Takayoshi Yamashita

Learn More
Tracking objects in low frame rate (LFR) video or with abrupt motion poses two main difficulties which most conventional tracking methods can hardly handle: 1) poor motion continuity and increased search space; 2) fast appearance variation of target and more background clutter due to increased search space. In this paper, we address the problem from a view(More)
In recent years, boosting has been successfully applied to many practical problems in pattern recognition and computer vision fields such as object detection and tracking. As boosting is an offline training process with beforehand collected data, once learned, it cannot make use of any newly arriving ones. However, an offline boosted detector is to be(More)
Most motion-based tracking algorithms assume that objects undergo rigid motion, which is most likely disobeyed in real world. In this paper, we present a novel motion-based tracking framework which makes no such assumptions. Object is represented by a set of local invariant features , whose motions are observed by a feature correspondence process. A(More)
We present a fast face detection system that can detect faces rotated to any angle in the image plane. Our system has two major characteristics: 1) It is very fast. On a Pentium4 3GHz machine, the average detection time for faces which can be as small as 20x20 in a QVGA sized image is approximately 0.1 seconds. 2) It has a very low false detection rate. The(More)
This paper proposes Relational HOG (R-HOG) features for object detection, and binary selection by using a wild-card " * " with Real AdaBoost. HOG features are effective for object detection, but their focus on local regions makes them high-dimensional features. To reduce the memory required for the HOG features, this paper proposes a new feature , R-HOG,(More)
Robust visual tracking is always a challenging but yet intriguing problem owing to the appearance variability of target objects. In this paper we propose a novel method to handle large changes in appearance based on online real-value boosting, which is utilized to incrementally learn a strong classifier to distinguish between objects and their background.(More)
In this paper, we proposed a fast and accurate human pose estimation framework that combines top-down and bottom-up methods. The framework consists of an initialization stage and an iterative searching stage. In the initialization stage, example based method is used to find several initial poses which are used as searching seeds of the next stage. In the(More)