Machine Recognition of Map Point Symbols Based on YOLOv3 and Automatic Configuration Associated with POI

This study is oriented towards machine autonomous mapping and the need to improve efficiency of map point symbol recognition configuration. Therefore, an intelligent method for symbols was developed using You Only Look Once Version 3 (YOLOv3) algorithm along with Convolutional Block Attention Module (CBAM). Then, results were associated interest (POI) achieve automatic To quantitatively analyze effectiveness this comparison symbols, recall, precision mean average (mAP) employed as evaluation metrics. The experimental indicate that enhanced compared original YOLOv3 algorithm, mAP increased by 0.55%. Compared Single Shot MultiBox Detector (SSD) Faster Region-based Neural Network (Faster RCNN) precision, recall rate, all performed well, achieving 97.06%, 99.72% 99.50%, respectively. On basis, recognized are POI, coordinate assigned through keyword matching enrich their attribute information. enables configuration achieves a relatively good effect