146 citations · 291 across the 27 of their papers we have counts for
13 papers · 1 filter
RTrack: Accelerating Convergence for Visual Object Tracking via Pseudo-Boxes Exploration
Guotian Zeng, Bi Zeng, Hong Zhang +2
Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the…
NPR: Nocturnal Place Recognition in Streets
Bingxi Liu, Yujie Fu, Feng Lu +3
Visual Place Recognition (VPR) is the task of retrieving database images similar to a query photo by comparing it to a large database of known images. In real-world applications, e…
A Convolutional-Transformer Network for Crack Segmentation with Boundary Awareness
Huaqi Tao, Bingxi Liu, Jinqiang Cui +1
Cracks play a crucial role in assessing the safety and durability of manufactured buildings. However, the long and sharp topological features and complex background of cracks make…
Perspective Phase Angle Model for Polarimetric 3D Reconstruction
Guangcheng Chen, Li He, Yisheng Guan +1
Current polarimetric 3D reconstruction methods, including those in the well-established shape from polarization literature, are all developed under the orthographic projection assu…
Sparse Optical Flow-Based Line Feature Tracking
Qiang Fu, Hongshan Yu, Islam Ali +1
In this paper we propose a novel sparse optical flow (SOF)-based line feature tracking method for the camera pose estimation problem. This method is inspired by the point-based SOF…
CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction
Shing Yan Loo, Ali Jahani Amiri, Syamsiah Mashohor +2
Reliable feature correspondence between frames is a critical step in visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) algorithms. In comparison with e…
Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network
Sepideh Hosseinzadeh, Moein Shakeri, Hong Zhang
In recent years, various shadow detection methods from a single image have been proposed and used in vision systems; however, most of them are not appropriate for the robotic appli…
Face Recognition using Multi-Modal Low-Rank Dictionary Learning
Homa Foroughi, Moein Shakeri, Nilanjan Ray +1
Face recognition has been widely studied due to its importance in different applications; however, most of the proposed methods fail when face images are occluded or captured under…
Object Classification with Joint Projection and Low-rank Dictionary Learning
Homa Foroughi, Nilanjan Ray, Hong Zhang
For an object classification system, the most critical obstacles towards real-world applications are often caused by large intra-class variability, arising from different lightings…
Joint Projection and Dictionary Learning using Low-rank Regularization and Graph Constraints
Homa Foroughi, Nilanjan Ray, Hong Zhang
In this paper, we aim at learning simultaneously a discriminative dictionary and a robust projection matrix from noisy data. The joint learning, makes the learned projection and di…
COROLA: A Sequential Solution to Moving Object Detection Using Low-rank Approximation
Moein Shakeri, Hong Zhang
Extracting moving objects from a video sequence and estimating the background of each individual image are fundamental issues in many practical applications such as visual surveill…
Stopping Rules for Bag-of-Words Image Search and Its Application in Appearance-Based Localization
Kiana Hajebi, Hong Zhang
We propose a technique to improve the search efficiency of the bag-of-words (BoW) method for image retrieval. We introduce a notion of difficulty for the image matching problems an…
An Efficient Index for Visual Search in Appearance-based SLAM
Kiana Hajebi, Hong Zhang
Vector-quantization can be a computationally expensive step in visual bag-of-words (BoW) search when the vocabulary is large. A BoW-based appearance SLAM needs to tackle this probl…