# CBHE: Corner-based Building Height Estimation for Complex Street Scene Images

## TL;DR

This paper introduces CBHE, a novel method for estimating building heights from street scene images that effectively handles complex scenes by combining corner and roofline detection with deep learning filtering.

## Contribution

The paper presents BuildingNet, a deep neural network for improved corner and roofline candidate filtering, enhancing building height estimation accuracy in complex street scenes.

## Key findings

- BuildingNet outperforms existing classifiers in candidate filtering accuracy.
- CBHE achieves over 10% higher accuracy than baseline methods.
- The approach is scalable and effective without high-resolution data.

## Abstract

Building height estimation is important in many applications such as 3D city reconstruction, urban planning, and navigation. Recently, a new building height estimation method using street scene images and 2D maps was proposed. This method is more scalable than traditional methods that use high-resolution optical data, LiDAR data, or RADAR data which are expensive to obtain. The method needs to detect building rooflines and then compute building height via the pinhole camera model. We observe that this method has limitations in handling complex street scene images in which buildings overlap with each other and the rooflines are difficult to locate. We propose CBHE, a building height estimation algorithm considering both building corners and rooflines. CBHE first obtains building corner and roofline candidates in street scene images based on building footprints from 2D maps and the camera parameters. Then, we use a deep neural network named BuildingNet to classify and filter corner and roofline candidates. Based on the valid corners and rooflines from BuildingNet, CBHE computes building height via the pinhole camera model. Experimental results show that the proposed BuildingNet yields a higher accuracy on building corner and roofline candidate filtering compared with the state-of-the-art open set classifiers. Meanwhile, CBHE outperforms the baseline algorithm by over 10% in building height estimation accuracy.