摘要
针对自然场景下鸟类检测任务中存在模型参数量大、计算量高和正负样本严重不平衡的问题,提出了YOLOBIRDS算法。一方面,对特征提取网络模型进行修改,将标准卷积神经网络结构修改为深度可分离残差模型。另一方面,对损失函数进行修改,将目标框大小与位置损失函数由均方误差修改为广义交并比(CIoU),在置信度损失函数中增加正负样本控制参数。实验结果表明,在衡水湖鸟类数据集中,YOLOBIRDS算法的平均精度均值(mAP)达87.12%,比原算法高2.71个百分点;参数个数达12425917,比原算法低79.88%;速度达32.67 frame/s,比原算法高19.98%。采用该算法训练得到的新模型对鸟类检测的精度更高,检测速度更快,对鸟类检测的整体识别率大幅度提高,平衡了正负样本的损失权重。
This study proposes the YOLOBIRDS algorithm to solve the challenges of several model parameters,high amount of calculation,and a considerable imbalance of positive and negative samples in bird detection tasks in natural scenes.The feature extraction network model was modified,and the standard convolution neural network structure was modified to the depthwise separable residual model.Additionally,the loss function was modified,and the object box size and position loss function were modified from mean square error to generalized intersection over union(CIoU).The confidence loss function includes the positive and negative sample control parameters.The experimental results show that in the Hengshui Lake bird dataset,the mean average precision(mAP)of the YOLOBIRDS algorithm reaches 87.12%,which is 2.71 percentage points higher than that of the original algorithm.Moreover,number of parameters reaches 12425917,which is 79.88%lower than that of the original algorithm.Finally,the speed reaches 32.67 frame/s,which is 19.98%higher than that of the original algorithm.The new model trained by the proposed algorithm has higher accuracy and faster detection speed,which greatly improves the overall recognition rate of bird detection and balances the loss weight of positive and negative samples.
作者
宋子盈
杨奎河
张宇
Song Ziying;Yang Kuihe;Zhang Yu(School of Computer and Information Technology,Beijing Jiaotong University,Beijing 100044,China;School of Information Science and Engineering,Hebei University of Science and Technology,Shijiazhuang 050018,Hebei,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2022年第18期329-336,共8页
Laser & Optoelectronics Progress
基金
中国留学基金委地方合作项目(201808130283)
中国教育部人工智能协同育人项目(201801003011)
河北科技大学校立课题(82/1182108)。
关键词
目标检测
深度可分离残差模型
广义交并比损失函数
YOLOv3算法
object detection
depthwise separable residual model
generalized intersection over union loss function
YOLOv3 algorithm
