Gstreamer issue in detectNet tutorial

seiazetsu · October 18, 2020, 11:15pm

Hi, I need help. By following this tutorial

and running my-detection.py , I get the following error after a while and the program stops.

** (python3:17067): CRITICAL **: 08:43:07.729: gst_adapter_push: assertion ‘GST_IS_BUFFER (buf)’ failed
Segmentation fault (core dumped)

Could you tell me the solution?

Thanks,

AastaLLL · October 29, 2020, 3:08am

Hi,

Do you have a CSI camera, which is directly connected to the Jetson board.
The default command is designed for the CSI camera.

Please note that the videoSource need to be updated into '/dev/video0' for a V4L2 camera (USB camera).

github.com

dusty-nv/jetson-inference/blob/master/python/examples/my-detection.py#L28


# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
#

import jetson.inference
import jetson.utils

net = jetson.inference.detectNet("ssd-mobilenet-v2", threshold=0.5)
camera = jetson.utils.videoSource("csi://0")      # '/dev/video0' for V4L2
display = jetson.utils.videoOutput("display://0") # 'my_video.mp4' for file

while display.IsStreaming():
	img = camera.Capture()
	detections = net.Detect(img)
	display.Render(img)
	display.SetStatus("Object Detection | Network {:.0f} FPS".format(net.GetNetworkFPS()))

Thanks.