Dwell Time Analysis with Computer Vision | Real-Time Stream Processing

Поделиться
HTML-код
  • Опубликовано: 21 ноя 2024

Комментарии • 88

  • @tobieabel7474
    @tobieabel7474 7 месяцев назад +3

    Another great tutorial. I'm glad you've covered the issues of latency and frames accumulating in the buffer causing crashes, I've been having trouble with that when trying to run CV applications for long periods.

    • @Roboflow
      @Roboflow  7 месяцев назад +3

      I’m curious why so few tutorials cover this topic in depth

  • @tomii5644
    @tomii5644 7 месяцев назад +4

    The system is amazing, thanks a lot for the tutorial :)

  • @paulelliotco
    @paulelliotco 3 месяца назад +1

    Thank you for the tutorial. Could you do one on shoplifting? Interesting use case.

  • @JohnnyThomas-py3jv
    @JohnnyThomas-py3jv 7 месяцев назад +2

    Your channel calms me

    • @Roboflow
      @Roboflow  7 месяцев назад +1

      Not really sure what you mean :/

    • @MrRobot-yb8cb
      @MrRobot-yb8cb 4 месяца назад

      @@RoboflowI think he is trying to say that your tutorials are chill af, and I can confirm it))))

  • @shahinamini7047
    @shahinamini7047 7 месяцев назад +1

    It is my thesis
    Thanks you so much

    • @Roboflow
      @Roboflow  7 месяцев назад

      My pleasure!

  • @amicoder6645
    @amicoder6645 Месяц назад

    i am new and understanding this logics and math is very difficult i hope i will learn it as soon as possible

    • @Roboflow
      @Roboflow  Месяц назад

      Any specific questions you have?

  • @thomasboosinger2758
    @thomasboosinger2758 7 месяцев назад +2

    Amazing video! Thanks!

  • @ItayHilel
    @ItayHilel 7 месяцев назад +3

    @Roboflow, what was done in the video is great! I loved it!!! . But it's a workaround; you took a video and turned it into an RTSP link. However, there are many challenges that occur when pulling footage from a stream.
    I would love to see that part done as well. Let's say you get permission for a few cameras from an office/gym or elsewhere and do an example project. It would be fascinating to see the process of pulling footage from these cameras, training a model, thinking of a use case that solves a real-world problem, coding it, and finally giving the result to the client (showing us thats the average time of a customer in checkout 6 is 50 sec on a given day) .
    Currently, most CV i see is done on 15-second videos and from one camera, and there isn't much value in that. real value is in solving real problems with multiple cameras models/logic that works together.
    I'm aware that what I'm talking about is a huge project and not an easy task, but if anyone can do it, it's @Roboflow and Piotr.
    I believe that a tutorial/series like I'm imagining would open the door for millions of CV applications to be built in the future.

    • @tobieabel7474
      @tobieabel7474 7 месяцев назад +3

      Thats exactly what we're doing at the moment for a soccer stadium in UK, taking multiple streams from the CCTV and measuring the average wait time at some turnstiles and food/drink stalls. If the Proof of Concept is successful we will also use CV to monitor occupancy and highlight spare seats in the stadium on a floorplan. Roboflow and Supervision are really useful tools for us!

    • @ItayHilel
      @ItayHilel 7 месяцев назад +1

      @@tobieabel7474 can you share your journey? i would love to read a blog or watch a video

    • @Roboflow
      @Roboflow  7 месяцев назад

      Great to know that the time spent creating these tools and tutorials is not wasted! I would love to learn more if possible!

    • @Roboflow
      @Roboflow  7 месяцев назад +1

      Today we are hosting a live community session. We will be talking mostly about real-time stream processing and time calculation. Would be awesome if you could join!

    • @tobieabel7474
      @tobieabel7474 7 месяцев назад +2

      Maybe​@@Roboflow can sponsor me to do a blog of the journey and put it on your channel! Sure, I'll be at the community session today

  • @RamphyRojas
    @RamphyRojas 7 месяцев назад +1

    amazing tutorial, thank you for your time!

  • @deep_singh01
    @deep_singh01 7 месяцев назад +1

    Amazing tutorial it help to us 👍

  • @sanchaythalnerkar9736
    @sanchaythalnerkar9736 7 месяцев назад

    Great Video as always!
    How did you create the intro explanation on white board with the text and diagrams?

