Temperature Compensation Technology of Speckle Structured Light Based on BP Neural Network

With the development of 3D vision technology in the field of consumption, speckle structured light based 3D measurement has been more and more used in various mobile terminals. Temperature compensation is one of the critical problems in speckle structured light. As a result of environmental temperature and self-heating, the operating temperature of speckle structured light module used in consumer field varies greatly. The wide range of temperature change makes it difficult to conduct accurate measurement. Due to the limitation of volume and cost, traditional temperature compensation methods play a very limited role in mobile terminals. This paper introduced the working principle of speckle structured light. Depth tilt caused by temperature changes was reported. A quantitative standard was established to evaluate the effect of temperature. The drift of speckle image was analyzed when the temperature changed. The relationship between speckle drift and depth tilt was studied. A temperature compensation technology based on BP (Back Propagation) neural network technology was proposed. The mapping between the corresponding points at different temperatures was obtained by training the BP neural network. The drift speckle image was corrected using the mapping relationship. Finally, a verification experiment was carried out. The results showed that after temperature compensation the depth tilt angle was suppressed significantly, which verified the effectiveness of the proposed method.