A machine learning approach to vehicle occupancy detection

Xu, Beilei; Paul, Peter V.; Artan, Yusuf; Perronnin, Florent

doi:10.1109/itsc.2014.6957856

Cited by 14 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parts of the proposed framework were earlier reported in (Xu et al 2014), (Artan et al 2016) and (Wshah et al 2016). This paper claims sufficient novelty and improvements over these previous works.…”

Section: Introductionmentioning

confidence: 53%

“…Intelligent Transportation Systems (ITS) improve safety and mobility through the integration of sensing, computational power and advanced communications into the transportation infrastructure (Xu et al 2014). Such systems enable efficient management of lanes by incorporating various aspects like carpooling, tolling, traffic management and transit in a multipurpose roadway.…”

Section: Introductionmentioning

confidence: 99%

“…Previous works (Xu et al 2014) in occupancy detection use DPM (Felzenszwalb et al 2010) for ROI extraction, but there are sizable limitations to it. DPM relies heavily on image preparation, cropping and in general the saliency of the Figure 2: Proposed vehicle occupancy count processing pipeline.…”

Section: Introductionmentioning

confidence: 99%

“…This paper claims sufficient novelty and improvements over these previous works. (Xu et al 2014) uses DPM for localization and Support Vector Machines (SVM) for classification while (Artan et al 2016) uses DPM for windshields extraction from images and feature-specific models for classification. (Wshah et al 2016) proposes a solution for detecting whether there is a passenger present in a vehicle or not, which is essentially a binary classification and thus can only be used for figuring HOV2+ violations.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

VPDS: An AI-Based Automated Vehicle Occupancy and Violation Detection System

Kumar

Gupta²,

Santra

et al. 2019

AAAI

View full text Add to dashboard Cite

High Occupancy Vehicle/High Occupancy Tolling (HOV/HOT) lanes are operated based on voluntary HOV declarations by drivers. A majority of these declarations are wrong to leverage faster HOV lane speeds illegally. It is a herculean task to manually regulate HOV lanes and identify these violators. Therefore, an automated way of counting the number of people in a car is prudent for fair tolling and for violator detection.In this paper, we propose a Vehicle Passenger Detection System (VPDS) which works by capturing images through Near Infrared (NIR) cameras on the toll lanes and processing them using deep Convolutional Neural Networks (CNN) models. Our system has been deployed in 3 cities over a span of two years and has served roughly 30 million vehicles with an accuracy of 97% which is a remarkable improvement over manual review which is 37% accurate. Our system can generate an accurate report of HOV lane usage which helps policy makers pave the way towards de-congestion.

show abstract

Section: Introductionmentioning

confidence: 53%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

VPDS: An AI-Based Automated Vehicle Occupancy and Violation Detection System

Kumar

Gupta²,

Santra

et al. 2019

AAAI

View full text Add to dashboard Cite

show abstract

“…1 photography and stereo imaging (Goodin et al, 2007) 2 structured lighting (LED) (Schijns, 2004;Morris et al, 2017) 3 video (Billheimer, 1990;Turner, 1998) 2005; Ungemah et al, 2008;Xu et al, 2014; for TruCount by NEC cf. https://www.necam.com/AdvancedRecognitionSystems/Products/TruCount) 6 RFID technology (Kelley, 2007) 7 inductive power transmission (Albesa and Gasulla, 2015) 8 weight sensors (Kisic et al, 2017) 9 ultrasonic sensors (Schijns, 2004) 10 neural networks for imaging analysis applications (Wshah, et al, 2016) and machine learning approaches (Xu et al, 2014) 11 Bluetooth occupancy detection (https://www.gocarma.com/) via in-vehicle systems.…”

Section: Moving Trafficmentioning

confidence: 99%

Carpooling and the Pan-European emergency call "eCall 112": Connected cars and their potential for environmental and transport policy

Schaefer¹

2019

IJATM

View full text Add to dashboard Cite

To meet transport sector obligations to emissions reductions, large effects may be derived from intelligent transportation systems (ITS) solutions. Substantial decrease of vehicle miles travelled (VMT) can be achieved using transportation systems management (TSM) measures, especially through high-occupancy vehicles (HOV) incentives. Of these, carpooling and vanpooling approaches proved to be effective. However, there is a lack of reliable enforcement procedures. A review of automated vehicle occupancy verification (AVOV) research and development (R&D) is followed by a proposal focused on the Pan European emergency call 'eCall 112'. The concept explores options for an eCall 112 application as an enforcement tool in TSM operations with vehicle occupancy data contained in the minimum set of data (MSD) as the base for new road transport policy tools. A set of incentives is described which support transport and environmental objectives. The proposed enforcement may impact congestion levels in combination with HOV-lanes and without them. Climate, environment, and the performance of road transportation systems could benefit from integrated road safety and TSM operations.

show abstract