Visible Camera Research Articles

Distinguishing tea stalks of Wuyuan green tea using hyperspectral imaging analysis and Convolutional Neural Network

Wuyuan green tea is a famous agricultural product in China and a product protected by national geo-graphical indications. The processed green tea also needs to remove impurities, such as stones, tea stalks, etc. However, tea stalks cannot be classified from Wuyuan green tea using photoelectric sorting and 2D image recognition technology since they have similar colors. This paper adopts hyperspectral imaging technology to solve the problem of inaccurate sorting caused by their similar colors. Green tea containing tea stalks was imaged using a visible and near-infrared camera with a wavelength of 400nm-1000nm. What’s more, Principal Component Analysis (PCA) was adopted to reduce the dimension of the col-lected hyperspectral image. And the Convolutional Neural Network (CNN) was used constructively to identify tea stalks in hyperspectral image, the CNN can automatically learn the corresponding features, avoid the complex feature extraction process. The experimental results showed that the recognition accuracy for tea stalks reaches 98.53%. The method has a high recognition rate and can meet the actual production requirements. After field testing, the selection rate is as high as 97.05%.

Image Restoration

Image restoration is an integral component of computer vision that tries to restore pictures that have been deteriorated or corrupted to their original or enhanced condition. In this study, we look into the wide-ranging terrain of picture restoration techniques, which includes both conventional filter-based approaches and cutting-edge deep learning models. There are certain circumstances in which traditional approaches, such as Wiener filtering and bilateral filtering, perform quite well, particularly when it comes to smoothing and noise reduction. On the other hand, the fact that they rely on handcrafted filters restricts their adaptation to more complicated forms of degradation. Visual restoration has been revolutionized by deep learning, which is led by convolutional neural networks (CNNs). Deep learning involves learning sophisticated representations of visual data. It is because of this that CNNs are able to deal with a wide variety of degradations, such as noise, blurring, artifacts, and missing data. Generative adversarial networks, often known as GANs, are continually pushing the limits of what is possible by utilizing adversarial training to accomplish spectacular outcomes in the areas of in painting and picture super-resolution. Despite amazing development, there are still obstacles to overcome: Understanding the inner workings of deep learning models continues to be a challenge, thanks to the limited interpretability of the data. Dependence on data: Acquiring large quantities of high-quality data is necessary for the training of successful models. Costs associated with computation: The process of training and deploying deep learning models may be quite computationally rigorous. The improvement of camera vision for autonomous cars in order to make navigation safer and more dependable overall. Image restoration technology has the potential to continue to revolutionize image processing and analysis, ultimately contributing to advancements across a wide range of scientific and technological domains. This can be accomplished by addressing the challenges that are currently being faced and concentrating on the promising research directions that are currently being pursued.

Optimization Method for Robot Moving Object Recognition and Grasping Strategy Based on Binocular Vision

<p>This article proposes a more accurate grasping strategy for the recognition and grasping of moving targets based on binocular vision cameras. Firstly, the front and back scene separation algorithm is used to identify the moving target grabbing object in the production line. Then, by setting an appropriate threshold, the SiamMask target tracking algorithm is improved to achieve dynamic target tracking. Finally, the conveyor belt speed is detected and the real-time position of the object is obtained. Then, the Cartesian strategy is used to achieve path planning and optimization methods for the robotic arm during movement. Through experimental simulation, the effectiveness and stability of the proposed method in this paper have been demonstrated.</p> <p> </p>

Optimising computer vision-based ergonomic assessments: sensitivity to camera position and monocular 3D pose model

