A Small-Sized Object Detection Oriented Multi-Scale Feature Fusion Approach With Application to Defect Detection

A printed circuit board (PCB) functions as a substrate essential for interconnecting and securing electronic components. Its widespread integration is evident in modern electronic devices, spanning computers, cell phones, televisions, digital cameras, and diverse apparatus. Ensuring product quality mandates meticulous defect inspection, a task exacerbated by the heightened precision of contemporary circuit boards, intensifying the challenge of defect detection. Conventional algorithms, hampered by inefficiency and limited accuracy, fall short of usage benchmarks. In contrast, PCB defect detection algorithms rooted in deep learning hold promise for achieving heightened accuracy and efficiency, bolstered by their adeptness at discerning novel defect types. This review presents a comprehensive analysis of machine vision-based PCB defect detection algorithms, traversing the realms of machine learning and deep learning. It commences by contextualizing and elucidating the significance of such algorithms, followed by an extensive exploration of their evolution within the machine vision framework, encompassing classification, comparison, and analysis of algorithmic principles, strengths, and weaknesses. Moreover, the introduction of widely used PCB defect detection datasets and assessment indices enhances the evaluation of algorithmic performance. Currently, the detection accuracy can exceed 95% at an Intersection over Union (IoU) of 0.5. Lastly, potential future research directions are identified to address the existing issues in the current algorithm. These directions include utilizing Transformers as a foundational framework for creating new algorithms and employing techniques like Generative Adversarial Networks (GANs) and reinforcement learning to enhance PCB defect detection performance.

Printed Circuit Board (PCB) defect detection is essential for ensuring reliability in electronic manufacturing, as defects such as spur, mouse bites, missing holes, and open circuits can severely degrade performance or cause board failure. Traditional AOI systems often suffer from high false alarm rates due to lighting variations and complex backgrounds, while many deep learning methods struggle to efficiently detect tiny defects. To address these challenges, this study proposes SCMEO-DETR, a lightweight and effective end-to-end detector built upon RT-DETR. The model integrates a Sparse Enhanced Pyramid Network (SEPN) and a Context-Guided Feature Pyramid Network (CGFPN) to strengthen fine-grained feature extraction and contextual reasoning. An Optimized and Adaptive Backbone (OA-backbone) and an improved Enhanced Upsampling Convolution Block with Shift Channel Mix (EUCB-SC) block further enhance representational efficiency through adaptive sampling and channel shift mechanisms. An upgraded Multi-Head Multi-Scale Intra-Scale Feature-fusion Module (M2-IFM) module also improves feature interaction. Experiments on the PKU-Market-PCB dataset demonstrate that SCMEO-DETR achieves 97.10% mAP@0.5, surpassing RT-DETR-R18 by 5.28% while reducing parameters and GFLOPs by 50% and 39%. These results confirm its effectiveness and deployability for real-time PCB defect detection.

Object detection (OD) in unmanned aerial vehicle (UAV) images faces many challenges, with diverse-scale objects and small objects being particularly prominent issues. To alleviate these challenges, we propose a novel multiscale feature learning and feature fusion network under the guidance of deformable convolution. First, a deformable convolution-guided feature learning (DCGFL) block is designed in the backbone to extract more effective multiscale features. The DCGFL block leverages the adaptability of deformable convolution to the shapes and scales of objects, akin to spatial attention. Moreover, it also employs channel attention to identify important feature maps. Hence, the proposed backbone possesses the functionality of spatial attention and channel attention. Second, in the neck, we devise a simple generalized feature pyramid network (SimpleGFPN) with several deformable convolution-guided feature fusion (DCGFF) blocks to fuse multiscale features. The proposed neck has cross-layer and cross-scale pathways, facilitating effective information exchange and fusion between shallow spatial and deep semantic features. Third, the SIoU loss is used to better model the bounding box regression loss. Finally, experimental results on the VisDrone2021 and UAVDT datasets show that the proposed method outperforms the compared OD methods. In terms of mean average precision, we obtain 37.8% on VisDrone2021 and 18.5% on UAVDT.

