As　an　advanced　video　compression　standard,　H.264/AVC　has　been　applied　to　various　fields　such　as　video　surveillance,　video　conference,　and　wireless　video　communication.　This　paper　presents　a　novel　scene　cut　detection　method　in　H.264/AVC　baseline　profile　compression　domain,　which　takes　advantage　of　the　available　features　from　H.264/AVC　bitstreams,　including　chroma　prediction　modes,　motion　vectors,　macroblock　types,　and　so　on.　Moreover,　in　this　method,　four　new　criterions　used　for　scene　cut　detection　have　been　proposed,　i.e.　the　distribution　difference　of　chroma　prediction　modes,　the　distribution　difference　of　macroblock　types,　the　accumulative　motion　amount,　and　the　difference　of　motion　vector　angles.　The　thresholds　of　the　criterions　are　mainly　determined　by　the　minimum　error　Bayesian　decision.　Experimental　results　show　that　the　proposed　method　can　detect　the　scene　cuts　at　I-frames　and　P-frames　correctly　without　the　information　of　bi-directional　prediction　which　is　not　available　in　H.264/AVC　baseline　profile.