fg-object-removal.blogspot.com
Foreground object removal: Preliminary pedestrian removal results
http://fg-object-removal.blogspot.com/2010/02/preliminary-pedestrian-removal-results.html
Sunday, February 28, 2010. Preliminary pedestrian removal results. Currently, this is my pipeline to remove pedestrians:. Compute homographies between two views (I1 and I2) using SIFT and RANSAC. Detect pedestrians on both views (with bounding boxes). Warp pedestrian bounding boxes using homography from step 1, determine overlap (if any). Use method proposed by James Davis. To obtain a dividing boundary in overlap region. March 3, 2010 at 9:17 PM. Subscribe to: Post Comments (Atom).
fg-object-removal.blogspot.com
Foreground object removal: How google does surface normals
http://fg-object-removal.blogspot.com/2010/02/how-google-does-surface-normals.html
Thursday, February 25, 2010. How google does surface normals. Apparently, google does use 3D laser point clouds to estimate surface normals (or building facades as they call them), see this quote from http:/ google-latlong.blogspot.com/2009/06/introducing-smart-navigation-in-street.html. We have been able to accomplish this by making a compact representation of the building facade and road geometry for all the Street View panoramas using laser point clouds and differences between consecutive pictures.
fg-object-removal.blogspot.com
Foreground object removal: A relevant paper
http://fg-object-removal.blogspot.com/2010/02/relevant-paper.html
Thursday, February 18, 2010. Found a paper that may be useful: " Piecewise Planar City 3D Modeling from Street View Panoramic Sequences. The focus of this paper is 3D modeling, but they mention a multi-view stereo technique for dense depth estimation. This may make it possible to remove foreground objects based on histogram analysis of pixel depths (similar to the way foreground objects were removed in Dr. Zakhor's work. Which was the inspiration for this project). Subscribe to: Post Comments (Atom).
fg-object-removal.blogspot.com
Foreground object removal: Hole filling (and reading)
http://fg-object-removal.blogspot.com/2010/02/hole-filling-and-reading.html
Wednesday, February 10, 2010. Hole filling (and reading). Since it is likely I will need to incorporate one more view of the scene, I have been reading about the trifocal tensor in Hartley and Zisserman. I've also been reading some material on how to further refine the estimated homography here. Subscribe to: Post Comments (Atom). Preliminary pedestrian removal results. How google does surface normals. Hole filling (and reading). CSE 190a Spring 2010 bees counting project. Real Time Detection of Groceries.
fg-object-removal.blogspot.com
Foreground object removal: March 2010
http://fg-object-removal.blogspot.com/2010_03_01_archive.html
Thursday, March 4, 2010. Seam carving for content-aware image resizing. Uses the same technique James Davis uses, but for a different application. See the "Object removal" section (section 4.6) for another interesting application. I may play around with this to reduce the artifacts after removing people. Subscribe to: Posts (Atom). CSE 190a Spring 2010 bees counting project. Real Time Detection of Groceries. Dancer Identification within Shot Boundaries. Forgot to Mention Histograms.
fg-object-removal.blogspot.com
Foreground object removal: January 2010
http://fg-object-removal.blogspot.com/2010_01_01_archive.html
Wednesday, January 27, 2010. Odd results and some runtime errors. At this point, I am trying to debug the Josh Wills' motion segmentation code. After altering the code to use SIFT correspondences, I encountered a few bugs:. Attempted to access IndexSam(4997,:); index out of bounds because size(IndexSam)=[4996,4]. Error in = get warps at 56. From reading the code, it appears this function is using RANSAC to estimate the homography. I changed a hard-coded iters. Monday, January 25, 2010. The correspondence...
fg-object-removal.blogspot.com
Foreground object removal: Interesting paper
http://fg-object-removal.blogspot.com/2010/03/interesting-paper.html
Thursday, March 4, 2010. Seam carving for content-aware image resizing. Uses the same technique James Davis uses, but for a different application. See the "Object removal" section (section 4.6) for another interesting application. I may play around with this to reduce the artifacts after removing people. Subscribe to: Post Comments (Atom). CSE 190a Spring 2010 bees counting project. Real Time Detection of Groceries. Dancer Identification within Shot Boundaries. Forgot to Mention Histograms.
fg-object-removal.blogspot.com
Foreground object removal: Pedestrian detection
http://fg-object-removal.blogspot.com/2010/02/pedestrian-detection.html
Monday, February 22, 2010. Due to the lack of progress with the proposed method, I decided to simplify and restrict the problem to removal of pedestrians only. From a privacy standpoint, this would be a step beyond the face blurring that google already does. I have been testing with pedestrian detection. Code by Bastian Leibe. Some results on google streetview data can be seen here. I also tried pedestrian detection software by Liming Wang. Subscribe to: Post Comments (Atom). Hole filling (and reading).
fg-object-removal.blogspot.com
Foreground object removal: February 2010
http://fg-object-removal.blogspot.com/2010_02_01_archive.html
Sunday, February 28, 2010. Preliminary pedestrian removal results. Currently, this is my pipeline to remove pedestrians:. Compute homographies between two views (I1 and I2) using SIFT and RANSAC. Detect pedestrians on both views (with bounding boxes). Warp pedestrian bounding boxes using homography from step 1, determine overlap (if any). Use method proposed by James Davis. To obtain a dividing boundary in overlap region. Thursday, February 25, 2010. How google does surface normals. Due to the lack of pr...
