End-to-end pedestrian collision warning system based on a convolutional neural network with semantic segmentation.
Heechul JungMin-Kook ChoiSoon KwonWoo Young JungPublished in: ICCE (2018)
Keyphrases
- end to end
- semantic segmentation
- convolutional neural network
- object detection
- face detection
- pascal voc
- object class
- object categories
- pedestrian detection
- scene classification
- conditional random fields
- superpixels
- label transfer
- weakly supervised
- object classes
- neural network
- object segmentation
- object recognition
- image set
- object classification
- congestion control
- human body
- image understanding
- computer vision
- bag of words
- topic models
- graphical models
- higher order
- multiscale