Deep learning based Detection of One Way Traffic Rule Violation of Three Wheeler Vehicles

Mampilayil, Helen Rose; Rahamathullah, K

doi:10.1109/iccs45141.2019.9065638

Cited by 16 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sebagian besar kecelakaan lalu lintas disebabkan oleh kelalaian pengemudi, seperti: menurunnya konsentrasi dan fokus pengemudi karena melakukan aktivitas lain di dalam kendaraan dan faktor kelelahan. Dalam hal ini, contoh mayoritas pelanggaran lalu lintas yang terjadi adalah lawan arah (Mampilayil, 2019) (Sushmitha, dkk, 2020), ngebut dan melanggar rambu-rambu lalu lintas (Hajeb, dkk, 2013) (Al-shabibi, dkk, 2014) (Goma, dkk, 2020) (Kulanthayan, dkk, 2007), yang terjadi mungkin secara sengaja maupun secara tidak disengaja atau karena kurang konsentrasi pengemudi.…”

Section: Pendahuluanunclassified

“…Pelanggaran batas kecepatan maksimal dapat dideteksi menggunakan teknik pengolahan citra dan computer vision (Aliane, dkk, 2014) (Bedruz, dkk, 2018) (Prakash, dkk, 2020), deteksi pelanggaran rambu lampu lalu lintas menggunakan teknologi computer vision (Goma, dkk, 2020) (Kulanthayan, dkk, 2007) (Bolsunovskaya, dkk, 2021), deteksi pelanggaran parkir menggunakan teknologi pemrosesan citra (Sushmitha, dkk, 2020), deteksi pelaku pelanggaran melalui pengenalan pelat nomor kendaraan (Agarwal, dkk, 2018). Deteksi pelanggaran lawan arah kendaraan selain roda-empat, juga terdapat metode untuk deteksi kendaraan roda-tiga, menggunakan metode video pengawasan (Mampilayil, 2019) (Sushmitha, dkk, 2020). Teknologi RFID juga digunakan untuk deteksi pelanggaran kecepatan kendaraan (Hajeb, dkk, 2013) (Al-shabibi, dkk, 2014.…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Pendeteksi Pelanggaran Lalu Lintas Kendaraan Lawan Arah berbasis Sensor Ultrasonik

HIDAYAT¹,

NAUFAL²,

Syafei³

2022

ELKOMIKA

View full text Add to dashboard Cite

ABSTRAKPelanggaran lalu lintas lawan arah kendaraan sepeda motor adalah pelanggaran yang banyak terjadi. Hal ini kerap menimbulkan korban. Makalah ini melaporkan prototipe sensor untuk deteksi pelanggaran lalu lintas lawan arah kendaraan sepeda motor di area lalu lintas Universitas Padjadjaran (Jatinangor) untuk keperluan pengelola dalam pengaturan lalu lintas kampus. Sistem sensor dibangun dari dua buah sensor ultrasonik (MB1030 MaxSonar EZ-3) untuk membaca arah pergerakan kendaraan. Sensor kendaraan mendeteksi pola spasial dan temporal gerakan kendaraan yang melintas. Pola pembacaan sensor ultrasonik diproses oleh mikrokontroller ATmega 328P dan hasilnya ditampilkan pada peraga LCD dan peraga buzzer. Data yang ditampilkan berupa jumlah pelanggaran lawan arah dan indikasi bunyi. Berdasarkan hasil pengujian, sistem dapat mendeteksi pelanggaran lawan arah sebesar 87,14%. Sistem ini juga dapat membedakan objek yang melintas antara kendaraan motor dengan pejalan kaki. Secara keseluruhan, sistem yang dibangun berfungsi sesuai rancangan untuk mendeteksi pelanggaran kendaraan sepeda motor lawan arah.Kata kunci: lawan arah, ultrasonik, kirim-pantul, spasial-temporal, mikrokontroler ABSTRACTOpposite direction traffic violations are the most occurrences of traffic violations. This often causes fatal human injuries. This paper reports a design of sensor for detection of opposite direction traffic violations of motorcycle vehicles in the internal traffic area of Universitas Padjadjaran, Jatinangor campus, for in-campus traffic management purposes. The sensor system is built from two ultrasonic sensors (MB1030 MaxSonar EZ-3) to detect the direction of vehicle object movement. The sensors detect the direction according to the spatial and temporal patterns. The ultrasonic sensor reading pattern is processed by the ATmega 328P microcontroller and the results are displayed on an LCD and a sound buzzer. The displayed parameter is the number of opposite directioan violation and a beep sound. Based on the testing results, the system can detect a violation of the opposite direction by 87.14%. This system enables to distinguish motor vehicles and pedestrians objects. In conclusion, the system functions as designed to detect violations of motorcycle in the opposite direction.Keywords: traffic violation, ultrasonic sensors, pulse-echo, spatial-temporal, microcontroller

show abstract

Section: Pendahuluanunclassified

Pendeteksi Pelanggaran Lalu Lintas Kendaraan Lawan Arah berbasis Sensor Ultrasonik

