Text Detection & Recognition in the Wild for Robot Localization
This work addresses the challenge of using signage for robot localization, which is incremental as it applies an existing text spotting framework to a specific domain.
The paper tackles the problem of robust text detection and recognition in the wild for robot localization, proposing an end-to-end scene text spotting model that outperforms state-of-the-art methods in precision and recall on the SCTP benchmark dataset.
Signage is everywhere and a robot should be able to take advantage of signs to help it localize (including Visual Place Recognition (VPR)) and map. Robust text detection & recognition in the wild is challenging due to such factors as pose, irregular text, illumination, and occlusion. We propose an end-to-end scene text spotting model that simultaneously outputs the text string and bounding boxes. This model is more suitable for VPR. Our central contribution is introducing utilizing an end-to-end scene text spotting framework to adequately capture the irregular and occluded text regions in different challenging places. To evaluate our proposed architecture's performance for VPR, we conducted several experiments on the challenging Self-Collected Text Place (SCTP) benchmark dataset. The initial experimental results show that the proposed method outperforms the SOTA methods in terms of precision and recall when tested on this benchmark.