Objective: The ventilators involved in non-invasive mechanical ventilation commonly provide ventilator support via a facemask. The interface of the mask with a patient promotes air leaks that cause errors in the feedback information provided by a pneumatic sensor and hence patient-ventilator asynchrony with multiple negative consequences. Our objective is to test the possibility of using chest-wall motion measured by an optical fibre-grating sensor as a more accurate non-invasive ventilator triggering mechanism. Approach: The basic premise of our approach is that the measurement accuracy can be improved by using a triggering signal that precedes pneumatic triggering in the neuro-ventilatory coupling sequence. We propose a technique that uses the measurement of chest-wall curvature by a long-period fibre-grating sensor. The sensor was applied externally to the rib-cage and interrogated in the lateral (edge) filtering scheme. The study was performed on 34 healthy volunteers. Statistical data analysis of the time lag between the fibre-grating sensor and the reference pneumotachograph was preceded by the removal of the unwanted heartbeat signal by wavelet transform processing. Main results: The results show a consistent fibre-grating signal advance with respect to the standard pneumatic signal by (230 ± 100) ms in both the inspiratory and expiratory phases. We further show that heart activity removal yields a tremendous improvement in sensor accuracy by reducing it from 60 ml to 0.3 ml. Significance: The results indicate that the proposed measurement technique may lead to a more reliable triggering decision. Its imperviousness to air leaks, non-invasiveness, low-cost and ease of implementation offer good prospects for applications in both clinical and homecare ventilation.