search

nwesem / mtcnn_facenet_cpp_tensorRT

Face Recognition on NVIDIA Jetson (Nano) using TensorRT
GNU General Public License v3.0
203 stars 72 forks source link

rtsp link is not working #27

Open jishang1602 opened 3 years ago

jishang1602 commented 3 years ago

i tried with the VideoStreamer videoStreamer = VideoStreamer("rtsp://192.168.10.21:8554/unicast", videoFrameWidth, videoFrameHeight); in main.cpp but it is getting error which is shown below.

End generating TensorRT runtime models Parsing Directory: ../imgs Segmentation fault (core dumped)

in videoStreamer.h and videoStreamer.cpp VideoStreamer(int nmbrDevice, int videoWidth, int videoHeight, int frameRate, bool isCSICam); i changed with VideoStreamer(const char* nmbrDevice, int videoWidth, int videoHeight, int frameRate, bool isCSICam);

but getting the error Segmentation fault (core dumped)

jishang1602 commented 3 years ago

I have checked with different frame size on camera or CSI camera. In Jetpack 4.4 it works with only 640480 resolution. If i am using rtsp original resolution (640360), The code is dump. I changed the size in main.cpp. still the code is dump. Do you know how to work with rtsp any resolution or by default resolution of the rtsp. because if the camera is resized than face identification not work. Could you please help me on this?

IllyaPysarchuk commented 3 years ago

Did you solve it?