Damage detection techniques for structural health monitoring are especially vital when computer vision is employed for measurement collection. A unique curvature technique is described in this presentation. Curvature as defined here is btained from the second order polynomial equations of a structure's deflection curve. The technique, as well as inclination angles, and primary data technique are applied for damage detection on a numerical model of a bridge girder.  The girder is subjected to a load induced by a slowly moving truck with multiple damage scenarios simulated.The model is loaded and unloaded at an in-tact and damaged states. The robustness of vision measurement approach for damage detection is validated at different levels of added measurement noise. The noise is expressed as the pixel resolutions achievable with the image processing algorithm at multiple camera field of views applied to target motions. Damage detection and location accuracies are influenced by damage extent, added measurement noise and type of response. Curvature can be used as a reliable damage detection and localisation technique, but only with higher measurement resolutions. Higher resolutions can be achieved either with a multiple cameras and a smaller field of view, or larger field of view with very high pixel resolution.