Vision Algorithms Research Articles

Enhancing geotechnical damage detection with deep learning: a convolutional neural network approach.

Most natural disasters result from geodynamic events such as landslides and slope collapse. These failures cause catastrophes that directly impact the environment and cause financial and human losses. Visual inspection is the primary method for detecting failures in geotechnical structures, but on-site visits can be risky due to unstable soil. In addition, the body design and hostile and remote installation conditions make monitoring these structures inviable. When a fast and secure evaluation is required, analysis by computational methods becomes feasible. In this study, a convolutional neural network (CNN) approach to computer vision is applied to identify defects in the surface of geotechnical structures aided by unmanned aerial vehicle (UAV) and mobile devices, aiming to reduce the reliance on human-led on-site inspections. However, studies in computer vision algorithms still need to be explored in this field due to particularities of geotechnical engineering, such as limited public datasets and redundant images. Thus, this study obtained images of surface failure indicators from slopes near a Brazilian national road, assisted by UAV and mobile devices. We then proposed a custom CNN and low complexity model architecture to build a binary classifier image-aided to detect faults in geotechnical surfaces. The model achieved a satisfactory average accuracy rate of 94.26%. An AUC metric score of 0.99 from the receiver operator characteristic (ROC) curve and matrix confusion with a testing dataset show satisfactory results. The results suggest that the capability of the model to distinguish between the classes 'damage' and 'intact' is excellent. It enables the identification of failure indicators. Early failure indicator detection on the surface of slopes can facilitate proper maintenance and alarms and prevent disasters, as the integrity of the soil directly affects the structures built around and above it.

Research on Athlete Posture Monitoring and Correction Technology Based on Wireless Sensing and Computer Vision Algorithms

Research on Athlete Posture Monitoring and Correction Technology Based on Wireless Sensing and Computer Vision Algorithms

Hybrid Sensor Fusion Mixed with Reinforcement Learning in Autonomous Dual-Arm Lifting Tasks Performed by Humanoid Robots

Humanoid robots often struggle with tasks such as lifting objects due to the complexity involved in identifying contact points, applying the correct force, and tracking task progress. We propose an integrated solution that leverages the dual-arm capability of humanoids and utilizes sensor fusion from vision and force sensors. Our system employs a computer vision algorithm to detect and characterize object properties (shape, size, position, orientation) and differentiate between parallel and non-parallel bi-manipulation tasks. The controller then identifies optimal contact points for the end effectors, generating trajectories fed into a closed-loop controller using force feedback. For parallel bi-manipulation, momentum cancellation is achieved through sensor fusion. For non-parallel surfaces, a reinforcement learning algorithm determines the appropriate lifting force to prevent slippage using only two contact points. Experimental validation on a real humanoid platform demonstrates the effectiveness of our approach in autonomously lifting objects, regardless of contact surface configuration. This advancement significantly enhances the reliability and versatility of humanoid robots in performing complex manipulation tasks, contributing to their practical deployment in human-oriented environments.

Power overwhelming: the one with the oscilloscopes

Visualization as a discipline has to investigate its practical implications in a world steadily moving toward greener computing methods. Quantifying the power consumption of visualization algorithms is thus essential, given the ever-increasing energy needs of GPUs. Previous approaches rely on integrated sensors or invasive methods that require modifications and special test setups. However, they still suffer from imprecision from low sampling rates and integration over time. Using a high-precision, high-frequency setup via steerable oscilloscopes, we can objectively measure the resulting quality of previous approaches. This is essential to establish a ground truth, pave the way for improved modeling of power consumption in general, and enable better estimates based on the output of lower-quality sensors. We finally discuss benefits that can be drawn from the additional insight of the higher-precision setup and which additional use cases can justify the incurred costs.Graphical abstract

Robot-assisted partial nephrectomy: Is it the future of kidney surgery? A comparison of nephron-sparing techniques in partial nephrectomy

