Robust, Efficient Depth Reconstruction with Hierarchical Confidence-Based Matching - 2017


In recent years, taking photos and capturing videos with mobile devices became increasingly standard. Emerging applications based mostly on the depth reconstruction technique have been developed, such as Google lens blur. But, depth reconstruction is tough thanks to occlusions, non-diffuse surfaces, repetitive patterns, and textureless surfaces, and it's become additional tough thanks to the unstable image quality and uncontrolled scene condition in the mobile setting. In this paper, we have a tendency to present a completely unique hierarchical framework with multi-read confidence-based matching for sturdy, efficient depth reconstruction in uncontrolled scenes. Particularly, the proposed framework combines native value aggregation with global cost optimization during a complementary manner that increases potency and accuracy. A depth map is efficiently obtained in a coarse-to-fine manner by using an image pyramid. Moreover, confidence maps are computed to robustly fuse multi-view matching cues, and to constrain the stereo matching on a finer scale. The proposed framework has been evaluated with challenging indoor and outdoor scenes, and has achieved sturdy and economical depth reconstruction.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE :Efficient, Non-Iterative Estimator for Imaging Contrast Agents With Spectral X-Ray DetectorsABSTRACT:An estimator to image contrast agents and body materials with x-ray spectral measurements is described. The estimator
PROJECT TITLE :Smart Skins: Could they be the ultimate sensing tool? TodayuFFFDs industry and personal medical care both strongly demand accurate, reliable, robust, loABSTRACT:Today???s trade and private medical care both strongly
PROJECT TITLE :A Robust, Opportunistic Clock Synchronization Algorithm for Ad Hoc Underwater Acoustic NetworksABSTRACT:Proliferation of deployed ocean-going autonomous platforms, like autonomous underwater vehicles (AUVs), unmanned
PROJECT TITLE :Frequency-Agile, Efficient, Circularly Polarized, Near-Field Resonant Antenna: Designs and MeasurementsABSTRACT:A frequency-agile, efficient, circularly polarized (CP), close to-field resonant parasitic (NFRP) antenna
PROJECT TITLE : Video Dissemination over Hybrid Cellular and Ad Hoc Networks - 2014 ABSTRACT: We study the problem of disseminating videos to mobile users by using a hybrid cellular and ad hoc network. In particular, we formulate

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry