Search Results (16)

This study addresses the critical challenge of variable image quality in deep learning-based automated pest identification. We propose a holistic pipeline that integrates systematic Image Quality Assessment (IQA) with tailored preprocessing to enhance the performance of a YOLOv5 object detection model. The methodology begins with a No-Reference IQA using BRISQUE, PIQE, and NIQE metrics to quantitatively diagnose image clarity, noise, and distortion. Based on this assessment, a tailored preprocessing stage employing six different filters (Wiener, Lucy–Richardson, etc.) is applied to rectify degradations. Enhanced images are then used to train a YOLOv5 model for detecting four common pest species. Experimental results demonstrate that our IQA-anchored pipeline significantly improves image quality, with average BRISQUE and PIQE scores reducing from 40.78 to 25.42 and 34.94 to 30.38, respectively. Consequently, the detection confidence for challenging pests increased, for instance, from 0.27 to 0.44 for Peach Borer after dataset enhancement. This work concludes that a methodical approach to image quality management is not an optional step but a critical prerequisite that directly dictates the performance ceiling of automated deep learning systems in agriculture, offering a reusable blueprint for robust visual recognition tasks. Full article

The proposed forest monitoring photo trap ecosystem integrates a cost-effective architecture for observation and transmission using Internet of Things (IoT) technologies and long-range digital radio systems such as LoRa (Chirp Spread Spectrum—CSS) and nRF24L01 (Gaussian Frequency Shift Keying—GFSK). To address low-bandwidth links, a novel approach based on the Monte Carlo sampling algorithm enables progressive, bandwidth-aware image transfer and its thumbnail’s reconstruction on edge devices. The system transmits only essential data, supports remote image deletion/retrieval, and minimizes site visits, promoting environmentally friendly practices. A key innovation is the integration of no-reference image quality assessment (NR IQA) to determine when thumbnails are ready for operator review. Due to the computational limitations of the Raspberry Pi 3, the PIQE indicator was adopted as the operational metric in the quality stabilization module, whereas deep learning-based metrics (e.g., HyperIQA, ARNIQA) are retained as offline benchmarks only. Although single-pass inference may meet initial timing thresholds, the cumulative time–energy cost in an online pipeline on Raspberry Pi 3 is too high; hence these metrics remain offline. The system was validated through real-world field tests, confirming its practical applicability and robustness in remote forest environments. Full article

The mobile tunnel scanning system (MTSS) enables efficient tunnel inspection; however, motion blur (MB) generated at high travel speeds remains a major factor undermining the reliability of deep-learning-based crack detection. This study focuses on investigating how horizontally oriented MB in MTSS imagery affects the crack-detection performance of convolutional neural networks (CNNs) and proposes a data-centric quality-assurance framework that leverages no-reference image quality assessment (NR-IQA) to optimize model performance. By intentionally applying MB to both public and real-world MTSS datasets, we analyzed performance changes in ResNet-, VGG-, and AlexNet-based models and established the correlations between four NR-IQA metrics (BRISQUE, NIQE, PIQE, and CPBD) and performance (F1 score). As the MB intensity increased, the F1 score of ResNet34 dropped from 89.43% to 4.45%, confirming the decisive influence of image quality. PIQE and CPBD exhibited strong correlations with F1 (−0.87 and +0.82, respectively), emerging as the most suitable indicators for horizontal MB. Using thresholds of PIQE ≤ 20 and CPBD ≥ 0.8 to filter low-quality images improved the AlexNet F1 score by 1.46%, validating the effectiveness of the proposed methodology. The proposed framework objectively assesses MTSS data quality and optimizes deep learning performance, enhancing the reliability of intelligent infrastructure maintenance systems. Full article

