计算机科学 ›› 2024, Vol. 51 ›› Issue (6): 247-255.doi: 10.11896/jsjkx.230300033
火星星1, 胡瑞敏2, 李怡欣1
HUO Xingxing1, HU Ruimin2, LI Yixin1
摘要： 行李X光安检员工作疲劳是造成错检、漏检的重要原因。目前疲劳检测的方法主要通过发现打哈欠、打瞌睡和长时间闭眼等明显的迹象来检测中晚期疲劳,然而对于安检工作人员来说,出现这样明确的标志时,可能已经发生了安检事故,此时再进行疲劳检测为时已晚。因此,在早期阶段发现疲劳,并对疲劳的发生及时预警是非常有价值的。由于早期疲劳会有细微的面部表现特性,时域参数的不可逆性导致其无法完全表示。为了解决此问题,提出了一种基于眼部特征频域信息的行李X光安检员早期疲劳检测方法,将原始时域信息转换到表达能力更强的频域特征空间。该方法首先通过面部检测算法获取眼部横纵比(Eye Aspect Ratio,EAR)时间序列;然后利用频域特征提取方法得到频域特征序列,来表示更加细微的特征;最后利用分层多尺度网络HM-LSTM进行训练及验证。在公开数据集UTA-RLDD上的对比实验结果表明,所提方法对早期疲劳的识别率提升了2%,证明了频域特征比时域特征有更好的表达能力。
中图分类号:
| [1]AKERSTEDT T,GILLBERG M.Subjective and objectives leepiness in the active individual[J].International Journal of Neuroscience,1990,52(1/2):29-37. [2]SMITH A P,ALLEN P H,WADSWORTH E J K.Seafarer fatigue:The Cardiff researchprogramme[J/OL].https://orca.cardiff.ac.uk/id/eprint/52615/. [3]JIA W,PENG H,RUAN N,et al.WiFind:Driver fatigue detection with fine-grained Wi-Fi signal features[J].IEEE Transactions on Big Data,2018,6(2):269-282. [4]LIU P,CHI H L,LI X,et al.Effects of dataset characteristics on the performance of fatigue detection for crane operators using hybrid deep neural networks[J].Automation in Construction,2021,132:103901. [5]LI G,CHUNG W Y.A context-aware EEG headset system for early detection of driver drowsiness[J].Sensors,2015,15(8):20873-20893. [6]GHODDOOSIAN R,GALIB M,ATHITSOS V.A realisticdataset and baseline temporal model for early drowsiness detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.2019. [7]VAN SEGBROECK M,TSIARTAS A,NARAYANAN S S.A robust frontend for VAD:exploiting contextual,discriminative and spectral cues of human voice[C]//INTERSPEECH.2013:704-708. [8]ZHANG R,LI P H,LIANG K W,et al.Voice Activity Detection by Jo1int MRCG and MFCC Features with Robustness Detection based GRU Networks[C]//2021 IEEE International Conference on Consumer Electronics-Taiwan(ICCE-TW).IEEE,2021. [9]ABDULLAH S,ZAMANI M,DEMOSTHENOUS A.A dis-crete wavelet transform-based voice activity detection and noise classification with sub-band selection[C]//2021 IEEE International Symposium on Circuits and Systems(ISCAS).IEEE,2021:1-5. [10]LIU F,DEMOSTHENOUS A.A computation efficient voice activity detector for low signal-to-noise ratio in hearing aids[C]//2021 IEEE International Midwest Symposium on Circuits and Systems(MWSCAS).IEEE,2021:524-528. [11]KAIDA K,TAKAHASHI M,AKERSTEDT T,et al.Validation of theKarolinska sleepiness scale against performance and EEG variables[J].Clinical Neurophysiology,2006,117(7):1574-1581. [12]XU C,WANG X,CHEN X.Modeling fatigue level by driver’s lane-keeping indicators[C]//ICTE 2013:Safety,Speediness,Intelligence,Low-Carbon,Innovation.2013:2282-2288. [13]ZHANG R,ZHU T J,ZOU Z L,et al.A Survey of Driver Fatigue Detection Methods[J].Computer Engineering and Application,2022,58(21):53-66. [14]ZHU X,ZHENG W L,LU B L,et al.EOG-based drowsiness detection using convolutional neural networks[C]//2014 