Technological advancements are significantly transforming various medical fields, including urology. The increasing adoption of minimally invasive surgical techniques and robotic assistance is particularly impactful. Three partial nephrectomy techniques are investigated: open partial nephrectomy, laparoscopic partial nephrectomy, and robot-assisted partial nephrectomy. Among these, robot-assisted partial nephrectomy is considered to be superior due to shorter warm ischemia time, reduced blood loss, better early renal functional preservation, and shorter hospital stays. The zero-ischemia partial nephrectomy concept aims to improve postoperative kidney function outcomes. The integration of robotic technology and advancements in artificial intelligence and surgical training systems are expected to further enhance surgical techniques. Artificial intelligence, particularly when combined with computer vision algorithms, shows potential for creating precise and automated three-dimensional models for surgical planning in complex robot-assisted partial nephrectomy procedures, potentially leading to better patient outcomes. This review identifies the current capabilities and prospective advancements in the application of robotic technology in partial nephrectomy.

Artificial Internet of Things, Sensor-Based Digital Twin Urban Computing Vision Algorithms, and Blockchain Cloud Networks in Sustainable Smart City Administration

The aim of this paper is to synthesize and analyze existing evidence on interconnected sensor networks and digital urban governance in data-driven smart sustainable cities. The research topic of this systematic review is whether and to what extent smart city governance can effectively integrate the Internet of Things (IoT), Artificial Intelligence of Things (AIoT), intelligent decision algorithms based on big data technologies, and cloud computing. This is relevant since smart cities place special emphasis on the involvement of citizens in decision-making processes and sustainable urban development. To investigate the work to date, search outcome management and systematic review screening procedures were handled by PRISMA and Shiny app flow design. A quantitative literature review was carried out in June 2024 for published original and review research between 2018 and 2024. For qualitative and quantitative data management and analysis in the research review process, data extraction tools, study screening, reference management software, evidence map visualization, machine learning classifiers, and reference management software were harnessed. Dimensions and VOSviewer were deployed to explore and visualize the bibliometric data.

Visual SLAM algorithm in dynamic environment based on deep learning

Visual SLAM algorithm in dynamic environment based on deep learning

Mint: Integrating scientific visualizations into virtual reality

We present an image-based approach to integrate state-of-the-art scientific visualization into virtual reality (VR) environments: the mint visualization/VR inter-operation system. We enable the integration of visualization algorithms from within their software frameworks directly into VR without the need to explicitly port visualization implementations to the underlying VR framework—thus retaining their capabilities, specializations, and optimizations. Consequently, our approach also facilitates enriching VR-based scientific data exploration with established or novel VR immersion and interaction techniques available in VR authoring tools. The separation of concerns enables researchers and users in different domains, like virtual immersive environments, immersive analytics, and scientific visualization, to independently work with existing software suitable for their domain while being able to interface with one another easily. We present our system architecture and inter-operation protocol (mint), an example of a collaborative VR environment implemented in the Unity engine (VRAUKE), as well as the integration of the protocol for the visualization frameworks Inviwo, MegaMol, and ParaView. Our implementation is publicly available as open-source software.Graphical abstract

Force-Directed Immersive 3D Network Visualization

Network visualization, in mathematics often referred to as graph visualization, has evolved significantly over time, offering various methods to effectively represent complex data structures. New methods and devices advance the possibilities of visualization both from the point of view of the quality of displayed information and of the possibilities of visualizing a larger amount of data. Immersive visualization includes the user directly in presented visual representation but requires a native 3D environment for direct interaction with visualized information. This article describes an approach to creating a force-directed immersive 3D network visualization algorithm available for application in immersive environments, such as a cave automatic virtual environment or virtual reality. The algorithm aims to address the challenge of creating visually appealing and easily interpretable visualizations by utilizing 3D space and the Unity engine. The results show successfully visualized data and developed interactive visualization methods, overcoming limitations of basic force-directed implementations. The main contribution of the presented research is the force-directed algorithm with springs and controlled placement as an immersive visualization technique that combines the use of springs and attractive forces to stabilize a network in a 3D environment.

