Robust Line Segments Matching via Graph Convolution Networks

Line matching plays an essential role in structure from motion (SFM) and simultaneous localization and mapping (SLAM), especially in low-textured and repetitive scenes. In this paper, we present a new method of using a graph convolution network to match line segments in a pair of images, and we design a graph-based strategy of matching line segments with relaxing to an optimal transport problem. In contrast to hand-crafted line matching algorithms, our approach learns local line segment descriptor and the matching simultaneously through end-to-end training. The results show our method outperforms the state-of-the-art techniques, and especially, the recall is improved from 45.28% to 70.47% under a similar presicion. The code of our work is available at https://github.com/mameng1/GraphLineMatching.

NaMemo: Enhancing Lecturers' Interpersonal Competence of Remembering Students' Names

Addressing students by their names helps a teacher to start building rapport with students and thus facilitate their classroom participation. However, this basic yet effective skill has become rather challenging for university lecturers (especially in Asian universities), who have to handle large-sized (sometimes exceeding 100) groups in their daily teaching. To enhance lecturers' competence in delivering interpersonal interaction, we develop NaMemo, a real-time name-indicating system based on a dedicated computer vision algorithm. This paper presents its design and feasibility study, which showed a plausible acceptance level from the participating teachers and students. We also reveal students' concerns on the abuse or misuse of this system: e.g., for checking attendance. Taken together, we discuss the opportunities and risks in design, and elaborate on the plan of a follow-up, in-depth implementation to further evaluate NaMemo's impacts on learning and teaching, as well as to probe design implications including privacy considerations.

Color Constancy with Derivative Colors

Information about the illuminant color is well contained in both achromatic regions and the specular components of highlight regions. In this paper, we propose a novel way to achieve color constancy by exploiting such clues. The key to our approach lies in the use of suitably extracted derivative colors, which are able to compute the illuminant color robustly with kernel density estimation. While extracting derivative colors from achromatic regions to approximate the illuminant color well is basically straightforward, the success of our extraction in highlight regions is attributed to the different rates of variation of the diffuse and specular magnitudes in the dichromatic reflection model. The proposed approach requires no training phase and is simple to implement. More significantly, it performs quite satisfactorily under inter-database parameter settings. Our experiments on three standard databases demonstrate its effectiveness and fine performance in comparison to state-of-the-art methods.