• Publications
  • Influence
Dynamic Control of Adaptive Mixture-of-Gaussians Background Model
TLDR
We propose a method for create a background model in non-stationary scenes. Expand
  • 102
  • 7
  • PDF
TransCut: Transparent Object Segmentation from a Light-Field Image
TLDR
We propose a method that overcomes these problems using the consistency and distortion properties of a light-field image to segment the transparent objects from the background. Expand
  • 36
  • 4
  • PDF
Early Recognition and Prediction of Gestures
TLDR
This paper is concerned with an early recognition and prediction algorithm of gestures and a gesture network for improving the performance of these algorithms. Expand
  • 75
  • 3
  • PDF
A fast algorithm for adaptive background model construction using parzen density estimation
TLDR
We present fast estimation of the probability density function (PDF) of pixel value using Parzen density estimation and foreground object detection based on the estimated PDF. Expand
  • 47
  • 3
An Easy-to-Setup 3D Phenotyping Platform for KOMATSUNA Dataset
TLDR
We present a 3D phenotyping platform that measures both plant growth and environmental information in small indoor environments for plant image datasets. Expand
  • 16
  • 3
  • PDF
Object detection based on spatiotemporal background models
TLDR
We propose two types of spatiotemporal background modeling frameworks that can adapt to illumination and dynamic changes in the background. Expand
  • 31
  • 2
Coupled dictionary learning and feature mapping for cross-modal retrieval
TLDR
We first leverage the coupled dictionary learning method to generate homogeneous sparse representations for different modalities by associating and jointly updating their dictionaries. Expand
  • 25
  • 2
Non-parametric Background and Shadow Modeling for Object Detection
TLDR
We propose a fast algorithm to estimate background models using Parzen density estimation in non-stationary scenes and apply it to cast-shadow modeling. Expand
  • 24
  • 2
Towards Robust Object Detection: Integrated Background Modeling Based on Spatio-temporal Features
TLDR
We propose a sophisticated method for background modeling based on spatio-temporal features that realizes robust object detection under varying illumination, which is shown in several experiments. Expand
  • 25
  • 2