Numerous computer vision algorithms have been developed to automate posture analysis and enhance the efficiency and accuracy of ergonomic evaluations. However, the most effective algorithm for conducting ergonomic assessments remains uncertain. Therefore, the aim of this study was to identify the optimal camera position and monocular 3D pose model that would facilitate precise and efficient ergonomic evaluations. We evaluated and compared four currently available computer vision algorithms: Mediapipe BlazePose, VideoPose3D, 3D-pose-baseline, and PSTMO to determine the most suitable model for conducting ergonomic assessments. Based on the findings, the side camera position yielded the lowest Mean Absolute Error (MAE) across static, dynamic, and combined tasks. This positioning proved to be the most reliable for ergonomic assessments. Additionally, VP3D_FB demonstrated superior performance among evaluated models. Practitioner Summary: This study aimed to determine the most effective computer vision algorithm and camera position for precise and efficient ergonomic evaluations. Evaluating four algorithms, we found that the side camera position with VideoPose3D yielded the lowest Mean Absolute Error (MAE), ensuring precise and efficient evaluations.

Retracted: Application and Analysis of RGB-D Salient Object Detection in Photographic Camera Vision Processing

Retracted: Application and Analysis of RGB-D Salient Object Detection in Photographic Camera Vision Processing

Low-cost single-shot complex optical field imaging with a simplified aperture

We report a new computational imaging methodology for complex optical field based on a single-frame diffraction intensity pattern acquisition with a simplified aperture and an extremely low-cost industrial machine vision camera. The current design of the apertures for the recovery of complex optical field was suffering from specific coding associated with the use of spatial light modulator or digital micromirror device, where it is difficult to make the optical implementations compact and cost-effective. In this work, we demonstrate that a simplified aperture without any pattern-like coding is efficient to establish the physical constraint for computational reconstruction. The aperture attached to the object defines the imaging region of interest (ROI) with coherent trans-illumination, and only one snapshot of the diffraction intensity pattern is required for recovering the ROI's complex field. Proof-of-concept numerical simulations and optical experiments have been carried out to validate the feasibility, noise robustness, resolution, and potential biological imaging applications of the proposed computational method.

Integrated web portal for non-destructive salt sensitivity detection of Camelina sativa seeds using fluorescent and visible light images coupled with machine learning algorithms.

Climate change has created unprecedented stresses in the agricultural sector, driving the necessity of adapting agricultural practices and developing novel solutions to the food crisis. Camelina sativa (Camelina) is a recently emerging oilseed crop with high nutrient-density and economic potential. Camelina seeds are rich in essential fatty acids and contain potent antioxidants required to maintain a healthy diet. Camelina seeds are equally amenable to economic applications such as jet fuel, biodiesel and high-value industrial lubricants due to their favorable proportions of unsaturated fatty acids. High soil salinity is one of the major abiotic stresses threatening the yield and usability of such crops. A promising mitigation strategy is automated, non-destructive, image-based phenotyping to assess seed quality in the food manufacturing process. In this study, we evaluate the effectiveness of image-based phenotyping on fluorescent and visible light images to quantify and qualify Camelina seeds. We developed a user-friendly web portal called SeedML that can uncover key morpho-colorimetric features to accurately identify Camelina seeds coming from plants grown in high salt conditions using a phenomics platform equipped with fluorescent and visible light cameras. This portal may be used to enhance quality control, identify stress markers and observe yield trends relevant to the agricultural sector in a high throughput manner. Findings of this work may positively contribute to similar research in the context of the climate crisis, while supporting the implementation of new quality controls tools in the agri-food domain.

Examining How Postpartum Videoconferencing Support Sessions Can Facilitate Connections between Parents: A Poststructural and Sociomaterial Analysis.

Postpartum support for new parents can normalize experiences, increase confidence, and lead to positive health outcomes. While in-person gatherings may be the preferred choice, not all parents can or want to join parenting groups in person. Online asynchronous chat spaces for parents have increased over the past 10 years, especially during the COVID pandemic, when "online" became the norm. However, synchronous postpartum support groups have not been as accessible. The purpose of our study was to examine how parents experienced postpartum videoconferencing support sessions. Seven one-hour videoconferencing sessions were conducted with 4-8 parents in each group (n = 37). Nineteen parents from these groups then participated in semi-structured interviews. Feminist poststructuralism and sociomaterialism were used to guide the research process and analysis. Parents used their agency to actively think about and interact using visual (camera) and audio (microphone) technologies to navigate socially constructed online discourses. Although videoconferencing fostered supportive connections and parents felt less alone and more confident, the participants also expressed a lack of opportunities for individual conversations. Nurses should be aware of the emerging opportunities that connecting online may present. This study was not registered.