Convolutional neural network (CNN) has led to significant progress in object detection. In order to detect the objects in various sizes, the object detectors often exploit the hierarchy of the multi-scale feature maps called feature pyramid, which is readily obtained by the CNN architecture. However, such feature maps do not fully consider the supplementary effect of contextual information on semantics. In this work, we proposed a feature fusion method of residual attention based on the SSD benchmark network call Improved SSD to make full use of context information to improve the characterization ability of feature maps. Besides, we use the residual attention mechanism to reinforce the key features to further improve the detector performance. The experiment result on benchmark dataset PASCAL VOC shows that the map of the proposed method with input image sizes of 300×300 and 512×512 is 78.8% and 80.7%.

Online knowledge distillation conducts knowledge transfer among all student models to alleviate the reliance on pre-trained models. However, existing online methods rely heavily on the prediction distributions and neglect the further exploration of the representational knowledge. In this paper, we propose a novel Multi-scale Feature Extraction and Fusion method (MFEF) for online knowledge distillation, which comprises three key components: Multi-scale Feature Extraction, Dual-attention and Feature Fusion, towards generating more informative feature maps for distillation. The multiscale feature extraction exploiting divide-and-concatenate in channel dimension is proposed to improve the multi-scale representation ability of feature maps. To obtain more accurate information, we design a dual-attention to strengthen the important channel and spatial regions adaptively. Moreover, we aggregate and fuse the former processed feature maps via feature fusion to assist the training of student models. Extensive experiments on CIF AR-10, CIF AR-100, and CINIC-10 show that MFEF transfers more beneficial representational knowledge for distillation and outperforms alternative methods among various network architectures

Printed circuit boards (PCBs) are ubiquitous and essential electronic components. Tiny targets and high precision are the focus of PCB defect detection. This paper proposes an improved model focusing on tiny defect detection and model compression to achieve better performance in PCB defect detection. The improved model has a compact structure based on MobileNet v3 Small-CA and an image-cutting layer. Moreover, it applies an improved multi-scale fusion step with a location weighted mechanism to enhance representation performance. The proposed model outperforms state-of-the-art detection algorithms such as Faster R-CNN, EfficientDet, SSD, and YOLO v7, based on experimental results on a public synthetic PCB dataset. The proposed tiny object detection model has better performances on speed and detection accuracy, thereby benefitting the manufacturing industries associated with PCBs.

With special consideration for complex scenes and densely distributed small objects, this frequently leads to serious false and missed detections for unmanned aerial vehicle (UAV) images in small object detection scenarios. Consequently, we propose a UAV image small object detection algorithm, termed SMA-YOLO. Firstly, a parameter-free simple slicing convolution (SSC) module is integrated in the backbone network to slice the feature maps and enhance the features so as to effectively retain the features of small objects. Subsequently, to enhance the information exchange between upper and lower layers, we design a special multi-cross-scale feature pyramid network (M-FPN). The C2f-Hierarchical-Phantom Convolution (C2f-HPC) module in the network effectively reduces information loss by fine-grained multi-scale feature fusion. Ultimately, adaptive spatial feature fusion detection Head (ASFFDHead) introduces an additional P2 detection head to enhance the resolution of feature maps to better locate small objects. Moreover, the ASFF mechanism is employed to optimize the detection process by filtering out information conflicts during multi-scale feature fusion, thereby significantly optimizing small object detection capability. Using YOLOv8n as the baseline, SMA-YOLO is evaluated on the VisDrone2019 dataset, achieving a 7.4% improvement in mAP@0.5 and a 13.3% reduction in model parameters, and we also verified its generalization ability on VAUDT and RSOD datasets, which demonstrates the effectiveness of our approach.

