Abstract—This paper presents a method to detect buildings in terrestrial images. High resolution terrestrial images are normally taken from land survey vehicles. These images and other surveyed data along roads are needed by many agencies that require new data as time passes by. Land use in rural area is an example that needs information about buildings and can benefit from terrestrial images. The proposed method was aimed to detect buildings in terrestrial images to benefit the above needs. The method consists of two stages. The first stage removes unwanted objects, performs image segmentation, and finds regions of interest. Image processing techniques such as greenness extraction, sky detection, color segmentation, color detection, shape detection are used. The second stage performs building detection. It includes the possible building parts detection, projection profiles finding, and the building determination. The method can identify a partial building if the whole building is not shown in an image. The proposed method was tested on 936 images (332 images with buildings and 604 images without buildings). The images were from Google Street View. The accuracy was determined by human inspection. The method gave promising results with an average accuracy of 82.5%. Positive faults were 4.7% average.

Index Terms—building detection, terrestrial image, image processing, image segmentation

Cite: Teerapat Chaloeivoot and Suebskul Phiphobmongkol, "Building Detection from Terrestrial Images," Journal of Image and Graphics, Vol. 4, No. 1, pp. 46-50, June 2016. doi: 10.18178/joig.4.1.46-50