Real-time traffic analysis at night-time

Mossi, José M.; Albiol, Alberto; Albiol, Antonio; Ornedo, Valery Naranjo

doi:10.1109/icip.2011.6116278

Cited by 7 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For traffic operational analysis, different types of algorithms, such as embedded algorithms for loop detector systems, computer vision-based algorithms and machine learning based algorithms, have been used for solving different traffic related problems (21)(22)(23)(24). Machine learning based algorithms improve the accuracy for traffic operational analysis compared to statistical methods, as it can learn from previous experience with similar roadway conditions.…”

Section: Related Studiesmentioning

confidence: 99%

Real-Time Pedestrian Detection Approach with an Efficient Data Communication Bandwidth Strategy

Rahman

Islam

Calhoun

et al. 2019

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Vehicle-to-Pedestrian (V2P) communication can significantly improve pedestrian safety at a signalized intersection. It is unlikely that pedestrians will carry a low latency communication enabled device and activate a pedestrian safety application in their hand-held device all the time. Because of this limitation, multiple traffic cameras at the signalized intersection can be used to accurately detect and locate pedestrians using deep learning and broadcast safety alerts related to pedestrians to warn connected and automated vehicles around a signalized intersection. However, unavailability of high-performance computing infrastructure at the roadside and limited network bandwidth between traffic cameras and the computing infrastructure limits the ability of real-time data streaming and processing for pedestrian detection. In this paper, we develop an edge computing based real-time pedestrian detection strategy combining pedestrian detection algorithm using deep learning and an efficient data communication approach to reduce bandwidth requirements while maintaining a high object detection accuracy. We utilize a lossy compression technique on traffic camera data to determine the tradeoff between the reduction of the communication bandwidth requirements and a defined object detection accuracy. The performance of the pedestrian-detection strategy is measured in terms of pedestrian classification accuracy with varying peak signal-to-noise ratios. The analyses reveal that we detect pedestrians by maintaining a defined detection accuracy with a peak signal-to-noise ratio (PSNR) 43 dB while reducing the communication bandwidth from 9.82 Mbits/sec to 0.31 Mbits/sec, a 31x reduction.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Real-Time Pedestrian Detection Approach with an Efficient Data Communication Bandwidth Strategy

Rahman

Islam

Calhoun

et al. 2019

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…However, these features cannot be applied at nighttime, as the difference between the vehicles and the environment background is very low. At nighttime, the pair of taillights or headlights is the most commonly used feature to describe a vehicle [ 4 – 26 ]. For vehicle detection, the features, e.g., intensity, sizes, shape, texture, color, symmetry, are usually used to identify the pair of taillights at night.…”

Section: Introductionmentioning

confidence: 99%

A Region Tracking-Based Vehicle Detection Algorithm in Nighttime Traffic Scenes

Wang

Sun²,

Guo

2013

Sensors

View full text Add to dashboard Cite

Abstract:The preceding vehicles detection technique in nighttime traffic scenes is an important part of the advanced driver assistance system (ADAS). This paper proposes a region tracking-based vehicle detection algorithm via the image processing technique. First, the brightness of the taillights during nighttime is used as the typical feature, and we use the existing global detection algorithm to detect and pair the taillights. When the vehicle is detected, a time series analysis model is introduced to predict vehicle positions and the possible region (PR) of the vehicle in the next frame. Then, the vehicle is only detected in the PR. This could reduce the detection time and avoid the false pairing between the bright spots in the PR and the bright spots out of the PR. Additionally, we present a thresholds updating method to make the thresholds adaptive. Finally, experimental studies are provided to demonstrate the application and substantiate the superiority of the proposed algorithm. The results show that the proposed algorithm can simultaneously reduce both the false negative detection rate and the false positive detection rate.

show abstract

“…Another popular approach is the use of top-hat filters. In (Mossi et al, 2011), an enhancement of these filters for detection of headlights is proposed by combining four morphological opening operations with rotated structuring elements. Vehicle lights are also exploited in (Gao et al, 2008), where they are fused with symmetry and edge features to produce a more robust result.…”

Section: Knowledge-based Methodsmentioning

confidence: 99%

Vision-based vehicle detection and tracking with a mobile camera using a statistical framework

Laborda¹

View full text Add to dashboard Cite

Aunque los que me conocen ya saben que soy más bien parco en palabras, no quiero dejar pasar esta oportunidad para reconocer en estas líneas a algunas personas cuya ayuda ha sido imprescindible para la realización de esta tesis. Para empezar, cómo no, quiero agradecer a mi director de tesis, Luis Salgado, por muchos motivos. Por supuesto, por ser el responsable de proponer, impulsar y conducir la investigación en el tema que aborda la tesis. Quiero agradecerte toda la sabiduría, paciencia, esfuerzo e ilusión que has puesto en esta tesis, has hecho una labor modélica. Creo honestamente que hemos hecho un buen equipo, no sólo a nivel científico, sino también humano. Sé que no te gusta que te lo digan, pero a lo largo todos estos años he aprendido mucho de ti o, si lo prefieres, contigo, a mucho niveles. Sabes que no me suelo prodigar en este tipo de digresiones: me cuesta tanto formularlas como a ti encajarlas. En cualquier caso, es de justicia, porque la mitad de esta tesis es tuya, y lo sabes.Quiero agradecer también a todos los profesores del GTI, en especial a Narciso por liderar el grupo y por la amabilidad y buena disposición que siempre ha mostrado conmigo, y por supuesto también a Fernando, Francisco, Julián y Nacho. Me gustaría agradecer a todos mis compañeros y ex-compañeros de fatigas en las lides del doctorado: a Raúl, eres un tío de 10; a Marcos, siempre recordaré nuestras luchas conjuntas contra OpenCV y nuestras conversaciones bajo los arcos de Turín; a César, por estar siempre ahí; a Carlos del Blanco, Carlos Cuevas y Guillermo por la paciencia que han demostrado al aguantarme durante estos últimos meses de estrés; y a todos los demás, por crear un ambiente de trabajo inigualable. No me olvido de todos los estudiantes de intercambio, especialmente de Ivana, Philippe y Hui, con los que he pasado grandes momentos que recuerdo con mucho cariño.Me acuerdo también de toda la gente, los amigos, que he conocido durante estos años en Madrid: Rafa,

show abstract

Real-time traffic analysis at night-time

Cited by 7 publications

References 8 publications

Real-Time Pedestrian Detection Approach with an Efficient Data Communication Bandwidth Strategy

Real-Time Pedestrian Detection Approach with an Efficient Data Communication Bandwidth Strategy

A Region Tracking-Based Vehicle Detection Algorithm in Nighttime Traffic Scenes

Vision-based vehicle detection and tracking with a mobile camera using a statistical framework

Contact Info

Product

Resources

About