Unmanned aerial vehicles (UAVs) have been widely used in post-disaster search and rescue operations, object tracking, and other tasks. Therefore, the autonomous perception of UAVs based on computer vision has become a research hotspot in recent years. However, UAV images include dense objects, small objects, and arbitrary object directions, which bring about significant challenges to existing object detection methods. To alleviate these issues, we propose a global-local feature enhanced network (GLF-Net). Considering the difficulty of processing UAV images with complex scenes and dense objects, we designed a backbone based on an involution and self-attention that can extract effective features from complex objects. A multiscale feature fusion module is also proposed to address the presence of numerous small objects in UAV images through multiscale object detection and feature fusion. To accurately detect rotated objects, a rotated regional proposal network was designed based on the midpoint offset representation, which can apply a rotated box to determine the real direction and contour of an object. GLF-Net achieves a state-of-the-art detection accuracy (86.52% mAP) on our created RO-UAV dataset, while achieving 96.95% and 97% mAP on the public datasets HRSC2016 and UCAS-AOU, respectively. The experimental results demonstrate that our method achieves a high detection accuracy and generalization, which can meet the practical requirements of UAVs under various complex scenarios.

A multi-scale semantic feature fusion method for remote sensing crop classification

Object detection is a fundamental task in the field of computer vision, and one of its essential requirements is high-quality feature fusion. Previous works have made various efforts in this regard: CNN-based detectors use convolutional blocks to fuse local features and dense prior knowledge to predict objects, while query-based detectors fuse global features by self-attention then decode features with object queries. However, their feature fusion methods are relatively monotonous. Considering that different modules are applicable to different dimensions, we proposed an object detector named CFFMixer which used hybrid architecture to achieve multi-dimensional feature fusion. The sampling strategy to extract abundant local and global features was first introduced then the Comprehensive Feature Fusion Network (CFFN) was proposed to integrate them. CFFN not only achieved local and global features interaction in the spatial dimension, but also fused semantics in the channel dimension. Furthermore, we conducted experiments and made a comparison with competitive models, our model finally got 43.0 mAP on COCO 2017 dataset within 12 epochs. Experimental results showed that the model’s accuracy benefits from the powerful feature fusion capability of CFFN. Besides, we performed ablation studies on our modules to evaluate their effectiveness.

General deep learning methods achieve high-level semantic feature representation by aggregating hierarchical features, which performs well in object detection tasks. However, issues arise with general deep learning methods in UAV-based remote sensing image object detection tasks. Firstly, general feature aggregation methods such as stride convolution may lead to information loss in input samples. Secondly, common FPN methods introduce conflicting information by directly fusing feature maps from different levels. These shortcomings limit the model’s detection performance on small and weak targets in remote sensing images. In response to these concerns, we propose an unmanned aerial vehicle (UAV) object detection algorithm, IF-YOLO. Specifically, our algorithm leverages the Information-Preserving Feature Aggregation (IPFA) module to construct semantic feature representations while preserving the intrinsic features of small objects. Furthermore, to filter out irrelevant information introduced by direct fusion, we introduce the Conflict Information Suppression Feature Fusion Module (CSFM) to improve the feature fusion approach. Additionally, the Fine-Grained Aggregation Feature Pyramid Network (FGAFPN) facilitates interaction between feature maps at different levels, reducing the generation of conflicting information during multi-scale feature fusion. The experimental results on the VisDrone2019 dataset demonstrate that in contrast to the standard YOLOv8-s, our enhanced algorithm achieves a mean average precision (mAP) of 47.3%, with precision and recall rates enhanced by 6.3% and 5.6%, respectively.

Abandoned object detection is a critical task in the field of public safety. However, existing methods perform poorly when detecting small and occluded objects, leading to high false detection and missed detection rates. To address this issue, this paper proposes an abandoned object detection method that integrates an adaptive dual-background model with SAO-YOLO (Small Abandoned Object YOLO). The goal is to reduce false and missed detection rates for small and occluded objects, thereby improving overall detection accuracy. First, the paper introduces an adaptive dual-background model that adjusts according to scene changes, reducing noise interference in the background model. When combined with an improved PFSM (Pixel-based Finite State Machine) model, this enhances detection accuracy and robustness. Next, a network model called SAO-YOLO is designed. Key improvements within this model include the SAO-FPN (Small Abandoned Object FPN) feature extraction network, which fully extracts features of small objects, and a lightweight decoupled head, SODHead (Small Object Detection Head), which precisely extracts local features and enhances detection accuracy through multi-scale feature fusion. Finally, experimental results show that SAO-YOLO increases mAP@0.5 and mAP@0.5:0.95 by 9.0% and 5.1%, respectively, over the baseline model. It outperforms other advanced detection models. Ultimately, after a series of experiments on the ABODA, PETS2006, and AVSS2007 datasets, the proposed method achieved an average detection precious of 91.1%, surpassing other advanced methods. It significantly outperforms other advanced detection methods. This approach notably reduces false and missed detections, especially for small and occluded objects.

