A5052318486- 3D Surveying and Cultural Heritage
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Robotics and Sensor-Based Localization
- Video Surveillance and Tracking Methods
- Remote Sensing and LiDAR Applications
- Image Retrieval and Classification Techniques
- 3D Shape Modeling and Analysis
Central South University
2024
National University of Defense Technology
2022-2024
Moving object detection in satellite videos (SVMOD) is a challenging task due to the extremely dim and small target characteristics. Current learning-based methods extract spatio-temporal information from multi-frame dense representation with labor-intensive manual labels tackle SVMOD, which needs high annotation costs contains tremendous computational redundancy severe imbalance between foreground background regions. In this paper, we propose highly efficient unsupervised framework for...
We study the problem of efficient object detection in 3D point clouds with voxel-point framework. Considering a large number redundant and dense proposals are usually generated for small-size objects during inference voxel-based single-stage detectors, existing detectors introduce extra subnetworks to filter further refine redundancy proposals. Albeit feasible, computational memory cost also increase inference. In this paper, we novel voxel-to-point detector, termed as V2P-SSD, which is...
Abstract. Due to the influence of imaging angle and terrain undulation, multi-view synthetic aperture radar (SAR) images are difficult be directly registered by traditional methods. Although feature matching solves issue image rotation maintains scale invariance, these methods often lead non-uniformity interest points may not achieve subpixel accuracy. The template method makes it generate correct matches for SAR oblique images. In this paper, a based on Best Buddy Similarity (BBS) is...
The tasks of point cloud analysis are very challenging. Designing efficient convolution operation is the key to accomplish these tasks. In order capture structure information, neighborhood usually needs be considered when designing convolution. At present, most works adopt K-Nearest Neighbor or ball query construct neighborhood. However, two methods only focus on spatial distance relationship and ignore long-distance dependence between points. this paper, Learnable-Graph Convolutional Neural...