Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) : Tesla M60
• DeepStream Version :6.0
• JetPack Version (valid for Jetson only) : No
• TensorRT Version : 8.0.1
• NVIDIA GPU Driver Version (valid for GPU only): 520.61.05
• Issue Type( questions, new requirements, bugs) : Question
Hi Team
We are running the given example of deepstream-image-meta-test and it gives the cropped image of the person or vehicle and save it as a jpg , Likewise I am trying to get the full frame of the inferenced image in jpg for what I have tried the following things
-
In user meta you are passing the obj_meta with the obj_meta_user_list instead of that we are giving frame meta along with frame_user_meta_list the pipeline is not running its giving segmentation fault
-
Instead of frame meta we are using GstMapInfo inmap to retrieve buffer data and save it an file , the pipeline is running fine and its giving OSD_imge_name.jpg but size is around 1Kb or 64bytes
-
So I tried the link as mentioned in your forum link (How to encode multiple images using the same objectMeta inside obj_meta_list) but the same problem is happening for image its size is around 1kb or 64 bytes
These are the issues I am facing while I am retrieving the full frame with the detected object after inference, Can you help me on part?
Note: Here I need the full frame with the object detection along with that in the frame, only full frame not a cropped Image