运行deepstream-test1

其他朋友的博客

拷贝sample_720p.h264到deepstream-test1
cd deepstream-test1/
make
./deepstream-test1-app sample_720p.h264

1、nvinfer—执行推理模型
关于推理的配置都在 config-file-path = dstest1_pgie_config.txt
2、muxer 多路调制端将所有输入的分辨率统一
3、gchar pgie_classes_str[4][32] = { “Vehicle”, “TwoWheeler”, “Person”,
“Roadsign”
4、Create nvstreammux instance to form batches from one or more sources
nvstreammux—源变batches
5、解码器输出用nvinfer进行推理，推理行为通过配置文件设置
6、engine就是推理引擎
7、根据nvosd的要求用convertor将NV12转换成RGBA
8、nvosd用来画出buffer
9、Finally render the osd output
file-source -> h264-parser -> nvh264-decoder ->nvinfer -> nvvidconv -> nvosd -> video-renderer

---

创建pipeline,将所有元素比如h264parser,decoder,streammux等等全放进去