see the screenshot that you mentioned in your message. Can you please try to attach it again or provide more details on how you are trying to access the CCTV camera with the IP address? This information will help us better understand your issue and provide you with the appropriate solution.

Thank you.

Yes, Please check this code

conf_score = 0.40 # change the value for confiedence score.

parser = argparse.ArgumentParser(description="Camera type.")
parser.add_argument("--cam", type=str, default=0)
args = parser.parse_args()

camera_type = 'rtsp://192.1.2.68/'

model = torch.hub.load('ultralytics/yolov5', 'custom', 'C:/Users/HP/Desktop/Fire-cmd/client.pt'

vid = cv2.VideoCapture(camera_type)
vid.open(camera_type)

classes = model.names
-Thank You.

glenn-jocher · 2023-05-13T06:18:02Z

@mansi733 Thank you for providing the code snippet to help us better understand your issue. Based on your code, it seems that you are trying to access an IP camera using RTSP protocol and then loading a custom YOLOv5 model to do object detection on the camera stream.

One thing to note is that the IP camera address and port number need to be specified in the camera_type variable. If the camera requires a username and password for authentication, you'll also need to include them in the address, like rtsp://username:password@192.1.2.68:554/.

Additionally, make sure the camera is connected and streaming video before running the script. If you're still having issues, you can try checking if the camera address and credentials are correct, or try a different protocol (like HTTP) to access the camera.

I hope this helps. Let us know if you have any further questions or concerns. Thank you.

philippneugebauer added the bug Something isn't working label Feb 16, 2021

philippneugebauer closed this as completed Feb 16, 2021

glenn-jocher mentioned this issue Feb 16, 2021

Add check_imshow() #2231

Merged

glenn-jocher mentioned this issue Feb 16, 2021

Add isdocker() #2232

Merged

This was linked to pull requests Feb 16, 2021

Add isdocker() #2232

Merged

Add check_imshow() #2231

Merged

This was referenced Apr 11, 2021

YOLOv5 v5.0 Release #2762

Merged

YOLOv5 v5.0 release compatibility update for YOLOv3 ultralytics/yolov3#1737

Merged

Yolov5 crashes with RTSP stream analysis #2226

Yolov5 crashes with RTSP stream analysis #2226

Comments

philippneugebauer commented Feb 16, 2021

🐛 Bug

To Reproduce (REQUIRED)

Expected behavior

Environment

github-actions bot commented Feb 16, 2021 • edited by UltralyticsAssistant Loading

Requirements

Environments

Status

glenn-jocher commented Feb 16, 2021

philippneugebauer commented Feb 16, 2021

glenn-jocher commented Feb 16, 2021

philippneugebauer commented Feb 16, 2021

glenn-jocher commented Feb 16, 2021 • edited Loading

philippneugebauer commented Feb 16, 2021

glenn-jocher commented Feb 16, 2021

philippneugebauer commented Feb 16, 2021

glenn-jocher commented Feb 16, 2021

ozett commented Sep 23, 2021 • edited Loading

glenn-jocher commented Sep 24, 2021 • edited Loading

How to create a Minimal, Reproducible Example

ozett commented Sep 25, 2021

glenn-jocher commented Sep 25, 2021 • edited by UltralyticsAssistant Loading

Environments

Status

jjqoie commented Nov 14, 2021 • edited Loading

andiandhika commented May 26, 2022

afrahthahir commented May 28, 2022

glenn-jocher commented May 28, 2022 • edited Loading

How to create a Minimal, Reproducible Example

andiandhika commented May 28, 2022 • edited Loading

glenn-jocher commented May 28, 2022

andiandhika commented May 28, 2022

andiandhika commented May 29, 2022 • edited Loading

glenn-jocher commented May 29, 2022

andiandhika commented May 29, 2022 • edited Loading

start streaming video from webcam

label for video

initialze bounding box to empty

andiandhika commented May 29, 2022

start streaming video from webcam

label for video

initialze bounding box to empty

glenn-jocher commented May 29, 2022 • edited Loading

andiandhika commented May 29, 2022 • edited by glenn-jocher Loading

andiandhika commented Jun 3, 2022

afrahthahir commented Oct 11, 2022 via email

afrahthahir commented Oct 11, 2022 via email

mansi733 commented May 12, 2023

glenn-jocher commented May 12, 2023

mansi733 commented May 13, 2023 • edited Loading

glenn-jocher commented May 13, 2023

github-actions bot commented Feb 16, 2021 •

edited by UltralyticsAssistant

Loading

glenn-jocher commented Feb 16, 2021 •

edited

Loading

ozett commented Sep 23, 2021 •

edited

Loading

glenn-jocher commented Sep 24, 2021 •

edited

Loading

glenn-jocher commented Sep 25, 2021 •

edited by UltralyticsAssistant

Loading

jjqoie commented Nov 14, 2021 •

edited

Loading

glenn-jocher commented May 28, 2022 •

edited

Loading

andiandhika commented May 28, 2022 •

edited

Loading

andiandhika commented May 29, 2022 •

edited

Loading

andiandhika commented May 29, 2022 •

edited

Loading

glenn-jocher commented May 29, 2022 •

edited

Loading

andiandhika commented May 29, 2022 •

edited by glenn-jocher

Loading

mansi733 commented May 13, 2023 •

edited

Loading