Multiscale object detection on complex architectural floor plans

Abstract

Architectural floor plans are essential documents for conveying building information among designers, engineers, and clients. Automated analysis of floor plans enhances user productivity and accuracy, though research on automatic object detection within architectural floor plans has been limited. In this paper, a convolutional neural network (CNN) based architecture, ArchNetv2, is proposed to detect various visual objects, such as stairs, windows, and doors. The proposed ArchNetv2 includes a convolutional block attention module to improve feature learning. It works at multiple detection scales and can efficiently recognize large objects (e.g., stairs) and small objects (e.g., windows) simultaneously. Experimental results show that ArchNetv2 can recognize thirteen types of objects commonly found in architectural floor plans with a mAP of 93.5%, which is superior compared to the state-of-the-art techniques. The proposed architecture can serve as an important module in an automated floor plan analysis system.