An Enhanced Lane Detection Technique based on Active Learning

The lane detecting algorithm plays a major role in advanced driver assistance systems and autonomous driving systems. In recent years, deep learning-based lane detection techniques have shown encouraging results; nonetheless, the quality and size of the training data set have a signi fi cant impact on how effective these techniques are. Active learning is a technique that can improve the capacity of deep learning-based lane identi fi cation systems to repeatedly choose and classify valuable samples from a large body of unlabeled data. In this research, a novel 1-dimensional deep learning approach is used to present an augmented Active Learning based Lane Detection Algorithm (ALDA) that picks informative samples based on diversity-and uncertainty-based criteria. Several benchmark datasets, including the CUlane, have been used to assess the suggested technique, In terms of accuracy and robustness, the suggested method ALDA performs better than four cutting-edge lane-detecting algorithms. The fi ndings show that active learning can signi fi cantly reduce the quantity of labeled data required for training while preserving good performance. The suggested method may improve the dependability and security of advanced driver assistance systems and autonomous driving systems. When compared with other distinct Deep Learning approaches, the proposed ALDA obtains an accuracy of 98.01 %, Precision of 98.5173 %, Recall of 95.2296 %, F1 score of 96.845 %, mAP of 92.7 %, and MSE of 0.0097.