This paper presents a database that can be used for boundary detection and image segmentation evaluation.Images in our database contain not only ground-truth segmentations but also ground-truth depth maps,which is a remarkable difference from existing databases.This characteristic will greatly facilitate the algorithms combining low-level cues such as brightness,color and texture with depth information to conduct boundary detection and image segmentation tasks.Besides,we have used the database to compare our proposed boundary detection method with the Berkeley boundary detector and experimental results indicate that our method has a better performance than the Berkeley boundary detector.