Monocular　depth　estimation　relied　on　RGB　images　is　an　important　ill　posed　problem　in　ithe　system　of　computer　vision.　Recently,　people　use　the　method　of　deep　learning　to　discuss　this　problem　Most　of　the　existing　monocular　depth　estimation　algorithms　relied　on　convolution　neural　network.　Depth　estimation　based　on　2D　images　has　important　applications　in　image　segmentation,　3D　object　detection,　robot　navigation,　object　tracking　and　autonomous　driving.　This　paper　gives　a　brief　overview　of　this　problem,　reviews,　evaluates　and　discusses　the　monocular　depth　estimation　algorithms　relied　on　deep　learning,　and　looks　forward　to　the　direction　of　further　research　in　the　face　of　some　challenges.　©　2020　IEEE.