The fusion of multiple sensor data to improve positioning accuracy and robustness is an important research direction in indoor positioning systems. In this paper, a Wi-Fi- and vision-based Fusion Adaptive Kalman Filter (FAKF) method is proposed for improving the accuracy of indoor positioning. To improve the accuracy of Wi-Fi positioning, a random forest algorithm with added region restriction is proposed. For visual positioning, YOLOv7 target detection and Deep SORT target tracking algorithms are combined in order to improve the stability of visual positioning. The fusion positioning method proposed in this study uses Kalman filtering for state estimation and updating by combining measurements from camera and Wi-Fi sensors, and it adaptively adjusts the parameters and weights of the filters by monitoring the residuals of the camera and Wi-Fi measurements in real time in order to optimize the accuracy and stability of the position estimation. In the experimental section, the real trajectory data and the predicted trajectory data generated using different positioning methods are compared. The experimental results show that the fused positioning method can significantly reduce positioning errors and the fused data can more accurately reflect the actual position of a target compared with single-sensor data.