Image‐based localisation using shared‐information double stream hourglass networks

Abstract

A shared-information double stream hourglass network architecture for camera localisation is proposed. The contributions are two folds, first, the ordinary single stream decoder is replaced by double streams for regressing location and orientation of camera separately, and the information is shared at the end. Secondly, uncertainty estimation of loss to balance the error of location and orientation is used. The experimental results show that the proposed method achieves better performance compared with state-of-the-art methods.

Simultaneous Iris and Periocular Region Detection Using Coarse Annotations

“…Therefore, in this work, we propose the simultaneous detection of the iris and periocular regions using two object detection models: YOLOv2 [16] and Faster R-CNN [17]. It should be noted that (i) we trained both models from scratch; (ii) such models were chosen because promising results were obtained using them in other detection tasks [18]- [20].…”

“…In this work, we compare the detection of the iris and periocular regions being performed separately and simultaneously using two well-known object detection networks: YOLOv2 [16] and Faster R-CNN [17]. Such deep models were chosen due to the fact that (i) promising results were recently obtained using them in other detection tasks [18]- [20]; and (ii) handcrafted features are easily affected by noise and might not be robust for unconstrained scenarios.…”