  • @Mesenqe
    @Mesenqe 7 месяцев назад +1

    Thank you for the great Tutorial. I always enjoy your tutorials. If you have time, I wish you could make tutorial of Camera Calibration 💙.

    • @Roboflow
      @Roboflow  7 месяцев назад +1

      I can’t add it to our TODO list but it is really long… we already have ideas for at least 5 videos.

  • @prithaa442
    @prithaa442 7 месяцев назад +1

    Superb sir

    • @Roboflow
      @Roboflow  7 месяцев назад

      Thanks a lot!

  •  7 месяцев назад +1

    Great video. What happen when the frames dropping are s?

    • @Roboflow
      @Roboflow  7 месяцев назад

      That’s a very good question. It is guaranteed that you will not drop s because of InferencePipeline logic. You may still drop it because of internet connection. But not because of InferencePipeline. We tested the logic on Jetson Nano decoding 4K stream and it worked really reliably.

  • @tiktak132
    @tiktak132 7 месяцев назад +1

    Where does the processed video get saved? also seems to be running really slow on the detection running a m1 mac. Great tutorial!

    • @Roboflow
      @Roboflow  7 месяцев назад

      In the repository you can find set it scripts that use ultralytics. It uses PyTorch as backend, and can use mps device accessible on M1 macs.

  • @EliSpizzichino
    @EliSpizzichino 7 месяцев назад +1

    More content like this congrats!

    • @Roboflow
      @Roboflow  7 месяцев назад

      We are not slowing down ;)

  • @unholytsar
    @unholytsar 7 месяцев назад

    Hi, thanks for the really great and easy to understand tutorial. Here, you implemented a clock based timer approach to calculate elapsed time from a real time stream. I am assuming that similar approach can be used to estimate the speed of an object (like car) from a real time stream as well. Is it correct? Would appreciate your valuable feedback.

  • @_ABDULGHANI
    @_ABDULGHANI 7 месяцев назад +1

    Thank you for this amazing tutorial, can I use these examples with other versions of YOLO algorithm like v7 or v6, or does this work on YOLOv8 only?

    • @Roboflow
      @Roboflow  7 месяцев назад

      You can swap the model. No problem.

    • @_ABDULGHANI
      @_ABDULGHANI 7 месяцев назад +1

      @@Roboflow OK, thank you I thought this is exclusive for the Ultralytics models only, I have already created a custom YOLOv7 & 6 model and I will use them with supervision.

    • @Roboflow
      @Roboflow  7 месяцев назад +1

      Can you run your YOLOv7 as stand alone model or do you have to use detect.py script?

    • @_ABDULGHANI
      @_ABDULGHANI 7 месяцев назад

      @@Roboflow I have used detect.py, but now I am working on a code to load my model and detect object, in case I want to implement anything with my model it will be easy for me to use my code.

  • @와드남-y6l
    @와드남-y6l 5 месяцев назад +1

    Can we proceed with the vehicle speed estimation in real-time, which is a whole project?

    • @Roboflow
      @Roboflow  5 месяцев назад +1

      You men you want us to make a video about it? :)

  • @GunaNadarWL
    @GunaNadarWL Месяц назад

    how much will it cost for a single stream for a month with maybe 2 fps provided we have already trained the model with roboflow?

  • @marwanahmed6752
    @marwanahmed6752 6 месяцев назад

    Thank you for this amazing tutorial, i just have a problem I'm working with project that detect and tracking people but in my model when people change thier position the model record it's another track so how i can enhance it

  • @chiragharish1020
    @chiragharish1020 7 месяцев назад

    Which architecture is used internalliy in
    Roboflow 3.0 Object Detection (Fast)????

  • @nestorjavierhurtado
    @nestorjavierhurtado 6 месяцев назад

    Se puede ejecutar en una jetson nano de 4GB?

  • @SyBacVo
    @SyBacVo 7 месяцев назад

    Great video for show, but the processing time is quite slow even if with ultralytics :( Is there any way to speed up the processing time without using GPU ? Thanks in advance!!! You guys are doing a great work in a great direction.

    • @Roboflow
      @Roboflow  7 месяцев назад

      What hardware you have and how fast would you like to run?

    • @SyBacVo
      @SyBacVo 7 месяцев назад +1

      @@Roboflow Processor: Intel(R) Core(TM) i5-4460 CPU @ 3.20GHz 3.20 GHz; RAM: 8.00 GB (7.87 GB usable); 24 fps (real time speed) is enough for me.

