Hongpeng Wang

Error aware multiple vertical planes based visual localization for mobile robots in urban environments

A novel error-aware visual localization method is proposed that utilizes vertical planes, such as vertical building facades in urban areas as landmarks. Vertical planes, reconstructed from coplanar vertical lines, are robust high-level features if compared with point features or line features. Firstly, the error models of vertical lines and vertical planes are built, where maximum likelihood estimation (MLE) is employed to estimate all vertical planes from coplanar vertical lines. Then, the closed-form representation of camera location error variance is derived. Finally, the minimum variance camera pose estimation is formulated into a convex optimization problem, and the weight for each vertical plane is obtained by solving this well-studied problem. Experiments are carried out and the results show that the proposed localization method has an accuracy of about 2 meters, at par with commercial GPS operating in open environments.

Indoor intrusion detection using an intelligent sensor network

To reduce redundant data volume, save energy expenditure, and enhance intelligent control for multiple video cameras in video surveillance. We present a scheme for the video surveillance system using wireless sensor network (WSN) technology. When an intrusion signal is detected by a wireless sensor module, video cameras are activated and snap pictures in fixed time interval. A neighborhood linkage problem (NLP) is also presented to trace the moving objects. Experimental results show that fusing the data of WSN and video cameras reduce the energy expenditure by 97% in intrusion detection.

A fast key frame extraction algorithm and an accurate feature matching method for 3D reconstruction from aerial video

In this paper, we present a fast method of key frame selection and an accurate feature point matching method for 3D reconstruction through the control of quadrotor. The quadrotor is controlled to fly at a fixed altitude and the gimbal camera has always been a downward direction. Therefore, the additional information of the quadrotor could be easily added to the 3D reconstruction process. As a result, we find a fast method to select key frames and an optimized matching method through the geometric constraints of the flight path and direction. The method is mainly to improve the efficiency of key frame selection and to get more accurate matching points. The advantage of our approach is to combine the two processes between video capture and video processing by adding flight control to the 3D scene reconstruction method. Therefore, it can use less time to complete the entire reconstruction task. The proposed approach is tested by quadrotor platform. Experiment results show that our method can greatly reduce the key frame selection time and get more matching points at the same accuracy.

A multi-scale kernel correlation filter tracker with feature integration and robust model updater

In recent years, the correlation filter-based trackers (CFTs) have shown to provide excellent results in different competitions and benchmarks, but there is still a need to improve the robustness of CFTs. Compared with the traditional kernel correlation filter tracker, the approach we present in this paper makes some significant improvements. The strong features including HOG and Color-naming are integrated to maintain a more powerful object representation, and PCA is applied to boost the computation speed. To deal with scale variation, a multiple scale adaptive method is adapted. Model updater is modified by considering all previous frames to update the discriminative classifier coefficients. Extensive evaluations are performed on 51 challenging benchmark sequences. The experiments results show that our approach outperforms state-of-the-art tracking methods. Additionally, the proposed approach is implemented in our practical project, and the results also prove the availability of our approach.