基于Faster R-CNN的仓库视频监控目标检测方法研究
|
摘要
针对目前电力仓库视频监控图像中目标检测算法对小目标物体、部分遮挡及尺寸大小不一存在检测难度大、漏检、错检等问题,提出基于Faster R-CNN的仓库视频监控目标检测方法,实现电力仓库视频监控中目标分类与识别及仓库智能化监控,保护仓库安全。实验结果表明,该方法提高了目标识别的准确度(m AP),减少了目标物体识别时间。
Aiming at the problems of difficult detection,missed detection and wrong detection of small target objects,partial occlusion and different sizes in video surveillance image of power warehouse,an object detection method based on Faster R-CNN for video monitoring of power warehouse is proposed,which realizes object classification and recognition in video monitoring of power warehouse video surveillance and intellectualized warehouse monitoring and protects warehouse security. The experimental results show that the method improves the accuracy of object recognition( m AP) and reduces the object recognition time.
Aiming at the problems of difficult detection,missed detection and wrong detection of small target objects,partial occlusion and different sizes in video surveillance image of power warehouse,an object detection method based on Faster R-CNN for video monitoring of power warehouse is proposed,which realizes object classification and recognition in video monitoring of power warehouse video surveillance and intellectualized warehouse monitoring and protects warehouse security. The experimental results show that the method improves the accuracy of object recognition( m AP) and reduces the object recognition time.
引文
[1]Huang J,Rathod V,Sun C.Speed/accuracy trade-offs for modern convolutional object detectors[C].2017 IEEE Conference on Computer Vision and Pattern Recognition,USA,2017:3296-3297.
[2]Girshick R,Donahue J,Darrell T,et al.Region-based convolutional networks for accurate object detection and segmentation[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2016,38(1):142-158.
[3]He K,Zhang X,Ren S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[4]伍伟明.基于Faster R-CNN的目标检测算法的研究[D].广州:华南理工大学,2018.
[5]Ren S,He Kai-ming,Girshick R.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(6):1137-1149.
[6]蒋胜,黄敏,朱启兵.基于R-FCN的行人检测方法研究[J].计算机工程与应用,2018,54(18):180-183.
[7]He K,Gkioxari G,Dollar P.Mask R-CNN[C].2017 IEEE International Conference on Computer Vision(ICCV),Venice,2017:2980-2988.
[8]肖永菲,郁钟铭,杨玉成.融合Faster R-CNN与Res Net的室外停车场空车位检测[J].福建电脑,2018,34(12):32-37.
[9]胡正委.基于深度学习的超市商品图像识别方法研究[D].合肥:中国科学技术大学,2018.
[10]郭毓,苏鹏飞,吴益飞.基于Faster R-CNN的机器人目标检测及空间定位[J].华中科技大学学报,2018,46(12):55-59.
[11]韩凯,张红英,王远.一种基于Faster R-CNN的车辆检测算法[J].西南科技大学学报:自然科学版,2017,32(4):65-70.
[12]Redmon J,Divvala S,Uirshic’k R.You only look once;unified,real-time object detection[C].2016 IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas,2016:779-788.
[13]冉鹏,王灵,李昕,等.改进Softmax分类器的深度卷积神经网络及其在人脸识别中的应用[J].上海大学学报:自然科学版,2018,24(3):352-366.
[14]Kawano Y,Yanai K.Foodcam:a real-time food recognition system on a smartphone[J].Multimedia Tools and Applications,2015,74(14):5263-5287.
[15]Xu R,Herranz L,Jianu S.Geolocalized modeling for dish recognitionn[J].IEEE Transactions on Multimedia,2015,17(8):1187-1199.
[16]Szegedy C,Liu W,Jia Y.Going deeper with convolutions[C].IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas,2015:1-9.
[2]Girshick R,Donahue J,Darrell T,et al.Region-based convolutional networks for accurate object detection and segmentation[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2016,38(1):142-158.
[3]He K,Zhang X,Ren S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[4]伍伟明.基于Faster R-CNN的目标检测算法的研究[D].广州:华南理工大学,2018.
[5]Ren S,He Kai-ming,Girshick R.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(6):1137-1149.
[6]蒋胜,黄敏,朱启兵.基于R-FCN的行人检测方法研究[J].计算机工程与应用,2018,54(18):180-183.
[7]He K,Gkioxari G,Dollar P.Mask R-CNN[C].2017 IEEE International Conference on Computer Vision(ICCV),Venice,2017:2980-2988.
[8]肖永菲,郁钟铭,杨玉成.融合Faster R-CNN与Res Net的室外停车场空车位检测[J].福建电脑,2018,34(12):32-37.
[9]胡正委.基于深度学习的超市商品图像识别方法研究[D].合肥:中国科学技术大学,2018.
[10]郭毓,苏鹏飞,吴益飞.基于Faster R-CNN的机器人目标检测及空间定位[J].华中科技大学学报,2018,46(12):55-59.
[11]韩凯,张红英,王远.一种基于Faster R-CNN的车辆检测算法[J].西南科技大学学报:自然科学版,2017,32(4):65-70.
[12]Redmon J,Divvala S,Uirshic’k R.You only look once;unified,real-time object detection[C].2016 IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas,2016:779-788.
[13]冉鹏,王灵,李昕,等.改进Softmax分类器的深度卷积神经网络及其在人脸识别中的应用[J].上海大学学报:自然科学版,2018,24(3):352-366.
[14]Kawano Y,Yanai K.Foodcam:a real-time food recognition system on a smartphone[J].Multimedia Tools and Applications,2015,74(14):5263-5287.
[15]Xu R,Herranz L,Jianu S.Geolocalized modeling for dish recognitionn[J].IEEE Transactions on Multimedia,2015,17(8):1187-1199.
[16]Szegedy C,Liu W,Jia Y.Going deeper with convolutions[C].IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas,2015:1-9.