{"id":53,"date":"2022-01-11T12:30:03","date_gmt":"2022-01-11T11:30:03","guid":{"rendered":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/?page_id=53"},"modified":"2022-01-24T16:37:11","modified_gmt":"2022-01-24T15:37:11","slug":"ai","status":"publish","type":"page","link":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/ai\/","title":{"rendered":"AI"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"53\" class=\"elementor elementor-53\" data-elementor-settings=\"[]\">\n\t\t\t\t\t\t\t<div class=\"elementor-section-wrap\">\n\t\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-0587a52 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"0587a52\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-4864613\" data-id=\"4864613\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-a8fb3fb elementor-widget elementor-widget-spacer\" data-id=\"a8fb3fb\" data-element_type=\"widget\" data-widget_type=\"spacer.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-spacer\">\n\t\t\t<div class=\"elementor-spacer-inner\"><\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-954ee04 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"954ee04\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-d8665ca\" data-id=\"d8665ca\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-001c568 elementor-widget elementor-widget-heading\" data-id=\"001c568\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.5.3 - 28-12-2021 *\/\n.elementor-heading-title{padding:0;margin:0;line-height:1}.elementor-widget-heading .elementor-heading-title[class*=elementor-size-]>a{color:inherit;font-size:inherit;line-height:inherit}.elementor-widget-heading .elementor-heading-title.elementor-size-small{font-size:15px}.elementor-widget-heading .elementor-heading-title.elementor-size-medium{font-size:19px}.elementor-widget-heading .elementor-heading-title.elementor-size-large{font-size:29px}.elementor-widget-heading .elementor-heading-title.elementor-size-xl{font-size:39px}.elementor-widget-heading .elementor-heading-title.elementor-size-xxl{font-size:59px}<\/style><h2 class=\"elementor-heading-title elementor-size-default\">Task of  AI<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-890ca1c elementor-widget elementor-widget-text-editor\" data-id=\"890ca1c\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.5.3 - 28-12-2021 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#818a91;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#818a91;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t<p>The task of the AI is the detection of the lane by processing an image as shown in the figure below.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0c03b2a elementor-widget elementor-widget-image\" data-id=\"0c03b2a\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.5.3 - 28-12-2021 *\/\n.elementor-widget-image{text-align:center}.elementor-widget-image a{display:inline-block}.elementor-widget-image a img[src$=\".svg\"]{width:48px}.elementor-widget-image img{vertical-align:middle;display:inline-block}<\/style>\t\t\t\t\t\t\t\t\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"237\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/road_prediction-e1643017470836-1024x237.png\" class=\"attachment-large size-large\" alt=\"\" srcset=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/road_prediction-e1643017470836-1024x237.png 1024w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/road_prediction-e1643017470836-300x70.png 300w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/road_prediction-e1643017470836-768x178.png 768w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/road_prediction-e1643017470836-1536x356.png 1536w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/road_prediction-e1643017470836-2048x475.png 2048w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1351ea6 elementor-widget elementor-widget-text-editor\" data-id=\"1351ea6\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p style=\"text-align: center;\">The AI predicting the lane.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-cb844bb elementor-widget elementor-widget-heading\" data-id=\"cb844bb\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Architecture<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-835a9d8 elementor-widget elementor-widget-text-editor\" data-id=\"835a9d8\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>There is one type of AI that performs best in object recognition on images, the convolutional neural network (CNN). Since we have an image as input and want an image as output, our network has an encoder with convolution and max-pooling layers and an decoder with deconvolution and upsampling layers. The figure below shows the architecture of the network. On the left side the encoder, and on the right side the decoder.