Face-to-face interaction is one of the most natural forms of human communication. Unsurprisingly, Video Conferencing (VC) Applications have experienced a significant rise in demand over the past decade. With the widespread availability of cellular devices equipped with high-resolution cameras, Instant Messaging Video Call Applications (IMVCAs) now constitute a substantial portion of VC communications. Given the multitude of IMVCA options, maintaining a high Quality of Experience (QoE) is critical. While content providers can measure QoE directly through end-to-end connections, Internet Service Providers (ISPs) must infer QoE indirectly from network traffic—a non-trivial task, especially when most traffic is encrypted. In this paper, we analyze a large dataset collected from WhatsApp IMVCA, comprising over 25,000 s of VC sessions. We apply four Machine Learning (ML) algorithms and a Large Multimodal Model (LMM)-based agent, achieving mean errors of 4.61%, 5.36%, and 13.24% for three popular QoE metrics: BRISQUE, PIQE, and FPS, respectively. Full article

The automation of the detection infrastructure in GPR imagery is a key issue, particularly in the context of the non-invasive acquisition of radargrams with a multi-antenna ground-penetrating radar. Due to the fact that the dataset acquired with a multi-antenna GPR is very large, in the context of automating the process of detecting hyperbolas, the authors have proposed an adaptive approach to the selection of GPR images. The aim of this project was to develop a method for the selection of GPR images by means of applying the appropriate quality indicators. The authors propose a new, adaptive approach to the selection of radargrams that were recorded during the route of a GPR in a single profile, where several radargrams were recorded. Depending on the obtained initial values of the standard indicators for the assessment of the quality and quality maps of the radargrams, those images from selected channels that will ensure the highest possible quality and efficiency of hyperbola detection were selected. The stage of image quality assessment is essential in the context of improving the effectiveness of the automated detection of underground infrastructure. The quality assessment was performed based on the entropy indicator, PIQE, and Laplacian variance. The selected quality indicators allowed the authors to assess the degree of blurring, noise, and the number of details representing the underground structures that are present in GPR images. An additional product of the quality assessment were the generated maps that present the distribution of entropy in the analyzed images. The image selection was verified based on the results of the parameters that assess the effectiveness of the detection of hyperbolas that represent underground networks. The proposed innovative adaptive approach to the selection of images acquired by GPR enabled a significant improvement in the efficiency of the detection of hyperbolas representing underground utility networks, by 15–40%, shortening data processing and infrastructure detection times. Full article

When objects are obscured by shadows or dim surroundings, image quality is improved by fusing near-infrared and visible-light images. At night, when visible and NIR lights are insufficient, long-wave infrared (LWIR) imaging can be utilized, necessitating the attachment of a visible-light sensor to an LWIR camera to simultaneously capture both LWIR and visible-light images. This camera configuration enables the acquisition of infrared images at various wavelengths depending on the time of day. To effectively fuse clear visible regions from the visible-light spectrum with those from the LWIR spectrum, a multi-band fusion method is proposed. The proposed fusion process subsequently combines detailed information from infrared and visible-light images, enhancing object visibility. Additionally, this process compensates for color differences in visible-light images, resulting in a natural and visually consistent output. The fused images are further enhanced using a night-to-day image translation module, which improves overall brightness and reduces noise. This night-to-day translation module is a trained CycleGAN-based module that adjusts object brightness in nighttime images to levels comparable to daytime images. The effectiveness and superiority of the proposed method are validated using image quality metrics. The proposed method significantly contributes to image enhancement, achieving the best average scores compared to other methods, with a BRISQUE of 30.426 and a PIQE of 22.186. This study improves the accuracy of human and object recognition in CCTV systems and provides a potential image-processing tool for autonomous vehicles. Full article