    • @Roboflow
      @Roboflow  7 месяцев назад

      If you don't have a GPU, perhaps you could use a smaller model? Eventually run object detection through OpenVINO - Intel hardware model accelerator. We could talk about it deeper during live community session today. It would be so cool if you could join. ruclips.net/video/u7XUC-3TqY8/видео.html&ab_channel=Roboflow

    • @SyBacVo
      @SyBacVo 7 месяцев назад

      @@Roboflow Sorry for not attending the live session, 10PM is quite late for me cause I am quite tired after a long working day :( ! Hey, I have a proposal like this, can you consult how to achieve this goal (funding, framework, algorithms..., ) docs.google.com/document/d/1ldpQ6q3MpJmox-nOSj2SLq-9sKBMEau1JxHbQClmHMg/edit?usp=sharing . In the past, I used traditional method.ruclips.net/video/N8i2gbh6RRI/видео.html but with the advance of AI, I think we can do further.

  • @lukewinters7981
    @lukewinters7981 5 месяцев назад

    Is there a simple way to save class detections in real time to an updating excel file or something similar? i.e. a continuous record of timestamps, with each timestamp containing the object detections, the zone it was detected in and/or bounding box positions/conf at that time, and this information is real-time updating an excel file?

  • @ridofajarrachmadi2605
    @ridofajarrachmadi2605 3 месяца назад

    Could I use a local trained dataset? because i can't afford roboflow premium so my dataset cant be trained better with roboflow

  • @SebastianVargas-yj7dh
    @SebastianVargas-yj7dh 7 месяцев назад +1

    Is ther any way i can set my model project to run with my gpu? currently it only runs over the processor

    • @Roboflow
      @Roboflow  7 месяцев назад +1

      Install inference-gpu package instead of inference. It will allow you to run faster on NVIDIA GPUs.

  • @romellfudi
    @romellfudi 7 месяцев назад +1

    is possible to run it into a mps device? such as M3

    • @Roboflow
      @Roboflow  7 месяцев назад +1

      I included scripts that use ultralytics to run the model. And you can use mps to accelerate inference with this model on M3?

    • @romellfudi
      @romellfudi 7 месяцев назад +1

      @@Roboflow yes

  • @baotrangia3837
    @baotrangia3837 5 месяцев назад +1

    Hello, is there anyway for me to custom for keeping the quality of frame more clearly, I have test and see the quality of frame stream is too bad

    • @Roboflow
      @Roboflow  5 месяцев назад +1

      Steam quality depends on resolution and compression algorithms. Usually stream source controls those parameters.

    • @baotrangia3837
      @baotrangia3837 5 месяцев назад

      @@Roboflow Thanks for your response, let me try it

  • @hamzamohammad7138
    @hamzamohammad7138 7 месяцев назад +1

    @Roboflow Wow this is great content so much exposure to unleash YOLO features. im working on a realtime project which is taking in about 10 stream feeds and has 6 different yolo models(Yolov8) with different usecases. i have currently applied threading on the usecases but im confused how can i feed in 10 streams parallel. im looking for suggestions from on prem deployment point of view as well

    • @Roboflow
      @Roboflow  7 месяцев назад

      Today we are hosting a live community session. It would be so cool if you could join. ruclips.net/video/u7XUC-3TqY8/видео.html&ab_channel=Roboflow

  • @hosseinhaghjoo
    @hosseinhaghjoo 5 месяцев назад

    I can't find link for the code you wrote

  • @PlottingMath
    @PlottingMath 5 месяцев назад +1

    is there a way to process high resolution stream in realtime to detect / track small objects in the stream?
    I have tried SAHI, but its not possible to run in real time if the images are 5000x576.

    • @Roboflow
      @Roboflow  5 месяцев назад

      It will always be a tradeoff between speed and accuracy. You have two options - increase inference resolution(imgsz parameter in YOLOv8) or use SAHI. Both will increase accuracy but decrease speed.

    • @PlottingMath
      @PlottingMath 5 месяцев назад

      @@Roboflow yes, thats what I also experienced. I am on the way to find a way to do parallel processing of small snippets and then merging the result. Lets see how far I can go

  • @otto8495
    @otto8495 3 месяца назад

    I am using yolo8 from ultralytics and bytetrack from supervision. I am doing exactly the same thing, Only difference is I am reading 2 videos at the same time. Yolo detecting humans but tracker doesn't update with that detections. Detection suddenly dissappear. What should be the problem?

