Measuring the straightness of the scraper conveyor, which is an indispensable piece of equipment in a fully mechanized coal face, can prevent accidents such as derailment of the shearer and is also important for the precise positioning of the shearer and the accurate control of the hydraulic support. The existing scraper conveyor straightness measurement methods have the disadvantages of ... [Show full abstract] inconsistent measurement cost, accuracy, and reliability as well as low dimension of straightness description. To this end, this paper proposes a method for monitoring the three-dimensional straightness of a scraper conveyor based on binocular vision. Trapezoidal window matching technology was used to realize the image acquisition of multiple stations and multiple sensors. The bit pose acquisition model of binocular vision 3D reconstruction was used to obtain the 3D coordinates of the feature points on the sign board in each local coordinate system and the bit pose information of each sign board. The pose relay videometric method was used to convert the straightness in each local coordinate system to the global coordinate system to realize the 3D reconstruction of the scraper conveyor. Finally, the straightness measurement test of the preset scraper conveyor was carried out, and the error analysis was carried out by comparing with the manual measurement results, which showed that the measurement errors were all within ±30 mm. At the same time, the standard deviation of errors in both directions was small, which indicates that the straightness measurement method for the scraper conveyor in this paper has high reliability. In addition, the visual measurement process is independent of each other, so there is no error accumulation in the visual straightness measurement method. The analysis shows that the method of measuring the straightness of a scraper conveyor based on binocular vision can realize continuous and real-time monitoring of the scraper conveyor.