Rain is a typical meteorological event that affects the visual appeal of outdoor pictures. The presence of rain streaks severely blurs image details, negatively impacting subsequent computer visual tasks. Due to the challenge of acquiring authentic photographs of rainfall, most deraining methods have been developed using generated samples. However, the inherent differences between generated and real data lead to poor generalization performance in practical applications. This study proposes a semi-supervised single-image rain removal approach using Transformer and wavelet transform. It fully utilizes the feature information of rainy images, addressing the issue that current methods focus too much on network structure innovation while neglecting rain streak features. The algorithm leverages the directional properties of wavelet transform to decompose rainy images into multi-scale components, with networks of varying sizes generating rain streak maps across different directions and scales. By combining supervised and unsupervised training in a semi-supervised system, the model improves deraining performance and generalization capability. Additionally, a residual detail recovery network restores fine-grained image details, further enhancing the deraining effect in real-world scenarios. Comprehensive tests on multiple standard datasets show that the proposed approach outperforms current methods, confirming its effectiveness in practical applications. Experimental results on common datasets demonstrate that it performs better than advanced rain removal algorithms. The method’s superiority is further validated by the PSNR and SSIM values of 34.86 dB and 0.961 on the Rain1200 synthetic dataset, and the NIQE and PIQE values of 11.52 and 9.13 on the RealRain dataset. Full article

Deploying high-performance image restoration models on drones is critical for applications like autonomous navigation, surveillance, and environmental monitoring. However, the computational and memory limitations of drones pose significant challenges to utilizing complex image restoration models in real-world scenarios. To address this issue, we propose the Simultaneous Learning Knowledge Distillation (SLKD) framework, specifically designed to compress image restoration models for resource-constrained drones. SLKD introduces a dual-teacher, single-student architecture that integrates two complementary learning strategies: Degradation Removal Learning (DRL) and Image Reconstruction Learning (IRL). In DRL, the student encoder learns to eliminate degradation factors by mimicking Teacher A, which processes degraded images utilizing a BRISQUE-based extractor to capture degradation-sensitive natural scene statistics. Concurrently, in IRL, the student decoder reconstructs clean images by learning from Teacher B, which processes clean images, guided by a PIQE-based extractor that emphasizes the preservation of edge and texture features essential for high-quality reconstruction. This dual-teacher approach enables the student model to learn from both degraded and clean images simultaneously, achieving robust image restoration while significantly reducing computational complexity. Experimental evaluations across five benchmark datasets and three restoration tasks—deraining, deblurring, and dehazing—demonstrate that, compared to the teacher models, the SLKD student models achieve an average reduction of 85.4% in FLOPs and 85.8% in model parameters, with only a slight average decrease of 2.6% in PSNR and 0.9% in SSIM. These results highlight the practicality of integrating SLKD-compressed models into autonomous systems, offering efficient and real-time image restoration for aerial platforms operating in challenging environments. Full article

An approach to detecting discontinuities in carbon fiber-reinforced polymers, caused by impact loading followed by compression testing, was developed. An X-ray sensor-based installation was used, while some algorithms were developed to improve the quality of the obtained low-contrast radiographic images with negligible signal-to-noise ratios. For epoxy/AF (#1) composite subjected to a “high-velocity” steel-ball impact with subsequent compression loading, it was not possible to detect discontinuities since the orientation of the extended zone of interlayer delamination was perpendicular to the irradiation axis. After drop-weight impacts with subsequent compression loading of epoxy/CF (#2) and PEEK/CF (#3) composites, the main cracks were formed in their central parts. This area was reliably detected through the improved radiographic images being more contrasted compared to that for composite #3, for which the damaged area was similar in shape but smaller. The phase variation and congruency methods were employed to highlight low-contrast objects in the radiographic images. The phase variation procedure showed higher efficiency in detecting small objects, while phase congruency is preferable for highlighting large objects. To assess the degree of image improvement, several metrics were implemented. In the analysis of the model images, the most indicative was the PSNR parameter (with a S-N ratio greater than the unit), confirming an increase in image contrast and a decrease in noise level. The NIQE and PIQE parameters enabled the correct assessment of image quality even with the S-N ratio being less than a unit. Full article