Benchmarking analysis of computer vision algorithms on edge devices for the real-time detection of digital dermatitis in dairy cows

Digital dermatitis (DD) is a bovine claw disease responsible for ulcerative lesions on the coronary band of the foot. It causes significant animal welfare and economic losses to the cattle industry. Early detection of DD can lead to prompt treatment and decrease lameness. Current detection and staging methods require a trained individual to evaluate the interdigital space on each foot for clinical signs of DD. Computer vision (CV), a type of artificial intelligence for image analysis, has demonstrated promising results on object detection tasks. However, farms require robust solutions that can be deployed in harsh conditions including dust, debris, humidity, precipitation, other equipment issues. The study aims to train, deploy, and benchmark DD detection models on edge devices. Images were collected from commercial dairy farms with the camera facing the interdigital space on the plantar surface of the foot. Images were scored for M-stages of DD by a trained investigator using the M-stage DD classification system. Models were trained to detect and score DD lesions and embedded on an edge device. The Tiny YOLOv4 model deployed on a CV specific integrated camera module connected to a single board computer achieved a mean average precision (mAP) of 0.895, an overall prediction accuracy of 0.873, and a Cohen’s kappa of 0.830 for agreement between the computer vision model and the trained investigator. The model reached a final inference speed of 40 frames per second (FPS) and ran stably without any interruptions. The CV model was able to detect DD lesions on an edge device with high performance and speed. The CV tool can be used for early detection and prompt treatment of DD in dairy cows. Real-time detection of DD on edge device will improve health outcomes, while simultaneously decreasing labor costs. We demonstrate that the deployed model can be a low-power and portable solution for real-time detection of DD on dairy farms. This result is a step towards applying CV algorithms to veterinary medicine and implementing real-time detection of health outcomes in precision farming.

Promote computer vision applications in pig farming scenarios: high-quality dataset, fundamental models, and comparable performance1

Computer vision is widely recognized as an influential technology in the field of precision management of animals. Emerging studies have demonstrated the potential to improve pig health and welfare through animal surveillance systems and computer vision (CV) algorithms. However, the lack of benchmark datasets and robust fundamental algorithms restrict CV applications for the commercial use. This study aims to bridge the gap between technology development and commercial applications in pig farming scenarios by introducing a general-purpose dataset (PigLife), comparing benchmark performances of foundational CV algorithms and model development workflows. The PigLife dataset contains video clips and images (38 short video clips, 2K image frames, 22K pig instances) across most pig production phases in a typical commercial pig farm: Breeding and Gestation, Farrow to Wean, Weaning & Nursery, and Growth to Finish. Three detection algorithms (Faster R-CNN, RetinaNet, TridentNet) and three segmentation algorithms (Mask R-CNN, MViTv2, Point-Rend) were trained on the PigLife dataset from scratch. Fine-tuning of pre-trained models (YOLO8-m, Faster-RCNN-r50) and no-training from zero-shot models (CLIP-SAM, Grouddino-HQSAM) were also evaluated to suggest faster CV development workflows for commercial applications in pig farming. This study emphasizes the necessity of a benchmark dataset for evaluating the robustness of algorithms and identifying the remaining difficulties and challenges across various algorithms. Furthermore, developing CV models from pre-trained algorithms or zero-shot models showed better performance and a faster process, which could reduce barriers when developing high-performance CV products in pig production industry.

The Application of Intelligent Welding Robots and Visual Detection Algorithms in Building Steel Structures

The Application of Intelligent Welding Robots and Visual Detection Algorithms in Building Steel Structures

Intelligent detection method with 3D ranging for external force damage monitoring of power transmission lines

The rapid development of smart grid requires more and more reliable power supply. The external force damage to transmission lines can significantly impact the safety and stability of the power grid, potentially causing electric shock accidents. Existing methods for monitoring external force damage in transmission corridors lack the ability to provide effective warnings based on the real-time distance between potential hazards and power lines. Additionally, limited computational power and storage capacity at edge terminals restrict the efficient deployment of high-precision (high complexity) visual algorithms. This study presents, for the first time, a lightweight intelligent detection method integrating detection and three-dimensional (3D) ranging. A regression loss optimized for small objects is introduced to compensate for the shortcomings of lightweight networks in detection accuracy. Simultaneously, based on the influence of convolutions in various modules of the baseline model on performance, lightweight improvements are made to the detector architecture using Omni-Dimensional Dynamic Convolution and Distribution Shifting Convolution. Finally, a 3D ranging module is integrated into the detector, involving operations such as 2D3D information matching and back-projection transformation. This method innovatively achieves automated ranging and hierarchical warning. Its effectiveness is validated in transmission corridor scenarios under various weather conditions and surveillance video. The results demonstrate that our method outperforms other algorithms in hazard detection accuracy and lightweight performance. Moreover, the distance prediction error rate is below 1.6%. The hierarchical warning solutions can be applied to more scenarios.

