Physical Cue based Depth-Sensing by Color Coding with Deaberration Network

no code implementations • 1 Aug 2019 • Nao Mishima, Tatsuo Kozakaya, Akihisa Moriya, Ryuzo Okada, Shinsaku Hiura

Color-coded aperture (CCA) methods can physically measure the depth of a scene given by physical cues from a single-shot image of a monocular camera.

Depth Estimation

Target Aware Network Adaptation for Efficient Representation Learning

no code implementations • 2 Oct 2018 • Yang Zhong, Vladimir Li, Ryuzo Okada, Atsuto Maki

This paper presents an automatic network adaptation method that finds a ConvNet structure well-suited to a given target task, e. g., image classification, for efficiency as well as accuracy in transfer learning.

Image Classification Representation Learning +1

COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation

no code implementations • ICCV 2015 • Viet-Quoc Pham, Tatsuo Kozakaya, Osamu Yamaguchi, Ryuzo Okada

This paper presents a patch-based approach for crowd density estimation in public scenes.

Density Estimation Scene Understanding