Large　and　complex　buildings　built　in　China　in　recent　years,　such　as　Olympic　venues,　airports,　and　large　hospitals,　have　brought　new　lire　evacuation　problems.　Many　designs　are　using　Internet　of　Things　(IoT)　technology　to　enhance　buildings＇　perception　of　flames　and　smoke.　In　this　paper,　in　addition　to　using　IoT　to　improve　the　fire-awareness　of　buildings,　a　set　of　algorithms　based　on　the　Dijkstra＇s　shortest　path　method　is　designed　to　operate　on　the　local　FPGA　computing　terminal　to　determine　the　current　optimal　evacuation　path.　An　IoT　system　with　an　evacuation　lighting　system　provides　an　optimal　route　indication　for　people　in　the　building.　Flame　image　recognition,　smoke　alarms　and　shortest　path　calculations　are　analyzed　by　the　FPGA　processor　and　all　evacuation　paths　are　updated　every　10　seconds.　The　indicator　system　is　implemented　in　the　emergency　lights,　using　LoRa　low-power　wireless　communication,　can　update　all　emergency　lights　within　5　seconds,　giving　a　new　emergency　route.　The　system　was　tested　in　the　office　building　of　Beijing　University　of　Technology,　which　can　effectively　indicate　the　path　under　different　fire　conditions.