Detection of Safety Helmet Wearing Based on Improved Faster R-CNN

Chen, Songbo; Tang, Wenhu; Ji, Tianyao; Zhu, Hui‐Ling; Ouyang, Ye; Wang, Wenbo

doi:10.1109/ijcnn48605.2020.9207574

Cited by 47 publications

(21 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Untuk perancangan sistem deteksi helm, dalam penelitian ini telah digunakan algoritma CNN (Convolutional Neural Network). Convolutional Neural Network [2], [4], [5] adalah salah satu algoritma pada deep learning yang dapat menerima sebuah inputan gambar dan di gunakan untuk mengidentifikasi dan mengenali sebuah gambar yang memiliki kelebihan yaitu mempunyai akurasi yang tinggi tetapi memiliki kelemahan yaitu proses pelatihan yang cukup lama. Dalam tahap awal proses pengembangan sistem deteksi helm ini, penulis melakukan percobaan perbandingan menggunakan beberapa arsitektur dari Convolutional Neural Network dan diharapkan dapat mendapatkan hasil yang maksimal.…”

Section: Pendahuluanunclassified

“…ConvNet sekarang menyediakan metode yang lebih terukur untuk klasifikasi gambar dan tugas pengenalan objek, menggunakan prinsip aljabar linier, terutama perkalian matriks, untuk mengenali pola dalam gambar. Dengan kata lain, mereka mungkin menuntut komputasi dan memerlukan unit pemrosesan grafis (GPU) untuk melatih model [4], [5], [16]- [18]. CNN mempunyai 3 lapisan utama, berikut adalah lapisan-lapisan tersebut: 1.…”

Section: Cnn(convolutional Neural Network)unclassified

See 1 more Smart Citation

Convolutional Neural Network Dalam Sistem Deteksi Helm Pada Pengendara Motor

et al. 2022

View full text Add to dashboard Cite

Di tahun ini sudah terjadi perubahan atau revolusi dalam sistem industri yaitu revolusi industri 4.0, di mana industri sudah mengimplementasikan sebuah mesin-mesin yang serba cepat dan praktis untuk membantu dalam hal produktivitas. Dengan semakin pesatnya teknologi, banyak alat-alat yang di ciptakan untuk perkembangan teknologi di dunia. Pemanfaatan teknologi di gunakan untuk sebagai penggerak di pesatnya sistem berbasis AI ini dapat di manfaatkan untuk di berbagai bidang, salah satunya adalah penerapan sistem deep learning dan salah satu teknik yang terkenal dan sudah banyak digunakan untuk klasifikasi citra adalah menggunakan metode Jaringan Syaraf Tiruan (JST) yang mampu mengenali wajah manusia dan suatu gambar citra lalu mengklasifikasinya atau bisa di sebut image classification dan image recognition. Untuk perancangan sistem deteksi helm pada penelitian ini akan menggunakan algoritma CNN(Convolutional Neural Network). Convolutional Neural Network dan untuk model arsitektur yang di gunakan adalah MobileNetV2 dengan akurasi 80%, yang dapat di kategorikan baik dalam sebuah akurasi.

show abstract

Section: Pendahuluanunclassified

Section: Cnn(convolutional Neural Network)unclassified

Convolutional Neural Network Dalam Sistem Deteksi Helm Pada Pengendara Motor

et al. 2022

View full text Add to dashboard Cite

show abstract

“…R.Girshick [13] combined R-CNN with SPPNet to create the Fast Regions with CNN (Fast R-CNN) target detection model, so that the detection model can simultaneously train classifiers and border regressors. Due to the sluggish selective search process utilized in the Fast R-CNN detection model's candidate region selection, S.Ren et al [14] introduced the Faster Regions with CNN (Faster R-CNN) method, the first end-to-end deep learning object recognition model.…”

Section: Introductionmentioning

confidence: 99%

Safety helmet wearing detection algorithm based on DSM-YOLO

Zhang,

Feng,

et al. 2024

Preprint

View full text Add to dashboard Cite

Safety helmets can effectively prevent miners from accidental head injuries, reduce accident rates during coal mine, and safety helmet-wearing detection is of great significance to the safety management of coal mine, and is an important component of video surveillance systems. This paper proposes a new safety helmet-wearing detection algorithm called Depthwise Separable Multi-factor YOLO (DSM-YOLO). First, the algorithm uses Depthwise Separable Convolution(DSConv) to reduce the number of parameters, deepens the extraction of deep feature information, speed up feature transfer in the model, and improves the speed of helmet detection. Second, in order to make a better match between the predicted box of the target and the corresponding ground truth box, a multi-factor loss function is introduced, and the multi-factor loss function simultaneously takes into account the intersection ratio loss, distance loss, aspect ratio loss, and angle perception loss, which improves the accuracy of helmet detection. The results of the experiments showed that the inference speed of the algorithm is 62.5 Frames/s, which is 19.0 Frames/s faster than the YOLOv7 algorithm; the average precision is 95.1%, which is 3.4% higher than the YOLOv7 algorithm, meeting the real-time detection requirements for safety helmet wearing in coal mine.

show abstract

“…Guo et al [8] presented the Faster R-CNN algorithm based on a VGG feature extraction network to determine whether a worker is wearing a helmet. Chen et al [9] adopted the kmeans ++ algorithm to re-cluster small targets in safety helmets, and then used the improved Faster R-CNN algorithm to judge whether to wear a safety helmet. As a representative work of the two-stage target detection algorithm, the Faster R-CNN [10] algorithm needs to obtain an anchor box before classifying and locating the target.…”

Section: Introductionmentioning

confidence: 99%

Safety Helmet Wearing Detection in Aerial Images Using Improved YOLOv4

Chen¹,

Liu²,

Zhou³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In construction, it is important to check whether workers wear safety helmets in real time. We proposed using an unmanned aerial vehicle (UAV) to monitor construction workers in real time. As the small target of aerial photography poses challenges to safety-helmet-wearing detection, we proposed an improved YOLOv4 model to detect the helmet-wearing condition in aerial photography: (1) By increasing the dimension of the effective feature layer of the backbone network, the model's receptive field is reduced, and the utilization rate of fine-grained features is improved. (2) By introducing the cross stage partial (CSP) structure into path aggregation network (PANet), the calculation amount of the model is reduced, and the aggregation efficiency of effective features at different scales is improved. (3) The complexity of the YOLOv4 model is reduced by introducing group convolution and the pruning PANet multi-scale detection mode for de-redundancy. Experimental results show that the improved YOLOv4 model achieved the highest performance in the UAV helmet detection task, that the mean average precision (mAP) increased from 83.67% of the original YOLOv4 model to 91.03%, and that the parameter amount of the model is reduced by 24.7%. The results prove that the improved YOLOv4 model can effectively respond to the requirements of real-time detection of helmet wearing by UAV aerial photography.

show abstract

Detection of Safety Helmet Wearing Based on Improved Faster R-CNN

Cited by 47 publications

References 18 publications

Convolutional Neural Network Dalam Sistem Deteksi Helm Pada Pengendara Motor

Convolutional Neural Network Dalam Sistem Deteksi Helm Pada Pengendara Motor

Safety helmet wearing detection algorithm based on DSM-YOLO

Safety Helmet Wearing Detection in Aerial Images Using Improved YOLOv4

Contact Info

Product

Resources

About