MOB LEC7 Semantic Segmentation

Problem Formulation

pixel-level prediction

Challenge of Semantic Segmentation

General vision challenges: occlusion, truncation, scale and illumination changes

Challenges specific to segmentation: smooth boundaries are hard to obtain due to the intrinsic ambiguity and resolution limitation in the image space.

Segmentation with DNN

Semantic Segmentation for Scene Understanding

RANSAC algorithm

boundaries

Additional material

True Positive, False Positive, False Negative

individual object

help object detection

Supplementary Material

1. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation.
2. Hough Transform Line Detection.
3. The Complete Guide to Panoptic Segmentation
4. Mask R-CNN (optional)

Origin: Dr. Chris Lu (Homepage) Translate + Edit: YangSier (Homepage)