Part

Camera

You might say: vision sensor, depth camera

A camera measures image intensity and colour; stereo or active depth cameras add a distance value for each pixel or point.

What it does
It supports object recognition, pose estimation, tracking, mapping and visual servoing.
Ask
Do we need colour, depth or both, and what resolution, frame rate, range and light robustness are required?
Typical
RealSense D455/D450-series specifications list an ideal depth range, field of view and RGB/depth modes; exact performance depends on the camera and conditions.
Trouble
Blur, glare, occlusion, textureless surfaces, sunlight and an incorrect camera model create missing or wrong depth and pose measurements.

What to look for

  1. Colour image
  2. Distance value per pixel or point
  3. Blur, glare or occlusion
  4. Missing or wrong depth

Catalogue: Camera

Sources

  1. RealSense, D450 Series, D455 technical specificationsColor and depth therefore describe the same scene more consistently during motion, supporting object recognition, mapping, scanning, teleoperation and AI perception pipelines.
  2. OpenCV, Camera Calibration, Camera model and calibrationTo find all these parameters, what we have to do is to provide some sample images of a well defined pattern (eg, chess board).
  3. Peter Corke, Robotics, Vision and Control, Ch. 11, Image FormationSection 11.2 introduces the topic of camera calibration, the estimation of the parameters of the perspective transformation.

Use it on your project

teardown-apply: hold "Camera" (camera) from the teardown at https://teardownatlas.com/robotics/ against my project

Paste it into a coding agent that has the teardown skills.

An AI agent wrote this map with the teardown skill. It can contain errors: check the sources before you rely on a part. About and legal