================================================================================ SUPPLEMENTARY DATA for the research on FEATURE POINT DETECTION UNDER EXTREME LIGHTING CONDITIONS ================================================================================ Authors: Bronislav Přibyl, ipribyl@fit.vutbr.cz Alan Chalmers, alan.chalmers@warwick.ac.uk Pavel Zemčík, zemcik@fit.vutbr.cz Description: This data has been created when carrying out the research on "feature point detection under extreme lighting conditions" at the Brno University of Technology, Faculty of Information Technology, Czech Republic and the University of Warwick, Warwick Manufacturing Group, United Kingdom. If you use any part of this material in a publication, please cite our paper "Přibyl, B., Chalmers, A., Zemčík, P.: Feature Point Detection under Extreme Lighting Conditions, In: Spring Conference on Computer Graphics, Smolenice, SK, UNIBA, 2012, p. 156-163, ISBN 978-80-223-3211-8". BibTex entry: @INPROCEEDINGS{pribyl2012FPDuExLC, author = {Bronislav P{\v{r}}ibyl and Alan Chalmers and Pavel Zem{\v{c}}{\'{i}}k}, title = {Feature Point Detection under Extreme Lighting Conditions}, pages = {156--163}, booktitle = {Spring Conference on Computer Graphics}, year = {2012}, location = {Smolenice, SK}, publisher = {Comenius University in Bratislava}, ISBN = {978-80-223-3211-8}, language = {english}, url = {http://www.fit.vutbr.cz/research/view_pub.php.en?id=9920} } The data contains images of two test scenes (2D and 3D) captured in three image sequences (distance-changing seq., lighting-chaning seq. and viewpoint-changing seq.) into four different image formats (LDR - ordinary low dynamic range image, HDR - high dynamic range image, GTM - HDR image tone mapped using a global tone mapper and LTM - HDR image tone mapped using a local tone mapper). Several single-exposure images were captured at different exposure levels at each camera position and then combined into a single HDR image. The HDR image was subsequently tone mapped using a global and a local tone mapper. From the HDR image containing all the dynamic range, a "single exposure" LDR image has been made by clipping the dynamic range to 8 stops. Four feature point (FP) detectors (Harris corner detector, Shi-Tomasi, FAST and Fast Hessian (the detector part of the SURF combined FP detector and descriptor)) were then carried out on the four described image formats which yielded 16 sets of feature points for each camera position. We then performed an automatic camera calibration from a dot pattern in each image sequence to obtain the camera parameters. Based on these parameters, we computed the geometric relations between individual views. The geometric relations allowed us to match the detected feature points automatically (in the case of 2D scene) or semi/ automatically (in the case of 3D scene). Finally, the repeatability rate of the feature point detectors was evaluated for individual image formats and image sequences. The results can be obtain from our aforementioned paper. Directory structure: / +-2D/ ..................... - scene folder | +-distance/ ............. - sequence subfolder | | +-100/ ................ - image subsubfolder | | | +-single_exposures/ - subfolder with single-exposure images used to | | | | create the HDR image (images are geometricaly | | | | corrected) | | | +-100.R.txt ......... - camera rotation matrix with respect to the | | | | reference image - see Format 1 below | | | +-100.T.txt ......... - camera translation vector with respect to | | | | reference image - see Format 2 below | | | +-100.ldr.jpg ....... - LDR image | | | +-100.hdr.hdr ....... - HDR image | | | +-100.gtm.jpg ....... - GTM image | | | +-100.ltm.jpg ....... - LTM image | | | +-100.ROI.txt ....... - Region Of Interest for FP detection - see Format 3 | | | | below | | | +-100.fast.ldr.txt .. - coords of FAST FPs detected in LDR image - see | | | | Format 4 below | | | +-100.fast.hdr.txt .. - coords of FAST FPs detected in HDR image | | | +-100.fast.gtm.txt .. - coords of FAST FPs detected in GTM image | | | +-100.fast.ltm.txt .. - coords of FAST FPs detected in GTM image | | | +-100.harr.ldr.txt .. - coords of Harris FPs detected in LDR image | | | +-100.harr.hdr.txt .. - coords of Harris FPs detected in HDR image | | | +-100.harr.gtm.txt .. - coords of Harris FPs detected in GTM image | | | +-100.harr.ltm.txt .. - coords of Harris FPs detected in LTM image | | | +-100.shit.ldr.txt .. - coords of Shi-Tomasi