Stereo vision based systems for sea-state measurement and floating structures monitoring

Using computer vision techniques such as stereo vision systems for sea state measurement or for offshore structures monitoring can improve the measurement fidelity and accuracy with no significant additional cost. In this paper, two experiments (in-lab/open-sea) are conducted to study the performance of stereo vision system to measure the water wave surface elevation and rigid body heaving motion. For the in-lab experiment, regular water waves are generated in a wave tank for different frequencies and wave heights, where the water surface is scanned by the stereo vision camera installed on the top of the tank. Surface elevation inferred by the stereo vision is verified by an installed stationary side camera that records the water surface through the tank transparent side window, water surface elevation measured by the side camera recordings is extracted using edge detection algorithm. During the in-lab experiment a heaving buoy is installed to test the performance of Visual Simultaneous Localization and Mapping (VSLAM) algorithm to monitor the buoy heave motion. The VSLAM algorithm fuses a buoy onboard stereo vision recordings with an embedded Inertial Measurement Unit (IMU) to estimate the 6-DOF of a rigid body. The Buoy motion VSLAM measurements are verified by a KLT tracking algorithm implemented on the video recordings of the stationary side camera. The open-sea experiment is implemented in Lake Somerville, Texas. The stereo vision system is installed to measure the water surface elevation and directional spectrum of the wind generated irregular waves. The open-sea wave measurements by the stereo vision are verified by a Sofar commercial wave buoys deployed in the testing location.

A novel AI‐powered IR‐Visible dual camera system for measuring and tracking ocular surface temperature

Aims/Purpose: To report the development of a novel artificial intelligence (AI) powered, dual camera (infrared (IR)/visible) system capable of measuring and tracking ocular surface temperature (OST) over any time period.Methods: The system consists of an IR camera (Teledyne FLIR IR A655sc) and a visible (V) camera (FLIR BFS 51S5C‐C), co‐mounted on a slit‐lamp for simultaneous and overlapping fields of view (FOV); designed control algorithms; computer hardware and connecting cables. Novel algorithms are leveraged to synchronize IR and V video streams of exposed ocular surface and adnexa for image and video registration. Localisation of the cornea in V video stream obtained by deep learning (DL) AI algorithms designed for semantic segmentation of the cornea. Coordinates of V video stream segmented cornea are then used to extract corresponding OST data from the IR video stream in each video stream frame. Data analysis algorithms are used to extract OST data from IR video stream. Further image segmentation algorithms isolated specific areas of interest (AOI) for OST analysis.Results: The DL algorithm was trained using V images captured using the V camera. Image registration and segmentation errors were calculated to determine accuracy of system. Mean square error for registration was 5.03 ± 1.82 (c.0.45 mm). Mean Intersection over Union (IoU) was 97.6%, representing accuracy in identifying corneal and scleral pixels in tracked eye segmentation. Analysis software extracted rate of OST change and relative OST change compared to baseline across cornea and selected AOI.Conclusions: A novel AI‐powered system for measuring and tracking OST over time was developed. The system synchronously records IR and V video streams of the eye surface and automatically extracts OST over time. The system can track eye movements and remove artefact eyelid blink frames from the data. A consistent AOI, i.e., pupil, whole cornea, inferior half, superior half, or selected corneal region, can be selected for OST extraction and analysis over time. Experimental results show that the system can track and analyse OST change over time.

