Traffic　signs　are　one　of　the　main　carriers　of　road　information,　the　reflectivity　of　traffic　signs　at　night　directly　affects　the　driver＇s　access　to　road　information.　Fast　and　accurate　traffic　sign　reflectivity　detection　method　is　conducive　to　the　efficient　operation　of　road　maintenance　operations　to　protect　the　lives　of　motorists.　This　paper　proposed　a　novel　method　for　detecting　the　reflectivity　of　traffic　signs,　which　proposed　the　concept　of　sign’s　luminance　value.　By　collecting　photos　of　traffic　signs　on　the　road　at　night　through　the　detection　vehicle,　using　Yolov4　algorithm　and　Deeplabv3　algorithm　for　sign　target　detection　and　image　segmentation　respectively,　then　the　signs　were　converted　into　grayscale　images　after　grayscale　processing,　and　the　difference　between　the　grayscale　value　of　the　sign　and　its　background　was　calculated　to　obtain　the　luminance　value　of　the　sign,　and　the　luminance　value　was　used　to　represent　the　reflective　performance　of　the　sign.　This　method　was　used　to　conduct　the　actual　test　experiment　of　road　traffic　sign　reflectivity,　and　compared　with　the　sign　reflectivity　results　obtained　by　the　traditional　retroreflective　coefficient　detection　method.　Through　data　analysis,　it　was　found　that　the　test　results　of　this　method　have　significant　correlation　with　the　test　results　of　the　traditional　method.　The　traffic　sign　reflectivity　detection　method　proposed　in　this　paper　obtains　more　accurate　detection　results　and　avoids　the　disadvantages　of　the　traditional　retroreflective　coefficient　detection　method,　such　as　complicated　operation,　high　instrument　requirements,　low　detection　efficiency,　and　failure　to　consider　the　impact　of　the　actual　installation　position　of　the　sign　on　the　driver＇s　visual　recognition,　and　is　more　suitable　for　engineering　practice.　©　2023　SPIE.