[vc_row][vc_column][vc_column_text][wonderplugin_video videotype=”mp4″ mp4=”https://mariosbikos.com/wp-content/uploads/2015/07/ICPBunny.mp4″ webm=”” poster=”” lightbox=0 lightboxsize=1 lightboxwidth=960 lightboxheight=540 autoopen=0 autoopendelay=0 autoclose=0 lightboxtitle=”” lightboxgroup=”” lightboxshownavigation=0 showimage=”” lightboxoptions=”” videowidth=800 videoheight=450 keepaspectratio=1 autoplay=1 loop=1 videocss=”position:relative;display:block;background-color:#000;overflow:hidden;max-width:100%;margin:0 auto;” playbutton=”https://mariosbikos.com/wp-content/plugins/wonderplugin-video-embed/engine/playvideo-64-64-0.png”][/vc_column_text][/vc_column][/vc_row][vc_row][vc_column width=”1/2″][vc_custom_heading source=”post_title” font_container=”tag:h2|font_size:32|text_align:left|color:%23000000″ google_fonts=”font_family:ABeeZee%3Aregular%2Citalic|font_style:400%20regular%3A400%3Anormal”][vc_column_text]Course Project at UCL[/vc_column_text][/vc_column][vc_column width=”1/2″][vc_column_text]Implementation of the 3D ICP algorithm, as well as some of its variants, affecting the speed/accuracy. The results were visualized for a better understanding of the registration.[/vc_column_text][vc_tweetmeme share_via=”mariosbikos” share_recommend=”framestore” share_hashtag=”magicleap,ar,framestore” large_button=”true” lang=”en”][/vc_column][/vc_row][vc_row][vc_column width=”1/3″][vc_title title=”Challenges”][vc_column_text]
- Learning how to use the provided framework.
- Learning about the registration process.
[/vc_column_text][/vc_column][vc_column width=”1/3″][vc_title title=”Technologies”][vc_column_text]
- Eigen
- LibANN
- GLFW
- OpenGL
[/vc_column_text][/vc_column][vc_column width=”1/3″][vc_title title=”Languages”][vc_column_text]
- C++
[/vc_column_text][/vc_column][/vc_row][vc_row][vc_column][vc_title title=”Project Details”][vc_column_text]The Iterative Closest Point algorithm is a general purpose algorithm intended to match various geometrical primitives. In this assignment, the 3D ICP algorithm was implemented, as well as some of its variants, affecting the speed/accuracy. We use the algorithm to match multiple scanned point cloud set versions (from different degrees 0,45,90,135,..) of the famous Stanford Bunny Model. The algorithm is utilized, in order to move a model M2 (45 degrees) towards model M1 (0 degrees) by estimating the optimal transformation (output of ICP). The results are visualized for a better understanding of the registration.[/vc_column_text][/vc_column][/vc_row][vc_row][vc_column][vc_title title=”Images”][/vc_column][/vc_row][vc_row][vc_column width=”1/3″][vc_single_image image=”1663″ img_size=”large” style=”vc_box_rounded” onclick=”link_image”][/vc_column][vc_column width=”1/3″][vc_single_image image=”1662″ img_size=”large” onclick=”link_image”][/vc_column][vc_column width=”1/3″][vc_single_image image=”1658″ img_size=”large” onclick=”link_image”][/vc_column][/vc_row]