The current study proposed and evaluated “residual squeeze and excitation attention gate” (rSEAG), a novel network that can improve image quality by reducing distortion attributed to artifacts. This method was established by modifying the Cycle Generative Adversarial Network (cycleGAN)-based generator network using projection data for pre-reconstruction processing in digital breast tomosynthesis. Residual squeeze and excitation were installed in the bridge of the generator network, and the attention gate was installed in the skip connection between the encoder and decoder. Based on the radiation dose index (exposure index and division index) incident on the detector, the cases approved by the ethics committee and used for the study were classified as reference (675 projection images) and object (675 projection images). For the cases, unsupervised data containing a mixture of cases with and without masses were used. The cases were trained using cycleGAN with rSEAG and the conventional networks (ResUNet and U-Net). For testing, predictive processing was performed on cases (60 projection images) that were not used for learning. Images were generated using filtered backprojection reconstruction (kernel: Ramachandran and Lakshminarayanan) from projection data for testing data and without pre-reconstruction processing data (evaluation: in-focus plane). The distortion was evaluated using perception-based image quality evaluation (PIQE) analysis, texture analysis (feature: “Homogeneity” and “Contrast”), and a statistical model with a Gumbel distribution. PIQE has a low rSEAG value. Texture analysis showed that rSEAG and a network without cycleGAN were similar in terms of the “Contrast” feature. In dense breasts, ResUNet had the lowest “Contrast” feature and U-Net had differences between cases. The maximal variations in the Gumbel plot, rSEAG reduced the high-frequency ripple artifacts. In this study, rSEAG could improve distortion and reduce ripple artifacts. Full article

Photogrammetry depends critically on the quality of the images used to reconstruct accurate and detailed 3D models. Selection of high-quality images not only improves the accuracy and resolution of the resulting 3D models, but also contributes to the efficiency of the photogrammetric process by reducing data redundancy and computational demands. This study presents a novel approach to image quality evaluation tailored for photogrammetric applications that uses the key point descriptors typically encountered in image matching. Using a LightGBM ranker model, this research evaluates the effectiveness of key point descriptors such as SIFT, SURF, BRISK, ORB, KAZE, FREAK, and SuperPoint in predicting image quality. These descriptors are evaluated for their ability to indicate image quality based on the image patterns they capture. Experiments conducted on various publicly available image datasets show that descriptor-based methods outperform traditional no-reference image quality metrics such as BRISQUE, NIQE, PIQE, and BIQAA and a simple sharpness-based image quality evaluation method. The experimental results highlight the potential of using key-point-descriptor-based image quality evaluation methods to improve the photogrammetric workflow by selecting high-quality images for 3D modeling. Full article

This paper aimed to develop a method for generating sand–dust removal and dehazed images utilizing CycleGAN, facilitating object identification on roads under adverse weather conditions such as heavy dust or haze, which severely impair visibility. Initially, the study addressed the scarcity of paired image sets for training by employing unpaired CycleGAN training. The CycleGAN training module incorporates hierarchical single-scale Retinex (SSR) images with varying sigma sizes, facilitating multiple-scaled trainings. Refining the training data into detailed hierarchical layers for virtual paired training enhances the performance of CycleGAN training. Conventional sand–dust removal or dehazing algorithms, alongside deep learning methods, encounter challenges in simultaneously addressing sand–dust removal and dehazing with a singular algorithm. Such algorithms often necessitate resetting hyperparameters to process images from both scenarios. To overcome this limitation, we proposed a unified approach for removing sand–dust and haze phenomena using a single model, leveraging images processed hierarchically with SSR. The image quality and image sharpness metrics of the proposed method were BRIQUE, PIQE, CEIQ, MCMA, LPC-SI, and S3. In sand–dust environments, the proposed method achieved the highest scores, with an average of 21.52 in BRISQUE, 0.724 in MCMA, and 0.968 in LPC-SI compared to conventional methods. For haze images, the proposed method outperformed conventional methods with an average of 3.458 in CEIQ, 0.967 in LPC-SI, and 0.243 in S3. The images generated via this proposed method demonstrated superior performance in image quality and sharpness evaluation compared to conventional algorithms. The outcomes of this study hold particular relevance for camera images utilized in automobiles, especially in the context of self-driving cars or CCTV surveillance systems. Full article

