Pixel-wise Segmentation of Street with Neural Networks
This work addresses street segmentation for self-driving cars, but it appears incremental as it applies existing methods to a specific domain without major breakthroughs.
The paper tackled pixel-wise street segmentation for self-driving cars by developing the SST framework to evaluate neural networks, achieving an F1-score of 89.5% with a simple feedforward neural network trained for regression.
Pixel-wise street segmentation of photographs taken from a drivers perspective is important for self-driving cars and can also support other object recognition tasks. A framework called SST was developed to examine the accuracy and execution time of different neural networks. The best neural network achieved an $F_1$-score of 89.5% with a simple feedforward neural network which trained to solve a regression task.