Automated　container　terminal　(ACT)　is　considered　as　port　industry　development　direction,　and　accurate　kinematic　data　(speed,　volume,　etc.)　is　essential　for　enhancing　ACT　operation　efficiency　and　safety.　Port　surveillance　videos　provide　much　useful　spatial-temporal　information　with　advantages　of　easy　obtainable,　large　spatial　coverage,　etc.　In　that　way,　it　is　of　great　importance　to　analyze　automated　guided　vehicle　(AGV)　trajectory　movement　from　port　surveillance　videos.　Motivated　by　the　newly　emerging　computer　vision　and　artificial　intelligence　(AI)　techniques,　we　propose　an　ensemble　framework　for　extracting　vehicle　speeds　from　port-like　surveillance　videos　for　the　purpose　of　analyzing　AGV　moving　trajectory.　Firstly,　the　framework　exploits　vehicle　position　in　each　image　via　a　feature-enhanced　scale-aware　descriptor.　Secondly,　we　match　vehicle　position　and　trajectory　data　from　the　previous　step　output　via　Kalman　filter　and　Hungarian　algorithm,　and　thus　we　obtain　the　vehicular　imaging　trajectory　in　a　frame-by-frame　manner.　Thirdly,　we　estimate　the　vehicular　moving　speed　in　real-world　via　the　help　of　perspective　projection　theory.　The　experimental　results　suggest　that　our　proposed　framework　can　obtain　accurate　vehicle　kinematic　data　under　typical　port　traffic　scenarios　considering　that　the　average　measurement　error　of　root　mean　square　deviation　is　0.675　km/h,　the　mean　absolute　deviation　is　0.542　km/h,　and　the　Pearson　correlation　coefficient　is　0.9349.　The　research　findings　suggest　that　cutting-edge　AI　and　computer　vision　techniques　can　accurately　extract　on-site　vehicular　trajectory　related　data　from　port　videos,　and　thus　help　port　traffic　participants　make　more　reasonable　management　decisions.