The object detection algorithm of the PCB (Printed Circuit Board) assembly scene based on CNN (Convolutional Neural Network) can significantly improve the production capacity of intelligent manufacturing of electronic products. However, the object class imbalance in the PCB assembly scene, the multi-scale feature imbalance, and the positive/negative sample imbalance in the CNN have become critical problems restricting object detection performance. Based on YOLOv3, this paper proposes a class-balanced Train/Val (Training set/Validation set) split method for object class imbalance, an additional feature fusion strategy for multi-scale feature imbalance, and an efficient anchor concept for positive/negative sample imbalance. These three contributions are Balanced-YOLOv3. After experimental verification, compared with other YOLOv3 series algorithms, the mAP@.5 (Mean Average Precision at Intersection over Union threshold 0.5) and mAP@.5:.95 (average mAP over different Intersection over Union thresholds, from 0.5 to 0.95, step 0.05) of Balanced-YOLOv3 have achieved the best results and ranked third in the metrics of parameter and inference time. Compared with other current anchor-based object detection algorithms, Balanced-YOLOv3 has excellent detection performance and low computational complexity, which effectively solves the problem of imbalanced object detection in PCB assembly scenarios.

/pdf/balanced-yolov3-addressing-the-imbalance-problem-of-object-3sm7xwqx.pdf

Balanced-YOLOv3: Addressing the Imbalance Problem of Object Detection in PCB Assembly Scene

Video object detection is a tough task due to the severe appearance degradation caused by rapid motion, sudden occlusion or rare poses. The great challenge facing video object detection is the simultaneous requirements on both accuracy and speed because the pursuit of one aspect usually causes significant expense to the other. Most existing methods mainly focus on improving detection accuracy with little attention to computationally efficient solutions, and thus they are impractical for many real-world applications. This motivates us to develop a real-time and high-accuracy video object detection method. In this paper, we propose a novel video object detector, called FastVOD-Net, which can yield highly accurate detection results at real-time speed. Specifically, we first develop a temporally-cascaded deformable alignment (TCDA) module to model the object displacements induced by video motion. Then, we introduce another two modules, namely spatially-refined temporal aggregation (SRTA) and attention-guided semantic distillation (AGSD), to improve the appearance feature of the currently processed frame and enhance the semantic representation of non-keyframes, respectively. For keyframe scheduling, we design an adaptive keyframe selection scheduler (AKSS) to adjust the keyframe interval online, making the keyframe usage more rational. On one hand, the characteristics of our FastVOD-Net enable it to sparsely perform expensive feature extraction, which significantly reduces the computational cost and thus guarantees real-time speed. On the other hand, the collaboration of the above tightly-coupled modules and adaptive keyframe scheduler makes FastVOD-Net fully exploit inter-frame temporal dependencies and thus guarantees high accuracy. Experiments on the ImageNet VID dataset show that our FastVOD-Net achieves 79.3% mAP at 29.6 fps or 81.2% mAP at 23.0 fps on an Nvidia RTX 2080 Ti GPU, which is the state-of-the-art performance in real time. 

FastVOD-Net: A Real-Time and High-Accuracy Video Object Detector

Video object detection is a tough task due to the severe appearance degradation caused by rapid motion, sudden occlusion or rare poses. The great challenge facing video object detection is the simultaneous requirements on both accuracy and speed because the pursuit of one aspect usually causes significant expense to the other. Most existing methods mainly focus on improving detection accuracy with little attention to computationally efficient solutions, and thus they are impractical for many real-world applications. This motivates us to develop a real-time and high-accuracy video object detection method. In this paper, we propose a novel video object detector, called FastVOD-Net, which can yield highly accurate detection results at real-time speed. Specifically, we first develop a temporally-cascaded deformable alignment (TCDA) module to model the object displacements induced by video motion. Then, we introduce another two modules, namely spatially-refined temporal aggregation (SRTA) and attention-guided semantic distillation (AGSD), to improve the appearance feature of the currently processed frame and enhance the semantic representation of non-keyframes, respectively. For keyframe scheduling, we design an adaptive keyframe selection scheduler (AKSS) to adjust the keyframe interval online, making the keyframe usage more rational. On one hand, the characteristics of our FastVOD-Net enable it to sparsely perform expensive feature extraction, which significantly reduces the computational cost and thus guarantees real-time speed. On the other hand, the collaboration of the above tightly-coupled modules and adaptive keyframe scheduler makes FastVOD-Net fully exploit inter-frame temporal dependencies and thus guarantees high accuracy. Experiments on the ImageNet VID dataset show that our FastVOD-Net achieves 79.3% mAP at 29.6 fps or 81.2% mAP at 23.0 fps on an Nvidia RTX 2080 Ti GPU, which is the state-of-the-art performance in real time.

