An U-Net Semantic Segmentation Vision System on a Low-Power Embedded Microcontroller Platform.
Laura FalaschettiSara BruschiMichele AlessandriniGiorgio BiagettiPaolo CrippaClaudio TurchettiPublished in: KES (2023)
Keyphrases
- vision system
- low power
- semantic segmentation
- low cost
- real time
- single chip
- power consumption
- high speed
- superpixels
- conditional random fields
- scene classification
- weakly supervised
- scene understanding
- computer vision
- object categories
- object classes
- stereo vision
- generative model
- image sensor
- probabilistic model
- object recognition
- natural scenes
- visual attention
- object segmentation
- long range
- multiscale
- image sequences