FPs detected in LDR image | | | +-100.shit.hdr.txt .. - coords of Shi-Tomasi FPs detected in HDR image | | | +-100.shit.gtm.txt .. - coords of Shi-Tomasi FPs detected in GTM image | | | +-100.shit.ltm.txt .. - coords of Shi-Tomasi FPs detected in LTM image | | | +-100.surf.ldr.txt .. - coords of Fast Hessian FPs detected in LDR image | | | +-100.surf.hdr.txt .. - coords of Fast Hessian FPs detected in HDR image | | | +-100.surf.gtm.txt .. - coords of Fast Hessian FPs detected in GTM image | | | +-100.surf.ltm.txt .. - coords of Fast Hessian FPs detected in LTM image | | | | | +-103/ | | | +-... | | | | | +-109/ | | | +-... | | | | | +-122/ | | | +-... | | | | | +-147/ | | | +-... | | | | | +-197/ | | | +-... | | | | | +-297/ | | | +-... | | | | | +-H.100.103.txt ....... - homography matrix between views 100 and 103 - see | | | Format 5 below | | +-H.100.109.txt ....... - homography matrix between views 100 and 109 | | +-H.100.122.txt ....... - homography matrix between views 100 and 122 | | +-H.100.147.txt ....... - homography matrix between views 100 and 147 | | +-H.100.197.txt ....... - homography matrix between views 100 and 197 | | +-H.100.297.txt ....... - homography matrix between views 100 and 297 | | +-K.txt ............... - camera matrix for given image sequence - see | | Format 6 below | | | +-lighting/ | | +-001/... | | +-010/... | | +-011/... | | +-100/... | | +-101/... | | +-110/... | | +-111/... | | +-H.111.001.txt ....... - homography matrix between views 111 and 001 - see | | | Format 5 below | | +-H.111.010.txt | | +-H.111.011.txt | | +-H.111.100.txt | | +-H.111.101.txt | | +-H.111.110.txt | | +-K.txt ............... - camera matrix for given image sequence - see | | Format 6 below | | | +-viewpoint/ | +-00/... | +-01/... | +-02/... | +-03/... | +-04/... | +-05/... | +-06/... | +-07/... | +-08/... | +-09/... | +-10/... | +-11/... | +-12/... | +-13/... | +-14/... | +-15/... | +-16/... | +-17/... | +-18/... | +-19/... | +-20/... | +-H.10.00.txt ......... - homography matrix between views 10 and 00 - see | | Format 5 below | +-H.10.01.txt | +-H.10.02.txt | +-H.10.03.txt | +-H.10.04.txt | +-H.10.05.txt | +-H.10.06.txt | +-H.10.07.txt | +-H.10.08.txt | +-H.10.09.txt | +-H.10.11.txt | +-H.10.12.txt | +-H.10.13.txt | +-H.10.14.txt | +-H.10.15.txt | +-H.10.16.txt | +-H.10.17.txt | +-H.10.18.txt | +-H.10.19.txt | +-H.10.20.txt | +-K.txt ............... - camera matrix for given image sequence | | +-3D/ +-distance/ | +-... | +-F.100.109.txt ....... - fundamental matrix between views 100 and 109 - see | | Format 7 below | +-... | +-lighting/ | +-... | +-F.111.001.txt ....... - fundamental matrix between views 111 and 001 - see | | Format 7 below | +-... | +-viewpoint/ | +-... | +-F.10.00.txt ......... - fundamental matrix between views 10 and 00 - see | | Format 7 below | +-... File formats: All numbers are floating point numbers (a.k.a. "floats") stored in a plain text format on 25 characters (aligned right, filled with spaces from left). The representation consists of: * an optional sign (-) * the mantisa - one digit before the decimal point - the decimal point (.) - several digits after the decimal point * the exponent sign (e) * the exponent - the sign (+ or -) - one to three digits Example floats: " -9.9993639314785610e-001", " 3.6202320949113728e+03". Entries of a matrix row are stored on one line of a text file. The entries are separated by a tab character( ). Example of a matrix row with 3 entries: " -9.9993639314785610e-001 -1.7425725739943524e-003 -1.1143298402206141e-002" == Format 1 == - rotation matrix - 3x3 matrix - each matrix row is on a separate line == Format 2 == - translation vector - 3x1 vector - each vector entry is on a separate line == Format 3 == - a region of interest (sequence of image coordinates defining a polygon; the first and last coordinate is NOT the same) - nx2 matrix - each coordinate pair (x y) is on a separate line == Format 4 == - coordinates of feature points - nx3 matrix - each feature point is on a separate line; first two entries are the (x y) coordinates, the last entry is the "strength" of the feature point (or the response of the feature point detector) == Format 5 == - homography matrix - the same as Format 1 == Format 6 == - camera matrix - the same as Format 1 - the meaning of individual matrix entries is explained at http://www.vision.caltech.edu/bouguetj/calib_doc/htmls/parameters.html (see 'camera matrix') == Format 7 == - fundamental matrix - the same as Format 1