@article{li2024fully, title={Fully sparse fusion for 3d object detection}, author={Li, Yingyan and Fan, Lue and Liu, Yang and Huang, Zehao and Chen, Yuntao and Wang, Naiyan and Zhang, Zhaoxiang}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, year={2024}, publi...
We present Fully Convolutional Networks with Densely Feature Fusion Models (DFF-FCN) which is an effective framework for multi-scale object detection. DFF-FCN reuses the inherent convolutional hierarchical features of regular convolutional neural networks from both forward and backward directions so that ...
Continuous Direct Sparse Visual Odometry from RGB-D Images[J]. arXiv preprint arXiv:1904.02266, 2019. 代码:https://github.com/MaaniGhaffari/cvo-rgbd 21. Map2DFusion(单目 SLAM 无人机图像拼接) 论文:Bu S, Zhao Y, Wan G, et al. Map2DFusion: Real-time incremental UAV image mosaicing based...
Cai et al. (2020) have proposed a novel end-to-end BS-Net framework for HSI band selection. The basic idea of the proposed framework is to treat HSI band selection as a sparse spectral reconstruction task. The method aims to clearly learn the significance of the spectral band, taking ...
Feature fusion is a very common and useful strategy in semantic segmentation tasks. In our proposed work, due to the modification of the decoder network, we introduce a novel CS module into the traditional skip-connection structure. In order to validate the necessity for class-wise circumstance,...
The paper presents the Proposal-Free Fully Convolutional Network (PF-FCN), a fully convolutional network designed for object detection to balance the accuracy and speed of detectors. In addition, the paper proposes a new concept called the “bounding box filter” based on the bounding box vector...
A parallel feature fusion is incorporated to fuse all the extracted features. The fused feature set is transmitted to multiple kernel learning (MKL) for object categorization in the remote sensing imagery. These categorized objects are then analyzed for the object-to-object relationship (OOR) ...
[19] compared the ground object classification ability of full and partially polarized SAR data of C-band and L-band and found that L-band full polarized data had the highest accuracy, and that multi-band data fusion could improve the classification accuracy by 7%. Langner et al. [20] ...
To remove redundant information in the cascaded features with high dimensionality, the manifold algorithm LPP based on graph embedding is utilized for dimensionality reduction before the final classification. Considering that features learned by the MFCN are already sparse and nonlinear, this work ...
The final 3D point cloud is obtained by data fusion of the horizontal scan lines provided by the object capturing laser scanner and the height component determined by the referencing laser scanner. It is worth mentioning that only relative changes in height are of interest so that a rigorous ...