A novel approach for detecting characteristic flow signatures precursory to stall along aerofoils is introduced. It uses arrays of flexible wind-hair like sensors distributed around the aerofoil which are tracked remotely using high-speed imaging and processing. The sensors act as “digital tufts" providing real-time readings of local velocity information with a high temporal resolution. Such sensors are integrated into a NACA0012 aerofoil and tested in a wind-tunnel for varying angles of attack in static tests and dynamically in a ramp-up test. For the static tests, the mean values of the sensor signals provide information on local free-stream velocity and angle of incidence. The fluctuating part of the signals show that at angles approaching separation prominent low frequency oscillations are detected, the magnitudes of which scale with the angle of incidence. These are hypothesised to be linked to breathing modes of the Laminar Separation Bubble causing a shear-layer flapping observed on the sensors. Such low-frequency oscillations were also detected short before separation in the ramp-up studies. As the high-speed cameras are mounted in a simulated “on-board" position, the sensing method could be used for early stall warnings in small-scale UAVs with integrated on-board object tracking cameras.