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-bce9242 elementor-widget elementor-widget-image\" data-id=\"bce9242\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"183\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/CNN_struc_legend-1024x183.png\" class=\"attachment-large size-large\" alt=\"\" srcset=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/CNN_struc_legend-1024x183.png 1024w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/CNN_struc_legend-300x54.png 300w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/CNN_struc_legend-768x137.png 768w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/CNN_struc_legend-1536x274.png 1536w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/CNN_struc_legend-2048x365.png 2048w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b2a49d2 elementor-widget elementor-widget-text-editor\" data-id=\"b2a49d2\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p style=\"text-align: center;\">CNN architecture<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8b62f60 elementor-widget elementor-widget-heading\" data-id=\"8b62f60\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Convolution<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8f79bc4 elementor-widget elementor-widget-text-editor\" data-id=\"8f79bc4\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Since convolution is the main part of a CNN, lets take a look on how it works. The figure below shows the input image with size 16&#215;8 on the left side. Applying the kernel size 3&#215;3 (in the middle of the figure) on each pixel of the input image, the output with size 14&#215;6 results (right side of the figure). In this context &#8216;applying&#8217; means: Placing the kernel on the input image in the left upper corner, then multiplying each image pixel with the overlying kernel pixel, adding them up and storing them in the output image. Then move the kernel one pixel and repeat the process until the whole image is filtered.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-043f741 elementor-widget elementor-widget-image\" data-id=\"043f741\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"246\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/Conv_BSP-1024x246.png\" class=\"attachment-large size-large\" alt=\"\" srcset=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/Conv_BSP-1024x246.png 1024w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/Conv_BSP-300x72.png 300w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/Conv_BSP-768x184.png 768w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/Conv_BSP-1536x369.png 1536w, https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/Conv_BSP.png 1820w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-524d496 elementor-widget elementor-widget-text-editor\" data-id=\"524d496\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p style=\"text-align: center;\">Applying a left upper to right lower diagonal kernel on an image (left: input, middle: kernel, right: output).<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-33cb67f elementor-widget elementor-widget-heading\" data-id=\"33cb67f\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Feature Maps<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-e7f2d2a elementor-widget elementor-widget-text-editor\" data-id=\"e7f2d2a\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>The figure below gives an insight into how the CNN works. Each block shows the feature maps (the output) of a layer.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ee619f3 elementor-arrows-position-inside elementor-pagination-position-outside elementor-widget elementor-widget-image-carousel\" data-id=\"ee619f3\" data-element_type=\"widget\" data-settings=\"{&quot;image_spacing_custom&quot;:{&quot;unit&quot;:&quot;px&quot;,&quot;size&quot;:60,&quot;sizes&quot;:[]},&quot;navigation&quot;:&quot;both&quot;,&quot;autoplay&quot;:&quot;yes&quot;,&quot;pause_on_hover&quot;:&quot;yes&quot;,&quot;pause_on_interaction&quot;:&quot;yes&quot;,&quot;autoplay_speed&quot;:5000,&quot;infinite&quot;:&quot;yes&quot;,&quot;speed&quot;:500}\" data-widget_type=\"image-carousel.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.5.3 - 28-12-2021 *\/\n.elementor-widget-image-carousel .swiper-container{position:static}.elementor-widget-image-carousel .swiper-container .swiper-slide figure{line-height:inherit}.elementor-widget-image-carousel .swiper-slide{text-align:center}.elementor-image-carousel-wrapper:not(.swiper-container-initialized) .swiper-slide{max-width:calc(100% \/ var(--e-image-carousel-slides-to-show, 3))}<\/style>\t\t<div class=\"elementor-image-carousel-wrapper swiper-container\" dir=\"ltr\">\n\t\t\t<div class=\"elementor-image-carousel swiper-wrapper\">\n\t\t\t\t\t\t\t\t<div class=\"swiper-slide\"><figure class=\"swiper-slide-inner\"><img decoding=\"async\" class=\"swiper-slide-image\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/input.png\" alt=\"input\" \/><figcaption class=\"elementor-image-carousel-caption\">input<\/figcaption><\/figure><\/div><div class=\"swiper-slide\"><figure class=\"swiper-slide-inner\"><img decoding=\"async\" class=\"swiper-slide-image\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/conv1.png\" alt=\"feature maps after first