Study of Various Computer Vision Algorithms for Registration in Augmented Reality: A Survey

Abstract: Augmented reality is defined as the fusion of virtual object in real world. Registration is basic step for creating an immersive AR experience to the user. The registration algorithms helps in placing the virtually created object in the most accurate position in the real world. This paper shows an in-depth comparative analysis of various registration algorithm under computer vision that are used for AR applications. The comparative analysis helps in identifying the strengths, weaknesses and the applicability of each algorithm in various AR fields by studying different case studies and real-world applications which helps in showing the practical implication of these algorithms. Also, the challenges associated with AR are discussed and future scope of this aims at advancement of the registration algorithms so as to make the AR experience more functionable and smooth. This survey paper can help researchers, developers who have interest in knowing or exploring the field of computer vision algorithms for solving the registration problem in Augmented Reality.

AUTOBILL – AN AI POWERED INSTANT CHECKOUT SYSTEM

Abstract -In today’s world, time is one of the most important things, an individual area unit refers to those things that consume time. Billings at stores takes a lot of time. Looking at future technology, we tend to come out with an associate new plan of “Autobill-an Ai powered instant checkout system”. The project aims to completely transform the shopping experience. By utilizing state-of-the-art computer vision and artificial intelligence technology, AutoBill provides both customers and shops with a smooth and effective purchasing experience. Customers are frequently frustrated and delayed by the lengthy lines and manual item scanning associated with traditional checkout procedures in retail establishments. These problems are solved by AutoBill since customers can pick up the things they want and leave the business without having to stop at the register. As customers travel through the store, the system uses sophisticated computer vision algorithms to precisely recognize and track things. Every item is instantly and automatically recognized and put into the customer's virtual cart. Key Words:AI-powered, automatic billing

A monocular visual body enhancement algorithm for recreating simulation training games for sports students on the field

At present, the simulation training game for sports students has become an important auxiliary tool in the field of sports training. However, how to provide a more authentic and immersive experience has always been a hot and difficult research topic. In view of this, this paper proposes a method of visual sense enhancement based on monocular vision. In order to improve the accuracy of motion information extraction, Scale-invariant feature transform and sliding window filtering algorithm were used to optimize the results of motion information extraction. The experimental results show that the displacement acceleration and angular velocity on each axis vary significantly from frame to frame, for example, the Y-axis angular velocity varies from 0.178 to 0.924. The monocular vision enhancement algorithm can effectively reflect the dynamic characteristics of objects in the process of motion, help to simulate and reproduce the real motion of things on the field more accurately, and help to improve the skill level of athletes in the training process.

AI-Driven Computer Vision Detection of Cotton in Corn Fields Using UAS Remote Sensing Data and Spot-Spray Application

To effectively combat the re-infestation of boll weevils (Anthonomus grandis L.) in cotton fields, it is necessary to address the detection of volunteer cotton (VC) plants (Gossypium hirsutum L.) in rotation crops such as corn (Zea mays L.) and sorghum (Sorghum bicolor L.). The current practice involves manual field scouting at the field edges, which often leads to the oversight of VC plants growing in the middle of fields alongside corn and sorghum. As these VC plants reach the pinhead squaring stage (5–6 leaves), they can become hosts for boll weevil pests. Consequently, it becomes crucial to detect, locate, and accurately spot-spray these plants with appropriate chemicals. This paper focuses on the application of YOLOv5m to detect and locate VC plants during the tasseling (VT) growth stage of cornfields. Our results demonstrate that VC plants can be detected with a mean average precision (mAP) of 79% at an Intersection over Union (IoU) of 50% and a classification accuracy of 78% on images sized 1207 × 923 pixels. The average detection inference speed is 47 frames per second (FPS) on the NVIDIA Tesla P100 GPU-16 GB and 0.4 FPS on the NVIDIA Jetson TX2 GPU, which underscores the relevance and impact of detection speed on the feasibility of real-time applications. Additionally, we show the application of a customized unmanned aircraft system (UAS) for spot-spray applications through simulation based on the developed computer vision (CV) algorithm. This UAS-based approach enables the near-real-time detection and mitigation of VC plants in corn fields, with near-real-time defined as approximately 0.02 s per frame on the NVIDIA Tesla P100 GPU and 2.5 s per frame on the NVIDIA Jetson TX2 GPU, thereby offering an efficient management solution for controlling boll weevil pests.