HIDAYAT¹,

NAUFAL²,

Syafei³

2022

ELKOMIKA

View full text Add to dashboard Cite

show abstract

“…There are plenty of studies on traffic violation inference [23], [24]. Artificial neural networks and deep learning approaches also have been used in traffic violation detection [25], [26]. Also, crowdsensing platforms for traffic violation reporting have been developed in many cities, such as Shanghai and Xiamen in China.…”

Section: Traffic Violation Inferencementioning

confidence: 99%

CrowdPatrol: A Mobile Crowdsensing Framework for Traffic Violation Hotspot Patrolling

Jiang

Zhu

Zhou

et al. 2021

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

Traffic violations have become one of the major threats to urban transportation systems, undermining human safety and causing economic losses. To alleviate this problem, crowd-based patrol forces including traffic police and voluntary participants have been employed in many cities. To adaptively optimize patrol routes with limited manpower, it is essential to be aware of traffic violation hotspots. Traditionally, traffic violation hotspots are directly inferred from experience, and existing patrol routes are usually fixed. In this paper, we propose a mobile crowdsensing-based framework to dynamically infer traffic violation hotspots and adaptively schedule crowd patrol routes. Specifically, we first extract traffic violation-prone locations from heterogeneous crowd-sensed data and propose a spatiotemporal context-aware self-adaptive learning model (CSTA) to infer traffic violation hotspots. Then, we propose a tensor-based integer linear problem modeling method (TILP) to adaptively find optimal patrol routes under human labor constraints. Experiments on real-world data from two Chinese cities (Xiamen and Chengdu) show that our approach accurately infers traffic violation hotspots with F1-scores above 90% in both cities, and generates patrol routes with relative coverage ratios above 85%, significantly outperforming baseline methods.

show abstract

“…Moreover, using improving computer vision techniques, infrastructure surveillance methods (Arabi et al., 2020; Rabie et al., 2005; Yan et al., 2020; B. Zhang et al., 2019) have become much easier to implement and more popular. For example, Mampilayil & Rahamathullah (2019) used a pretrained TensorFlow object detection model to detect vehicles and track them by their centroids in order to detect WWD.…”

Section: Introductionmentioning

confidence: 99%

“…Zhang et al, 2019) have become much easier to implement and more popular. For example, Mampilayil & Rahamathullah (2019) used a pretrained TensorFlow object detection model to detect vehicles and track them by their centroids in order to detect WWD.…”

mentioning

confidence: 99%

A computer vision‐based deep learning model to detect wrong‐way driving using pan–tilt–zoom traffic cameras

Haghighat

Sharma

2022

Computer aided Civil Eng

View full text Add to dashboard Cite

Hundreds of fatal accidents occur each year due to wrong-way driving (WWD). Although several methods have been developed to detect WWD using existing closed-circuit television (CCTV) data, they all require manual recalibration whenever a camera rotates, and are thus not scalable across statewide CCTV networks. This paper, therefore, proposes an end-to-end deep-learning-based model that considers camera orientation as a variable, detecting camera rotation automatically and learning new decision criteria accordingly using a neural network model. We show that our proposed solution can detect WWD with a precision of 0.99 and a recall of 0.97. Due to its cheap computational cost and high error tolerance, our solution is easily scalable for statewide surveillance on a real-time basis to help decision-makers reduce fatalities due to WWD. INTRODUCTIONBased on the National Highway Traffic Safety Administration's Fatality Analysis Reporting System, the annual average of 269 fatal crashes from 2004 through 2011 due to wrong-way driving (WWD) resulted in more than 350 people dying each year (Pour-Rouholamin et al., 2015).According to federal and state crash data, 20% to 25% of crashes from WWD are fatal. This percentage is significant, compared to the 0.5% fatality rate, for vehicle crashes overall (MH Corbin, 2020).Several studies (such as Baratian-Ghorghi et al., 2014;Leduc, 2008;Zhou et al., 2012) have investigated different factors in WWD accidents and have shown that in 58% of the crashes, drivers were under the influence of alcohol.To prevent drivers from entering the wrong side of the road, several passive mechanisms have been implemented, such as wrong-way signs or raised pavement markers on roads (Baratian-Ghorghi & Zhou, 2017;Cooner et al., 2003) and in-pavement warning lights. In parallel with deploying passive mechanisms to minimize WWD incidents, many

show abstract

Deep learning based Detection of One Way Traffic Rule Violation of Three Wheeler Vehicles

Cited by 16 publications

References 16 publications

Pendeteksi Pelanggaran Lalu Lintas Kendaraan Lawan Arah berbasis Sensor Ultrasonik

Pendeteksi Pelanggaran Lalu Lintas Kendaraan Lawan Arah berbasis Sensor Ultrasonik

CrowdPatrol: A Mobile Crowdsensing Framework for Traffic Violation Hotspot Patrolling

A computer vision‐based deep learning model to detect wrong‐way driving using pan–tilt–zoom traffic cameras

Contact Info

Product

Resources

About