Camera-based Smart Traffic State Detection in India using Deep Learning Models

Agarwal, Nimish; Jangid, Aman; Sharma, Ashutosh; Kumar, Nikhil; Kumar, M. Ramesh; Kumar, Pankaj; Chakraborty, Pranamesh

doi:10.1109/comsnets51098.2021.9352904

Cited by 5 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…start, mid and end of shift) can be automatically identified using job dispatch and routing management systems, while traffic state (i.e. high or low) can be automatically detected from road-facing camera images using computer vision techniques [50], [51] or obtained from location based systems e.g., Google Maps.…”

Section: B Effects Of Contextual Factors On Hgv Drivers' Performancementioning

confidence: 99%

Contextual Intelligent Decisions: Expert Moderation of Machine Outputs for Fair Assessment of Commercial Driving

Mase¹,

Pekaslan²,

Agrawal³

et al. 2022

Preprint

View full text Add to dashboard Cite

Commercial driving is a complex multifaceted task influenced by personal traits and external contextual factors, such as weather, traffic, road conditions, etc. Previous intelligent commercial driver-assessment systems do not consider these factors when analysing the impact of driving behaviours on road safety, potentially producing biased, inaccurate, and unfair assessments. In this paper, we introduce a methodology (Expertcentered Driver Assessment) towards a fairer automatic road safety assessment of drivers' behaviours, taking into consideration behaviours as a response to contextual factors. The contextual moderation embedded within the intelligent decisionmaking process is underpinned by expert input, comprising of a range of associated stakeholders in the industry. Guided by the literature and expert input, we identify critical factors affecting driving and develop an interval-valued response-format questionnaire to capture the uncertainty of the influence of factors and variance amongst experts' views. Questionnaire data are modelled and analysed using fuzzy sets, as they provide a suitable computational approach to be incorporated into decisionmaking systems with uncertainty. The methodology has allowed us to identify the factors that need to be considered when moderating driver sensor data, and to effectively capture experts' opinions about the effects of the factors. An example of our methodology using Heavy Goods Vehicles professionals input is provided to demonstrate how the expert-centred moderation can be embedded in intelligent driver assessment systems.

show abstract

Section: B Effects Of Contextual Factors On Hgv Drivers' Performancementioning

confidence: 99%

Contextual Intelligent Decisions: Expert Moderation of Machine Outputs for Fair Assessment of Commercial Driving

Mase¹,

Pekaslan²,

Agrawal³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…start, mid and end of shift) can be determined using job dispatch and routing management systems, while traffic state (i.e. high or low) can be automatically recognised from road-facing camera images using computer vision techniques (Chakraborty et al [2018], Agarwal et al [2021]) or obtained from location based systems e.g., Google Maps. For time pressure, it is still very difficult to automatically detect.…”

Section: Work-life Factors and External Pressuresmentioning

confidence: 99%

Contextually Intelligent Decisions: A Co-designed Approach for Commercial Driving Assessment

Mase

Pekaslan

Agrawal

et al. 2022

Preprint

View full text Add to dashboard Cite

Commercial driving is a complex multifaceted task influenced by drivers' personal traits and external contextual factors, such as weather, traffic, and road conditions. Current intelligent commercial driving assessment systems only focus on the manner by which drivers operate vehicle controls when analysing driving performance and the impact of driver behaviour on road safety, potentially producing incomplete and unfair assessments. In this paper, we introduce a stakeholder co-designed approach to complement current driver-assessment systems and provide more context-aware, comprehensive and we hope--fairer assessments of commercial driving. The approach engages key stakeholders in the commercial driving sector to capture the impact of personal traits and external contextual factors on driving performance and provides a systematic approach to embed this knowledge into the assessment of commercial drivers. We demonstrate the effectiveness and utility of the approach by illustrating its end-to-end deployment in the context of heavy goods vehicle driving assessment.

show abstract