Automatically　driving　based　on　computer　vision　has　attracted　more　and　more　attentions　from　both　research　and　industrial　fields.　It　has　two　main　challenges,　high　road　and　vehicle　detection　accuracy　and　real-time　performance.　To　study　the　two　problems,　we　developed　a　driving　simulation　platform　in　a　virtual　scene.　In　this　paper,　as　the　first　step　of　final　solution,　the　Extreme　Learning　Machine　(ELM)　has　been　used　to　detect　the　virtual　roads　and　vehicles.　The　Support　Vector　Machine　(SVM)　and　Back　Propagation　(BP)　network　have　been　used　as　benchmark.　Our　experimental　results　show　that　the　ELM　has　the　fastest　performance　on　road　segmentation　and　vehicle　detection　with　the　similar　accuracy　compared　with　other　techniques.　(C)　2013　Elsevier　B.V.　All　rights　reserved.