How To Use a Stereo Camera for Object Detection and Measurement — BMW No Code AI

1. Hemistereo NX 180 X Camera

Hemistereo NX 180 X Camera

1.1. Edge AI

1.2. Wide Field of View

1.3. Ultra-High Resolution

Shot of an RGB depth image in real-time

1.4. Made for Developers

Note: System Status

  • sudo hemistereo_apps_list
  • sudo hemistereo_apps_status
  • sudo hemistereo_app_run
  • sudo hemistereo_app_stop
  • sudo hemistereo_app_enable
  • sudo hemistereo_app_disable

2. Developed Inference API

2.1. Installation

2.2. API Endpoints

List of Hemistereo inference API’s endpoints

/set_camera_settings

Input:

  • cam_ip: IP of the camera the user is using.
  • vertical_fov: Vertical field of view of the sensor in degrees.
  • horizontal_fov: Horizontal field of view of the sensor in degrees.

Output:

  • Returns null. It changes the settings in the camera.
/set_camera_settings request screenshot

/single_shot

Input:

  • cam_ip: IP of the camera the user is using.

Output:

  • Returns the image captured by the camera.
/single_shot request and response screenshot

/single_shot/distance_map

Input:

  • cam_ip: IP of the camera that the user is using.

Output:

  • Returns the depth map and the picture captured bu the camera combined in one single image.
/single_shot/distance_map request and response screenshot

/set_threshold

Input:

  • cam_ip: IP of the camera that the user is using.
  • model: Previously trained model needed to detect an object in the image.
  • server: Server that contains the model. Note that the URL must end with a “/“.

Output:

  • Returns the predicted threshold value and sets it in the camera settings.
/set_threshold request and response screenshot

/detect

Input:

  • cam_ip: IP of the camera that the user is using.
  • model: Previously trained model needed to detect an object in the image.
  • server: Server that contains the model. Note that the URL must end with a “/“.
  • vertical_fov: Vertical field of view of the sensor in degrees.
  • horizontal_fov: Horizontal field of view of the sensor in degrees.

Output:

  • It returns bounding boxes, distance and dimensions: width, depth and height. Note that the dimensions could be a bit inaccurate if the model used is not trained well (e.g. wide bounding box case).
/detect response screenshot

/detect_input

Input:

  • image: Image the user wants to label.
  • model: Previously trained model needed to detect an object in the image.
  • server: Server that contains the model. Note that the URL must end with a “/“.
  • vertical_fov: Vertical field of view of the sensor in degrees.
  • horizontal_fov: Horizontal field of view of the sensor in degrees.

Output:

  • It returns bounding boxes, distance and dimensions: width, depth and height. Note that the dimensions could be a bit inaccurate if the model used is not trained well (e.g. wide bounding box case).
/detect_input request and response screenshot

/detect_save_image

Input:

  • image: Image the user wants to label.
  • model: Previously trained model needed to detect an object in the image.
  • server: Server that contains the model. Note that the URL must end with a “/“.
  • vertical_fov: Vertical field of view of the sensor in degrees.
  • horizontal_fov: Horizontal field of view of the sensor in degrees.

Output:

  • It returns the labeled image the user wants to save.
/detect_save_image response screenshot

3. Hemistereo Viewer Software

3.1. Maximum Disparities

3.2. Field of View

3.3. Textureness Filter Settings

4. Conclusion

References

--

--

--

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

ResNet: A Brief Introduction.

Deep Neural Network in Single Of Code

Deploying Object Detection Model with TensorFlow Serving — Part 2

Ever Wondered Why Normal Distribution Is So Important?

Making of Trumporate: Building markovipy, the Markov Chain sentence generator — Part 1

A-Eye: Auditory Supplement for the Legally Blind

Jorge Luis BoTges

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Rami Naffah

Rami Naffah

More from Medium

A Smile Can Brighten the Room…or Maybe Even a Video?

Status Quo: Getting into AI, ML, DNNs, …

Where to get started with Machine Learning

A backpropagation Neural Network Model to Predict the Plasmapause Location

Learning to rank with two objective functions in LambdaMART