International Joint Conference on Neural Networks(IJCNN).IEEE,2014:128-134. [15]JIAO Y,DENG Y,LUO Y,et al.Driver sleepiness detectionfrom EEG and EOG signals using GAN and LSTM networks[J].Neurocomputing,2020,408:100-111. [16]NIU J,WANG F,SONG J Q,et al.Video Emotion Recognition of Face Features and Pulse Signal Features[J].Journal of Chongqing University of Technology(Natural Science),2021,35(8):144-150. [17]CHEN S,SUN Y,ZHANG H,et al.Speech Fatigue DetectionBased on Deep Learning[C]//Journal of Physics:Conference Series.IOP Publishing,2022. [18]XIE Y,LI F,WU Y,et al.Real-time detection for drowsy dri-ving via acoustic sensing on smartphones[J].IEEE Transactions on Mobile Computing,2020,20(8):2671-2685. [19]TAO H,ZHANG G,ZHAO Y,et al.Real-time driver fatigue detection based on face alignment[C]//Ninth International Conference on Digital Image Processing(ICDIP 2017).SPIE,2017:6-11. [20]BEKHOUCHE S E,RUICHEK Y,DORNAIKA F.Driverdrowsiness detection in video sequences using hybrid selection of deep features[J].Knowledge-Based Systems,2022,252:109436. [21]YADAV S,RAI A.Frequency and temporal convolutional attention for text-independent speaker recognition[C]//IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP 2020).IEEE,2020:6794-6798. [22]CECH J,SOUKUPOVA T.Real-time eye blink detection using facial landmarks[J/OL].https://dspace.cvut.cz/bitstream/handle/10467/64839/F3-DP-2016-Soukupova-Tereza-SOUKUPOVA_DP_2016.pdf;jsessionid=3C81CDFAD46C8E54026CF6FB17C9BCE9?sequence=－1. [23]LEE Y,MIN J,HAN D K,et al.Spectro-temporal attention-based voice activity detection[J].IEEE Signal Processing Letters,2019,27:131-135. [24]DING K,ZHENG S,QI X,et al.Acoustic Target Recognition Based on MFCC and SVM[C]//Man-Machine-Environment System Engineering:Proceedings of the 22nd International Conference on MMESE.Singapore:Springer Nature Singapore,2022:418-423. [25]TADESSE E,SHENG W,LIU M.Driver drowsiness detection through HMM based dynamic modeling[C]//2014 IEEE International Conference on Robotics and Automation(ICRA).IEEE,2014:4003-4008. [26]REDDY B,KIM Y H,YUN S,et al.Real-time driver drowsiness detection for embedded system using model compression of deepneural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.2017:121-128. [27]PARK S,PAN F,KANG S,et al.Driver drowsiness detectionsystem based on feature representation learning using various deep networks[C]//Computer Vision－ACCV 2016 Workshops:ACCV 2016 International Workshops,Taipei,Taiwan,Revised Selected Papers,Part III.Springer,2017:154-164. [28]WENG C H,LAI Y H,LAI S H.Driver drowsiness detection via a hierarchical temporal deep belief network[C]//Computer Vision－ACCV 2016 Workshops:ACCV 2016 International Workshops,Taipei,Taiwan,Revised Selected Papers,Part III 13.Springer,2017:117-133. [29]ABTAHI S,OMIDYEGANEH M,SHIRMOHAMMADI S,et al.YawDD:A yawning detection dataset[C]//Proceedings of the 5th ACM Multimedia Systems Conference.2014:24-28. |
|
||
首页