Aiming　at　the　problem　that　the　small　target　size　is　small　and　the　feature　extraction　is　difficult,　which　leads　to　the　poor　detection　effect　of　small　target,　this　paper　proposes　a　target　detection　algorithm　based　on　the　fusion　of　spatial　information.　Firstly,　this　paper　takes　the　single-stage　target　detection　algorithm　yolov5　as　the　basic　model,　and　adds　a　spatial　information　detection　network　module　to　solve　the　problem　that　the　features　of　small　targets　are　gradually　reduced　or　completely　lost　in　down-sample,　so　as　to　retain　more　spatial　information　in　the　low-level　network.　Secondly,　in　the　feature　fusion　part,　multiscale　feature　fusion　module　is　used　to　fuse　high-level　semantic　information　and　low-level　spatial　information,　so　as　to　locate　small　targets　more　accurately.　Finally,　the　fusion　features　are　used　for　the　detection　task　to　improve　the　accuracy　of　small　target　detection.　The　experimental　results　show　that　the　Mean　Average　Precision　(mAP)　value　detected　on　the　COCO　test　set　reaches　42%,　which　proves　the　effectiveness　of　the　algorithm　for　small　target　detection.　　©　2022　IEEE.