Image　denoising　is　an　important　step　in　image　processing　of　pools　intelligent　life-saving　system,　adaptive　denoising　algorithms　has　based　on　wavelet　in　this　paper.　Firstly,　the　threshold　value　selection　was　discussed　and　then　the　effect　of　threshold　functions　on　denoising　result　was　evaluated.　Finally,　an　improved　adaptive　nonlinear　threshold　function　was　put　forward.　Simulation　results　showing　that　the　adaptive　denoising　algorithm　designed　in　this　paper　can　achieve　higher　PSNR　value,　and　time　cost　can　be　satisfy　the　real-time　demand　of　pool　intelligent　life-saving　system　simultaneously.