About this document
Forward Vehicle Detection for ADAS by Nick Gino is a document available to read on EtoBox.
This thesis proposes a forward collision warning system using a customized single shot detector for real-time vehicle detection from monocular cameras on mobile devices. The thesis analyzes the bounding box distribution of vehicles in a dataset to customize the default boxes of SSD for better accuracy. Experiments show the customized SSD uses less memory, has a higher frame rate, and lower battery consumption than popular object detectors, making it suitable for mobile applications.
- Author
- Nick Gino
- Language
- EN