A fiducial marker system usually consists of markers, a detection algorithm, and a coding system. The appearance of markers and the detection robustness are generally limited by the existing detection algorithms, which are hand-crafted with traditional low-level image processing techniques. Furthermore, a sophisticatedly designed coding system is required to overcome the shortcomings of both markers and detection algorithms. To improve the flexibility and robustness in various applications, we propose a general deep learning based framework, DeepTag, for fiducial marker design and detection. DeepTag not only supports detection of a wide variety of existing marker families, but also makes it possible to design new marker families with customized local patterns. Moreover, we propose an effective procedure to synthesize training data on the fly without manual annotations. Thus, DeepTag can easily adapt to existing and newly-designed marker families. To validate DeepTag and existing methods, beside existing datasets, we further collect a new large and challenging dataset where markers are placed in different view distances and angles. Experiments show that DeepTag well supports different marker families and greatly outperforms the existing methods in terms of both detection robustness and pose accuracy. Both code and dataset are available at https://herohuyongtao.github.io/research/publications/deep-tag/.

This study investigated Chinese speakers’ eye movements when they were asked to identify audiovisual Mandarin lexical tones and vowels. In the lexical tone identification task, Chinese speakers were presented with an audiovisual clip of Mandarin monosyllables (/ă/, /à/, /ĭ/, /ì/) and asked to identify whether the syllables were presented in a dipping (/ă/, / ĭ/) or falling tone (/à/, /ì/). In the vowel identification task, they were asked to identify whether the vowels were/a/or/i/regardless of lexical tone. These audiovisual syllables were presented in clear, noisy, and silent conditions. An eye-tracker recorded the participants’ eye movements. Results showed participants gazed more at the mouth than the eyes in both lexical tones and vowels. Additionally, when acoustic conditions degraded from clear to noisy and eventually silent, Chinese speakers increased their gaze towards the mouth rather than the eyes. These findings suggest the mouth to be the primary area that is utilised during audiovisual speech perception. The similar patterns of eye movements between vowels and lexical tones indicate that the mouth acts as a perceptual cue that provides articulatory information.

Fiducial markers have been playing an important role in augmented reality (AR), robot navigation, and general applications where the relative pose between a camera and an object is required. Here we introduce TopoTag, a robust and scalable topological fiducial marker system, which supports reliable and accurate pose estimation from a single image. TopoTag uses topological and geometrical information in marker detection to achieve higher robustness. Topological information is extensively used for 2D marker detection, and further corresponding geometrical information for ID decoding. Robust 3D pose estimation is achieved by taking advantage of all TopoTag vertices. Without sacrificing bits for higher recall and precision like previous systems, TopoTag can use full bits for ID encoding. TopoTag supports tens of thousands unique IDs and easily extends to millions of unique tags resulting in massive scalability. We collected a large test dataset including in total 169,713 images for evaluation, involving in-plane and out-of-plane rotation, image blur, different distances, and various backgrounds, etc. Experiments on the dataset and real indoor and outdoor scene tests with a rolling shutter camera both show that TopoTag significantly outperforms previous fiducial marker systems in terms of various metrics, including detection accuracy, vertex jitter, pose jitter and accuracy, etc. In addition, TopoTag supports occlusion as long as the main tag topological structure is maintained and allows for flexible shape design where users can customize internal and external marker shapes. Code for our marker design/generation, marker detection, and dataset are available at http://herohuyongtao.github.io/research/publications/topo-tag/.