pinto0309 / mobilenet-ssdlite-realsense-tf Goto Github PK

Your device:
Raspberry Pi 3 Model B+

Your device's CPU architecture:
The Pi 3 Model B+ has a 1.4GHz 64-bit quad-core Broadcom Arm Cortex A53-architecture processor

Your OS:
Raspbian Stretch OS - Kernel version: 4.14

Your method for Ubuntu works on my laptop everything is successful ( Ubuntu 18.04)

[Required] Details of the work you did before the problem occurred:

I did everything up till step 8 on the raspberry pi and step 9 fails




[Required] Error message:
pi@raspberrypi:~/librealsense $ cd build/
pi@raspberrypi:~/librealsense/build $ make -j1
[ 58%] Built target tm
[ 58%] Built target realsense-file
[ 58%] Built target realsense2
[ 58%] Linking CXX executable rs-software-device
/usr/bin/ld: /usr/local/lib/libglfw3.a(x11_window.c.o): undefined reference to symbol 'XConvertSelection'
//usr/lib/arm-linux-gnueabihf/libX11.so.6: error adding symbols: DSO missing from command line
collect2: error: ld returned 1 exit status
examples/software-device/CMakeFiles/rs-software-device.dir/build.make:98: recipe for target examples/software-device/rs-software-device' failed
make[2]: *** [examples/software-device/rs-software-device] Error 1
CMakeFiles/Makefile2:282: recipe for target 'examples/software-device/CMakeFiles/rs-software-device.dir/all' failed
make[1]: *** [examples/software-device/CMakeFiles/rs-software-device.dir/all] Error 2 Makefile:127: recipe for target 'all' failed make: *** [all] Error 2
pi@raspberrypi:~/librealsense/build $

Overview of problems and questions:
I followed everything up to step 8 but I can't seem to move past step 9 (installing the SDK). I tried different solutions but I can't seem to get it going. It keeps saying
//usr/lib/arm-linux-gnueabihf/libX11.so.6: error adding symbols: DSO missing from command line

On my laptop that runs ubuntu I am able to run the object detection script but not on the raspbian stretch.

Is there a work around to this?

Any help is appreciated

your title is “ without Neural Compute Stick(NCS)” .Neural Compute Stick can not support TF?
I am only familiar with TF.I want apply NCS to TF.could you give me some suggestions？

the number meters away is the groundtruth and how to define it？
RealSense compute the number?
If I want to get the real position of the object，What do I need to do?
thanks！

Hello,

Thank you for your work on this project! I am doing something similar by making use of the D435i and Tensorflow on a Jetson Xavier NX (Ubuntu 18.04) to run object detection inference.

Would like to get your advice on how to obtain the distance from the object to the camera (as seen in your inference) without making use of OpenGL?

Thanks in advance!

Hello,
Thank you so much for all your work on this, I am working on a similar project and you have helped me out.
Some questions, maybe you can comment:

1. Have you used the google coral USB accelerator yet? Could you see adding it to this tensor flow project?
2. Have you used the Raspberry Pi 4 with this yet?
3. In addition to getting the depth, d, to the identified object, have you worked out getting the X and Y coordinates as well? Any advice for this?

Thank you!

[Required] RaspberryPi3, LaptopPC, or other device name): RaspberryPi4

[Required] Your device's CPU architecture (armv7l, x86_64, or other architecture name): armv7l

[Required] Your OS (Raspbian, Ubuntu1604, or other os name): raspbian buster

[Required] Details of the work you did before the problem occurred: I followed the tutorial from github






[Required] Error message: However, I keep on getting this error when I try to run the program:
File "/home/pi/.local/lib/python3.7/site-packages/google/protobuf/internal/python_message.py", line 866, in HasField
field = hassable_fields[field_name]
KeyError: 'frequency'