Linear feature extraction for highways and road centerlines using remote sensing is an important component of geographic information systems (GIS). This article considers the use of various image processing methods for mapping smuggler trail networks crossing the U.S.-Mexico border. The authors report on a study in which very high spatial-resolution, digital, multispectral imagery was acquired in three visible and one nearinfrared wavelength bands along the U.S.-Mexico border using an Airborne Data Acquisition and Registration (ADAR) digital camera system mounted on a helicopter. Four image enhancement methods and one neural-network based automated feature extraction technique were tested. Measures of trail length were compared with a ground-based GPS trail survey to evaluate accuracy. The results showed that the optimal image enhancement method for trail mapping varied with topography and vegetation structure. The authors conclude that the most effective and efficient approach to trail mapping was a hybrid of an automated linear feature extraction routine, followed by manual interpretation, delineation, and editing.