Using Covariance Matrices as Feature Descriptors for Vehicle Detection from a Fixed Camera
Seminar paper from the year 2006 in the subject Computer Science - Applied, grade: A, Boston University, course: Digital Image Processing and Communication, - entries in the bibliography, language: English, abstract: A method is developed to distinguish between cars and trucks present in a video feed of a highway. The method builds upon previously done work using covariance matrices as an accurate descriptor for regions. Background subtraction and other similar proven image processing techniques are used to identify the regions where the vehicles are most likely to be, and a distance metric comparing the vehicle inside the region to a fixed library of vehicles is used to determine the class of vehicle.
What people are saying - Write a review
We haven't found any reviews in the usual places.
algorithm’s ability average image bimg binary image BOSTON UNIVERSITY bounding box c=cov reshape calculated Car Car Car Car detection car or truck cars and trucks Cars/Trucks classes of vehicles classified colormap bone Correctly Identified covariance matrices covs data set detection with pole distance finding/covariance matrix distance metric elseif end end end)=abs diff end)=abs diff k end+1)=zeros feature vector figure imagesc imgs finding/covariance matrix ontology Fixed Camera Kevin Fx,y Gil Reese grayscale Hk(x Ik(x image segmentation image set Images Car Car imdba img=ing imgin imshow(test jb=1:length(filen junk detection k-means algorithm laplacian approximation line xmax line xmin end line xmin(j Mader and Gil MATLAB Matrices as Feature method minimum distance finding/covariance multiple object detection obdb obdba Overlapping Vehicle pixels Ri,k segmentation algorithm sensitivity and specificity Sensitivity Specificity 15 sobel Station wagons truck detection ttlmg Tuzel uiwait(msgbox(’Click Vehicle Detection xmax end xmax,ymin ymax ymax]=findcars imgs ymin end ymin j):ymax