Real-time HybridNets detects traffic object, drivable area, and road lane
Real-time HybridNets detects traffic object, drivable area, and road lane
HybridNets: End-to-End Perception Network
arXiv paper abstract https://arxiv.org/abs/2203.09035
arXiv PDF paper https://arxiv.org/ftp/arxiv/papers/2203/2203.09035.pdf
GitHub https://github.com/datvuthanh/HybridNets
End-to-end Network has become increasingly important in multi-tasking. One … example … is … perception system in autonomous driving.
… proposes several key optimizations to improve accuracy. First, … proposes efficient segmentation head and box/class prediction networks based on weighted bidirectional feature network.
Second, … proposes automatically customized anchor for each level in the weighted bidirectional feature network.
Third, … proposes an efficient training loss function and training strategy to balance and optimize network.
… developed an end-to-end perception network to perform multi-tasking, including traffic object detection, drivable area segmentation and lane detection simultaneously, called HybridNets, which achieves better accuracy than prior art.
… can perform visual perception tasks in real-time and thus is a practical and accurate solution to the multi-tasking problem. …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
