Abstract
Stereo matching methods have achieved remarkable improvements by exploiting various attempts. However, most stereo matching algorithms still suffer from problems such as ambiguous region and inherent ambiguities. In particular, some problems affecting cost aggregation step have the greatest impact on depth results. To resolve the above-mentioned problems, we propose a new cost aggregation method using the modified total generalized variation with fusion tensor. First, two kinds of diffusion tensors are extracted from the guidance color image and the guidance depth map. They are incorporated into an energy functional to obtain the total generalized variation. After formulating the final energy functional, it is optimized via a primal-dual energy minimization method. The performance of the proposed method is experimentally verified by qualitatively and quantitatively comparing the results to those of other algorithms.
Highlights
Depth estimation has traditionally been one of the most crucial tasks in the field of computer vision. It is highly fundamental for various computer vision-based applications including 3D object recognition [1], extraction of information from aerial surveys [2], geometry extraction for 3D object mapping [3], self-driving cars, and obstacle estimation [4]
Depth information can be acquired by several methods such as active depth cameras and passive depth cameras
Active depth sensor resolves depth information using a physical sensor. It emits light onto the scene and derives depth information based on the known speed of light, whereas passive depth cameras measure the correlation of images captured from two or more cameras
Summary
Depth estimation has traditionally been one of the most crucial tasks in the field of computer vision. Passive depth camera estimates depth information indirectly from 2D images These cameras can be used outdoors during daytime and can generate a high-resolution depth map. The ambiguous region problem affecting cost aggregation step has the greatest impact on depth results. To tackle these difficulties, several approaches have been addressed. Zheng et al proposed a cross-scale cost aggregation, which estimates accurate disparity values in homogeneous regions [17]. This method constructs a hierarchical structure to aggregate matching costs.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