Seasonal Phragmites australis classification in Long Point National Wildlife Area wetlands using a remotely piloted aircraft system and random forest machine learning

This study produced a high-accuracy remotely piloted aircraft system (RPAS) imagery classification method for identifying the invasive reed Phragmites australis ( Cav.) Trin. Ex Steud subsp. australis using random forest (RF) machine learning. RPAS imagery was collected in the spring and fall of 2019 using a fixed-wing RPAS equipped with a visible spectrum camera (eBee X, S.O.D.A. 3D; senseFly) in Long Point, Ontario, Canada. Imagery was used to produce separate early and late season classifications and a bi-temporal classification which used imagery from both dates. The overall accuracy achieved for each was 97%, 96%, and 91%, respectively. Digital surface models (DSMs) were the most important variable for identifying Phragmites in all classifications due to their greater height when compared to surrounding herbaceous vegetation. The bi-temporal classification, which utilized change in DSM value during the growing season, resulted in an estimated 47.8% new growth of Phragmites and appeared to capture sparse growth better than traditional classification differencing alone. This study highlights the promising use of high-resolution DSMs produced from RPAS imagery to classify invasive Phragmites and monitor within-year patch expansions.

Role of Quantum Dots and Nanostructures in Photovoltaic Energy Conversion

Nanostructures and quantum dots have substantial effects on enhancing photovoltaic energy conversion efficiency, as evidenced in this comprehensive study. Materials that are nanostructured and nanosized particles are commonly used to address the urgent issues related to energy conversion. The use of nanostructured substances to address issues with energy and natural resources has garnered a lot of interest lately. Directional nanostructures in particular show promise for the conversion, collection, and storage of energy. Due to their unique properties, such as electrical conductivity, mechanical energy, and photoluminescence, quantum dots made from carbon (CQDs) and graphene quantum dots (GQDs) have been integrated into hybrid photovoltaic-thermoelectric systems (PV-TE). It evaluates the effects of nanostructures on solar energy technologies, in particular how they can improve power conversion and light absorption in solar cells. Optical light detectors, which transform photonic energy into signals that are electrical, are among the many optoelectronic uses of CQDs that have drawn attention because they are essential components of contemporary imaging and communication systems, such as visible light cameras, machine vision, medical X-ray and near-infrared image processing, and visible light detection devices. Besides supercapacitors, the study investigates how nanostructures could play a crucial role in contributing to addressing the global energy crisis sustainably, by working as photocatalysts for hydrogen synthesis and supercapacitors.

Preliminary experimental results of tungsten wire calorimeter for CRAFT NNBI

The comprehensive Research Facility for Fusion Technology(CRAFT) has been carried out since 2019 in China and as an important component of CRAFT, a negative ion-based neutral beam injection sysgem(NNBI) (200–400 keV, 2 MW) is under construction. In order to realize online diagnosis of beam uniformity, a tungsten wirecalorimeteris developed. The tungsten wire calorimeter is characterized by double-layer tungsten wire mesh structure. During beam bombardment, the tungsten wire mesh is heated and emits light, a visible light camera is used to photograph the tungsten wire calorimeter. The beam profile is obtained by digitizing the light intensity distribution map. In this paper, through the thermal simulation anslysis of tungsten wire,the installation position of tungsten wire calorimeter are determined and the spatial resolution under different beam divergence are also analyzed.The tungsten wire calorimeter was tested on the beam source test platform, the light intensity distribution maps of the tungsten wire calorimeter under 15 keV–40 keV beam energy were obtained. The work above will accumulate experience for the operation of tungsten wire calorimeter for full scale beam source in the next stage, and provide technical means for the conditioning of negative beam sources.

