A　great　deal　of　attentions　is　currently　focused　on　multisensor　data　fusion.　A　very　important　aspect　of　it　is　track-to-track　association　and　track　fusion　in　distributed　multisensor-multitarget　environments.　The　approach　based　on　Hopfield　neural　network　has　been　developed.　But　the　performance　of　this　approach　is　limited　because　Hopfield　neural　network　is　often　trapped　in　the　local　minima.　This　paper　try　to　solve　this　problem　with　an　approach　based　on　chaotic　neural　network　(CNN).　Furthermore,　in　order　to　improve　the　performance　of　neural　network,　the　association　statistic　between　tracks　from　different　sensors　is　modified.　Computer　simulation　results　indicate　that　this　approach　is　more　efficient　than　the　algorithm　based　on　continuous　Hopfield　neural　network　(CHNN).　©2009　IEEE.