Part 1: Introduction & Feature Detection
Some people claim to have a poor sense of direction. They might compare themselves to a robot and feel much better.
[Read More]SLAM - Parti 2
Implement my system of localization and mapping
Part 2: Pose Optimization Once our features are detected and associated, we aim to estimate the movement between the two observations.
After Part 1, which focused on feature detection and association, we now delve into estimating our position and orientation over time.
Choosing the Pose Model to Optimize A pose represents the position and orientation of our robot in space. We can express it in the way and in the coordinate system that suits us best (I’ve seen spherical, but here, we prefer Cartesian).
[Read More]
Depth Map Segmentation
In this post, I implement a real time depth map segmentation system, based on normal map analysis.
[Read More]Monocular Depth Map
Generate a depth map from a monocular video
Use a video taken by a single camera to estimate the depth of objects in an image. A small dip in the world of epipolar geometry and key points analysis.
[Read More]De CAPE et d'Opés
Correct and optimize the code of a publication
Certainly! Here is the translation:
CAPE (Cylinder And Plane Extraction) is an extremely efficient method for extracting planes and cylinders in RGB-D images, based on an AHC (Agglomerative Hierarchical Clustering) method. Despite the effectiveness of this method, the C++ implementation of the paper has many flaws.
In this post, I will explain how I fixed most of these issues.
[Read More]