ABSTRACT

Identifying land forms and land cover classes are important tasks in image interpretation. Sometimes, a phenomenon called terrain reversal effect (TRE) causes an inverted perception of 3D forms. When this inversion occurs, valleys appear as ridges and vice versa. While the TRE can severely impair the ability to identify 3D land forms, ‘correcting’ for the TRE in imagery can introduce new problems. Importantly, one of most commonly-proposed methods – shaded relief map (SRM) overlay – appears to impair the ability to identify land cover classes. In this paper, we report a comparative empirical evaluation of an SRM overlay solution, and its ‘enhanced’ versions supported by various other cues (stereopsis, motion, labels). In response to the different solutions, we measure the effectiveness, efficiency, confidence and preferences of our participants in land form and land cover identification tasks. All examined methods significantly improve the ability to detect land forms accurately, but they also impair the ability to identify the land cover classes to different degrees. Additionally, participants’ visualization preferences contradict their performance with them, calling for reflection on the visual effects of the applied correction methods. Based on the study, recommendations concerning the correction of the TRE are drawn, and gaps are identified.

摘要

识别土地形式和土地覆盖类别是图像解释中的重要任务。有时，这种现象称为地形反转效应（TRE）导致对3D形式的反感。发生这种反演时，谷表现为山脊，反之亦然。尽管TRE可能严重损害识别3D地形的能力，但对图像中TRE的“校正”可能会带来新的问题。重要的是，最常用的方法之一-阴影地形图（SRM）叠加-似乎会削弱识别土地覆被类别的能力。在本文中，我们报告了SRM叠加解决方案及其“增强”版本的比较经验评估，该解决方案还受到其他各种提示（立体定位，运动，标签）的支持。针对不同的解决方案，我们在土地形式和土地覆被识别任务中衡量参与者的有效性，效率，信心和偏好。所有检查过的方法都可以显着提高准确检测土地形态的能力，但是它们也会在不同程度上削弱识别土地覆被类别的能力。此外，参与者的可视化偏好与他们的表现相矛盾，要求对所应用的校正方法的视觉效果进行反思。在这项研究的基础上，提出了有关TRE校正的建议，并找出了差距。