Robust Vehicle Speed Measurement Based on Feature Information Fusion for Vehicle Multi-Characteristic Detection

Yang, Lei; Luo, Jianchen; Song, Xiaowei; Li, Menglong; Wen, Peng; Xiong, Zixiang

doi:10.3390/e23070910

Cited by 12 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Melalui rekaman video teknologi segmentasi citra dapat digunakan untuk mengawasi kawasan lalu lintas padat disuatu daerah. Segmentasi citra dapat digunakan untuk melakukan proses objek deteksi, diantaranya adalah deteksi plat nomor, jenis kendaraan, dan laju kendaraan [4] [5].…”

Section: Pendahuluanunclassified

Sistem Deteksi Laju dan Plat Nomor Kendaraan Berbasis Video Rekaman Menggunakan YOLOv5-DeepSORT dan HyperLPR

Setya Budi,

Baiquni,

Mulyanti

et al. 2024

Jurnal Ilmiah Telekomunikasi, Kendali dan Elektronika Terapan

View full text Add to dashboard Cite

- Salah satu penyebab terjadinya kecelakaan adalah kurangnya kewaspadaan pengendara dan pelanggaran laju kendaraan melampaui batas maksimal. Untuk mengurangi tindak pelanggaran tersebut diperlukan pengawasan lalu lintas pada area jalan terutama di area yang rawan terjadi kecelakaan. Dalam penelitian ini dikembangkan sistem deteksi laju dan plat nomor kendaraan berbasis video rekaman menggunakan YOLOv5-DeepSORT dan HyperLPR untuk mengatasi permasalahan tersebut. Dalam sistem ini digunakan YOLOv5 dan DeepSORT untuk mendeteksi dan melacak pergerakan kendaraan sehingga diperoleh perpindahan jarak kendaraan yang digunakan sebagai acuan deteksi laju kendaraan. Adapun HyperLPR digunakan untuk mendeteksi plat nomor dari kendaraan tersebut. Metode yang digunakan dalam penelitian ini yaitu metode experimen dengan melakukan perekaman video pada ruas jalan tol Cipali yang digunakan sebagai input dari program deteksi laju dan plat nomor kendaraan. Hasil pengujian deteksi objek kendaraan menggunakan YOLOv5 diperoleh nilai evaluasi metric precision sebesar 100%. Dan pengujian deteksi laju kendaraan diperoleh nilai rata-rata presentase eror sebesar 7,6% terhadap nilai sebenarnya. Adapun dari deteksi plat nomor kendaraan diperoleh hasil akurasi karakter secara keseluruhan sebesar 91,82 %. Dari hasil tersebut dapat disimpulkan bahwa sistem deteksi laju dan plat nomor kendaraan yang dikembangkan memiliki akurasi yang sangat baik dan dapat dipertimbangkan untuk digunakan dengan memperhatikan beberapa kriteria implementasi yang telah ditentukan. Kata kunci: Laju kendaraan, plat nomor kendaraan, YOLOv5, DeepSORT HyperLPR.

show abstract

Section: Pendahuluanunclassified

Sistem Deteksi Laju dan Plat Nomor Kendaraan Berbasis Video Rekaman Menggunakan YOLOv5-DeepSORT dan HyperLPR

Setya Budi,

Baiquni,

Mulyanti

et al. 2024

Jurnal Ilmiah Telekomunikasi, Kendali dan Elektronika Terapan

View full text Add to dashboard Cite

show abstract

“…Zha, M. et al [ 35 ] used feature pyramid network and coordinate attention [ 36 ] for forestry pest detection, and obtained 38.62% mAP on the COCO dataset based on MobileNetv2. Yang, L et al [ 37 ] proposed a vehicle multi-feature detection algorithm based on binocular cameras, combined with feature pyramid network to realize the recognition of the three characteristics of license plate, sign and light, improving the robustness of vehicle speed measurement.…”

Section: Related Workmentioning

confidence: 99%

Visual Recognition of Traffic Signs in Natural Scenes Based on Improved RetinaNet

Liu

Cai

Tang

et al. 2022

Entropy

View full text Add to dashboard Cite

Aiming at recognizing small proportion, blurred and complex traffic sign in natural scenes, a traffic sign detection method based on RetinaNet-NeXt is proposed. First, to ensure the quality of dataset, the data were cleaned and enhanced to denoise. Secondly, a novel backbone network ResNeXt was employed to improve the detection accuracy and effection of RetinaNet. Finally, transfer learning and group normalization were adopted to accelerate our network training. Experimental results show that the precision, recall and mAP of our method, compared with the original RetinaNet, are improved by 9.08%, 9.09% and 7.32%, respectively. Our method can be effectively applied to traffic sign detection.

show abstract

“…The detection method's speed, precision, and complexity are greatly enhanced. YOLOv4 is also utilized in the inspection of vehicles (Yang et al, 2021 ; Mu et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Real-time vehicle target detection in inclement weather conditions based on YOLOv4

Wang

Zhao

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

As a crucial component of the autonomous driving task, the vehicle target detection algorithm directly impacts driving safety, particularly in inclement weather situations, where the detection precision and speed are significantly decreased. This paper investigated the You Only Look Once (YOLO) algorithm and proposed an enhanced YOLOv4 for real-time target detection in inclement weather conditions. The algorithm uses the Anchor-free approach to tackle the problem of YOLO preset anchor frame and poor fit. It better adapts to the detected target size, making it suitable for multi-scale target identification. The improved FPN network transmits feature maps to unanchored frames to expand the model's sensory field and maximize the utilization of model feature data. Decoupled head detecting head to increase the precision of target category and location prediction. The experimental dataset BDD-IW was created by extracting specific labeled photos from the BDD100K dataset and fogging some of them to test the proposed method's practical implications in terms of detection precision and speed in Inclement weather conditions. The proposed method is compared to advanced target detection algorithms in this dataset. Experimental results indicated that the proposed method achieved a mean average precision of 60.3%, which is 5.8 percentage points higher than the original YOLOv4; the inference speed of the algorithm is enhanced by 4.5 fps compared to the original, reaching a real-time detection speed of 69.44 fps. The robustness test results indicated that the proposed model has considerably improved the capacity to recognize targets in inclement weather conditions and has achieved high precision in real-time detection.

show abstract

Robust Vehicle Speed Measurement Based on Feature Information Fusion for Vehicle Multi-Characteristic Detection

Cited by 12 publications

References 45 publications

Sistem Deteksi Laju dan Plat Nomor Kendaraan Berbasis Video Rekaman Menggunakan YOLOv5-DeepSORT dan HyperLPR

Sistem Deteksi Laju dan Plat Nomor Kendaraan Berbasis Video Rekaman Menggunakan YOLOv5-DeepSORT dan HyperLPR

Visual Recognition of Traffic Signs in Natural Scenes Based on Improved RetinaNet

Real-time vehicle target detection in inclement weather conditions based on YOLOv4

Contact Info

Product

Resources

About