Visual localization uses images to regress camera position and orientation. It has many applications in computer vision such as autonomous driving, augmented reality (AR) and virtual reality (VR), and so on. The convolutional neural network simulates biological vision and has a good image feature extraction ability, so using it in visual localization can improve regression accuracy. Although our team has built an image indoor localization model for Southern Branch of the National Palace Museum, this paper tries to use new network and loss function to achieve better positioning accuracy. In this paper, we use ResNet-50 as backbone network, and change the output layer to 3-dimensional position and 4-dimensional orientation quaternion, and use learnable weights loss function. We compare different pretrained models and normalization methods, and the best result improves the positioning accuracy by about 60%.
|Translated title of the contribution||Visual Localization Based on Deep Learning ⎯ Take Southern Branch of the National Palace Museum for Example|
|Original language||Chinese (Traditional)|
|Number of pages||6|
|Journal||Journal of the Chinese Institute of Civil and Hydraulic Engineering|
|Publication status||Published - 2022 May|
All Science Journal Classification (ASJC) codes
- Civil and Structural Engineering