{"id":334,"date":"2019-04-05T22:01:00","date_gmt":"2019-04-05T22:01:00","guid":{"rendered":"http:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/?p=334"},"modified":"2019-04-05T22:01:54","modified_gmt":"2019-04-05T22:01:54","slug":"block-detection-with-selective-search","status":"publish","type":"post","link":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/2019\/04\/05\/block-detection-with-selective-search\/","title":{"rendered":"Block Detection with Selective Search"},"content":{"rendered":"

The proposed block detection pipeline is implemented as follows:<\/p>\n

1.\u00a0 <\/span>We collected images of the blocks and fit a logistic regression classifier to the data contain-<\/p>\n

ing red blocks, blue blocks and a background class. Some examples of the training set<\/p>\n

is shown in the Figure.<\/p>\n

2.\u00a0 <\/span>Given an image of the scene, we run selective search to obtain region proposals in the<\/p>\n

image.<\/p>\n

3.\u00a0 <\/span>We\u00a0 <\/span>then\u00a0 <\/span>classify\u00a0 <\/span>every\u00a0 <\/span>patch\u00a0 <\/span>using\u00a0 <\/span>a\u00a0 <\/span>trained\u00a0 <\/span>logistic\u00a0 <\/span>regression\u00a0 <\/span>model\u00a0 <\/span>and\u00a0 <\/span>run\u00a0 <\/span>non-<\/p>\n

maximal suppression to obtain the best bounding box for every block in the scene.<\/p>\n

 <\/p>\n

\"\"<\/p>\n

<\/div>\n
Examples in the training set. The top row represents red blocks (class 1), middle<\/div>\n
row represents blue blocks (class 2) and the bottom row represents the back-<\/div>\n
ground class (class 0)<\/div>\n
<\/div>\n
Selective Search\u00a0<\/strong><\/div>\n
\n
Selective search is a region proposal algorithm that works by grouping hierarchical repre-<\/div>\n
sentations of pixels with similar colour, shape, size and texture. It works by first over seg-<\/div>\n
menting the image as an initialization and beings grouping adjacent segments based on<\/div>\n
the similarity in colour, shape, size and texture.<\/div>\n<\/div>\n
<\/div>\n
\"\"<\/div>\n
<\/div>\n
Logistic Regression<\/strong><\/div>\n
\n
Logistic regression fits a linear model to a set of data points. A sigmoid activation func-<\/div>\n
tions is applied on the output of the linear model to map the outputs between 0 and 1 to<\/div>\n
represent a probability distribution. The model is optimized to minimize the cross entropy<\/div>\n
between the predicted distribution and the true distribution given by the labels of the data.<\/div>\n
The weights are usually updated using gradient descent since this is a non-linear optimiza-<\/div>\n
tion problem.<\/div>\n
\"\"<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

The proposed block detection pipeline is implemented as follows: 1.\u00a0 We collected images of the blocks and fit a logistic regression classifier to the data contain- ing red blocks, blue blocks and a background class. Some examples of the training set is shown in the Figure. 2.\u00a0 Given an image of the scene, we run
+ Read More<\/a><\/p>\n","protected":false},"author":147,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-334","post","type-post","status-publish","format-standard","hentry","category-cv"],"_links":{"self":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/posts\/334","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/users\/147"}],"replies":[{"embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/comments?post=334"}],"version-history":[{"count":3,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/posts\/334\/revisions"}],"predecessor-version":[{"id":343,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/posts\/334\/revisions\/343"}],"wp:attachment":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/media?parent=334"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/categories?post=334"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teamc\/wp-json\/wp\/v2\/tags?post=334"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}