原视频\opt\nvidia\deepstream\deepstream\samples\streams\sample_cam6.mp4如上图所示，是一个360度的球型视频，DeepStream的nvdewarper插件可以将原视频拆分成多个单独的视频，nvdewarper可以生成最大4个dewarped surfaces.
\opt\nvidia\deepstream\deepstream-7.1\sources\apps\sample_apps\deepstream-dewarper-test例子只是将nvdewarper拆分的视频进行显示，并没有做推理，pipeline是source->dewarper->nvstreammux->tiler->sink.
deepstream-app可以支持对nvdewarper拆分的视频进行推理，
source2_dewarper_test.yml内容如下：
bash
####################################################################################################
# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: LicenseRef-NvidiaProprietary
#
# NVIDIA CORPORATION, its affiliates and licensors retain all intellectual
# property and proprietary rights in and to this material, related
# documentation and any modifications thereto. Any use, reproduction,
# disclosure or distribution of this material and related documentation
# without an express license agreement from NVIDIA CORPORATION or
# its affiliates is strictly prohibited.
####################################################################################################
application:
enable-perf-measurement: 1
perf-measurement-interval-sec: 5
gie-kitti-output-dir: streamscl
tiled-display:
enable: 1
rows: 1
columns: 2
width: 1920
height: 1080
gpu-id: 0
#(0): nvbuf-mem-default - Default memory allocated, specific to particular platform
#(1): nvbuf-mem-cuda-pinned - Allocate Pinned/Host cuda memory applicable for Tesla
#(2): nvbuf-mem-cuda-device - Allocate Device cuda memory applicable for Tesla
#(3): nvbuf-mem-cuda-unified - Allocate Unified cuda memory applicable for Tesla
#(4): nvbuf-mem-surface-array - Allocate Surface Array memory, applicable for Jetson
nvbuf-memory-type: 0
source:
csv-file-path: sources_2.csv
sink0:
enable: 1
#Type - 1=FakeSink 2=EglSink 3=File
type: 2
sync: 1
source-id: 0
gpu-id: 0
nvbuf-memory-type: 0
sink1:
enable: 1
type: 3
#1=mp4 2=mkv
container: 1
#1=h264 2=h265
codec: 1
#encoder type 0=Hardware 1=Software
enc-type: 0
sync: 0
#iframeinterval=10
bitrate: 2000000
#H264 Profile - 0=Baseline 2=Main 4=High
#H265 Profile - 0=Main 1=Main10
# set profile only for hw encoder, sw encoder selects profile based on sw-preset
profile: 0
output-file: out.mp4
source-id: 0
# "num-surfaces-per-frame" in all dewarper configs should be same
# and should be equal to "num-surfaces-per-frame" in "streammux" config
# following config is applicable to [source0]
dewarper0:
enable: 1
source-id: 6
config-file: /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-dewarper-test/config_dewarper.txt
gpu-id: 0
nvbuf-memory-type: 0
num-output-buffers: 4
# following config is applicable to [source1]
dewarper1:
enable: 1
#Camera Id
source-id: 11
config-file: /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-dewarper-test/config_dewarper.txt
gpu-id: 0
nvbuf-memory-type: 0
num-output-buffers: 4
num-batch-buffers: 4
osd:
enable: 1
gpu-id: 0
border-width: 1
text-size: 15
text-color: 1;1;1;1
text-bg-color: 0.3;0.3;0.3;1
font: Serif
show-clock: 0
clock-x-offset: 800
clock-y-offset: 820
clock-text-size: 12
clock-color: 1;0;0;0
nvbuf-memory-type: 0
display-mask: 1
streammux:
gpu-id: 0
##Boolean property to inform muxer that sources are live
batch-size: 8
##time out in usec, to wait after the first buffer is available
##to push the batch even if the complete batch is not formed
batched-push-timeout: 33000
## Set muxer output width and height
width: 960
height: 752
##Enable to maintain aspect ratio wrt source, and allow black borders, works
##along with width, height properties
enable-padding: 0
nvbuf-memory-type: 0
num-surfaces-per-frame: 4
## If set to TRUE, system timestamp will be attached as ntp timestamp
## If set to FALSE, ntp timestamp from rtspsrc, if available, will be attached
# attach-sys-ts-as-ntp: 1
primary-gie:
enable: 1
gpu-id: 0
model-engine-file: ../../models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b4_gpu0_int8.engine
batch-size: 4
#Required by the app for OSD, not a plugin property
bbox-border-color0: 1;0;0;1
bbox-border-color1: 0;1;1;1
bbox-border-color2: 0;0;1;1
bbox-border-color3: 0;1;0;1
interval: 0
gie-unique-id: 1
nvbuf-memory-type: 0
config-file: config_infer_primary.yml
tests:
file-loop: 0sources_2.csv内容如下：
bash
# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: LicenseRef-NvidiaProprietary
#
# NVIDIA CORPORATION, its affiliates and licensors retain all intellectual
# property and proprietary rights in and to this material, related
# documentation and any modifications thereto. Any use, reproduction,
# disclosure or distribution of this material and related documentation
# without an express license agreement from NVIDIA CORPORATION or
# its affiliates is strictly prohibited.
enable,type,uri,num-sources,gpu-id,cudadec-memtype
1,3,file://../../streams/sample_cam6.mp4,1,0,0
1,3,file://../../streams/sample_cam6.mp4,1,0,0命令如下：deepsteram-app -c source2_dewarper_test.yml
结果如下：
可以看到，源有两个，每个源可以分成4个单独的图像，nvinfer再对8个单独图像做推理，画面上都有bbox。