Yuanwei Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuanwei Wu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Guanghui Wang
College of Engineering and Applied Sciences, Nanjing University, Nanjing, China
3 shared publications - Curtis Padgett
NASA Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USA
1 shared publication - Sushil Pratap Bharati
Electrical Engineering and Computer Science, The University of Kansas, Lawrence, Kansas United States 66045
1 shared publication Yao Sui
Harvard Medical School, Harvard University, Boston, MA, USA
1 shared publication- Yao Sui
Harvard Medical School
1 shared publication - Ziming Zhang
Department of Robotics Engineering Worcester Polytechnic Institute 01609 Worcester MA USA
1 shared publication
Latest Publications
- Open Access
Unsupervised Deep Feature Transfer for Low Resolution Image Classification
In this paper, we propose a simple while effective unsupervised deep feature transfer algorithm for low resolution image classification. No fine-tuning on convenet filters is required in our method. We use pre-trained convenet to extract features for both high- and low-resolution images, and then feed them into a two-layer feature transfer network for knowledge transfer. A SVM classifier is learned directly using these transferred low resolution features. Our network can be embedded into the state-of-the-art deep neural networks as a plug-in feature enhancement module. It preserves data structures in feature space for high resolution images, and transfers the distinguishing features from a well-structured source domain (high resolution features space) to a not well-organized target domain (low resolution features space). Extensive experiments on VOC2007 test set show that the proposed method achieves significant improvements over the baseline of using feature extraction.
Open AccessUnsupervised Deep Feature Transfer for Low Resolution Image Classification
In this paper, we propose a simple while effective unsupervised deep feature transfer algorithm for low resolution image classification. No fine-tuning on convenet filters is required in our method. We use pre-trained convenet to extract features for both high- and low-resolution images, and then feed them into a two-layer feature transfer network for knowledge transfer. A SVM classifier is learned directly using these transferred low resolution features. Our network can be embedded into the state-of-the-art deep neural networks as a plug-in feature enhancement module. It preserves data structures in feature space for high resolution images, and transfers the distinguishing features from a well-structured source domain (high resolution features space) to a not well-organized target domain (low resolution features space). Extensive experiments on VOC2007 test set show that the proposed method achieves significant improvements over the baseline of using feature extraction.
- 8 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 3 (2) , 185-197
Real-Time Obstacle Detection and Tracking for Sense-and-Avoid Mechanism in UAVs
Obstacle detection and tracking is an important research topic in computer vision with a number of practical applications. Though an ample amount of research has been done in this domain, implementing automatic obstacle detection and tracking in real-time is still a big challenge. To address this issue, we propose a fast and robust obstacle detection and tracking approach by integrating an adaptive obstacle detection strategy within a kernelized correlation filter (KCF) framework in this paper. A suitable salient object detection method auto-initializes the KCF tracker for this purpose. Moreover, an adaptive obstacle detection strategy is proposed to refine the location and boundary of the object when the confidence value of the tracker drops below a predefined threshold. In addition, a reliable post-processing technique is implemented to accurately localize the obstacle from a saliency map recovered from the search region. The proposed approach has been extensively tested through quantitative and qualitative evaluations on a number of challenging datasets. The experiments demonstrate that the proposed approach significantly outperforms the state-of-the-art methods in terms of tracking speed and accuracy.
- 8 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 3 (2) , 185-197
Real-Time Obstacle Detection and Tracking for Sense-and-Avoid Mechanism in UAVs
Obstacle detection and tracking is an important research topic in computer vision with a number of practical applications. Though an ample amount of research has been done in this domain, implementing automatic obstacle detection and tracking in real-time is still a big challenge. To address this issue, we propose a fast and robust obstacle detection and tracking approach by integrating an adaptive obstacle detection strategy within a kernelized correlation filter (KCF) framework in this paper. A suitable salient object detection method auto-initializes the KCF tracker for this purpose. Moreover, an adaptive obstacle detection strategy is proposed to refine the location and boundary of the object when the confidence value of the tracker drops below a predefined threshold. In addition, a reliable post-processing technique is implemented to accurately localize the obstacle from a saliency map recovered from the search region. The proposed approach has been extensively tested through quantitative and qualitative evaluations on a number of challenging datasets. The experiments demonstrate that the proposed approach significantly outperforms the state-of-the-art methods in terms of tracking speed and accuracy.
- Open Access
- 23 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 5, 23969-23978
Vision-Based Real-Time Aerial Object Localization and Tracking for UAV Sensing System
This paper focuses on the problem of vision-based obstacle detection and tracking for unmanned aerial vehicle navigation. A real-time object localization and tracking strategy from monocular image sequences is developed by effectively integrating the object detection and tracking into a dynamic Kalman model. At the detection stage, the object of interest is automatically detected and localized from a saliency map computed via the image background connectivity cue at each frame; at the tracking stage, a Kalman filter is employed to provide a coarse prediction of the object state, which is further refined via a local detector incorporating the saliency map and the temporal information between two consecutive frames. Compared with existing methods, the proposed approach does not require any manual initialization for tracking, runs much faster than the state-of-the-art trackers of its kind, and achieves competitive tracking performance on a large number of image sequences. Extensive experiments demonstrate the effectiveness and superior performance of the proposed approach.
- 23 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 5, 23969-23978
Open AccessVision-Based Real-Time Aerial Object Localization and Tracking for UAV Sensing System
This paper focuses on the problem of vision-based obstacle detection and tracking for unmanned aerial vehicle navigation. A real-time object localization and tracking strategy from monocular image sequences is developed by effectively integrating the object detection and tracking into a dynamic Kalman model. At the detection stage, the object of interest is automatically detected and localized from a saliency map computed via the image background connectivity cue at each frame; at the tracking stage, a Kalman filter is employed to provide a coarse prediction of the object state, which is further refined via a local detector incorporating the saliency map and the temporal information between two consecutive frames. Compared with existing methods, the proposed approach does not require any manual initialization for tracking, runs much faster than the state-of-the-art trackers of its kind, and achieves competitive tracking performance on a large number of image sequences. Extensive experiments demonstrate the effectiveness and superior performance of the proposed approach.