Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false...Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false detection rates when applying object recognition algorithms tailored for remote sensing imagery.Additionally,these complexities contribute to inaccuracies in target localization and hinder precise target categorization.This paper addresses these challenges by proposing a solution:The YOLO-MFD model(YOLO-MFD:Remote Sensing Image Object Detection withMulti-scale Fusion Dynamic Head).Before presenting our method,we delve into the prevalent issues faced in remote sensing imagery analysis.Specifically,we emphasize the struggles of existing object recognition algorithms in comprehensively capturing critical image features amidst varying scales and complex backgrounds.To resolve these issues,we introduce a novel approach.First,we propose the implementation of a lightweight multi-scale module called CEF.This module significantly improves the model’s ability to comprehensively capture important image features by merging multi-scale feature information.It effectively addresses the issues of missed detection and mistaken alarms that are common in remote sensing imagery.Second,an additional layer of small target detection heads is added,and a residual link is established with the higher-level feature extraction module in the backbone section.This allows the model to incorporate shallower information,significantly improving the accuracy of target localization in remotely sensed images.Finally,a dynamic head attentionmechanism is introduced.This allows themodel to exhibit greater flexibility and accuracy in recognizing shapes and targets of different sizes.Consequently,the precision of object detection is significantly improved.The trial results show that the YOLO-MFD model shows improvements of 6.3%,3.5%,and 2.5%over the original YOLOv8 model in Precision,map@0.5 and map@0.5:0.95,separately.These results illustrate the clear advantages of the method.展开更多
Detecting surface defects on steel,especially in complex loading environments,poses significant challenges.In response,we introduce EDFW-YOLO,an algorithm built upon you only look once version 8(YOLOv8)specifically de...Detecting surface defects on steel,especially in complex loading environments,poses significant challenges.In response,we introduce EDFW-YOLO,an algorithm built upon you only look once version 8(YOLOv8)specifically designed for detecting surface defects on hot-rolled steel strips.Our method enhances multi-scale feature fusion through the incorporation of the multi-scale conversion module(C2f-EMSC).Additionally,we elevate detection accuracy by integrating the dynamic head target detection head,the focal modulation module,and the WIoU_Loss bounding box regression function.Experimental results on the NEU-DET dataset demonstrate that our optimized YOLOv8 model achieves the mean average precision(mAP)of 77.7%,with a 5.2%increase in network constraint rate.To adapt to different operating environments,it further improved the mAP to 78.5%through data enhancement.Verification results on PCB defect data show that the algorithm has excellent generalization ability.This optimized algorithm significantly improves the extraction and fusion of surface defect features on hot-rolled strip steel and serves as a valuable reference for surface defect detection in alloy materials.展开更多
基金the Scientific Research Fund of Hunan Provincial Education Department(23A0423).
文摘Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false detection rates when applying object recognition algorithms tailored for remote sensing imagery.Additionally,these complexities contribute to inaccuracies in target localization and hinder precise target categorization.This paper addresses these challenges by proposing a solution:The YOLO-MFD model(YOLO-MFD:Remote Sensing Image Object Detection withMulti-scale Fusion Dynamic Head).Before presenting our method,we delve into the prevalent issues faced in remote sensing imagery analysis.Specifically,we emphasize the struggles of existing object recognition algorithms in comprehensively capturing critical image features amidst varying scales and complex backgrounds.To resolve these issues,we introduce a novel approach.First,we propose the implementation of a lightweight multi-scale module called CEF.This module significantly improves the model’s ability to comprehensively capture important image features by merging multi-scale feature information.It effectively addresses the issues of missed detection and mistaken alarms that are common in remote sensing imagery.Second,an additional layer of small target detection heads is added,and a residual link is established with the higher-level feature extraction module in the backbone section.This allows the model to incorporate shallower information,significantly improving the accuracy of target localization in remotely sensed images.Finally,a dynamic head attentionmechanism is introduced.This allows themodel to exhibit greater flexibility and accuracy in recognizing shapes and targets of different sizes.Consequently,the precision of object detection is significantly improved.The trial results show that the YOLO-MFD model shows improvements of 6.3%,3.5%,and 2.5%over the original YOLOv8 model in Precision,map@0.5 and map@0.5:0.95,separately.These results illustrate the clear advantages of the method.
基金supported by the National Natural Science Foundation of China(No.61961037).
文摘Detecting surface defects on steel,especially in complex loading environments,poses significant challenges.In response,we introduce EDFW-YOLO,an algorithm built upon you only look once version 8(YOLOv8)specifically designed for detecting surface defects on hot-rolled steel strips.Our method enhances multi-scale feature fusion through the incorporation of the multi-scale conversion module(C2f-EMSC).Additionally,we elevate detection accuracy by integrating the dynamic head target detection head,the focal modulation module,and the WIoU_Loss bounding box regression function.Experimental results on the NEU-DET dataset demonstrate that our optimized YOLOv8 model achieves the mean average precision(mAP)of 77.7%,with a 5.2%increase in network constraint rate.To adapt to different operating environments,it further improved the mAP to 78.5%through data enhancement.Verification results on PCB defect data show that the algorithm has excellent generalization ability.This optimized algorithm significantly improves the extraction and fusion of surface defect features on hot-rolled strip steel and serves as a valuable reference for surface defect detection in alloy materials.
