An object tracking method based on guided filter for night fusion image |
| |
Affiliation: | 1. Key Laboratory of the Three Gorges Reservoir Region''s Eco-Environment (Ministry of Education), Chongqing University, Chongqing 400042, PR China;2. The National Centre for International Research of Low-carbon and Green Buildings, Chongqing University, Chongqing 400042, PR China;3. The School of Civil Engineering, Guangzhou University, Guangzhou 510006, PR China;1. School of Energy and Power Engineering, Jiangsu University, Zhenjiang 212013, China;2. Institute for Energy Research, Key Laboratory of Zhenjiang, Jiangsu University, Zhenjiang 212013, China;3. College of Engineering, Wayne State University, MI 48202, United States;4. State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha 410082, China;1. College of Shipbuilding Engineering, Harbin Engineering University, Harbin, 150001, China;2. Beijing Institute of Astronautical Systems Engineering, Beijing, 100076, China;3. China Academy of Launch Vehicle Technology, Beijing, 100076, China;4. School of Astronautics, Harbin Institute of Technology, Harbin, 150001, China;1. Joint International Research Laboratory of Green Building and Built Environment, Ministry of Education, Chongqing University, 400045, China;2. National Centre for International Research of Low-carbon and Green Buildings, Chongqing University, Chongqing, 400045, China;3. Key Laboratory of Three Gorges Reservoir Region’s Eco-Environment, Ministry of Education, Chongqing University, 400045, China |
| |
Abstract: | Online object tracking is a challenging problem as it entails learning an effective model to account for appearance change caused by intrinsic and extrinsic factors. In this paper, we propose a novel online object tracking with guided image filter for accurate and robust night fusion image tracking. Firstly, frame difference is applied to produce the coarse target, which helps to generate observation models. Under the restriction of these models and local source image, guided filter generates sufficient and accurate foreground target. Then accurate boundaries of the target can be extracted from detection results. Finally timely updating for observation models help to avoid tracking shift. Both qualitative and quantitative evaluations on challenging image sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-art methods. |
| |
Keywords: | Target tracking Guided filter Color fusion image Observation model |
本文献已被 ScienceDirect 等数据库收录! |
|