  • @SamuelKwok-ge3iw
    @SamuelKwok-ge3iw 6 месяцев назад

    Hi Do you know how to generate the config.json file required by
    --zone_configuration_path "data/checkout/config.json" . Thanks

  • @shahinamini7047
    @shahinamini7047 6 месяцев назад

    hi!
    why i can't open it in google colab?

  • @akhiljx3591
    @akhiljx3591 6 месяцев назад

    i am not able to use the cuda/gpu support to the code. i tried by using code: model.to('cuda') but getting error. can someone help me on how to implement cuda to the above code. please

  • @thomasantony3381
    @thomasantony3381 Месяц назад

    Can anyone help me by mentioning if I can do this with GDPR compliance

    • @Roboflow
      @Roboflow  Месяц назад

      I was working in similar project under GDPR regime. It all depends on your use case, but in general it is possible.

    • @thomasantony3381
      @thomasantony3381 Месяц назад

      ​@@Roboflow Thank you the mention of its possibility
      My use case is to track the number of people that went by the camera and the dwell time infront of the camera I was thinking if bluring the faces of people make it GDPR complaint No collection of any other Personally identifiable data
      I wasn't able to find any good resource to back up this possibility
      Thanks again

  • @mryan744
    @mryan744 7 месяцев назад

    Is there a github repo with all of the code?

    • @Roboflow
      @Roboflow  7 месяцев назад +1

      Yup, the link is in the YT description

    • @ahmedhosam9029
      @ahmedhosam9029 7 месяцев назад

      @@Roboflow I could not find the link for this project code in the description could you please help ?

  • @ItayHilel
    @ItayHilel 7 месяцев назад

    why didn't you do this for a live video stream??

    • @Roboflow
      @Roboflow  7 месяцев назад

      I’m not really sure what you mean. I did?

    • @ItayHilel
      @ItayHilel 7 месяцев назад +1

      @Roboflow, what was done in the video is great! I loved it!!! 😍. But it's a workaround; you took a video and turned it into an RTSP link. However, there are many challenges that occur when pulling footage from a stream.
      I would love to see that part done as well. Let's say you get permission for a few cameras from an office/gym or elsewhere and do an example project. It would be fascinating to see the process of pulling footage from these cameras, training a model, thinking of a use case that solves a real-world problem, coding it, and finally giving the result to the client (showing us thats the average time of a customer in checkout 6 is 50 sec on a given day) .
      Currently, most CV i see is done on 15-second videos and from one camera, and there isn't much value in that. real value is in solving real problems with multiple cameras models/logic that works together.
      I'm aware that what I'm talking about is a huge project and not an easy task, but if anyone can do it, it's @Roboflow and Piotr.
      I believe that a tutorial/series like I'm imagining would open the door for millions of CV applications to be built in the future.

    • @Roboflow
      @Roboflow  7 месяцев назад

      The biggest problem for me is the lack of video footage that I could use to make such a tutorial....

    • @ItayHilel
      @ItayHilel 7 месяцев назад +1

      @@Roboflow what do you mean? is it a copyright issue? why is there a lack of video footage?

    • @Roboflow
      @Roboflow  7 месяцев назад

      @@ItayHilel there is simple no data like this that I can use in tutorials. I'd need footage from multiple cameras from store or gym. And people do not share that online :/

  • @ComputerVisionEngineerin-qs1yq
    @ComputerVisionEngineerin-qs1yq 7 месяцев назад +1

    Very Great Tutorial 🤩 I have done this before with @Lxuonis OAK. I also experienced the same challenges. Regards!

    • @Roboflow
      @Roboflow  7 месяцев назад

      Yes, the topic is much more complicated than it seems at first glance. I am very happy that you like the video.

    • @mryan744
      @mryan744 7 месяцев назад +1

      Can you send the link here ?, I dont seem to find the full stream code in the description 😅

    • @Roboflow
      @Roboflow  7 месяцев назад

      take a look here: github.com/roboflow/supervision/tree/develop/examples/time_in_zone

  • @sansonnsansonn1581
    @sansonnsansonn1581 5 месяцев назад

    no funciona