Measurement　data　sometimes　contain　a　few　outliers　that　have　a　large　deviation　from　the　actual　value.　For　such　data,　the　reconstruction　results　will　be　greatly　distorted　around　the　outliers.　To　solve　this　problem,　a　robust　surface　approximation　method　based　on　moving　total　least　squares　(MTLSs)　is　presented　in　this　article,　in　which　an　improved　random　sample　consensus　(RANSAC)　and　classification　and　regression　tree　(CART)　are　introduced　into　the　support　domain　to　detect　outliers.　First,　the　residuals　of　points　in　the　support　domain　are　calculated　by　the　improved　RANSAC　with　an　introduced　parameter,　and　then,　the　abnormal　residuals　are　identified　by　the　CART　algorithm.　The　points　corresponding　to　abnormal　residuals　are　considered　as　abnormal　points.　After　the　abnormal　points　are　eliminated,　the　remaining　data　are　processed　by　weighted　total　least　squares　(WTLSs)　to　obtain　local　fitting　parameters.　This　method　can　avoid　the　adverse　impact　of　human　intervention　and　over　elimination.　The　reconstruction　results　of　the　numerical　simulation　and　measurement　experiment　illustrate　the　effectiveness　of　our　method.