Characterizing Space‐Time Channel Network Dynamics in a Mediterranean Intermittent Catchment of Central Italy Combining Visual Surveys and Cameras

AbstractNon‐perennial streams have a global prevalence, but quantitative knowledge of the temporal dynamics of their flowing length—namely the extent of the wet portion of the stream network—remains limited, as the monitoring of the spatiotemporal configuration of wet channels is challenging in most settings. This work combines the high spatial resolution of visual surveys and the high temporal resolution of camera‐based approaches to reconstruct the space‐time stream network dynamics in a 3.7 km2 Mediterranean catchment of central Italy. Information on the hydrological status of the stream network derived from 40 field surveys and sub‐hourly images collected with 21 stage‐cameras are combined exploiting the hierarchical principle. The latter postulates the existence of a Bayesian chain, defined from the local persistence of the nodes that dictates their wetting/drying order during expansion/retraction cycles of the flowing stream network. Our results highlight the complexity of network dynamics in the study area: while the number of wet nodes decreases during the dry season and increases during the wet season, the local persistency exhibits a highly heterogeneous non‐monotonic spatial pattern, originating a dynamically disconnected network. Despite this heterogeneity, the hierarchical model well approximates the temporal evolution of the state of the network nodes, with an accuracy that exceeds 99%. Crucially, the model allows the reconstruction of the wet portion even in cases in which part of the network was not observed. This work provides a novel conceptual approach for the reconstruction of the wet portion of the network in poorly accessible sites.

Multi-focused Image fusion in HDWT Domain

Multi-focused image fusion becomes crucial one to extend depth of field of machine vision cameras. It combines two or more images focusing different objects of the same scene to form multi-focused fused image. This paper proposes simple and effective method of multi-focused image fusion using local gradient energy in higher density discrete wavelet transform domain, which is shift invariant and over complete by a factor of 5. This wavelet transform transfers all spectral and spatial information of all source images into multi-focused fused image without any distortions. The qualitative and quantitative analyses using metrics without reference prove the proposed method is considerably superior than other fusion methods using Discrete wavelet transform, Stationary wavelet transform, and double density discrete wavelet transform.

A Real-Time Automotive Safety System Based on Advanced AI Facial Detection Algorithms

This research aims to design and implement a complete safety and comfort device that integrates a Driving Monitoring System (DMS) and a car Seat Electronic Control Unit (SECU). The DMS employs a combination of infrared sensors and a pre-trained Artificial Intelligence (AI) algorithm with advanced facial recognition capabilities. It aims to monitor and control the driver's distraction and drowsiness level during daytime and nighttime driving conditions by accurately detecting head pose and eye status. If the system detects the driver is drowsy or distracted from the road, a warning system will be activated by sending an electrical signal to the aforementioned car SECU. The designed SECU initiates a car seat vibration and triggers an audible signal to alert the driver of a dangerous situation by managing the seat movement process and protection features. It provides the basic drive and control of the seat motor drivers and position sensors. The most important consideration of this SECU is meeting the following requirements: real-time control of various motors, fast processing speed, low power, low heat dissipation, low quiescent current, and low Electromagnetic Interference (EMI). The two systems were integrated into a single compact device that includes a night vision camera mounted on the steering column to record data without obstructing the driver's view. The system has high precision at a maximum detection rate of 45 Frames Per Second (FPS) in real-time. Furthermore, the system is robust under actual driving conditions without being affected by the time of day, facial expressions, or eye occlusions.

Research on the Innovative Development of Digital Media Enabled by Computer Visual Arts

Abstract This paper explores the integration of computer visual art with digital media, highlighting the innovative potential of computer technology in creating dynamic digital media art. Initially, we review relevant theories of computer-based visual art and examine their applications in digital media art. We then detail an immersive scene design using Web3D technology, where images are processed via a computer vision camera imaging model, transformed, and analyzed with the SIFT algorithm to extract feature points. These are integrated with the incremental SFM algorithm for three-dimensional image reconstruction in immersive environments. We validate these methods with real datasets and controlled experiments to assess user experience improvements in digital media applications. Results indicate that the SIFT algorithm’s image-matching accuracy ranges from 50% to 78%, and the incremental SFM algorithm shows an average rotation error of only 0.183°. User sentiment scores improved significantly, from 11.583 to 23.452, post-experience, demonstrating enhanced realism and a new direction for digital media art.

