2-D and 3-D rock-penetrating radar data were acquired on the wall of a pillar in an underground limestone mine. The objective was to test the ability of radar to image fractures and karst voids and to characterize their geometry, aperture, and fluid content, with the goal of mitigating mining hazards. Strong radar reflections in the field data correlate with fractures and a cave exposed on the pillar walls. Large pillar wall topography was included in the steep-dip Kirchhoff migration algorithm because standard elevation corrections are inaccurate. The depth-migrated 250 MHz radar images illuminate fractures, karst voids, and the far wall of the pillar up to ~25 m depth into the rock, with a spatial resolution of lt;0.5 m. Higher-frequency radar improved image resolution and aided the interpretation, but at the cost of shallower depth of penetration and extra acquisition effort. Due to the strong contrast in physical properties between rock and fracture fluid, fractures with apertures as thin as a fiftieth of a radar wavelength were imaged. Water-filled fractures with mm-scale aperture and air-filled fractures with cm-scale aperture produce strong reflections at 250 MHz. Strong variation in reflection amplitude along each fracture is interpreted to represent both variable fracture aperture and non-planar fracture structure. Fracture apertures were quantitively measured, but distinguishing water- from air-filled the fractures was not possible due to the complex radar wavelet and fracture geometry. Two conjugate fracture sets were imaged. One of these fracture sets dominates rock mass stability and water inrush challenges throughout the mine. All of the detected voids and a large cave are at the intersection of two fractures, indicating preferential water flow and dissolution along conjugate fracture intersections. Detecting, locating, and characterizing fractures and voids prior to excavation can enable miners to mitigate potential collapse and flood hazards before they occur.