Images/videos　captured　in　low-light　conditions　often　present　low　luminance　and　contrast.　Although　the　existing　algorithms　can　improve　the　subjective　perception,　color　distortion　and　over-enhancement　usually　appear,　which　will　disturb　the　subsequent　intelligent　analysis.　Otherwise,　due　to　high　computational　complexity,　the　existing　algorithms　are　difficult　to　process　a　high　resolution　(HR)　video　(1280×720)　in　real-time.　Therefore,　a　real-time　low-light　enhancement　algorithm　for　intelligent　analysis　is　proposed　in　this　paper.　Firstly,　an　enhancement　model　is　established　in　RGB　color　space.　Then,　to　judge　the　influence　of　light　intensity,　images　of　ColorChecker　color　chart　are　captured　under　a　series　of　light　conditions.　Finally,　the　enhancement　factor　in　the　proposed　model　is　evaluated　by　the　captured　images.　Experimental　results　demonstrate　that　the　proposed　algorithm　can　significantly　improve　the　performance　of　vehicle　license　plate　localization　and　skin　color　detection　compared　to　the　existing　algorithms.　Furthermore,　the　proposed　algorithm　can　process　the　HR　videos　at　the　speed　of28.3fps　on　average.　©　2016　SPIE.