串联两个检测模型

比如第一个模型检测汽车，第二个模型检测车牌，如果将两个模型串联起来。可以参考deepstream_lpr_app 代码。

测试的gstreamer命令如下：

gst-launch-1.0 filesrc location=/home/lpr/us.mp4 ! qtdemux ! h264parse ! nvv4l2decoder ! mux.sink_0 nvstreammux name=mux batch-size=1 width=1920 height=1080 nvbuf-memory-type=3 ! nvinfer config-file-path=../../../configs/nvinfer/trafficcamnet_tao/pgie_trafficcamnet_config.yml   ! nvtracker name=tracker1 ll-config-file=/opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app/config_tracker_NvDCF_perf.yml ll-lib-file=/opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so tracker-width=640 tracker-height=384 user-meta-pool-size=128  ! nvinfer config-file-path=../../../configs/nvinfer/LPD_us_tao/sgie_lpd_DetectNet2_us.yml ! nvvideoconvert ! 'video/x-raw(memory:NVMM),format=RGBA' ! nvdsosd ! nvvideoconvert ! nvv4l2h264enc ! h264parse ! qtmux ! filesink location=./out.mp4

结果如下：

贴不了图，真是不好用。