Semantic video segmentation for autonomous driving
arXiv:2010.15250v1
Originality Synthesis-oriented
AI Analysis
This work addresses the need for efficient video segmentation in autonomous driving, but it is incremental as it builds on existing methods.
The paper tackled real-time road detection in autonomous driving by applying a fully convolutional network to video segmentation, achieving a 50% reduction in processing speed while maintaining accuracy on the KITTI dataset.
We aim to solve semantic video segmentation in autonomous driving, namely road detection in real time video, using techniques discussed in (Shelhamer et al., 2016a). While fully convolutional network gives good result, we show that the speed can be halved while preserving the accuracy. The test dataset being used is KITTI, which consists of real footage from Germany's streets.