Depth estimation from a video sequence with moving and deformable objects

Martinello, Manuel; Favaro, Paolo

doi:10.1049/cp.2012.0425

Cited by 8 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MFNR algorithm can be extended to other image and data manipulation techniques wherever NLM is used to enhance data cleaning [14] and various data processes e.g. interpolation [14] and depth maps regularization [15].…”

Section: Related Workmentioning

confidence: 99%

MFNR: Multi-Frame Method for Complete Noise Removal of all PDF Types in Multi-Dimensional Data Using KDE

Nazir¹,

Younis²,

Shahzad³

2020

Preprint

View full text Add to dashboard Cite

In research applications across several areas, noise removal is indispensable for accuracy of final results. Noise is caused due to physical principals, such as background electronic noise, quantum effect, and wave rebound effect to name a few. Noise removal can help improve results in medical, astronomy, defense, and numerous other fields. Addressing this limitation would result in potentially low cost, automatic, and reliable systems. In this paper, a generalized new approach i.e. Multi-Frame Noise Removal (MFNR) is proposed for noise removal. Given any type of data, the probability density function (PDF) of the noise can be determined. Herein, we extracted the noise PDF parameters using KDE (Kernel Density Estimation). Because the data is corrupted by “deterministic” noise, hence can be cleaned. This could be used as a general purpose noise removal tool. The data point with same position in multiple frames helps us determine the noise PDF characteristics and hence making it possible to remove noise. The conventional wisdom which states that noise removal and detail preservation are contrary to each other is not true for MFNR. Experimental results validate our proposed method which showed practically complete noise reduction based on number of frames used, as compared to existing benchmark methods.

show abstract

Section: Related Workmentioning

confidence: 99%

MFNR: Multi-Frame Method for Complete Noise Removal of all PDF Types in Multi-Dimensional Data Using KDE

Nazir¹,

Younis²,

Shahzad³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…More accurate results can be obtained with less computational burden. To obtain smoother and temporally consistent depth maps, Martinello and Favaro [12] use succeeding frames in a coded aperture image sequence for regularization of the depth map. However, they do not compute explicit correspondences between frames and exploit only objects that move parallel to the image plane.…”

Section: Related Workmentioning

confidence: 99%

Coded Aperture Flow

Sellent

Favaro

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Real cameras have a limited depth of field. The resulting defocus blur is a valuable cue for estimating the depth structure of a scene. Using coded apertures, depth can be estimated from a single frame. For optical flow estimation between frames, however, the depth dependent degradation can introduce errors. These errors are most prominent when objects move relative to the focal plane of the camera. We incorporate coded aperture defocus blur into optical flow estimation and allow for piecewise smooth 3D motion of objects. With coded aperture flow, we can establish dense correspondences between pixels in succeeding coded aperture frames. We compare several approaches to compute accurate correspondences for coded aperture images showing objects with arbitrary 3D motion.

show abstract

“…Different types of sensors have been proposed in the literature for depth estimation [1], [2], [3], [4], [5], [6], most common among them are vision sensors because of the rich amount of information available in them [7]. Single camera mounted on the robot can only give a 2-D projection of the scene on the image plane.…”

Section: Introductionmentioning

confidence: 99%

Object detection and depth estimation of real world objects using single camera

Liaquat

Khan

ur-Rehman

2015

2015 Fourth International Conference on Aerospace Science and Engineering (ICASE)

View full text Add to dashboard Cite

This research paper proposes a single camera based depth estimation technique. The proposed technique takes images of walls in a room and detects objects of interest in a cluttered environment. Having detected different objects in a room the proposed technique calculates their areas. Based on training data and polynomial curve fitting approach the proposed technique estimates the distance of the camera from the objects. For a real world object one can determine a fixed equation which can then be used to find any random distance. The approach is efficient and can effectively be applied to any indoor navigation or motion planning algorithm. Based on the estimated distances from different objects the proposed algorithm estimates the accurate location of the camera (mounted on a robot) in a room. For detection we have used template matching technique. Algorithm compares the reference template with the objects of interest in a cluttered environment by using SURF (speeded up robust features). The proposed algorithm is tested on real world images and compared with the existing depth estimation techniques.

show abstract

Depth estimation from a video sequence with moving and deformable objects

Cited by 8 publications

References 27 publications

MFNR: Multi-Frame Method for Complete Noise Removal of all PDF Types in Multi-Dimensional Data Using KDE

MFNR: Multi-Frame Method for Complete Noise Removal of all PDF Types in Multi-Dimensional Data Using KDE

Coded Aperture Flow

Object detection and depth estimation of real world objects using single camera

Contact Info

Product

Resources

About