Computer Vision Detection Research Articles

Rapid computer vision detection of apple diseases based on AMCFNet

Rapid computer vision detection of apple diseases based on AMCFNet

The Application of Interactive Visualization and Computer Vision in Intelligent Education Based on Big Data AI Technology

Considering the problem that teachers’ command gesture tracking error is due to their poor detection ability in the intelligent education of big data or technology, the application method of interactive visualization and computer vision in the intelligent education of big data or technology is designed. Three-dimensional coordinate transformations of teaching content information and visual processing of teaching information. Use computer vision to detect teachers’ actions and complete computer vision detection of interactive teaching. Using the rendering algorithm, the AI education environment is optimized without affecting computer vision detection. So far, the interactive visualization and computer vision application method design in intelligent big data technology education has been completed. The experimental results show that combining these two technologies can significantly improve the tracking effect of teachers’ instruction gestures, optimize the design effect of teaching content, and raise teaching levels.

Body Pose Estimation using Deep Learning

Abstract: Healthcare, sports analysis, gaming, and entertain- ment are just some of the many fields that could benefit from solving the challenging issue of real-time human pose detection and recognition in computer vision. Capturing human motion, analysing physical exercise, and giving feedback on performance can all benefit from reliable detection and recognition of body poses. The recent progress in deep learning has made it possible to create real-time systems that can accurately and quickly recognise and identify human poses.

Autonomous Anomaly Detection System for Crime Monitoring and Alert Generation

Nowadays violence in society impacts more than any weapon used by people. Over the last few years, autonomous vehicles have been used to observe and recognize the abnormality in the behavior of people and classifying them as a crime or not. Detecting crime on live stream is a classification of any event in a crime or not a crime and generating alerts to designated authorities which in turn can take required actions and ensure the security assessment of the city. Such kind of effective techniques for live video stream processing in computer vision is the need of the hour. There are many techniques that can be used, while Long Short-Term Memory (LSTM) networks and OpenCV provide the most accurate prediction for this task. OpenCV is used for the task of object detection in computer vision which will take the input from either drone or any autonomous vehicle. LSTM is used to classify any event or behavior in crime or not. This live stream is also encrypted for more security. To make this system more secure with the use of a security algorithm. This system uses the Elliptic curve algorithm to protect data from any kind of manipulation.
 Through its ability to sense its surroundings, an autonomous vehicle is able to operate itself and execute critical activities without the need for human interaction. Video surveillance of computer vision technology can be used to take care of the security of the city by observing the crowd as well as individual activities. Much crowd-based crimes like mob lynching and individual crimes like murder, burglary, terrorism can be protected with advanced deep learning-based Anamoly detection techniques. Machine learning model use dataset for learning is taken from different sources specific for crime detection with the 90% accuracy.
 

Smoking Driving Behavior Detection Based on Deep Learning

Smoking in driving not only reduces the accuracy of driving operation, but also leads to insufficient oxygen and higher possibility of traffic accident. Therefore, considering the safety of life and avoiding accidents as far as possible, a detection model based on deep learning which can quickly detect smoking driving behavior is designed. In this model, convolutional neural network is used to process the input frames of the video stream captured by the camera. After the shape feature extraction, fuzzy feature processing, motion feature detection and color feature region comparison, the smoking driving behavior can be judged. Through the design of a series of computer vision detection modules, not only can reduce the calculation of the model, but also improve the efficiency of deduction, so as to meet the performance requirements of real-time monitoring. In order to quickly find out the driver smoking behavior and trigger warning, so as to avoid unnecessary traffic accidents and ensure life safety.

Edge Detection Techniques Using Character Segmentation for OCR of Devanagari Text

An image processing technique called edge detection is used to find and identify the edges, curves, and objects in digital images. Edge detection includes various mathematical calculations that focus on locating the edges and curves where a digital image's brightness abruptly shifts or has discontinuities. In the fields of feature detection and feature extraction in image processing and computer vision, edge detection is a fundamental tool. The application of an edge detector results in the development of a set of connected curves that represent surface marks, character boundaries, and discontinuities in surface orientation. Character boundaries are described via edges. The majority of a feature is described by its edges. A group of pixels called an edge is used to describe an area where abrupt variations in intensity occur. Because it removes items of interest for actions like description, segmentation is a vital stage in an image recognition system. This paper focuses on edge detection techniques that can be implemented on characters for effective character recognition. Devanagari text includes curvy edges which need to be detected for proper recognition hence different edge detector operators are implemented to find the most effective amongst them to acquire clear edges of the text. There are several methods for segmenting images, including segmentation based on artificial neural networks, clustering, edges, regions, and thresholds. In this paper, edge-based segmentation is used. The Canny, Laplacian, Sobel, Prewitt, and Robert operators are used to detect edges, and the generated image is compared to the original binary image. The pre-processing phase includes the binarization step.

