DeepStream SDK FAQ

Accelerated Computing Intelligent Video Analytics DeepStream SDK
17

12. [DSx_Jetson_App]: Dump NV12 NvBufSurface into a YUV file
Each NV12 NvBufSurface includes two semi-planes which are not continuous in memory.
gstnvinfer_dump_NV12_NvBufSurface.patch (4.9 KB)

This is a sample change to /opt/nvidia/deepstream/deepstream-5.1/sources/gst-plugins/gst-nvinfer/gstnvinfer.cpp to dump the NV12 NvBufSurface before transforming to RGB data.
After getting the YUV file, we can view it with GitHub - IENT/YUView: The Free and Open Source Cross Platform YUV Viewer with an advanced analytics toolset

Note: Also verified with DeepStream 6.2 on Jetson

How to convert NvBufSurface to jpeg?
Dump jpeg in deepstream5.0
Sgie custom preprocessing
Help，dump image from nvv4l2decoder problem
Populate NvBufSurface from cv::Mat
Many frames are undetectable for DS5.0 Yolo example with a usb camera
How to get image data from frame_meta?
How to save ip_surf image data?
How to save original frame data and convert OpenCv mat?before infer data
Image Data Access after nvdsosd plugin
Deepstream
DS 6.2 - NvBufSurfaceMap - SIGSEGV
Issue with Cropping and Saving a Specific Frame Area in .jpg Format
How to view/save the image resized by the nvinfer element?
Detections change in Deepstream 6.2
Black frames using python demo deepstream_imagedata-multistream
Parse NV12_ER Format Deepstream 5.0
Package the tensorRT inference results into GstBuffer and push them to the downstream
Reading R,G,B values for specific pixel from NvBufSurface
Populating NvBuvSurface from cv::Mat in Jetson
Send detected object buffer to external API
To access a gray frame from YUV420p(progressive)
Problems converting/saving cropped NvBufSurface to JPEG file using ffmpeg
DS 6.1.1 - NvBufSurfaceMap - SIGSEGV
Cannot find the objectDetector_FastRCNN example
In Deepstream application, how to send a frame as image to kafka?
Image processing before preprocessing in nvinfer
cudaMemcpy: invalid argument when retrieving raw image
How to save cropped objects using deepstream-5.1 and convert to base64
During the migration from DeepStream 6.3 to 6.4, the dataSize attribute of surface->surfaceList[frame_meta->batch_id] changed
Custom Autoencoder Model
[Deepstream] How can I do my own image processing in C++?
Deepstream plugin causes buffer overwriting for parallel pipeline medias for python plugin
Crop images of detected objects and save them using Service Maker
Dynamically changing input resolution of RTSP streams
Jetson/Python: Gpu mapped buffer from gstreamer
Using HDF5 model
How to Use an Image Fusion Model in DeepStream
Request for Assistance in Improving Output Render Quality
How to read eglImage in NvMOTFrame
Extracting Processed Frames After Inference in Nvidia DeepStream Efficiently
Slight difference between original image from OpenCV (HTTP) and DeepStream gRPC