SF-YOLOv5: A Lightweight Small Object Detection Algorithm Based on Improved Feature Fusion Mode

Liu, Haiying; Sun, Fengqian; Deng, Lixia

doi:10.3390/s22155817

Cited by 101 publications

(28 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One-stage methods do not need to select the sample candidate frame. They can directly obtain the coordinates and type of the target, which not only has better real-time performance, but also has advantages in small-target detection [ 15 , 16 , 17 , 18 ].…”

Section: Methodsmentioning

confidence: 99%

An Efficient and Intelligent Detection Method for Fabric Defects based on Improved YOLOv5

Lin

Liu

Xia

et al. 2022

Sensors

View full text Add to dashboard Cite

Limited by computing resources of embedded devices, there are problems in the field of fabric defect detection, including small defect size, extremely unbalanced aspect ratio of defect size, and slow detection speed. To address these problems, a sliding window multihead self-attention mechanism is proposed for the detection of small targets, and the Swin Transformer module is introduced to replace the main module in the original YOLOv5 algorithm. First, to reduce the distance between several scales, the weighted bidirectional feature network is employed on embedded devices. In addition, it is helpful to improve the perception of small-target faults by incorporating a detection layer to achieve four-scale detection. At last, to improve the learning of positive sample instances and lower the missed detection rate, the generalized focal loss function is finally implemented on YOLOv5. Experimental results show that the accuracy of the improved algorithm on the fabric dataset reaches 85.6%, and the mAP is increased by 4.2% to 76.5%, which meets the requirements for real-time detection on embedded devices.

show abstract

Section: Methodsmentioning

confidence: 99%

An Efficient and Intelligent Detection Method for Fabric Defects based on Improved YOLOv5

Lin

Liu

Xia

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The Prediction Head uses a preset prior bounding box to perform confidence calculation and bounding box regression on each pixel in the three feature maps to obtain a multidimensional array including object class, class confidence, box coordinates, and width and height information. By setting the corresponding threshold to filter the useless information in the array and performing the non-maximum suppression (NMS) process, the final detection information can be output [21], [22].…”

Section: A Yolov5 Network Structure and Improvementsmentioning

confidence: 99%

“…Head outputs the prediction results, and the prediction includes the bounding box loss function and non-maximum suppression [27]. YOLOv5 uses the GIOU loss function as the bounding box loss function [28], and the GIOU is calculated as shown in equation ( 2 Then a confidence calculation and bounding box regression are performed for each pixel in the feature map using a predefined prior anchor. A non-maximum suppression process is performed by setting the corresponding thresholds.…”

Section: Adding a Small Object Detection Layermentioning

confidence: 99%

An Improved YOLOv5 Method for Small Object Detection in UAV Capture Scenes

et al. 2023

View full text Add to dashboard Cite

Aiming at the problem of a large number of small dense objects in high-altitude shooting and complex background noise interference in the captured scenes, an improved object detection algorithm for YOLOv5 UAV capture scenes is proposed. A Feature Enhancement Block (FEBlock) is first proposed to generate adaptive weights for different receptive field features by convolution, assigning major weights to shallow feature maps to improve small object feature extraction ability. The FEBlock is then integrated into Spatial Pyramid Pooling (SPP) to generate Enhanced Spatial Pyramid Pooling (ESPP), which performs feature enhancement for the result of each maximum pooling; and creates new features containing multiscale contextual information with better feature characterization capability by weighting fused contextual features. Secondly, the Self-Characteristic Expansion Plate (SCEP) is proposed, which achieves the fusion and expansion of feature information through compression, non-linear mapping, and expansion with its own module, further improving the network's capacity for feature extraction and generating a new spatial pyramid pooling (ESPP-S) by splicing with ESPP. Finally, a shallower feature map is added as a detection layer to the YOLOv5 network model's large, medium, and small detection layers to improve the network's detection performance for medium and long-range objects. Experiments were conducted on the VisDrone2021 dataset, and the results showed that the improved YOLOv5 model improved mAP0.5 by 4.6%, mAP0.5:0.95 by 2.9%, and precision by 2.7%. The mAP0.5 of the model trained at the input resolution of 1024 × 1024 reached 56.8%. The experiments show that the improved YOLOv5 model can improve object detection accuracy for UAV capture scenes.

show abstract

“…However, YOLO only solved the target of full size. When the project becomes a special scene with a special size, its performance is not as good as some current small-size object detection algorithms [25] [26]. In order to solve this problem, this paper proposed the DC-YOLOv8 algorithm.…”

Section: Of 12mentioning

confidence: 99%

DC-YOLOv8: Small Size Object Detection Algorithm Based on Camera Sensor

Lou¹,

Duan²,

Guo³

et al. 2023

Preprint

View full text Add to dashboard Cite

Traditional camera sensors rely on human eyes for observation. However, the human eye 1 is prone to fatigue when observing targets of different sizes for a long time in complex scenes, and 2 human cognition is limited, which often leads to judgment errors and greatly reduces the efficiency. 3 Target recognition technology is an important technology to judge the target category in camera 4 sensor. In order to solve this problem, a small size target detection algorithm for special scenarios was 5 proposed by this paper. Its advantage is that this algorithm not only has higher precision for small 6 size target detection, but also can ensure that the detection accuracy of each size is not lower than the 7 existing algorithm. In this paper, a new down-sampling method was proposed, which could better 8 preserve the context feature information. The feature fusion network was improved to effectively 9 combine shallow information and deep information. A new network structure was proposed to 10 effectively improve the detection accuracy of the model. In terms of accuracy, it is better than: YOLOX, 11 YOLOXR, YOLOv3, scaled YOLOv5, YOLOv7-Tiny and YOLOv8.Three authoritative public data sets 12 were used in this experiment: a) On Visdron data sets (small size targets), DC-YOLOv8 is 2.5% more 13 accurate than YOLOv8. b) On Tinyperson data sets (minimal size targets), DC-YOLOv8 is 1% more 14 accurate than YOLOv8. c) On PASCAL VOC2007 data sets (Normal size target), DC-YOLOv8 is 0.5% 15 more accurate than YOLOv8.

show abstract

SF-YOLOv5: A Lightweight Small Object Detection Algorithm Based on Improved Feature Fusion Mode

Cited by 101 publications

References 39 publications

An Efficient and Intelligent Detection Method for Fabric Defects based on Improved YOLOv5

An Efficient and Intelligent Detection Method for Fabric Defects based on Improved YOLOv5

An Improved YOLOv5 Method for Small Object Detection in UAV Capture Scenes

DC-YOLOv8: Small Size Object Detection Algorithm Based on Camera Sensor

Contact Info

Product

Resources

About