Classification of tomato ripeness in the agricultural industry using a computer vision system

Machine vision systems (SVA) occupy an important place in the field of food and agriculture, these techniques are performed in situ, are efficient, non-invasive, time-saving and more economical than traditional techniques. Tomatoes (Solanum lycopersicum) are extensively cultivated throughout the world, are essential in the agricultural and culinary fields and are recognized for their beneficial contributions to health. Lack of knowledge about fruit maturity, proper harvesting and postharvest handling are factors responsible for large postharvest losses. Therefore, the objective of this research was the construction of a VAS that allows establishing relationships between color and maturity stage of the Chonto Roble F1 tomato. The VAS built is composed of hardware and software duly synchronized through the application of computer vision algorithms in Python 3.9 software that allow it to perform the acquisition and segmentation of the image and present the user with the color coordinates in the CIEL*a*b* system. Finally, color measurements were performed on tomato samples at different stages of ripening in the VAS and a HunterLab ColorQuest XE (EHL) spectrophotometer. The results obtained indicated that there are no significant differences in both measurement systems for L* values, the changes produced in b* and a* were statistically significant for tomato samples. The results obtained indicated the potential use of the constructed VAS for the determination of the degree of maturity of tomatoes in real time, in a non-invasive and low-cost way.

Computer Vision Algorithm Design in Image Processing Based on Projective Geometry

Image processing with computer vision, particularly in the realm of projective geometry, offers remarkable potential for various applications. Through the lens of projective geometry, images can be transformed, augmented, and reconstructed with precision, facilitating tasks such as image rectification, 3D reconstruction, and object tracking. Landmark estimation in computer vision is a vital task with broad applications across various domains. This process involves identifying key points or landmarks within images, enabling tasks such as facial recognition, object tracking, and gesture recognition. This paper, proposed a novel approach for landmark estimation in computer vision using Projective Geometry Landmark Estimation (PGLM). The proposed model aims to estimate the landmark features by a projective geometry model. With the estimation of the geometry features landmarks related to the facial, object, and medical images are computed. The PGLM model uses the point features for the location of the landmark features. In order to compare PGLM's performance to that of more conventional classification methods like Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM), simulation analysis is carried out. From what we can see, PGLM routinely beats these alternatives when we compare their accuracy, precision, recall, and F1 score. The findings stated the effectiveness of PGLM as a promising approach for landmark estimation in image processing tasks, paving the way for further advancements in this domain.

Emotional recognition and feedback of students in English e-learning based on computer vision and face recognition algorithms

In existing English teaching, teachers often find it difficult to accurately understand students’ emotional changes, thus unable to adjust teaching strategies in a timely manner. Therefore, the introduction of computer vision and facial recognition algorithms will help improve the effectiveness of English teaching. This article is based on computer vision technology and facial recognition algorithms. Based on the sample data provided during the learning process, a model is learned and established to recognize facial expressions under different emotions and identify students’ emotional states. Use computer vision technology to capture and analyze students’ facial expressions in real-time. Then, facial recognition algorithms are used to recognize and classify the captured facial features to determine the current emotional state of the students. Finally, based on the students’ emotional state, the system will provide corresponding feedback. This technology based on computer vision and facial recognition algorithms can help teachers better understand students’ emotional changes, adjust teaching strategies in a timely manner, provide personalized learning feedback, and thereby improve students’ learning effectiveness and the quality of English teaching. This technology can also provide students with a better learning experience, enhancing their learning motivation and interest.