Vehicles Lane-changing Behavior Detection
This work addresses lane-level localization for autonomous vehicles, but it is incremental as it applies existing methods like SVM and CNN to a specific task.
This project tackled the problem of improving lane-level localization for autonomous vehicles by developing a mono-camera lane-changing behavior detection module to correct lateral GPS errors, achieving performance comparisons between SVM-based classification with/without PCA and a CNN method.
The lane-level localization accuracy is very important for autonomous vehicles. The Global Navigation Satellite System (GNSS), e.g. GPS, is a generic localization method for vehicles, but is vulnerable to the multi-path interference in the urban environment. Integrating the vision-based relative localization result and a digital map with the GNSS is a common and cheap way to increase the global localization accuracy and thus to realize the lane-level localization. This project is to develop a mono-camera based lane-changing behavior detection module for the correction of lateral GPS localization. We implemented a Support Vector Machine (SVM) based framework to directly classify the driving behavior, including the lane keeping, left and right lane changing, from a sampled data of the raw image captured by the mono-camera installed behind the window shield. The training data was collected from the driving around Carnegie Mellon University, and we compared the trained SVM models w/ and w/o the Principle Component Analysis (PCA) dimension reduction technique. The performance of the SVM based classification method was compared with the CNN method.