Papers by Hidetomo Sakaino
2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
ACM SIGGRAPH 2007 posters
ACM SIGGRAPH 2007 posters
Fourteenth Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm), 2014
This paper presents numerical simulations based on the concept of local and global dimensional an... more This paper presents numerical simulations based on the concept of local and global dimensional analysis to reproduce the thermodynamics and aerodynamics of server-fins, i.e., detachable flat/curved fins on the inlet/outlet of a server, for enhancing energy efficiency in data centers. Server-fin designs, combinations of shapes and opening angles, are evaluated by transient analysis, vorticity analysis, temperature change rate analysis, and a modified Return Heat Index. Various numerical simulations from local to global dimensions confirm the effectiveness of the server-fins proposed herein in enhancing energy efficiency in data centers compared to their omission.
Thispaper proposes anewanimation editing method for creating animations froma single texture imag... more Thispaper proposes anewanimation editing method for creating animations froma single texture image. A standard warping methodcannothandle a physical motion effect because ofamanual control. TheNavierStokes equation basedmethodisknowntobeableto animate afluid-like animation. However, thedifficulties ofdefining initial- andboundary-conditions withmany control parameters remainunsolved fora stable and desired animation. Anditoffers aheavycomputation. In this paper, anadvection equation that isaphysical-based andcompact equation isused. A unique interface isalso introduced witha gallery ofmanyvelocity vectors: convergence, rotation andvibration. Ourmethodis versatile because that thecombination ofsuchvelocity patterns cananimate aquasi-linear motion overtimeby solving asetofthelinear equations. We havecarried out several experiments using somereal images. Theresults ofanimations showthat thePDT iseffective, efficient, andeasy touse.
IEEE Transactions on Image Processing, 2019
Videos are spatio-temporally rich in static to dynamic objects/scenes, sparse to dense, and perio... more Videos are spatio-temporally rich in static to dynamic objects/scenes, sparse to dense, and periodic to non-periodic motions. Particularly, dynamic texture (DT) exhibits complex appearance and motion changes that remain challenge to deal with. This paper presents an energy optimization method for feature extraction and recognition in videos. For noise and background jitter, Tikhonov regularization (TR) with eigen-vector and Frenet-Serret formula based energy constraints is also proposed. Different periodicity of DT can be adapted by the time-varying number of learning temporal frames. Optimal duration of an image sequence is determined from the temporal property of its eigen-values. Unlike state-of-the-art recognition methods, i.e., sparse coding and slow feature analysis, the proposed method can capture physical property of objects and scenes: velocity, acceleration, and orientation. Also, static and dynamic image regions can be locally classified. Owing to these spatio-temporal features, stability, robustness, and accuracy of feature extraction and recognition are enhanced. Using DT videos, the superiority of the proposed method to state-ofthe-art recognition methods is experimentally shown.
IEEE Transactions on Image Processing, 2016
Video extrapolation/prediction methods are often used to synthesize new videos from images. For f... more Video extrapolation/prediction methods are often used to synthesize new videos from images. For fluid-like images and dynamic textures as well as moving rigid objects, most state-of-the-art video extrapolation methods use non-physics-based models that learn orthogonal bases from a number of images but at high computation cost. Unfortunately, data truncation can cause image degradation, i.e., blur, artifact, and insufficient motion changes. To extrapolate videos that more strictly follow physical rules, this paper proposes a physics-based method that needs only a few images and is truncation-free. We utilize physics-based equations with image intensity and velocity: optical flow, Navier-Stokes, continuity, and advection equations. These allow us to use partial difference equations to deal with the local image feature changes. Image degradation during extrapolation is minimized by updating model parameters, where a novel time-varying energy balancer model that uses energy based image features, i.e., texture, velocity, and edge. Moreover, the advection equation is discretized by high-order constrained interpolation profile for lower quantization error than can be achieved by the previous finite difference method in long-term videos. Experiments show that the proposed energy based video extrapolation method outperforms the state-of-the-art video extrapolation methods in terms of image quality and computation cost.
Journal of Advanced Computational Intelligence and Intelligent Informatics, 2004
This paper discusses a method to precisely recognize which tool is to be used based on the optica... more This paper discusses a method to precisely recognize which tool is to be used based on the optical flow and HMM from short-time sequential images that operate a variety of hand-operated carpenter tools in the real environment. Operation recognition from a single-eye camera includes problems on differences in the difficulty of fixing the shape of the tool and poor motion periodicity due to occlusion of the fingers, back of the hand, and arm of the operator. This paper models operation without separating the integrated motions of the hand and tool and recognizes it with four tools divided into different categories from these motions. The optical flow method via the nonlinear robust function is used to suppress possible error caused by discontinuous motion components, HMM with a flexible time axis is applied to implement learning and recognition. The average vector of the optical flow mapped into the conversion diagram was designed to output symbol numbers for the generation of symbol ...
The Journal of The Institute of Image Information and Television Engineers, 2010
Electronics and Communications in Japan (Part III: Fundamental Electronic Science), 1998
IEEE Transactions on Image Processing, 2015
IEEE Sensors Journal, 2016
Sixth IEEE Workshop on Applications of Computer Vision, 2002. (WACV 2002). Proceedings.
Object recognition supported by user interaction for service robots
ABSTRACT Discusses a robust velocity estimation method for moving vehicles in road traffic image ... more ABSTRACT Discusses a robust velocity estimation method for moving vehicles in road traffic image sequences under snowy and misty weather conditions. In such environments, it is difficult to detect the velocity of vehicles because of discontinuities, occlusions, noise, and brightness variations. It should also be noted that falling snow results in indefinite shapes and motion, which occludes the region of interest. In order to estimate and recognize moving vehicles in images, a two-stage method has been proposed. Firstly, a non-linear smoothing is applied based on an anisotropic diffusion method. Secondly, a minimization of an objective function with movements and photometric variations is carried out. The fitting residual error in the function is reduced by a nonlinear robust function in discontinuity regions. Thus the velocity of moving vehicles can be estimated, stably and robustly, even in low contrast images. To verify this, a simple recognition experiment is performed to estimate the number of moving vehicles in images. The high recognition rate shows the validity and power of the proposed scheme.
2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008
ABSTRACT This paper presents a fluid flow estimation method for ocean/river waves, clouds, and sm... more ABSTRACT This paper presents a fluid flow estimation method for ocean/river waves, clouds, and smoke based on the physical properties of waves. Most of the previous optical flow methods based on fluid dynamics/mechanics estimate a smooth flow using a continuity equation and/or div-curl velocity constraint. However, abrupt or inhomogeneous image motion changes in such fluid-like images are not estimated well. In this paper, we assume that many fluid-like motion changes are due to wave phenomena that lead to a brightness change. Thus, a wave generation equation is applied with a two-step optimization. A novel constraint based on the velocity-frequency relationship equation and a wave statistical property are used. The results of experiments on synthetic and real image sequences show the validity of our method.
2005 IEEE International Conference on Multimedia and Expo
Electronics and Communications in Japan (Part III: Fundamental Electronic Science), 1994
2009 16th IEEE International Conference on Image Processing (ICIP), 2009
This paper presents a motion estimation method for semi-transparent objects with a long-range dis... more This paper presents a motion estimation method for semi-transparent objects with a long-range displacement between frames, i.e., falling snow in video. Previous optical flow based methods have been treated with non-transparent, rigid, and fluid-like moving objects in a short-range displacement. However, they fail to match between frames when moving objects are transparent/homogenoeous color in a long-range displacement. To meet with
Uploads
Papers by Hidetomo Sakaino