Abstract:
Drowsiness driving is a principal factor of many fatal traffic accidents. This paper presents the first event-based drowsiness driving detection (EDDD) system by using the recently developed neuromorphic vision sensor. Compared with traditional frame-based cameras, neuromorphic vision sensors, such as Dynamic Vision Sensors (DVS), have a high dynamic range and do not acquire full images at a fixed frame rate but rather have independent pixels that output intensity changes (called events) asynchronously at the time they occur. Since events are generated by moving edges in the scene, driving detection is considered as an efficient and effective drive detector for the drowsiness driving-related motions. Based on this unique output, this work first proposes a highly efficient method to recognize and localize the driver’s eyes and mouth motions from event streams. We further design and extract event-based drowsiness-related features directly from the event streams caused by eyes and mouths motions, then the Event-Based Drowsiness Driving Detection model is established based on these features. Additionally, we provide the EDDD dataset, the first public dataset dedicated to event-based drowsiness driving detection. The EDDD dataset has 260 recordings in daytime and evening with several challenging scenes such as subjects wearing glasses/sunglasses. Experiments are conducted based on this dataset and demonstrate the high efficiency and accuracy of our method under different illumination conditions. As the first investigation of the usage of DVS in drowsiness driving detection applications, we hope that this work will inspire more event-based drowsiness driving detection research.
Author Keywords
- Event-based camera,
- neuromorphic vision,
- drowsiness driving detection
IEEE Keywords
- Vision sensors,
- Neuromorphic,
- Vehicles,
- Cameras,
- Feature extraction,
- Mouth,
- Streaming media
Introduction
Driving for an extended period is prone to trigger the drowsiness of drivers, which is a serious threat to road safety. There is substantial statistical evidence to indicate that drowsiness driving is one of the primary reasons for many traffic accidents, casualties, and property losses all over the world. The National Highway Traffic Safety Administrator (NHTSA) reported that there are about 100,000 crashes in the USA caused by drowsiness driving annually, which results in more than 1500 death and 71,000 injuries [1].
Conclusion
In this work, the first event-based drowsiness driving detection system through facial motion analysis is proposed. By using a novel neuromorphic vision sensor, the proposed work simplifies the traditional vision-based detection process as our new sensor is a natural motion detector for the drowsiness driving-related motions. The unique properties of DVS inspire us to propose a highly efficient method to recognize and localize the driver’s eyes and mouth motions from the event streams. We further design and extract drowsiness-related features directly from these motions to establish the EDDD model. Additionally, an EDDD dataset is provided in this work, the first public dataset dedicated to event-based drowsiness driving detection. Both offline and online experiments are conducted and demonstrate the high efficiency and accuracy of the proposed method. Especially, the proposed method can get robust and high-accuracy performance in corner-case scenarios such as Driving Detection with sunglasses or driving at night, which is very challenging for traditional frame-based vision sensors. The preliminary research work shows that the neuromorphic vision sensor has the potential to be an alternative sensor for drowsiness driving detection. In future work, we would like to extend our system to a real driving scenario by considering the real-time detection of the driver’s head from other sensing modalities such as RGB images. As the event stream includes no color information, it is difficult to locate and track the eyes and mouth by only using the event stream, especially when the driver switches his/her gaze frequently. Thus, developing a fusion system from both RGB and event data is worth exploring.
About KSRA
The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.
KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.
Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.
The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.
Bibliography
Author
G. Chen, L. Hong, J. Dong, P. Liu, J. Conradt, and A. Knoll
Year
2020
Title
EDDD: Event-Based Drowsiness Driving Detection Through Facial Motion Analysis With Neuromorphic Vision Sensor
Publish in
in IEEE Sensors Journal, vol. 20, no. 11, pp. 6170-6181, 1 June 1, 2020
Doi
10.1109/JSEN.2020.2973049
FULL Paper PDF file:
EDDD: Event-Based Drowsiness Driving Detection Through Facial Motion Analysis With Neuromorphic Vision Sensor
PDF reference and original file: Click here