A Unified Interactive Model Evaluation for Classification, Object Detection, and Instance Segmentation in Computer Vision.

Existing model evaluation tools mainly focus on evaluating classification models, leaving a gap in evaluating more complex models, such as object detection. In this paper, we develop an open-source visual analysis tool, Uni-Evaluator, to support a unified model evaluation for classification, object detection, and instance segmentation in computer vision. The key idea behind our method is to formulate both discrete and continuous predictions in different tasks as unified probability distributions. Based on these distributions, we develop 1) a matrix-based visualization to provide an overview of model performance; 2) a table visualization to identify the problematic data subsets where the model performs poorly; 3) a grid visualization to display the samples of interest. These visualizations work together to facilitate the model evaluation from a global overview to individual samples. Two case studies demonstrate the effectiveness of Uni-Evaluator in evaluating model performance and making informed improvements.

Yolo Versions Architecture: Review

Deep learning techniques are used across a wide range of fields for several applications. In recent years, deep learning-based object detection from aerial or terrestrial photos has gained popularity as a study topic. The goal of object detection in computer vision is to anticipate the presence of one or more objects, along with their classes and bounding boxes. The YOLO (You Only Look Once) modern object detector can detect things in real-time with accuracy and speed. A neural network from the YOLO family of computer vision models makes one-time predictions about the locations of bounding rectangles andclassification probabilities for an image. In layman's terms, it is a technique for instantly identifying and recognizing items in images.This article, will be focusing on comparing the main differences among the YOLO version's Architecture, and will discuss its evolution from YOLO to YOLOv8, its network architecture, newfeatures, and applications. Itstarts by looking at the basic ideas and design of the first YOLO model, which laid the groundwork for the following improvements in the YOLO family. In additionally, this article will provide a step-by-step guide on how to use the YOLO version architecture, Understanding the primary drivers, feature development, constraints, and even relationships for the versions is crucial as the YOLO versions advance.Researchers interested in object detection, especially beginning researchers, would find this paper useful and enlightening

Defect detection of large wind turbine blades based on image stitching and improved Unet network

Aiming at the problem that the existing computer vision detection technology is difficult to comprehensively and carefully detect the damage status of large wind turbine blades due to the limitation of the field of view, this paper proposes a refined and multi-scale detection method for large-scale wind turbine blades by combining an image stitching algorithm and a deep learning network. First of all, combining the image stitching algorithm with image weighted fusion, images of large wind turbine blades shot in close range are stitched together, so as to realize the clear restoration of the full size and defects of the blades. On this basis, an improved Unet network VGG16Unet is proposed. Combined with transfer learning, the classification and detection of various defects on wind turbine blades under the condition of small dataset training are realized. Finally, by the aid of the combination of the image stitching algorithm and the semantic segmentation network, the refined damage detection of the overall structure of large wind turbine blades is implemented. The research shows that the mean pixel accuracy and the mean intersection over union of the VGG16Unet model are 95.33% and 85.20%, respectively, which is better than the classical semantic segmentation models, fully convolutional neural network model and Unet model. The combination of the VGG16Unet model and the image stitching algorithm not only realizes the global detection of the entire structure but also ensures the detailed detection of each local area, which makes the detection of large wind turbine blades more comprehensive and refined.

Jetson Nano와 3D프린터를 이용한 인공지능 교육용 키트 제작

In this paper, an educational kit that can be used in AI education was developed to solve the difficulties of AI education. Through this, object detection and person detection in computer vision using CNN and OpenCV to learn practical-oriented experiences from theory-centered and user image recognition (Your Own) that learns and recognizes specific objects Image Recognition), user object classification (Segmentation) and segmentation (Classification Datasets), IoT hardware control that attacks the learned target, and Jetson Nano GPIO, an AI board, are developed and utilized to develop and utilize textbooks that help effective AI learning made it possible.

Comparison of GPU and FPGA Hardware Acceleration of Lane Detection Algorithm

The two fundamental components of a complete computer vision system are detection and classification. The Lane detection algorithm, which is used in autonomous driving and smart vehicle systems, is within the computer vision detection area. In a sophisticated road environment, lane marking is the responsibility of the lane detection system. The warning system for a car that leaves its lane also heavily relies on lane detection. The two primary stages of the implemented lane detection algorithm are edge detection and line detection. In order to assess the trade-offs for latency, power consumption, and utilisation, we will compare the state-of-the-art implementation performance attained with both FPGA and GPU in this work. Our analysis highlights the benefits and drawbacks of the two systems.

Nonlinear and Dotted Defect Detection with CNN for Multi-Vision-Based Mask Inspection.

