Results 31 to 40 of about 25,036,571 (294)
Survey and Evaluation of RGB-D SLAM
IEEE Access, 2021 The traditional visual SLAM systems take the monocular or stereo camera as input sensor, with complex map initialization and map point triangulation steps needed for 3D map reconstruction, which are easy to fail, computationally complex and can cause ...
Shishun Zhang, Longyu Zheng, Wenbing Tao
doaj +1 more source
Non-Local Means Hole Repair Algorithm Based on Adaptive Block
Applied Sciences, 2023 RGB-D cameras provide depth and color information and are widely used in 3D reconstruction and computer vision. In the majority of existing RGB-D cameras, a considerable portion of depth values is often lost due to severe occlusion or limited camera ...
Bohu Zhao, Lebao Li, Haipeng Pan
doaj +1 more source
Absolute and Relative Depth-Induced Network for RGB-D Salient Object Detection
Sensors, 2023 Detecting salient objects in complicated scenarios is a challenging problem. Except for semantic features from the RGB image, spatial information from the depth image also provides sufficient cues about the object.
Yuqiu Kong +5 more
doaj +1 more source
Finite-Time Synchronization of Neural Networks With Proportional Delays for RGB-D Image Protection
, 2023 Since the depth information of images facilitates the analysis of the spatial distance of objects in computer vision applications, it is necessary to protect the image depth information.
He, X +4 more
core +1 more source
CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection [PDF]
, 2022 Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction ...
Lin, Qinwei +6 more
core +1 more source
Expanding the Detection of Traversable Area with RealSense for the Visually Impaired
Sensors, 2016 The introduction of RGB-Depth (RGB-D) sensors into the visually impaired people (VIP)-assisting area has stirred great interest of many researchers. However, the detection range of RGB-D sensors is limited by narrow depth field angle and sparse depth map
Kailun Yang +3 more
doaj +1 more source
Action recognition based on 2D skeletons extracted from RGB videos [PDF]
MATEC Web of Conferences, 2019 In this paper a methodology to recognize actions based on RGB videos is proposed which takes advantages of the recent breakthrough made in deep learning.
Aubry Sophie +3 more
doaj +1 more source
Study on traffic scene semantic segmentation method based on convolutional neural network
Tongxin xuebao, 2018 In order to improve the semantic segmentation accuracy of traffic scene,a segmentation method was proposed based on RGB-D image and convolutional neural network.Firstly,on the basis of semi-global stereo matching algorithm,the disparity map was obtained ...
Linhui LI +4 more
doaj +2 more sources
Intrinsic Scene Decomposition from RGB-D Images [PDF]
2015 IEEE International Conference on Computer Vision (ICCV), 2015 In this paper, we address the problem of computing an intrinsic decomposition of the colors of a surface into an albedo and a shading term. The surface is reconstructed from a single or multiple RGB-D images of a static scene obtained from different views. We thereby extend and improve existing works in the area of intrinsic image decomposition.
Mohammed Hachama +2 more
openaire +2 more sources
Multimodal Deep Feature Fusion (MMDFF) for RGB-D Tracking
Complexity, 2018 Visual tracking is still a challenging task due to occlusion, appearance changes, complex motion, etc. We propose a novel RGB-D tracker based on multimodal deep feature fusion (MMDFF) in this paper.
Ming-xin Jiang +4 more
doaj +1 more source