For traffic object detection in foggy environment based on convolutional neural network(CNN),data sets in fog-free environment are generally used to train the network directly.As a result,the network cannot learn the ...For traffic object detection in foggy environment based on convolutional neural network(CNN),data sets in fog-free environment are generally used to train the network directly.As a result,the network cannot learn the object characteristics in the foggy environment in the training set,and the detection effect is not good.To improve the traffic object detection in foggy environment,we propose a method of generating foggy images on fog-free images from the perspective of data set construction.First,taking the KITTI objection detection data set as an original fog-free image,we generate the depth image of the original image by using improved Monodepth unsupervised depth estimation method.Then,a geometric prior depth template is constructed to fuse the image entropy taken as weight with the depth image.After that,a foggy image is acquired from the depth image based on the atmospheric scattering model.Finally,we take two typical object-detection frameworks,that is,the two-stage object-detection Fster region-based convolutional neural network(Faster-RCNN)and the one-stage object-detection network YOLOv4,to train the original data set,the foggy data set and the mixed data set,respectively.According to the test results on RESIDE-RTTS data set in the outdoor natural foggy environment,the model under the training on the mixed data set shows the best effect.The mean average precision(mAP)values are increased by 5.6%and by 5.0%under the YOLOv4 model and the Faster-RCNN network,respectively.It is proved that the proposed method can effectively improve object identification ability foggy environment.展开更多
There is a CAD （computer-aided design） data exchange format named SXF （scadec exchange format） in the field of Japanese public works which was developed by a consortium in 1999 to be based on the ISO 10303-202, so...There is a CAD （computer-aided design） data exchange format named SXF （scadec exchange format） in the field of Japanese public works which was developed by a consortium in 1999 to be based on the ISO 10303-202, so that the MLIT （Ministry of Land, Infi＇astructure, Transportation and Tourism） could start e-delivery （e-submit） of CAD drawings. It is one of targets for CALS/EC （continuous acquisition and lifecycle support/electric commerce） program which MLIT are promoting since 1999. Most of local governments have followed the MLIT to start e-delivery, so that SXF has become to be a standard in the public works in Japan with many problems. SXF is an exchange format and so many design companies or contractors would submit the CAD drawings with transferred format before the delivery of e-submit even if they use usually another CAD in their offices. This paper will introduce the standard of CAD exchange format SXF through the activities of Japanese public works.展开更多
文摘For traffic object detection in foggy environment based on convolutional neural network(CNN),data sets in fog-free environment are generally used to train the network directly.As a result,the network cannot learn the object characteristics in the foggy environment in the training set,and the detection effect is not good.To improve the traffic object detection in foggy environment,we propose a method of generating foggy images on fog-free images from the perspective of data set construction.First,taking the KITTI objection detection data set as an original fog-free image,we generate the depth image of the original image by using improved Monodepth unsupervised depth estimation method.Then,a geometric prior depth template is constructed to fuse the image entropy taken as weight with the depth image.After that,a foggy image is acquired from the depth image based on the atmospheric scattering model.Finally,we take two typical object-detection frameworks,that is,the two-stage object-detection Fster region-based convolutional neural network(Faster-RCNN)and the one-stage object-detection network YOLOv4,to train the original data set,the foggy data set and the mixed data set,respectively.According to the test results on RESIDE-RTTS data set in the outdoor natural foggy environment,the model under the training on the mixed data set shows the best effect.The mean average precision(mAP)values are increased by 5.6%and by 5.0%under the YOLOv4 model and the Faster-RCNN network,respectively.It is proved that the proposed method can effectively improve object identification ability foggy environment.
文摘There is a CAD （computer-aided design） data exchange format named SXF （scadec exchange format） in the field of Japanese public works which was developed by a consortium in 1999 to be based on the ISO 10303-202, so that the MLIT （Ministry of Land, Infi＇astructure, Transportation and Tourism） could start e-delivery （e-submit） of CAD drawings. It is one of targets for CALS/EC （continuous acquisition and lifecycle support/electric commerce） program which MLIT are promoting since 1999. Most of local governments have followed the MLIT to start e-delivery, so that SXF has become to be a standard in the public works in Japan with many problems. SXF is an exchange format and so many design companies or contractors would submit the CAD drawings with transferred format before the delivery of e-submit even if they use usually another CAD in their offices. This paper will introduce the standard of CAD exchange format SXF through the activities of Japanese public works.