This paper addresses the problem of nonlinear and dotted defect detection for multi-vision-based mask inspection systems in mask manufacturing lines. As the mask production amounts increased due to the spread of COVID-19 around the world, the mask inspection systems require more efficient defect detection algorithms. However, the traditional computer vision detection algorithms suffer from various types and very small sizes of the nonlinear and dotted defects on masks. This paper proposes a deep learning-based mask defect detection method, which includes a convolutional neural network (CNN) and efficient preprocessing. The proposed method was developed to be applied to real manufacturing systems, and thus all the training and inference processes were conducted with real data produced by real mask manufacturing systems. Experimental results show that the nonlinear and dotted defects were successfully detected by the proposed method, and its performance was higher than the previous method.

Efficient imaging and computer vision detection of two cell shapes in young cotton fibers.

The shape of young cotton (Gossypium) fibers varies within and between commercial cotton species, as revealed by previous detailed analyses of one cultivar of G. hirsutum and one of G. barbadense. Both narrow and wide fibers exist in G. hirsutum cv. Deltapine 90, which may impact the quality of our most abundant renewable textile material. More efficient cellular phenotyping methods are needed to empower future research efforts. We developed semi-automated imaging methods for young cotton fibers and a novel machine learning algorithm for the rapid detection of tapered (narrow) or hemisphere (wide) fibers in homogeneous or mixed populations. The new methods were accurate for diverse accessions of G. hirsutum and G. barbadense and at least eight times more efficient than manual methods. Narrow fibers dominated in the three G. barbadense accessions analyzed, whereas the three G. hirsutum accessions showed a mixture of tapered and hemisphere fibers in varying proportions. The use or adaptation of these improved methods will facilitate experiments with higher throughput to understand the biological factors controlling the variable shapes of young cotton fibers or other elongating single cells. This research also enables the exploration of links between early cell shape and mature cotton fiber quality in diverse field-grown cotton accessions.

Deep Learning Based Egg Fertility Detection.

Simple SummaryThis study employs a Mask R-CNN technique along with the transfer learning model to accurately detect fertile and infertile eggs. It is a novel study that uses a single DL model to carry out detection, classification and segmentation of fertile and infertile eggs based on incubator images. This study investigates the implementation of deep learning (DL) approaches to the fertile egg-recognition problem, based on incubator images. In this study, we aimed to classify chicken eggs according to both segmentation and fertility status with a Mask R-CNN-based approach. In this manner, images can be handled by a single DL model to successfully perform detection, classification and segmentation of fertile and infertile eggs. Two different test processes were used in this study. In the first test application, a data set containing five fertile eggs was used. In the second, testing was carried out on the data set containing 18 fertile eggs. For evaluating this study, we used AP, one of the most important metrics for evaluating object detection and segmentation models in computer vision. When the results obtained were examined, the optimum threshold value (IoU) value was determined as 0.7. According to the IoU of 0.7, it was observed that all fertile eggs in the incubator were determined correctly on the third day of both test periods. Considering the methods used and the ease of the designed system, it can be said that a very successful system has been designed according to the studies in the literature. In order to increase the segmentation performance, it is necessary to carry out an experimental study to improve the camera and lighting setup prepared for taking the images.

Automatic detection for the world's rarest primates based on a tropical rainforest environment

Hainan gibbons are the most endangered primates in the world and are at risk of extinction at any time. Infrared trigger camera technology is one of the most effective means at present, however, the data obtained are characterized by massive fragmentation, which is not conducive to post-processing and analysis. Therefore, a computer vision detection model for Hainan gibbons is proposed for the first time in this paper. Because of the foggy tropical rainforest, the image is pre-processed through an image filter whose parameters are obtained from a convolutional neural network. And then input it to the YOLO V3 network for Hainan gibbon detection. We produced a dataset containing 6000 images of Hainan gibbons for experimental training. The detection quality of Hainan gibbons based on YOLO V3 and image-filter YOLO (IF-YOLO) was evaluated. The results show that IF-YOLO maintains excellent performance on sunny days while improving the weakness of YOLO. Increasing the content of the dataset will extend the kinds of species detected by the model, which opens up new avenues for detecting others species in harsh conditions.

Non-Sinusoidal micro-Doppler Estimation Based on Dual-Branch Network

The fine state of targets can be represented by the extracted micro-Doppler (m-D) components from the radar echo. However, current methods do not consider the specialty of the m-D components, and their performance with non-sinusoidal components is poor. In this paper, a neural network is applied to signal extraction for the first time. Inspired by the semantic line detection in computer vision, the extraction of the m-D components is transformed into the network-based time–frequency curves detection problem. Specifically, a novel dual-branch network-based m-D components extraction method is proposed. According to the property of intersected multiple m-D components, the dual-branch network consisting of a continuous m-D components extraction branch, and a crossing point detection branch is designed to obtain components and cross points at the same time. In addition, a shuffle attention-fast Fourier convolution (SA-FFC) module is proposed to fuse local and global contexts and focus on key features. To solve the error correlation problem of multi-component signals, the first-order parametric continuous condition and cubic spline interpolation are employed to obtain complete and smooth components curves. Simulation and measurement results show that this method of good robustness is a good candidate for separating the non-sinusoidal m-D components with intersections.

