<tt id="602a2"><acronym id="602a2"></acronym></tt>
<acronym id="602a2"><center id="602a2"></center></acronym>
  Quick Search:       Advanced Search
SUI Bingdong,ZHANG Pai,WANG Xiaojun.A gesture recognition algorithm based on improved YOLOv3[J].Journal of Hebei University of Science and Technology,2021,42(1):22-29
一種改進YOLOv3的手勢識別算法
A gesture recognition algorithm based on improved YOLOv3
Received:September 28, 2020  Revised:October 16, 2020
DOI:10.7535/hbkd.2021yx01004
中文關鍵詞:  計算機神經網絡  YOLOv3  目標檢測  手勢識別  DIoU  Focal損失函數
英文關鍵詞:computer neural network  YOLOv3  object detection  gesture recognition  DIoU  Focal loss function
基金項目:國防科技重點實驗室項目(6142205190401)
Author NameAffiliationE-mail
SUI Bingdong School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 410032349@qq.com 
ZHANG Pai School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang  
WANG Xiaojun School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang  
Hits: 10422
Download times: 10012
中文摘要:
      為了解決YOLOv3算法在手勢識別中存在識別精度低及易受光照條件影響的問題,提出了一種改進的YOLOv3手勢識別算法。首先,在原來3個檢測尺度上新增加1個更小的檢測尺度,提高對小目標的檢測能力;其次,以DIoU代替原來的均方差損失函數作為坐標誤差損失函數,用改進后的Focal損失函數作為邊界框置信度損失函數,目標分類損失函數以交叉熵作為損失函數。結果表明,將改進的YOLOv3手勢識別算法用于手勢檢測中,mAP指標達到90.38%,較改進前提升了6.62%,FPS也提升了近2倍。采用改進的YOLOv3方法訓練得到的新模型,識別手勢精度更高,檢測速度更快,整體識別效率大幅提升,平衡了簡單樣本和困難樣本的損失權重,有效提高了模型的訓練質量和泛化能力。
英文摘要:
      In order to solve the problems of low recognition accuracy and easily affected by illumination conditions in the gesture recognition, an improved YOLOv3 gesture recognition algorithm was proposed. Firstly, a smaller detection scale was added to the original three detection scales to improve the detection ability of small targets; secondly, DIoU was used instead of the original mean square error loss function as the coordinate error loss function, the improved focal loss function was used as the confidence loss function of the boundary frame, and the cross entropy was used as the loss function of the target classification loss function. The results show that when the improved YOLOv3 gesture recognition algorithm is applied to gesture detection, the map index reaches 90.38%, which is 6.62% higher than that before the improvement, and FPS is nearly twice as high as before. After the new model is trained by the improved YOLOv3 method, the gesture recognition accuracy is higher, the detection speed is faster, the overall recognition efficiency is greatly improved, the loss weights of simple samples and difficult samples are balanced, and the training quality and generalization ability of the model are effectively improved.
View Full Text  View/Add Comment  Download reader
Close
彩票时时乐