Ocr the video timestamp in Deepstream

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 7.0
• JetPack Version (valid for Jetson only) 6.0
• TensorRT Version 8.6.2.3
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) question
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

I am new to Nvidia Deepstream and I am working on video analytics project using Deepstream. Earlier, I have created this video analystics project using basic python, opencv and pytorch, which is working fine. Now I want to do the same using Deepstream for better utilization of the resources.
The challenge I am facing that my video contains timestamp at a specific location as shown in picture, which I need to ocr.

vlcsnap-2024-10-26-07h46m20s470
vlcsnap-2024-10-26-07h46m20s4701920×1080 164 KB

Earlier, in my python code, I have trained my custom digit classifier that takes only a digit as image and returns me the digit. Since, I know the location of each of the digit, I crop each digit image pass to the custom digit classifier to get the digit.
I am wondering how can I do this in deepstream in the best way.

3
  1. Since the the place of timestamp will not change. you can set a ROI functionality of nvdspreprocess, which will crop the ROI of the full frame. please refer to the the sample deepstream-preprocess-test.
  2. please refer to the sample deepstream_lpr_app for digit recognition. the sample include three models, the first detects vehicles, the second detects car license plates, the third recognize characters of car license plate .
4

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.