Optimized lightweight CA-transformer: Using transformer for fine-grained visual categorization

As a rapidly developing research direction in computer vision (CV), related algorithms such as image classification and object detection have achieved inevitable research progress. Improving the accuracy and efficiency of algorithms for fine-grained identification of plant diseases and birds in agriculture is essential to the dynamic monitoring of agricultural environments. In this study, based on the computer vision detection and classification algorithm, combined with the architecture and ideas of the CNN model, the mainstream Transformer model was optimized, and then the CA-Transformer (Transformer Combined with Channel Attention) model was proposed to improve the ability to identify and classify critical areas. The main work is as follows: (1) The C-Attention mechanism is proposed to strengthen the feature information extraction within the patch and the communication between feature information so that the entire network can be fully attentive while reducing the computational overhead; (2) The weight-sharing method is proposed to transfer parameters between different layers, improve the reusability of model data, and at the same time increase the knowledge distillation link to reduce problems such as excessive parameters and overfitting; (3) Token Labeling is proposed to generate score labels according to the position of each Token, and the total loss function of this study is proposed according to the CA-Transformer model structure. The performance of the CA-Transformer model proposed in this study is compared with the current mainstream models on datasets of different scales, and ablation experiments are performed. The results show that the accuracy and mIoU of the CA-Transformer proposed in this study reach 82.89% and 53.17MS, respectively, and have good transfer learning ability, indicating that the model has good performance in fine-grained visual categorization tasks and can be used in ecological information. In the context of more diverse ecological information, this study can provide reference and inspiration for the practical application of information.

A Small Target Forest Fire Detection Model Based on YOLOv5 Improvement

Forest fires are highly unpredictable and extremely destructive. Traditional methods of manual inspection, sensor-based detection, satellite remote sensing and computer vision detection all have their obvious limitations. Deep learning techniques can learn and adaptively extract features of forest fires. However, the small size of the forest fire target in the long-range-captured forest fire images causes the model to fail to learn effective information. To solve this problem, we propose an improved forest fire small-target detection model based on YOLOv5. This model requires cameras as sensors for detecting forest fires in practical applications. First, we improved the Backbone layer of YOLOv5 and adjust the original Spatial Pyramid Pooling-Fast (SPPF) module of YOLOv5 to the Spatial Pyramid Pooling-Fast-Plus (SPPFP) module for a better focus on the global information of small forest fire targets. Then, we added the Convolutional Block Attention Module (CBAM) attention module to improve the identifiability of small forest fire targets. Second, the Neck layer of YOLOv5 was improved by adding a very-small-target detection layer and adjusting the Path Aggregation Network (PANet) to the Bi-directional Feature Pyramid Network (BiFPN). Finally, since the initial small-target forest fire dataset is a small sample dataset, a migration learning strategy was used for training. Experimental results on an initial small-target forest fire dataset produced by us show that the improved structure in this paper improves mAP@0.5 by 10.1%. This demonstrates that the performance of our proposed model has been effectively improved and has some application prospects.

LICENSE PLATE DETECTION METHODS BASED ON OPENCV

With the popularization of automobile and the progress of computer vision detection technology, intelligent license plate detection technology has gradually become an important part of intelligent traffic management. License plate detection is used to segment vehicle image and obtain license plate area for follow-up recognition system to screen. It is widely used in intelligent traffic management, vehicle video monitoring and other fields. In this paper, two license plate detection methods are studied, one is based on Sobel edge detection and the other is based on morphological gradient detection. Basing on OpenCV and visual studio 2012 under Windows system, two methods of license plate detection are implemented, and the two algorithms are compared in detail from the aspects of license plate detection accuracy. These methods have high efficiency and good interactivity, which provide a reference for later license platere cognition.

A Study on a Complex Flame and Smoke Detection Method Using Computer Vision Detection and Convolutional Neural Network

This study sought an effective detection method not only for flame but also for the smoke generated in the event of a fire. To this end, the flame region was pre-processed using the color conversion and corner detection method, and the smoke region could be detected using the dark channel prior and optical flow. This eliminates unnecessary background regions and allows selection of fire-related regions. Where there was a pre-processed region of interest, inference was conducted using a deep-learning-based convolutional neural network (CNN) to accurately determine whether it was a flame or smoke. Through this approach, the detection accuracy is improved by 5.5% for flame and 6% for smoke compared to when a fire is detected through the object detection model without separate pre-processing.