Road accident detection plays an important role in abnormal scene reconstruction for Intelligent Transportation Systems and abnormal events warning for autonomous driving.This paper presents a novel 3D object detector...Road accident detection plays an important role in abnormal scene reconstruction for Intelligent Transportation Systems and abnormal events warning for autonomous driving.This paper presents a novel 3D object detector and adaptive space partitioning algorithm to infer traffic accidents quantitatively.Using 2D region proposals in an RGB image,this method generates deformable frustums based on point cloud for each 2D region proposal and then frustum-wisely extracts features based on the farthest point sampling network(FPS-Net)and feature extraction network(FE-Net).Subsequently,the encoder-decoder network(ED-Net)implements 3D-oriented bounding box(OBB)regression.Meanwhile,the adaptive least square regression(ALSR)method is proposed to split 3D OBB.Finally,the reduced OBB intersection test is carried out to detect traffic accidents via separating surface theorem(SST).In the experiments of KITTI benchmark,our proposed 3D object detector outperforms other state-of-theartmethods.Meanwhile,collision detection algorithm achieves the satisfactory performance of 91.8%accuracy on our SHTA dataset.展开更多
Accident detection plays a critical role in improving traffic safety by enabling timely emergency response and reducing the impact of road incidents.The main challenge lies in achieving real-time,reliable and highly a...Accident detection plays a critical role in improving traffic safety by enabling timely emergency response and reducing the impact of road incidents.The main challenge lies in achieving real-time,reliable and highly accurate detection across diverse Internet-of-vehicles(IoV)environments.To overcome this challenge,this paper leverages deep learning to automatically learn patterns from visual data to detect accidents with high accuracy.A visual classification model based on the ResNet-50 architecture is presented for distinguishing between accident and non-accident images.The model is trained and tested on a labeled dataset and achieves an overall accuracy of 91.84%,with a precision of 94%,recall of 90.38%,and an F1-score of 92.14%.Training behavior is observed over 100 epochs,where the model has shown rapid accuracy gains and loss reduction within the first 30 epochs,followed by gradual stabilization.Accuracy plateaues between 90−93%,and loss values remain consistent between 0.1 and 0.2 in later stages.To understand the effect of training strategy,the model is optimized using three different algorithms,namely,SGD,Adam,and Adadelta with all showing effective performance,though with varied convergence patterns.Further,to test its effectiveness,the proposed model is compared with existing models.In the end,the problems encountered in implementing the model in practical automotive settings and offered solutions are discussed.The results support the reliability of the approach and its suitability for real-time traffic safety applications.展开更多
Lightning stroke is one of the important causes of the accidents that occur on transmission lines.With the development of power system,the proportion of outages on transmission lines because of lightning stroke also i...Lightning stroke is one of the important causes of the accidents that occur on transmission lines.With the development of power system,the proportion of outages on transmission lines because of lightning stroke also increases.And according to the lightning accidents results,the lightning stroke characteristics is related to the time factors tightly.In order to analyze the correlativity between the lightning flashover amount and the time factors,about 425 times lightning flashover on 187 lines in 10 power supply companies of 220 kV and 500 kV transmission lines during 2000-2007 are investigated in this paper.The correlativity between the lightning flashover amount and the time factors is analyzed.According to the lightning stroke accidents investigation records,the lightning flashover amount of transmission line increases from the year of 2000 to 2007.In each year lightning flashovers mostly happen in the month of June,July and August.Similarly in each day the flashover amount also varies with the time of day obviously.These lightning flashovers mainly occur during 14:00-21:00 in the afternoon.The analysis results in this paper have a good agreement with the meteorological observations and lightning detection data of lightning location system(LLS).And these results provide good reference for the lightning protection work in power system.展开更多
基金National Natural Science Foundation of China(No.51805312)in part by Shanghai Sailing Program(No.18YF1409400)+4 种基金in part by Training and Funding Program of Shanghai College young teachers(No.ZZGCD15102)in part by Scientific Research Project of Shanghai University of Engineering Science(No.2016-19)in part by Science and Technology Commission of Shanghai Municipality(No.19030501100)in part by the Shanghai University of Engineering Science Innovation Fund for Graduate Students(No.18KY0613)in part by National Key R&D Program of China(No.2016YFC0802900).
