In this study, we propose an indoor visual positioning method based on image features. RGB-D camera data are used to establish an image database used for positioning. The 3D coordinates of pixels are obtained from an RGB image and depth information, and then the oriented fast and rotated brief (ORB) features of the image are extracted. The bag-of-visual-words model is used in combination with the K-means algorithm and a k-dimensional tree structure to classify storage and expressions in the dictionary. In the positioning process, the positioning image is obtained using a camera with known parameters, and the term frequency–inverse document frequency model is used to achieve image feature indexing to match the most similar image. Finally, using the matching feature points in the image, an efficient perspective-n-point method and a bundle adjustment method are used to calculate the camera pose information on the positioning image to complete indoor positioning. Experiments on real scenes verify the feasibility of the proposed method and its positioning accuracy. The results presented in this study provide a useful reference in the research and application of vision-based indoor positioning.