According　to　analyze　vision　system　of　hazard　cameras　for　lunar　rover　BH2　and　characteristics　of　working　environment,　firstly,　the　dense　disparity　map　is　generated　by　photometric　consistency　dense　matching;　Secondly,　environmental　noise　is　filtered　out　by　morphology　filtering;　Finally,　the　paper　can　obtain　reliable　dense　disparity　map.　Furthermore,　the　paper　uses　three　sets　of　experiment　results　on　the　disparity　map　for　lunar　rover　BH2　to　validate　the　algorithm.　The　experimental　results　show　that　the　disparity　map　extraction　algorithm　possesses　the　features　with　less　calculation　amount,　high　reliability,　robustness　of　illumination　change　and　environmental　noise,　which　can　achieve　dense　reliable　disparity　map　and　meet　the　avoid　obstacle　requirement　of　BH2.