SE-YOLOv5x: An Optimized Model Based on Transfer Learning and Visual Attention Mechanism for Identifying and Localizing Weeds and Vegetables

Zhang, Jianlin; Su, Wen-Hao; Zhang, Heyi; Peng, Yankun

doi:10.3390/agronomy12092061

Cited by 34 publications

(21 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows for proper cross-channel interaction and avoids the complexity of the model that a fully connected layer would otherwise create. Finally, the weights of each channel generated after the 2D convolutional feature transformation and Sigmoid feature mapping are multiplied by their respective weights [25].…”

Section: B Improvements In Spatial Pyramidal Poolingmentioning

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

Section: B Improvements In Spatial Pyramidal Poolingmentioning

confidence: 99%

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

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Many previous studies have used the SE attention mechanism to improve network detection performance [22,23,24], but this attention mechanism only considers inter-channel information and ignores location information, although subsequent researchers have proposed attention mechanisms such as CBAM [25,26] to try to use convolution to extract the location information after reducing the channel dimension, The Coordinate Attention (CA) [21] used in this paper can encode horizontal and vertical location information into channel attention, making the detection model capable of extracting a wide range of location information without incurring too much computational cost.…”

Section: Ca Attention Mechanismmentioning

confidence: 99%

Automotive air conditioning vent defect detection method based on improved yolov5

Zheng

et al. 2023

Preprint

View full text Add to dashboard Cite

In response to the low efficiency and high miss rate in the manual quality inspection of automotive air vent trim rings by current automotive suppliers, this paper proposes an improved YOLOv5-based method for detecting defects in automotive air vent trim rings. Firstly, the Coordinate Attention(CA) is introduced into the network to improve the feature extraction capability of the network for defects in automotive air vent trim rings. Secondly, the Space-to-Depth(SPD) module is introduced for downsampling to reduce the loss of subtle features during the downsampling process, which is beneficial for improving the feature extraction of the network for trim ring defects. Finally, the detection head is replaced with a decoupling head to alleviate the conflict between the classification task and the regression task, thereby improving the defect detection rate. On a self-generated dataset of defects in automotive air conditioning vent trim rings, the improved network achieves a mean accuracy(mAP) of 93.6%, an accuracy of 91.3%, and a recall rate of 88. 9%. Compared with the original network, the precision is improved by 3.4%, the accuracy is improved by3.2%,and the recall rate is improved by 3%.The proposed method can achieve defect detection in automotive air conditioning vent trim rings, laying a foundation for building an automated quality inspection system for automotive air conditioning vent trim rings.

show abstract

“…Other studies were carried out on the classification of weed species based on supervised and semi-supervised learning methods [68,69]. In the future, advanced network models and more comprehensive datasets are needed to enable the identification of multiple crops and common weeds [70]. GCN-graph convolutional network; CNN-LVQ-convolutional neural network-learning vector quantization; DRCNN-deep residual convolutional neural network; MTS-CNN-multi-task semantic segmentation-convolutional neural network.…”

Section: Weed and Crop Recognition And Segmentationmentioning

confidence: 99%

Convolutional Neural Networks in Computer Vision for Grain Crop Phenotyping: A Review

Wang

2022

Agronomy

Self Cite

View full text Add to dashboard Cite

Computer vision (CV) combined with a deep convolutional neural network (CNN) has emerged as a reliable analytical method to effectively characterize and quantify high-throughput phenotyping of different grain crops, including rice, wheat, corn, and soybean. In addition to the ability to rapidly obtain information on plant organs and abiotic stresses, and the ability to segment crops from weeds, such techniques have been used to detect pests and plant diseases and to identify grain varieties. The development of corresponding imaging systems to assess the phenotypic parameters, yield, and quality of crop plants will increase the confidence of stakeholders in grain crop cultivation, thereby bringing technical and economic benefits to advanced agriculture. Therefore, this paper provides a comprehensive review of CNNs in computer vision for grain crop phenotyping. It is meaningful to provide a review as a roadmap for future research in such a thriving research area. The CNN models (e.g., VGG, YOLO, and Faster R-CNN) used CV tasks including image classification, object detection, semantic segmentation, and instance segmentation, and the main results of recent studies on crop phenotype detection are discussed and summarized. Additionally, the challenges and future trends of the phenotyping techniques in grain crops are presented.

show abstract

SE-YOLOv5x: An Optimized Model Based on Transfer Learning and Visual Attention Mechanism for Identifying and Localizing Weeds and Vegetables

Cited by 34 publications

References 39 publications

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

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

Automotive air conditioning vent defect detection method based on improved yolov5

Convolutional Neural Networks in Computer Vision for Grain Crop Phenotyping: A Review

Contact Info

Product

Resources

About