Table 5 Comparative analysis of driver behavior monitoring research
Paper | Year | Focus | Methodology | Scope | Significance | Key Contributions | Differences |
|---|---|---|---|---|---|---|---|
Ours | 2023 | Monitoring driver behavior using computer vision and machine learning techniques. | Neural network-based methodologies (ANNs, CNNs, RNNs, LSTMs). | Specifically focused on computer vision and machine learning technologies for driver behavior monitoring. | Relevant for developing specific driver behavior monitoring systems in autonomous vehicles and driver assistance systems. | In-depth insights into specific technologies with practical applications in autonomous driving. | Baseline for comparison |
[147] | 2023 | Systematic literature review of driver behavior classification methods. | Various AI algorithms used for driver behavior classification, including machine learning and deep learning techniques. | Broader in scope, covering a variety of driver behaviors and classification methods. | Comprehensive view of the field of driver behavior classification. | Systematic overview of the field, identifying key contributions and potential research directions. | Systematic literature review, wider AI algorithm scope. |
[148] | 2022 | Developing vehicle occupant-invariant models for activity characterization, focusing on violence and non-violence detection. | Adversarial learning, bilevel learning, and integration of pose information. | Creating actor-invariant models, emphasizing the integration of body posture data. | Insights into the challenges of actor bias in activity characterization. | Novel approaches to enhance the accuracy and transferability of activity recognition systems in vehicles. | Focuses on actor-invariant models, different methodological approach. |
[149] | 2021 | Utilization of in-vehicle cameras for analyzing driver behavior, focusing on distracted and drowsy driving. | Traditional handcrafted feature-based methods and advanced deep learning techniques like CNNs. | Evolution of driver behavior analysis techniques, from traditional methods to advanced machine learning algorithms. | Comprehensive overview of driver behavior analysis using in-vehicle cameras for road safety. | Highlights gaps in NDS video data analytics and potential areas for future computer vision research. | Focuses on in-vehicle cameras, different data analytics approach. |
[150] | 2019 | Reviews driver behavior analysis methods using smartphones for drowsiness and abnormal driving detection. | Smartphone-based sensing schemes and detection algorithms. | Explores smartphone technologies and potential integration with other systems. | Broad applicability and advantages of smartphone solutions in driver behavior analysis for enhancing road safety. | Comprehensive overview of smartphone-based methods, addressing challenges and future directions. | Smartphone-based methods, different technological scope |
[151] | 2018 | Range of driver behavior detection techniques and their application in road safety. | Sensor-based, vision-based, and hybrid systems for driver behavior detection. | Broader range of technologies and approaches for detecting driver behavior. | Comprehensive overview of driver behavior detection technologies for road safety improvements. | Broad overview but may lack depth specific to computer vision and machine learning techniques. | Broader range of detection methods, less ML-specific. |
[152] | 2017 | Comprehensive survey of various techniques for detecting driver behavior in intelligent transportation systems. | Covers a range of technologies including ADAS, mobile phone sensors, and more. | Wider focus on intelligent transportation systems. | Provides a broader understanding of technologies in intelligent transportation systems. | Overview of various technologies, less depth in machine learning specifics. | Broader focus on technologies, less depth in machine learning |
[153] | 2016 | Advancements in driver behavior modeling for ADAS and autonomous vehicles. | Big data, mobile cloud computing, and context-aware services for driver behavior modeling. | Broader scope, including mobile cloud computing and various approaches in modeling driver behavior. | Comprehensive overview of current developments and future directions in driver behavior modeling. Broader perspective on the evolving field of driver behavior modeling, highlighting current challenges and future research directions. Broader scope with big data and cloud computing. | Broader perspective on the evolving field of driver behavior modeling, highlighting current challenges and future research directions. | Broader scope with big data and cloud computing |
[154] | 2015 | Addresses driver drowsiness and distraction, covering a wide range of detection techniques and the use of mobile technologies. | Visual and non-visual feature-based detection techniques, and the use of smartphones and wearable devices. | Broad scope including mobile technologies and vehicular ad hoc networks for driver safety. | Comprehensive overview of driver safety technologies. | Insights into various detection methods and the potential integration of driver behavior analysis into car-to-car communication. | Covers mobile technologies, broader safety focus. |
[155] | 2013 | Reviews various methods for monitoring driver and driving behavior, with a focus on drowsiness and distraction detection. | Visual and non-visual features of driver behavior, driving performance behaviors, and vehicle-based features. | Wider range of methods, including physiological signals and vehicle-based features. | Comprehensive overview of methods for enhancing driver safety systems. Different approaches for driver behavior monitoring and their significance in road safety. Varied monitoring methods, including physiological signals | Different approaches for driver behavior monitoring and their significance in road safety. | Varied monitoring methods, including physiological signals |