Results 71 to 80 of about 16,759,811 (301)

Cross-Modal Feature Integration Network for Human Eye-Fixation Prediction in RGB-D Images

IEEE Access, 2020
With the advent of convolutional neural networks, research progress in visual saliency prediction has been impressive. While integrating features at different stages from the backbone network is important, feature extraction itself is equally relevant. A
Wenyu Liu, Wujie Zhou, Ting Luo
doaj   +1 more source

RGB-D people tracking by detection for a mobile robot [PDF]

, 2011
In this work, we propose a fast and robust multi-people long-term tracking algorithm for mobile platforms equipped with RGB-D sensors. The approach we followed is based on the clustering of the scene by using 3D information in conjunction with a reliable
Basso, Filippo
core  

Development of a Solid‐Liquid Hybrid Electrolyte Composed of LiTa2PO8 and [C2mim][FSA]–Li[FSA] Ionic Liquid for Rechargeable Lithium Metal Batteries

Advanced Materials Interfaces, EarlyView.
LiTa2PO8 (LTPO) suffers from high interfacial resistance when paired with Li metal due to poor solid‐solid contact. Coating LTPO with an ionic liquid (IL) markedly improves interfacial stability, maintaining favorable resistance up to 2000 cycles. However, contact between IL‐coated LTPO and Li metal induces discoloration of LTPO, which is attributed to
Mizuki Fukuda, Dorian Unbehauer, Koichi Hamamoto, Akihito Imanishi, Yuwei Liu, Tetsuya Tsuda   +5 more
wiley   +1 more source

Coherent Absorption Reveals Colors Hidden in a Grey Fabry–Pérot Cavity

Advanced Optical Materials, EarlyView.
A dielectric thin film shows colors depending on its thickness; this effect can be used to encode information normally accessible through single‐beam spectroscopy. We developed a method to conceal this kind of information, based on coating the dielectric with a matched conductor, that suppresses the color‐bearing thin‐film resonances.
Giuseppe E. Lio, Giulio Carotta, Lorenzo Lavista, Andrea Camposeo, Giacomo Venturi, Agnese Guernieri, Alessandro Pitanti, Simon A. R. Horsley, Giuseppe C. La Rocca, Alessandro Tredicucci, Simone Zanotto   +10 more
wiley   +1 more source

A Post-Rectification Approach of Depth Images of Kinect v2 for 3D Reconstruction of Indoor Scenes

ISPRS International Journal of Geo-Information, 2017
3D reconstruction of indoor scenes is a hot research topic in computer vision. Reconstructing fast, low-cost, and accurate dense 3D maps of indoor scenes have applications in indoor robot positioning, navigation, and semantic mapping.
Jichao Jiao, Libin Yuan, Weihua Tang, Zhongliang Deng, Qi Wu   +4 more
doaj   +1 more source

Electrically Induced Photonic Assemblies of Faceted ZIF‐8 Crystals Exhibiting Binary Angle‐Dependent Structural Color and Metamerism

Advanced Optical Materials, EarlyView.
Electric fields drive dynamic photonic assemblies that reversibly generate structural color. By tuning nanoscale organization through controlled particle disorder, the presented system exhibits a unique binary color response, switching between blue and pink depending on viewing angle. Combined with metameric design, this allows for a two‐factor optical
Flora Schöfbeck, Tolga Zorlu, Michael R. Reithofer, Julian Lemmel, Daniel Hetey, Chao‐Chin Huang, Youven Benseghir, Yu‐Chueh Hung, Lucas V. Besteiro, Jia Min Chin   +9 more
wiley   +1 more source

Grounding Large Language Models for Robot Task Planning Using Closed‐Loop State Feedback

Advanced Robotics Research, EarlyView.
BrainBody‐Large Language Model (LLM) introduces a hierarchical, feedback‐driven planning framework where two LLMs coordinate high‐level reasoning and low‐level control for robotic tasks. By grounding decisions in real‐time state feedback, it reduces hallucinations and improves task reliability.
Vineet Bhat, Ali Umut Kaypak, Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami   +4 more
wiley   +1 more source

Temporal and Spatial Denoising of Depth Maps

Sensors, 2015
This work presents a procedure for refining depth maps acquired using RGB-D (depth) cameras. With numerous new structured-light RGB-D cameras, acquiring high-resolution depth maps has become easy. However, there are problems such as undesired occlusion,
Bor-Shing Lin, Mei-Ju Su, Po-Hsun Cheng, Po-Jui Tseng, Sao-Jie Chen   +4 more
doaj   +1 more source

Multi-modal RGB-D Image Segmentation from Appearance and Geometric Depth Maps

TecnoLógicas, 2020
Classical image segmentation algorithms exploit the detection of similarities and discontinuities of different visual cues to define and differentiate multiple regions of interest in images.
Isail Salazar, Said Pertuz, Fabio Martínez   +2 more
doaj   +1 more source

Improving the Robustness of Visual Teach‐and‐Repeat Navigation Using Drift Error Correction and Event‐Based Vision for Low‐Light Environments

Advanced Robotics Research, EarlyView.
Visual teach‐and‐repeat (VTR) navigation allows robots to learn and follow routes without building a full metric map. We show that navigation accuracy for VTR can be improved by integrating a topological map with error‐drift correction based on stereo vision.
Fuhai Ling, Ze Huang, Tony J. Prescott
wiley   +1 more source