Imaging sensors have been deployed for a variety of nonintrusive diagnostics in photogrammetry, videometry, and other pertinent gross-field visualization. Especially, three-dimensional (3-D) remote sensing based on stereoscopic vision has become increasingly important in many research and industrial applications. Typical applications can be particle tracking in flow visualization, motion/deformation detection in dynamics and stress analysis, and robot vision in automation and quality control, to name a few. The use of an appropriate calibration technique for image sensing is thus essential in both laboratory and field applications. To provide a robust and reliable calibration capability for stereoscopic 3-D detection, we develop a hybrid technique that is based on the use of artificial neural networks and a conventional physical-mathematical model. The hybrid technique is advantageous in procedural simplicity; that is, ease in hardware setup and speed in data processing. Our results show that the hybrid approach can improve the accuracy in predicting the object space coordinates by about 30% compared to those based on a purely physical-mathematical model. It appears that the hybrid technique can combine the merits of both physical-mathematical model and artificial neural networks to improve the overall performance.