YOLO-ACN: Focusing on Small Target and Occluded Object Detection

Li, Yongjun; Li, Shasha; Du, Haohao; Chen, Lijia; Zhang, Dongming; Yao, Li

doi:10.1109/access.2020.3046515

Cited by 103 publications

(38 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Based on the domain, the attention mechanisms could be classified into spatial, channel, and mixed domain attention mechanisms. Overall, attention mechanisms have shown significant potential in the area of object detection due to their intuitiveness, versatility, and interpretability [21].…”

Section: B Attentionmentioning

confidence: 99%

Improved Vision-Based Vehicle Detection and Classification by Optimized YOLOv4

et al. 2022

View full text Add to dashboard Cite

Rapid and precise detection and classification of vehicles are vital for the intelligent transportation systems (ITSs). However, due to small gaps between vehicles on the road and interference features of photos, or video frames, containing vehicle images, it is difficult to detect and identify vehicle types quickly and precisely. For solving this problem, a new vehicle detection and classification model, named YOLOv4_AF, is proposed in this paper, based on an optimization of the YOLOv4 model. In the proposed model, an attention mechanism is utilized to suppress the interference features of photos through both the channel dimension and spatial dimension. In addition, a modification on the Feature Pyramid Network (FPN) part of the Path Aggregation Network (PAN), utilized by YOLOv4, is applied in order to enhance further the effective features through down-sampling. This way, the objects can be steadily positioned in the 3D space and the object detection and classification performance of the model can be improved. The results, obtained through experiments conducted on two public data sets, demonstrate that the proposed YOLOv4_AF model outperforms, in this regard, both the original YOLOv4 model and two other state-of-the-art models, Faster R-CNN and EfficientDet, in terms of the mean average precision (mAP) and F1 score, by achieving respective values of 83.45% and 0.816 on the BIT-Vehicle data set, and 77.08% and 0.808 on the UA-DETRAC data set.

show abstract

Section: B Attentionmentioning

confidence: 99%

Improved Vision-Based Vehicle Detection and Classification by Optimized YOLOv4

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Menurut (Li et al 2020) dalam penelitiannya yang berjudul " YOLO-ACN: Focusing on Small Target and Occluded Object Detection " hasil eksperimen kuantitatif menunjukkan bahwa dibandingkan dengan model canggih lainnya, YOLO-ACN yang diusulkan memiliki akurasi dan kecepatan tinggi dalam mendeteksi target kecil dan objek yang terhalang. YOLO-ACN mencapai mAP50 (presisi rata-rata rata-rata) 53,8% dan AP (presisi rata-rata untuk objek) sebesar 18,2% pada kecepatan waktu nyata 22 ms pada dataset MS COCO, dan mAP untuk satu kelas pada dataset KAIST bahkan mencapai lebih dari 80% pada NVIDIA Tesla K40.…”

Section: Pendahuluanunclassified

Implementasi Deteksi Real Time Klasifikasi Jenis Kendaraan Di Indonesia Menggunakan Metode YOLOV5

Mulyana¹,

Rofik²

2022

jptam

View full text Add to dashboard Cite

Negara Indonesia mempunyai kepadatan penduduk yang sangat padat, terutama dikota-kota besar yang dimana jalan selalu dipadati oleh berbagai jenis kendaran. Pada jam sibuk banyaknya kendaraan yang membuat kemacetan dijalan. Oleh karna itu dibutuhkan pembangunan pelebaran jalan untuk menampung kendaraan yang dipadati oleh berbagai jenis kendaraan yang melintas. Agar pembangunan pelebaran jalan yang tepat pada lokasi yang sering terjadinya kepadatan, maka dibutuhkan sistem pendeteksian jenis-jenis kendaraan yang melintas dijalan raya. Meningkatnya pada macam-macam penelitian tentang pengolahan citra digital diantaranya tentang pendeteksian objek, untuk klasifikasi deteksi jenis kendaraan dijalan raya. Pada penelitian ini penulis membuat sistem pendedeteksi objek memakai metode YOLOV5 untuk mendeteksi jenis kendaraan dijalan raya. Penulis menggunakan dataset sebesar 1332 gambar dengan kelas bajaj, becak, bus, mobil, mobil molen, mobil pik’up, sepedah, sepeda motor, dan truk. Pada hasil penelitian menggunakan metode YOLOV5 yang dapat mengenali objek secara konsisten dengan tingkat akurasi yang cukup tinggi dan memiliki nilai akurasi 90%.

show abstract

“…M. Li et al [ 33 ] proposed SE-YOLO, a real-time pedestrian object detection algorithm for small objects in infrared images, which improves the feature modeling ability of the network by introducing an SE block [ 34 ] into YOLOv3, which improved the feature expression ability of the network combined with the SE block. Li et al [ 35 ] developed a detector, YOLO-ACN, by introducing an attention module and a depth-wise separable convolution. Sun et al [ 36 ] proposed I-YOLO, which modified the backbone with EfficientNet and added a preposition network, DRUNet, to reduce the noise of infrared images.…”

Section: Related Workmentioning

confidence: 99%

CAA-YOLO: Combined-Attention-Augmented YOLO for Infrared Ocean Ships Detection

Yuan

Qian

et al. 2022

Sensors

View full text Add to dashboard Cite

Infrared ocean ships detection still faces great challenges due to the low signal-to-noise ratio and low spatial resolution resulting in a severe lack of texture details for small infrared targets, as well as the distribution of the extremely multiscale ships. In this paper, we propose a CAA-YOLO to alleviate the problems. In this study, to highlight and preserve features of small targets, we apply a high-resolution feature layer (P2) to better use shallow details and the location information. In order to suppress the shallow noise of the P2 layer and further enhance the feature extraction capability, we introduce a TA module into the backbone. Moreover, we design a new feature fusion method to capture the long-range contextual information of small targets and propose a combined attention mechanism to enhance the ability of the feature fusion while suppressing the noise interference caused by the shallow feature layers. We conduct a detailed study of the algorithm based on a marine infrared dataset to verify the effectiveness of our algorithm, in which the AP and AR of small targets increase by 5.63% and 9.01%, respectively, and the mAP increases by 3.4% compared to that of YOLOv5.

show abstract

YOLO-ACN: Focusing on Small Target and Occluded Object Detection

Cited by 103 publications

References 40 publications

Improved Vision-Based Vehicle Detection and Classification by Optimized YOLOv4

Improved Vision-Based Vehicle Detection and Classification by Optimized YOLOv4

Implementasi Deteksi Real Time Klasifikasi Jenis Kendaraan Di Indonesia Menggunakan Metode YOLOV5

CAA-YOLO: Combined-Attention-Augmented YOLO for Infrared Ocean Ships Detection

Contact Info

Product

Resources

About