With the rising number of vehicle ownership nationwide and the consequent increase in traffic accidents, vehicle detection for traffic surveillance video is an effective method to reduce traffic accidents. However, existing video surveillance vehicle detection methods suffer from high computational load, low accuracy, and excessive reliance on large-scale computing servers. Therefore, the research will try to fuse coordinate attention mechanism to improve YOLOv5 network, choose lightweight YOLOv5s for image recognition, and use K-means algorithm to modify the aiming frame according to the characteristics of vehicle detection; meanwhile, in order to get more accurate results, coordinate attention mechanism algorithm, which is also a lightweight algorithm, is inserted into YOLOv5s for improvement, so that the designed The lightweight vehicle detection model can be run on embedded devices. The measurement experiments show that the YOLOv5+CA model completes convergence when the iterations exceed 100, and the localization loss and confidence loss gradually stabilize at 0.002 and 0.028, and the classification loss gradually stabilizes at 0.017. Comparing YOLOv5+CA with SSD algorithm, ResNet-101 algorithm and RefineDet algorithm, YOLOv5 +CA detection accuracy is better than other algorithms by about 9%, and the accuracy can be approximated to 1.0 at a confidence level of 0.946. The experimental results show that the research design provides higher accuracy and high computational efficiency for video surveillance vehicle detection, and can better provide reference value and reference methods for video surveillance vehicle detection and operation management. Keywords—Attention mechanism; YOLOv5; vehicle detection; image recognition; deep learning

/pdf/video-surveillance-vehicle-detection-method-incorporating-11h4lqln.pdf

Video Surveillance Vehicle Detection Method Incorporating Attention Mechanism and YOLOv5

Abstract In intelligent vehicles, road environment perception technology is a key component of autonomous driving assistance systems. This component is the foundation for vehicle decision‐making and control, and is a guarantee of safety during the driving of the vehicle. The existing environment perception technology mainly targets well‐lit environments and requires visible light imaging equipment. Therefore, in low visibility environments, this technology cannot make good judgments about the external environment. Many existing perception systems mainly rely on sensors. Under low visibility conditions, these sensors weaken their effectiveness due to signal transmission, reflection, or absorption, resulting in incomplete or distorted data collection. Reduced visibility often affects the sensing range of various sensors, hindering the system's ability to detect and recognize distant objects, thereby limiting the necessary advance warning and response time for safe navigation. In response to this issue, this study proposed a combined method of infrared imaging and polarized imaging to collect feature data on road conditions in low visibility environments. Then, the obtained images were denoised and enhanced. The processed images were input into the system for recognition, and the images were analyzed and recognized using a low visibility road situation semantic segmentation algorithm based on deep learning. The research outcomes denoted that the pixel accuracy, average pixel accuracy, and average intersection ratio of the variable weight combination model in polarized degree images were 91.2%, 89.1%, and 71.6%, respectively. Those in infrared images were 83.6%, 90.6%, and 62.1%, respectively. The various indicators of the variable weight combination model were higher than those of the U‐shaped neural network model, indicating its performance is relatively excellent. The research results indicated that infrared imaging helps to acquire information at night or in low light conditions, while polarized imaging can provide better adaptation to cluttered light and reflections, enabling the system to provide more robust environmental sensing in complex weather conditions. It fills a critical gap in perception for autonomous driving systems in adverse weather conditions. 

<scp>AI</scp> monitoring and warning system for low visibility of freeways using variable weight combination model

The purpose of this paper is to use the most popular deep learning algorithm to complete the vehicle detection in the urban area of MiniSAR image, and provide reliable means for ground monitoring.,An accurate detector called the rotation region-based convolution neural networks (CNN) with multilayer fusion and multidimensional attention (M2R-Net) is proposed in this paper. Specifically, M2R-Net adopts the multilayer feature fusion strategy to extract feature maps with more extensive information. Next, the authors implement the multidimensional attention network to highlight target areas. Furthermore, a novel balanced sampling strategy for hard and easy positive-negative samples and a global balanced loss function are applied to deal with spatial imbalance and objective imbalance. Finally, rotation anchors are used to predict and calibrate the minimum circumscribed rectangle of vehicles.,By analyzing many groups of experiments, the validity and universality of the proposed model are verified. More importantly, comparisons with SSD, LRTDet, RFCN, DFPN, CMF-RCNN, R3Det, SCRDet demonstrate that M2R-Net has state-of-the-art detection performance.,The progress in the field of MiniSAR application has been slow due to strong speckle noise, phase error, complex environments and a low signal-to-noise ratio. In addition, four kinds of imbalances, i.e. spatial imbalance, scale imbalance, class imbalance and objective imbalance, in object detection based on the CNN greatly inhibit the optimization of detection performance.,This research can not only enrich the means of daily traffic monitoring but also be used for enemy intelligence reconnaissance in wartime.

M2R-Net: deep network for arbitrary oriented vehicle detection in MiniSAR images

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Chunping Wang

Author Tools

Chat about Author

Papers

M2R-Net: deep network for arbitrary oriented vehicle detection in MiniSAR images