Photographs taken under harsh ambient lighting can suffer from a number of image quality degradation phenomena due to insufficient exposure. These include reduced brightness, loss of transfer information, noise, and color distortion. In order to solve the above problems, researchers have proposed many deep learning-based methods to improve the illumination of images. However, most existing methods face the problem of difficulty in obtaining paired training data. In this context, a zero-reference image enhancement network for low light conditions is proposed in this paper. First, the improved Encoder-Decoder structure is used to extract image features to generate feature maps and generate the parameter matrix of the enhancement factor from the feature maps. Then, the enhancement curve is constructed using the parameter matrix. The image is iteratively enhanced using the enhancement curve and the enhancement parameters. Second, the unsupervised algorithm needs to design an image non-reference loss function in training. Four non-reference loss functions are introduced to train the parameter estimation network. Experiments on several datasets with only low-light images show that the proposed network has improved performance compared with other methods in NIQE, PIQE, and BRISQUE non-reference evaluation index, and ablation experiments are carried out for key parts, which proves the effectiveness of this method. At the same time, the performance data of the method on PC devices and mobile devices are investigated, and the experimental analysis is given. This proves the feasibility of the method in this paper in practical application. Full article

Sentinel-2 satellites can provide free optical remote-sensing images with a spatial resolution of up to 10 M, but the spatial details provided are not enough for many applications, so it is worth considering improving the spatial resolution of Sentinel-2 satellites images through super-resolution (SR). Currently, the most effective SR models are mainly based on deep learning, especially the generative adversarial network (GAN). Models based on GAN need to be trained on LR–HR image pairs. In this paper, a two-step super-resolution generative adversarial network (TS-SRGAN) model is proposed. The first step is having the GAN train the degraded models. Without supervised HR images, only the 10 m resolution images provided by Sentinel-2 satellites are used to generate the degraded images, which are in the same domain as the real LR images, and then to construct the near-natural LR–HR image pairs. The second step is to design a super-resolution generative adversarial network with strengthened perceptual features, to enhance the perceptual effects of the generated images. Through experiments, the proposed method obtained an average NIQE as low as 2.54, and outperformed state-of-the-art models according to other two NR-IQA metrics, such as BRISQUE and PIQE. At the same time, the comparison of the intuitive visual effects of the generated images also proved the effectiveness of TS-SRGAN. Full article

In general, the quality of imagery from Unmanned Aerial Vehicles (UAVs) is evaluated after the flight, and then a decision is made on the further value and use of the acquired data. In this paper, an a priori (preflight) image quality prediction methodology is proposed to estimate the preflight image quality and to avoid unfavourable flights, which is extremely important from a time and cost management point of view. The XBoost Regressor model and cross-validation were used for machine learning of the model and image quality prediction. The model was learned on a rich database of real-world images acquired from UAVs under conditions varying in both sensor type, UAV type, exposure parameters, weather, topography, and land cover. Radiometric quality indices (SNR, Entropy, PIQE, NIQE, BRISQUE, and NRPBM) were calculated for each image to train and test the model and to assess the accuracy of image quality prediction. Different variants of preflight parameter knowledge were considered in the study. The proposed methodology offers the possibility of predicting image quality with high accuracy. The correlation coefficient between the actual and predicted image quality, depending on the number of parameters known a priori, ranged from 0.90 to 0.96. The methodology was designed for data acquired from a UAV. Similar prediction accuracy is expected for other low-altitude or close-range photogrammetric data. Full article