文摘Road accident detection plays an important role in abnormal scene reconstruction for Intelligent Transportation Systems and abnormal events warning for autonomous driving.This paper presents a novel 3D object detector and adaptive space partitioning algorithm to infer traffic accidents quantitatively.Using 2D region proposals in an RGB image,this method generates deformable frustums based on point cloud for each 2D region proposal and then frustum-wisely extracts features based on the farthest point sampling network(FPS-Net)and feature extraction network(FE-Net).Subsequently,the encoder-decoder network(ED-Net)implements 3D-oriented bounding box(OBB)regression.Meanwhile,the adaptive least square regression(ALSR)method is proposed to split 3D OBB.Finally,the reduced OBB intersection test is carried out to detect traffic accidents via separating surface theorem(SST).In the experiments of KITTI benchmark,our proposed 3D object detector outperforms other state-of-theartmethods.Meanwhile,collision detection algorithm achieves the satisfactory performance of 91.8%accuracy on our SHTA dataset.
基金the Deanship of Graduate Studies and Scientific Research at Najran University for funding this work under the Growth Funding Program grant code(NU/GP/SERC/13/358-6)。
文摘Accident detection plays a critical role in improving traffic safety by enabling timely emergency response and reducing the impact of road incidents.The main challenge lies in achieving real-time,reliable and highly accurate detection across diverse Internet-of-vehicles(IoV)environments.To overcome this challenge,this paper leverages deep learning to automatically learn patterns from visual data to detect accidents with high accuracy.A visual classification model based on the ResNet-50 architecture is presented for distinguishing between accident and non-accident images.The model is trained and tested on a labeled dataset and achieves an overall accuracy of 91.84%,with a precision of 94%,recall of 90.38%,and an F1-score of 92.14%.Training behavior is observed over 100 epochs,where the model has shown rapid accuracy gains and loss reduction within the first 30 epochs,followed by gradual stabilization.Accuracy plateaues between 90−93%,and loss values remain consistent between 0.1 and 0.2 in later stages.To understand the effect of training strategy,the model is optimized using three different algorithms,namely,SGD,Adam,and Adadelta with all showing effective performance,though with varied convergence patterns.Further,to test its effectiveness,the proposed model is compared with existing models.In the end,the problems encountered in implementing the model in practical automotive settings and offered solutions are discussed.The results support the reliability of the approach and its suitability for real-time traffic safety applications.
基金Supported by Eleventh—five Year Science and Teehnology Program of SGCC(SGKJ[2007]787).
文摘Lightning stroke is one of the important causes of the accidents that occur on transmission lines.With the development of power system,the proportion of outages on transmission lines because of lightning stroke also increases.And according to the lightning accidents results,the lightning stroke characteristics is related to the time factors tightly.In order to analyze the correlativity between the lightning flashover amount and the time factors,about 425 times lightning flashover on 187 lines in 10 power supply companies of 220 kV and 500 kV transmission lines during 2000-2007 are investigated in this paper.The correlativity between the lightning flashover amount and the time factors is analyzed.According to the lightning stroke accidents investigation records,the lightning flashover amount of transmission line increases from the year of 2000 to 2007.In each year lightning flashovers mostly happen in the month of June,July and August.Similarly in each day the flashover amount also varies with the time of day obviously.These lightning flashovers mainly occur during 14:00-21:00 in the afternoon.The analysis results in this paper have a good agreement with the meteorological observations and lightning detection data of lightning location system(LLS).And these results provide good reference for the lightning protection work in power system.
