Results 11 to 20 of about 146,533 (343)
Clothes-Changing Person Re-identification with RGB Modality Only [PDF]
Computer Vision and Pattern Recognition, 2022 The key to address clothes-changing person re-identification (re-id) is to extract clothes-irrelevant features, e.g., face, hairstyle, body shape, and gait.
Xinqian Gu +5 more
semanticscholar +1 more source
Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks [PDF]
IEEE Robotics and Automation Letters, 2023 Recently, RGB-Thermal based perception has shown significant advances. Thermal information provides useful clues when visual cameras suffer from poor lighting conditions, such as low light and fog.
Mingjian Liang +5 more
semanticscholar +1 more source
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras [PDF]
IEEE Transactions on robotics, 2016 We present ORB-SLAM2, a complete simultaneous localization and mapping (SLAM) system for monocular, stereo and RGB-D cameras, including map reuse, loop closing, and relocalization capabilities. The system works in real time on standard central processing
Raul Mur-Artal, J. D. Tardós
semanticscholar +1 more source
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis [PDF]
Computer Vision and Pattern Recognition, 2016 Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+Dbased action recognition benchmarks
Amir Shahroudy, Jun Liu, T. Ng, G. Wang
semanticscholar +1 more source
HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness [PDF]
IEEE Transactions on Image Processing, 2023 RGB-D saliency detection aims to fuse multi-modal cues to accurately localize salient regions. Existing works often adopt attention modules for feature modeling, with few methods explicitly leveraging fine-grained details to merge with semantic cues ...
Zongwei Wu +4 more
semanticscholar +1 more source
Frustum PointNets for 3D Object Detection from RGB-D Data [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017 In this work, we study 3D object detection from RGBD data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by ...
C. Qi +4 more
semanticscholar +1 more source
Klasifikasi Kualitas Pisang Ambon Menggunakan Metode K-Nearest Neighbor
Jurnal Sarjana Teknik Informatika, 2022 Pisang merupakan jenis buah-buahan yang banyak ditemukan di Indonesia. Pengklasifikasian kematangan buah pisang menggunakan cara nondestruktif dilakukandengan melihat warna dan tekstur kulit pisang yang merupakan komponen eksternal dari buah pisang tanpa
Gading Surya Lesmana, Murinto Kusno
doaj +1 more source
Study of changes in color characteristics of steel under thermal exposure [PDF]
Омский научный вестник, 2022 The article presents the results of studies of steel samples under thermal exposure, by measuring color characteristics using a model of color decomposition into RGB components.
A. S. Gorbunov +2 more
doaj +1 more source
Dense RGB SLAM with Neural Implicit Maps [PDF]
International Conference on Learning Representations, 2023 There is an emerging trend of using neural implicit functions for map representation in Simultaneous Localization and Mapping (SLAM). Some pioneer works have achieved encouraging results on RGB-D SLAM.
Heng Li +5 more
semanticscholar +1 more source
Matterport3D: Learning from RGB-D Data in Indoor Environments [PDF]
International Conference on 3D Vision, 2017 Access to large, diverse RGB-D datasets is critical for training RGB-D scene understanding algorithms. However, existing datasets still cover only a limited number of views or a restricted scale of spaces.
Angel X. Chang +8 more
semanticscholar +1 more source