convolution\" \/><figcaption class=\"elementor-image-carousel-caption\">feature maps after first convolution<\/figcaption><\/figure><\/div><div class=\"swiper-slide\"><figure class=\"swiper-slide-inner\"><img decoding=\"async\" class=\"swiper-slide-image\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/conv2.png\" alt=\"feature maps after second convolution\" \/><figcaption class=\"elementor-image-carousel-caption\">feature maps after second convolution<\/figcaption><\/figure><\/div><div class=\"swiper-slide\"><figure class=\"swiper-slide-inner\"><img decoding=\"async\" class=\"swiper-slide-image\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/conv3.png\" alt=\"feature maps after third convolution\" \/><figcaption class=\"elementor-image-carousel-caption\">feature maps after third convolution<\/figcaption><\/figure><\/div><div class=\"swiper-slide\"><figure class=\"swiper-slide-inner\"><img decoding=\"async\" class=\"swiper-slide-image\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/upsample2.png\" alt=\"feature maps after second upsampling\" \/><figcaption class=\"elementor-image-carousel-caption\">feature maps after second upsampling<\/figcaption><\/figure><\/div><div class=\"swiper-slide\"><figure class=\"swiper-slide-inner\"><img decoding=\"async\" class=\"swiper-slide-image\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/deconv5.png\" alt=\"feature maps after fourth deconvolution\" \/><figcaption class=\"elementor-image-carousel-caption\">feature maps after fourth deconvolution<\/figcaption><\/figure><\/div><div class=\"swiper-slide\"><figure class=\"swiper-slide-inner\"><img decoding=\"async\" class=\"swiper-slide-image\" src=\"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-content\/uploads\/2022\/01\/output.png\" alt=\"output\" \/><figcaption class=\"elementor-image-carousel-caption\">output<\/figcaption><\/figure><\/div>\t\t\t<\/div>\n\t\t\t\t\t\t\t\t\t\t\t\t<div class=\"swiper-pagination\"><\/div>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<div class=\"elementor-swiper-button elementor-swiper-button-prev\">\n\t\t\t\t\t\t<i aria-hidden=\"true\" class=\"eicon-chevron-left\"><\/i>\t\t\t\t\t\t<span class=\"elementor-screen-only\">Previous<\/span>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t<div class=\"elementor-swiper-button elementor-swiper-button-next\">\n\t\t\t\t\t\t<i aria-hidden=\"true\" class=\"eicon-chevron-right\"><\/i>\t\t\t\t\t\t<span class=\"elementor-screen-only\">Next<\/span>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-adacc7f elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"adacc7f\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-d48b51f\" data-id=\"d48b51f\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-2686808 elementor-widget elementor-widget-text-editor\" data-id=\"2686808\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>The input and output images have size 40&#215;20 pixel. The reason for such a low resolution is to save computing power. By applying a convolution each pixel needs at least one arithmetic operation.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2f84103 elementor-widget elementor-widget-heading\" data-id=\"2f84103\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Fixed-Point Model<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-3af8469 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"3af8469\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-8436aa9\" data-id=\"8436aa9\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-fa24f80 elementor-widget elementor-widget-text-editor\" data-id=\"fa24f80\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>For later use in the FPGA the trained floating-point model of the CNN was converted to a 1.15 fixed-point model. For conversion a Matlab script was implemented, which reads in a H5-file, reorders the weights and biases for better indexing while processing, converts them to fixed-point and writes them to a binary file.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Task of AI The task of the AI is the detection of the lane by processing an image as shown in the figure below. The AI predicting the lane. Architecture There is one type of AI that performs best in object recognition on images, the convolutional neural network (CNN). Since we have an image as [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-53","page","type-page","status-publish","hentry","entry"],"_links":{"self":[{"href":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-json\/wp\/v2\/pages\/53","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-json\/wp\/v2\/comments?post=53"}],"version-history":[{"count":93,"href":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-json\/wp\/v2\/pages\/53\/revisions"}],"predecessor-version":[{"id":529,"href":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-json\/wp\/v2\/pages\/53\/revisions\/529"}],"wp:attachment":[{"href":"https:\/\/carvision.projekte.fh-hagenberg.at\/wordpress\/wp-json\/wp\/v2\/media?parent=53"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}