基于深度學(xué)習(xí)的動(dòng)態(tài)手勢(shì)檢測(cè)與識(shí)別算法研究
打開(kāi)文本圖片集
中圖分類(lèi)號(hào)：TP391.4 文獻(xiàn)標(biāo)識(shí)碼：A 文章編號(hào)：2096-4706（2025）08-0054-07
Abstract： Gesture recognition is of great significance torealize human-computer interaction.In order torealize highprecisiontarget detection and recognition under dynamicconditions，this paper is based on YOLOv5 target detection firstly and determines the coordinate informationof the target gesture byusing thefeature pyramid structureand multi-scale fusion structuralfeaturesinsidethealgorithm.ThenitusestheMediaPipemodeltodetectthekeypointsofthehand，deterinesthe vectorangleofthehand joints，andanalyzes thefingerbendingsituation，soas tojudge the specific gesture.Using themethods of positiondeterminationand implementationbyusingseparate models foractionclasficationeffectivelyimproves the problem that thereduced recognitionrateof gesturescaused byfactors suchasrotationandoccusionin dynamicconditions.The training samplesare selected fromsixcategories intheopen-source gesturedataset HaGRID.Theexperimentaltestresults demostrate that the mean value of one-hand recognition detection accuracy of the combined algorithm is up to and the detection speed is up to 40 FPS，and the model size is 88.5 MB.
Keywords： gesture recognition; YOLOv5;MediaPipe; hand joint point detection; gesture dataset
0 引言
人機(jī)交互是指人與計(jì)算機(jī)之間通過(guò)某種特殊方式實(shí)現(xiàn)信息交換的過(guò)程，傳統(tǒng)人機(jī)交互采用穿戴傳感器的方式，由于傳感器的感知范圍有限且信號(hào)不具有普適性的問(wèn)題，無(wú)法滿足人們?nèi)粘Ｉ畹膶?shí)際要求。（剩余5938字）