Exploration of Virtual Reality Technology Enabling Diversified Teaching Models of Civics and Politics

Abstract The wide application of virtual reality technology has brought opportunities for teaching ideology and politics, breaking traditional education’s time and space limitations. This paper proposes an automatic three-dimensional modeling technology model, combined with computer vision camera imaging principles, to optimize the amount of data and improve optimization efficiency. And on this basis, it further proposes the Civics virtual scene construction technology, combined with the improved QEM grid simplification algorithm of edge segmentation, to optimize the virtual scene by simplifying the complex three-dimensional grid model. The experimental group’s students have shown good acceptance of this teaching method when teaching Civics in VR venues. In the cognitive and knowledge level of Civics learning, there is a significant difference between the experimental group and the control group in the dimensions of value identity and knowledge retention (P<0.05), and the mean value in the dimension of value identity is as high as 4.55, which is a very significant difference from the control class (P<0.01). And in the experiential feedback of Civics learning, the students in the experimental group have a greater sense of scene realism than the students in the control group (P<0.01), a stronger sense of realism of the interactive experience in learning (P<0.05), a higher degree of concentration in learning (P<0.01), and a more minor degree of interference by the external environment (P<0.01).

Semi-Supervised Learning With Heterogeneous Distribution Consistency for Visible Infrared Person Re-Identification.

Visible infrared person re-identification (VI-ReID) exposes considerable challenges because of the modality gaps between the person images captured by daytime visible cameras and nighttime infrared cameras. Several fully-supervised VI-ReID methods have improved the performance with extensive labeled heterogeneous images. However, the identity of the person is difficult to obtain in real-world situations, especially at night. Limited known identities and large modality discrepancies impede the effectiveness of the model to a great extent. In this paper, we propose a novel Semi-Supervised Learning framework with Heterogeneous Distribution Consistency (HDC-SSL) for VI-ReID. Specifically, through investigating the confidence distribution of heterogeneous images, we introduce a Gaussian Mixture Model-based Pseudo Labeling (GMM-PL) method, which adaptively adjusts different thresholds for each modality to label the identity. Moreover, to facilitate the representation learning of unutilized data whose prediction is lower than the threshold, Modality Consistency Regularization (MCR) is proposed to ensure the prediction consistency of the cross-modality pedestrian images and handle the modality variance. Extensive experiments with different label settings on two VI-ReID datasets demonstrate the effectiveness of our method. Particularly, HDC-SSL achieves competitive performance with state-of-the-art fully-supervised VI-ReID methods on RegDB dataset with only 1 visible label and 1 infrared label per class.

2013–2022年福建漳江口互花米草分布无人机遥感数据集

The invasion of exotic Spartina alterniflora into Chinese coastal wetlands poses a threat to biodiversity and ecosystem functions. Thus monitoring the spatio-temporal distribution of the invasion is important for the conservation/restoration and scientific management of coastal wetlands. This dataset includes S. alterniflora spatial data, derived from UAV-based RGB photos over Zhangjiang Estuary, Fujian Province from 2013 to 2022. Using a drone equipped with a visible light camera, we selected low-tide periods during the day, we captured the aerial images in the Zhangjiang Estuary wetland in Fujian Province from 2013 to 2022. Subsequently, we employed the dynamic structure-from-motion (SFM) techniques to reconstruct a three-dimensional model by mosaicking the collected aerial images to obtain a digital orthophoto image covering the study area. This process was repeated annually, resulting in a total of ten orthophoto images. Based on the classified data derived from these orthophoto images, the spatial distribution data of S. alterniflora over ten consecutive years were extracted. The high-quality UAV photos in this dataset are comprehensive and uniformly color-balanced. Located within the Zhangjiang Estuary Mangrove National Nature Reserve with coastal wetland vegetations such as mangroves and S. alterniflora, the study area is one of the most typical mangrove-S. alterniflora ecotones in China. This long-term (over ten consecutive years) and high-resolution (20 cm) image dataset for mangrove-S. alterniflora ecotone can be used in many studies including monitoring coastal wetland vegetation succession, mangrove conservation and restoration, and S. alterniflora invasion.