Object detection is challenging in large-scale images captured by unmanned aerial vehicles (UAVs), especially when detecting small objects with significant scale variation. Most solutions employ the fusion of different scale features by building multi-scale feature pyramids to ensure that the detail and semantic information are abundant. Although feature fusion benefits object detection, it still requires the long-range dependencies information necessary for small objects with significant scale variation detection. We propose a simple yet effective scale enhancement pyramid network (SEPNet) to address these problems. A SEPNet consists of a context enhancement module (CEM) and feature alignment module (FAM). Technically, the CEM combines multi-scale atrous convolution and multi-branch grouped convolution to model global relationships. Additionally, it enhances object feature representation, preventing features with lost spatial information from flowing into the feature pyramid network (FPN). The FAM adaptively learns offsets of pixels to preserve feature consistency. The FAM aims to adjust the location of sampling points in the convolutional kernel, effectively alleviating information conflict caused by the fusion of adjacent features. Results indicate that the SEPNet achieves an AP score of 18.9% on VisDrone, which is 7.1% higher than the AP score of state-of-the-art detectors RetinaNet achieves an AP score of 81.5% on PASCAL VOC.

The detection of defects is indispensable in industrial production. Surface defects have different scales. Both minimal flaws and significant scratches may appear on the same product. The standard method uses a multi-scale feature fusion network, introducing many parameters that may reduce the inference speed. In actual industrial production scenarios, inference speed and accuracy play an equally important role. Therefore we propose an algorithm to effectively improve the detection speed while improving the detection accuracy. The model proposed in this paper called “YOLO with lightweight feature fusion network(LFF-YOLO).” First, we use ShuffleNetv2 as a feature extraction network to reduce the number of parameters. Then, to improve the efficiency of multi-scale feature fusion, we propose the lightweight feature pyramid network (LFPN). Considering that the fixed receptive field is difficult to adapt to the defects of different scales, it may lead to the difficulty of model convergence and seriously affect the detection performance. Therefore, we propose the adaptive receptive field feature extraction (ARFFE) module, which weights the multi-receptive field channels to generate multi-receptive field information. In addition, focal loss is used to solve the problem of imbalance between positive and negative samples. Finally, we conducted experiments on NEU-DET (79.23% mAP), Peking University printed circuit board defect dataset (93.31% mAP),and GC10-DET (59.78% mAP), respectively. Extensive experiments show that our proposed method achieves optimal detection speed compared with the prevailing methods, and the detection accuracy of our method is also highly competitive.

Printed Circuit Board (PCB) defect inspection is critical in electronics manufacturing, yet annotating large training sets is labor-intensive and costly. This paper proposes a semi-supervised PCB defect detection framework based on YOLOv5, which leverages a small labeled dataset and a larger pool of unlabeled images through an iterative self-training pipeline. A YOLOv5 detector is first trained on the limited labeled data, then used to generate pseudo-labels on unlabeled images; high-confidence detections are retained as defect annotations, and the model is retrained on the combination of labeled and pseudo-labeled data. This pseudo-labeling and retraining cycle is repeated for multiple iterations to progressively refine the detector. The approach is evaluated on a PCB defect dataset with 100 labeled and 1,000 unlabeled images, and shows significant gains over a fully supervised baseline. The proposed semi-supervised YOLOv5 achieves 91.6% mAP@0.5 with only 100 labeled images, outperforming both the baseline (87.0% mAP) and prior semi-supervised methods, while substantially improving recall and precision. The results demonstrate that the method effectively reduces annotation effort while maintaining high detection accuracy, providing a simple, confidence-thresholded self-training strategy for deploying PCB defect detectors under limited labeling resources. This work directly supports SDG 9 by enabling cost-efficient, high-accuracy AI-based PCB inspection that strengthens intelligent and sustainable manufacturing systems.