Perception - Notes¶

Agenda - What's Perception? - Perception Architecture Pipeline - Applications - Tools and Frameworks - Perception Approaches - Datasets - Perception Algorithms - References

What's Perception?¶

Machine perception is the capability of a computer system to interpret data in a manner that is similar to the way humans use their senses to relate to the world around them.

Perception Architecture Pipeline¶

Applications¶

Robotics
Humanoid robots
Mobile & stationary robots
Autonomous Transportation
Self-Driving Cars
Robotaxi

Tools and Frameworks¶

Point Cloud Library - PCL

Perception Approaches¶

Computer Vision - Based
Machine Learning - Based
Deep Learning - Based

Datasets¶

Lane Detection - Lane detection

Semantic Segmentation - Segmentation

Perception Algorithms¶

Fully Convolutional Network for Road Segmentation
YOLO for 2D Object Detection
Deep SORT for Object Tracking
KITTI 3D Data Visualization for Homogenous - Transformations
Multi Task Attention Network (MTAN) for Multi - Task Learning
SFA 3D for 3D Object Detection
UNetXST for Camera to Bird's Eye View
An Algorithmic Implementation of an Autonomous Driving LiDAR Perception Stack with PCL