olive® Camera ​

Technical Specifications ​

TPU ​

A TPU, or Tensor Processing Unit, is a type of AI accelerator specifically designed by Google to accelerate machine learning tasks. TPUs are application-specific integrated circuits (ASICs) that have been optimized for the efficient execution of tensor operations, which are fundamental to deep learning and other machine learning algorithms.

The primary goal of a TPU is to enhance the performance and energy efficiency of machine learning workloads, allowing AI models to be trained and executed more quickly and with lower power consumption than traditional CPU or GPU-based hardware. This is achieved through a combination of specialized hardware components and optimizations tailored to the unique requirements of machine learning tasks.

Enable / Disable TPU acceleration ​

In order to enable the tpu chip do

./opt/olive/script/enable_tpu.sh

./opt/olive/script/enable_tpu.sh

and to disable the tpu do

./opt/olive/script/disable_tpu.sh

./opt/olive/script/disable_tpu.sh

to verify the TPU is enabled you can do

lsusb

lsusb

The result will be:

Bus 001 Device 004: ID 1a6e:089a Global Unichip Corp.
Bus 001 Device 003: ID 32e4:9230 HD USB Camera HD USB Camera
Bus 001 Device 002: ID 1a40:0101 Terminus Technology Inc. Hub
Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 002 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub

Bus 001 Device 004: ID 1a6e:089a Global Unichip Corp.
Bus 001 Device 003: ID 32e4:9230 HD USB Camera HD USB Camera
Bus 001 Device 002: ID 1a40:0101 Terminus Technology Inc. Hub
Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 002 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub

Which the "Global Unichip Corp" is the TPU chip.

TPU Apps ​

All the python3 based TPU examples are located in /home/olive/apps. To run an object detection example using TPU after enabling the tpu in the previus step run

python3 /home/olive/apps/packages/src/app_tpu_python/tpu_python/app_node.py

python3 /home/olive/apps/packages/src/app_tpu_python/tpu_python/app_node.py

After running this example the camera will detect objects based on Coral object detection example.

General pipeline diagram

For more information about Google® coral please visit:

https://coral.ai/examples/

For other python example source projects please visit:

https://github.com/olive-robotics/olv_camera_tpu_playground_py

Quick Setup ​

Quick start guide for the olive® Camera module:

1. Install ROS2 (https://docs.ros.org/en/humble/index.html) on your host computer. This will provide the necessary tools and libraries to communicate with the Olive Robotics modules.

2. Connect the Olive Robotics modules to your host computer using the USB Type C cables.

3. Check if your compueter asigns an IP address to your component. This may take up to 30~60 seconds. Each module ships with a defauld static IP address asigned to it. The defauls address for smart components is 10.42.0.7 and can be changed later via the web interface.

   • You can check the if the connection is stablished or not in two ways:

     1. ping the device using the following command in your terminal:

        ping 10.42.0.7

        ping 10.42.0.7

        and if the module is connected successfully, you should see something like this:

        PING 10.42.0.7 (10.42.0.7) 56(84) bytes of data.
        64 bytes from 10.42.0.7: icmp_seq=1 ttl=64 time=0.402 ms
        64 bytes from 10.42.0.7: icmp_seq=2 ttl=64 time=0.371 ms
        64 bytes from 10.42.0.7: icmp_seq=3 ttl=64 time=0.397 ms
        64 bytes from 10.42.0.7: icmp_seq=4 ttl=64 time=0.398 ms

        PING 10.42.0.7 (10.42.0.7) 56(84) bytes of data.
        64 bytes from 10.42.0.7: icmp_seq=1 ttl=64 time=0.402 ms
        64 bytes from 10.42.0.7: icmp_seq=2 ttl=64 time=0.371 ms
        64 bytes from 10.42.0.7: icmp_seq=3 ttl=64 time=0.397 ms
        64 bytes from 10.42.0.7: icmp_seq=4 ttl=64 time=0.398 ms

     2. Check if the network adapter is attached and recognized by your host computer.

        ifconfig

        ifconfig

        and if the device is recognized successfully, you should see something like this:

        enxd8de9b838d35: flags=4163<UP,BROADCAST,RUNNING,MULTICAST>  mtu 1500
                inet 10.42.0.79  netmask 255.255.255.0  broadcast 10.42.0.255
                inet6 fe80::ef0a:e686:27aa:6307  prefixlen 64  scopeid 0x20<link>
                ether d8:de:9b:83:8d:35  txqueuelen 1000  (Ethernet)
                RX packets 1846  bytes 272143 (272.1 KB)
                RX errors 0  dropped 0  overruns 0  frame 0
                TX packets 195  bytes 34984 (34.9 KB)
                TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0

        enxd8de9b838d35: flags=4163<UP,BROADCAST,RUNNING,MULTICAST>  mtu 1500
                inet 10.42.0.79  netmask 255.255.255.0  broadcast 10.42.0.255
                inet6 fe80::ef0a:e686:27aa:6307  prefixlen 64  scopeid 0x20<link>
                ether d8:de:9b:83:8d:35  txqueuelen 1000  (Ethernet)
                RX packets 1846  bytes 272143 (272.1 KB)
                RX errors 0  dropped 0  overruns 0  frame 0
                TX packets 195  bytes 34984 (34.9 KB)
                TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0

4. Check if the data is alreaddy published to your system using:

   ros2 topic list

   ros2 topic list

   you should be able to see all the topics published from the module. For exampe for IMU module you will see:

   /olive/imu/x1681709875/image/camera_info
   /olive/imu/x1681709875/image/compressed
   /olive/imu/x1681709875/imu
   /olive/imu/x1681709875/magnetometer
   /olive/imu/x1681709875/status
   /olive/imu/x1681709875/switch
   /olive/imu/x1681709875/led
   /parameter_events
   /rosout

   /olive/imu/x1681709875/image/camera_info
   /olive/imu/x1681709875/image/compressed
   /olive/imu/x1681709875/imu
   /olive/imu/x1681709875/magnetometer
   /olive/imu/x1681709875/status
   /olive/imu/x1681709875/switch
   /olive/imu/x1681709875/led
   /parameter_events
   /rosout

5. Visualize the data using:

   1. Embedded Web Interface (https://docs.olive-robotics.com/software/gui/gui.html)

   2. rqt (https://docs.ros.org/en/humble/Tutorials/Beginner-CLI-Tools/Introducing-Turtlesim/Introducing-Turtlesim.html#install-rqt)

      • Visualize the topics:

      • Plot the data from the IMU messages:

      • Visualize the Image:

      • Change the parameters of the DCM:

   3. rviz2 (https://github.com/ros2/rviz).

      • Visualize the IMU data in Rviz2

6. Visualize the data and change the parameters like IP, Topic Name, etc using the embedded web interface. You just need to open your browser on your host computer and enter the IP address of the device. If you didn't change the IP address, then it must be 10.42.0.7.

ROS Topics and Services ​

Advanced Settings ​

The device allows certain parameters to be changed at runtime. To get an overview of all changeable parameters use ros2 param list. To change a parameter use ros2 param set /dcm_camera <parameter> <new_value>

Camera ​

IMU ​

System ​

Downloads ​