SERN 기반 운전자의 다중 행동 특징을 이용한 졸음 검출 시스템
A Drowsiness Detection System Using Multiple Driver Behavior Features Based on SERN
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 교통사고의 주요한 원인 중 하나인 운전자 졸음으로 인한 교통사고를 예방하기 위해 졸음 인식 연구가 활발히 진행되는 중이다. 기존 졸음 인식 시스템은 운전자의 신체적 특징을 이용하여 졸음 상태를 인식하지만 신체 부위 폐색에 의한 가려짐으로 제한되는 한계가 있다. 본 논문에서는 운전자의 다중 행동 특징을 이용한 SERN(Squeeze and Excitation Resnet Network) 기반 졸음 인식 시스템을 제안한다. 제안한 시스템은 다중 행동적 특징 기반 특징 추출 과정, 데이터의 계층적 레이블링 세분화 과정, SERN 모델에 의한 졸음 인식 과정으로 구성된다. 공개 DB인 NTHU-DDD를 사용한 실험 결과, 제안하는 SERN 모델 기반 운전자 졸음 검출 성능이 기존 네트워크 모델보다 정확도 1.03% 우수함을 확인했다.
Abstract
Recently, driver drowsiness has been one of the major causes of traffic accidents, and study on drowsiness detection has been actively conducted to prevent drowsiness-related accidents. Existing drowsiness detection systems recognize the drowsy state of the driver using the driver's physical features, but they have limitations due to occlusion caused by obstructed body parts. In this paper, we propose a drowsiness detection system based on the squeeze and excitation resnet network (SERN) using the driver's multi-behavioral features. The proposed system consists of a multi-behavioral feature extraction process, a hierarchical data labeling refinement process, and a drowsiness detection process using the SERN model. As a result of an experiment using public DB’s NTHU-DDD, it was confirmed that the proposed SERN model based driver drowsiness detection performance was 1.03% better than the existing network model.
참고문헌 (18)
- M. Ramzan, "A survey on state-of-the-art drowsiness detection techniques", IEEE Access, 7, pp.61904~61919 (2019)
- Y. Albadawi, "A review of recent developments in driver drowsiness detection systems", Jour. Sensors, 22 (2022), MDPI
- M. Ahmed, "Intelligent driver drowsiness detection for traffic safety based on multi CNN deep model and facial subsampling", IEEE, Trans, Syst, 23 (2022)
- C. H. Weng, "Driver drowsiness detection via a hierarchical temporal deep belief network", Comp, Vision(ACCV 2016), 10118, pp.117~133 (2017), Springer
- Y. Katyal, "Safe driving by detecting lane discipline and driver drowsiness", IEEE, Int. Conf. Compu. Tech (2015)
- S. Arefnezhad, "Driver drowsiness detection based on steering wheel data applying adaptive neuro-fuzzy feature selection", Jour. Sensors, 19 (2019), MDPI
- S. Gangadharan, "Drowsiness detection using portable wireless EEG", Comput. Biom, 214(106535), pp.1~8 (2022), Elsevier
- U. Budak, "An effective hybrid model for EEG-based drowsiness detection", Sensors. Jour, 19 (2019), IEEE
- I. Kayadibi, "An eye state recognition system using transfer learning : alexnet based deep convolutional neural network", Int. Jour. Comput. Intell. Syst, pp.1~49 (2022), Springer
- E. Civik, "Real-time driver fatigue detection system with deep learning on a low-cost embedded system", Micpro. Micsyst, 99 (2023), Elsevier
- B. K. Savas, "Real time driver fatigue detection system based on Multi-Task ConNN", IEEE Access, 8, pp.12491~12498 (2020)
- A. Ghourabi, "Driver drowsiness detection based on joint monitoring of yawning, blinking and nodding", Intel. Conf. Comm. Proc(ICCP) (2020), IEEE
- F. Safarov, "Real-time deep learning-based drowsiness detection : leveraging computer-vision and eye-blink analyses for enhanced road safety", Jour. Sensors, 23 (2023), MDPI
- D. Ford, "Why do you yawn — and is it contagious?", Cleveland Clinic, Health. Library. Body. Syst, ~ (2023)
- K. He, "Deep residual learning for image recognition", IEEE, Comp. Vision. Pattern. Recog, pp.770~778 (2016)
- J. Hu, "Squeezeand-excitation networks", IEEE, Comp. Vision. Pattern. Recog, pp.7132~7141 (2018)
- W. Liu, "Convolutional two-stream network using multi-facial feature fusion for driver fatigue detection", Jour. Future. Inter, 11 (2019), MDPI
- N. Dalal, "Histograms of oriented gradients for human detection", IEEE, Comp, Society, Conf, Vision, Recong, 11 (2005)