I try to change the example program, add read usb camera as source. And connect the source with nvstreammux.
The runtime error is as follows:
nvbuf_utils: dmabuf_fd -1 mapped entry NOT found
nvbuf_utils: Can not get HW buffer from FD… Exiting…
Segmentation fault (core dumped)
The detailed output log is as follows:
Copy of xzh@xzh:~/Desktop/4.ds_tracker $ ./build/ds_app
With tracker
source-bin-00
linking success
Creating H264 Encoder
Creating H264 rtppay
*** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***
Opening in BLOCKING MODE
0:00:00.295406078 19111 0x557eb8e380 WARN v4l2 gstv4l2object.c:2388:gst_v4l2_object_add_interlace_mode:0x557eb55390 Failed to determine interlace mode
0:00:00.295500663 19111 0x557eb8e380 WARN v4l2 gstv4l2object.c:2388:gst_v4l2_object_add_interlace_mode:0x557eb55390 Failed to determine interlace mode
0:00:00.295553060 19111 0x557eb8e380 WARN v4l2 gstv4l2object.c:2388:gst_v4l2_object_add_interlace_mode:0x557eb55390 Failed to determine interlace mode
0:00:00.295606603 19111 0x557eb8e380 WARN v4l2 gstv4l2object.c:2388:gst_v4l2_object_add_interlace_mode:0x557eb55390 Failed to determine interlace mode
0:00:00.295741449 19111 0x557eb8e380 WARN v4l2 gstv4l2object.c:4476:gst_v4l2_object_probe_caps:encoder:src Failed to probe pixel aspect ratio with VIDIOC_CROPCAP: Unknown error -1
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
gstnvtracker: Batch processing is ON
gstnvtracker: Past frame output is OFF
!! [WARNING][NvTrackerParamsTargetManager] Unknown param found: preserveStreamUpdateOrder
[NvMultiObjectTracker] Initialized
WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
Deserialize yoloLayer plugin: YoloLayer
0:00:06.198177308 19111 0x557eb8e380 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() < nvdsinfer_context_impl.cpp:1900>[UID=1] : deserialized trt engine from :/home/xzh/Desktop/4.ds_tracker copy/weights/yolov5.engine
INFO: [Implicit Engine Info]: layers num: 5
0 INPUT kFLOAT images 3x640x640
1 OUTPUT kINT32 DecodeNumDetection 1
2 OUTPUT kFLOAT DecodeDetectionBoxes 25200x4
3 OUTPUT kFLOAT DecodeDetectionScores 25200
4 OUTPUT kINT32 DecodeDetectionClasses 25200
0:00:06.200164740 19111 0x557eb8e380 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() [UID=1] : Use deserialized engine model: Copy of /home/xzh/Desktop/4.ds_tracker /weights/yolov5.engine
0:00:06.214677763 19111 0x557eb8e380 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus: [UID 1]: Load new model:config/pgie_config.txt successfully
0:00:06.215500643 19111 0x557e74af70 FIXME videodecoder gstvideodecoder.c:933:gst_video_decoder_drain_out: Sub-class should implement drain()
0:00:06.215510174 19111 0x557eb8e380 WARN v4l2src gstv4l2src.c:692:gst_v4l2src_query: Can’t give latency since framerate isn’t fixed !
Running…
FPS: 0.00
0:00:06.334613371 19111 0x557e74af70 WARN v4l2bufferpool gstv4l2bufferpool.c:790:gst_v4l2_buffer_pool_start:mysrc:pool:src Uncertain or not enough buffers, enabling copy threshold
0:00:06.680119936 19111 0x557e74af70 FIXME videodecoder gstvideodecoder.c:933:gst_video_decoder_drain_out: Sub-class should implement drain()
NvMMLiteOpen : Block : BlockType = 4
===== NVMEDIA: NVENC =====
NvMMLiteBlockCreate : Block : BlockType = 4
0: 00: 06.717753742 19111 0x557E74AF70 Warn V4L2BufferPool GSTV4L2BufferPool.c: 1087: GST_V4L2_Buffer_Start: <Encoder: SRC> UNCERTAIN OR NO t access
nvbuf_utils: dmabuf_fd -1 mapped entry NOT found
nvbuf_utils: Can not get HW buffer from FD… Exiting…
Segmentation fault (core dumped)
Does anyone have a solution?