J
Jiri Matas
Researcher at Czech Technical University in Prague
Publications - 359
Citations - 50878
Jiri Matas is an academic researcher from Czech Technical University in Prague. The author has contributed to research in topics: RANSAC & Video tracking. The author has an hindex of 78, co-authored 345 publications receiving 44739 citations. Previous affiliations of Jiri Matas include University of Surrey & IEEE Computer Society.
Papers
More filters
Using periodic texture as a tool for wide-baseline stereo
TL;DR: This work addresses the problem of wide-baseline stereo and demonstrates that the presence and proper analysis of distinct periodic textures can facilitate the creation of correct disparity maps for regions with periodic 3D textures.
Proceedings ArticleDOI
Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects
TL;DR: A novel method that tracks fast moving objects, mainly non-uniform spherical, in full 6 degrees of freedom, estimating simultaneously their 3D motion trajectory, 3D pose and object appearance changes with a time step that is a fraction of the video frame exposure time is proposed.
Posted Content
Inertial-Based Scale Estimation for Structure from Motion on Mobile Devices
TL;DR: This work proposes a method that recovers the metric scale given inertial measurements and camera poses, and shows that the algorithm outperforms the state-of-the-art in both accuracy and convergence speed of the scale estimate.
Proceedings ArticleDOI
ALFA: Agglomerative Late Fusion Algorithm for Object Detection
TL;DR: In this paper, the authors proposed ALFA, a novel late fusion algorithm for object detection based on agglomerative clustering of object detector predictions taking into consideration both the bounding box locations and the class scores.
Patent
Efficient unconstrained stroke detector
TL;DR: In this article, a stroke-specific keypoints detector is proposed for text detection, which is scale and rotation invariant and produces significantly less false detections than the detectors commonly used in scene text localization.