Search

Recent technological developments have enabled computers to identify and categorize facial expressions to determine a person's emotional state in an image or a video. This process, called "Facial Expression Recognition (FER)", has become one of the most popular research areas in computer vision. In recent times, deep FER systems have primarily concentrated on addressing two significant challenges: the problem of overfitting due to limited training data availability, and the presence of expression-unrelated variations, including illumination, head pose, image resolution, and identity bias. In this paper, a comprehensive survey is provided on deep FER, encompassing algorithms and datasets that offer insights into these intrinsic problems. Initially, this paper presents a detailed timeline showcasing the evolution of methods and datasets in deep facial expression recognition (FER). This timeline illustrates the progression and development of the techniques and data resources used in FER. Then, a comprehensive review of FER methods is introduced, including the basic principles of FER (components such as preprocessing, feature extraction and classification, and methods, etc.) from the pro-deep learning era (traditional methods using handcrafted features, i.e., SVM and HOG, etc.) to the deep learning era. Moreover, a brief introduction is provided related to the benchmark datasets (there are two categories: controlled environments (lab) and uncontrolled environments (in the wild)) used to evaluate different FER methods and a comparison of different FER models. Existing deep neural networks and related training strategies designed for FER, based on static images and dynamic image sequences, are discussed. The remaining challenges and corresponding opportunities in FER and the future directions for designing robust deep FER systems are also pinpointed. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) fault detection is crucial because undetected PV faults can lead to significant energy losses, with some cases experiencing losses of up to 10%. The efficiency of PV systems depends upon the reliable detection and diagnosis of faults. The integration of Artificial Intelligence (AI) techniques has been a growing trend in addressing these issues. The goal of this systematic review is to offer a comprehensive overview of the recent advancements in AI-based methodologies for PV fault detection, consolidating the key findings from 31 research papers. An initial pool of 142 papers were identified, from which 31 were selected for in-depth review following the PRISMA guidelines. The title, objective, methods, and findings of each paper were analyzed, with a focus on machine learning (ML) and deep learning (DL) approaches. ML and DL are particularly suitable for PV fault detection because of their capacity to process and analyze large amounts of data to identify complex patterns and anomalies. This study identified several AI techniques used for fault detection in PV systems, ranging from classical ML methods like k-nearest neighbor (KNN) and random forest to more advanced deep learning models such as Convolutional Neural Networks (CNNs). Quantum circuits and infrared imagery were also explored as potential solutions. The analysis found that DL models, in general, outperformed traditional ML models in accuracy and efficiency. This study shows that AI methodologies have evolved and been increasingly applied in PV fault detection. The integration of AI in PV fault detection offers high accuracy and effectiveness. After reviewing these studies, we proposed an Artificial Neural Network (ANN)-based method for PV fault detection and classification. [ABSTRACT FROM AUTHOR]

The activation function introduces nonlinearity into convolutional neural network, which greatly promotes the development of computer vision tasks. This paper proposes elastic adaptively parametric compounded units to improve the performance of convolutional neural networks for image recognition. The activation function takes the structural advantages of two mainstream functions as the function's fundamental architecture. The SENet model is embedded in the proposed activation function to adaptively recalibrate the feature mapping weight in each channel, thereby enhancing the fitting capability of the activation function. In addition, the function has an elastic slope in the positive input region by simulating random noise to improve the generalization capability of neural networks. To prevent the generated noise from producing overly large variations during training, a special protection mechanism is adopted. In order to verify the effectiveness of the activation function, this paper uses CIFAR-10 and CIFAR-100 image datasets to conduct comparative experiments of the activation function under the exact same model. Experimental results show that the proposed activation function showed superior performance beyond other functions. [ABSTRACT FROM AUTHOR]

Quality evaluation of food products, agricultural produce to be specific, has gained momentum from past few decades due to the increased awareness among consumers across the world. This has resulted in the increased emphasis on the development and use of quality assessment techniques in food industry. Moreover, there is a need to automate the quality monitoring of agricultural produce like fruits and vegetables which is otherwise done manually in developing countries hence labor intensive, time consuming and subjective in nature. This paper presents an empirical analysis to build a rapid, robust, real-time, non-destructive computer vision based quality assessment model for mango fruits. The work employs the automatic disease classification of mango fruits based on machine and deep learning models. Firstly, the dataset of colored mango fruits images with 2279 images falling into three classes and another dataset of soft X-ray images of mango fruits with 572 images belonging to two quality classes are developed for detecting external and internal defects, respectively. The multilayer perceptron neural network (MLP NN) with two hidden layers, which may be considered as the starting point for deep learning technique, is proposed as machine learning model to classify the color images of mango fruits into one of three external quality classes with 95.1% accuracy and also to classify the soft X-ray images into two internal quality classes with 97.5% accuracy. In order to step out of feature engineering, actual deep learning convolutional neural network (CNN) models, a customized CNN model and pre-trained CNN models, VGGNet (VGG16) and DenseNet121 were also explored for mango disease classification. The maximum validation accuracy of custom CNN was found to be with 91.52% and 98.7% for color and augmented X-ray images, respectively. The classification accuracy of pre-trained models were found to be reasonably good for the color images but exhibited high variability in results and made it difficult to draw a general conclusion for the proposed datasets. However, the proposed MLP NN model based on few basic intensity and geometric features and also the proposed customized CNN model were found to be the best models and they outperform the state of the art reported in the literature. [ABSTRACT FROM AUTHOR]

Automatic image description, also known as image captioning, aims to describe the elements included in an image and their relationships. This task involves two research fields: computer vision and natural language processing; thus, it has received much attention in computer science. In this review paper, we follow the Kitchenham review methodology to present the most relevant approaches to image description methodologies based on deep learning. We focused on works using convolutional neural networks (CNN) to extract the characteristics of images and recurrent neural networks (RNN) for automatic sentence generation. As a result, 53 research articles using the encoder-decoder approach were selected, focusing only on supervised learning. The main contributions of this systematic review are: (i) to describe the most relevant image description papers implementing an encoder-decoder approach from 2014 to 2022 and (ii) to determine the main architectures, datasets, and metrics that have been applied to image description. [ABSTRACT FROM AUTHOR]

The purpose of image dehazing is to remove the interference from weather factors in degraded images and enhance the clarity and color saturation of images to maximize the restoration of useful features. Single image dehazing is one of the most important tasks in the field of image restoration. In recent years, due to the progress of deep learning, single image dehazing has made great progress. With the success of Transformer in advanced computer vision tasks, some research studies also began to apply Transformer to image dehazing tasks and obtained surprising results. However, both the deconvolution-neural-network-based dehazing algorithm and Transformer based dehazing algorithm magnify their advantages and disadvantages separately. Therefore, this paper proposes a novel Transformer–Convolution fusion dehazing network (TCFDN), which uses Transformer's global modeling ability and convolutional neural network's local modeling ability to improve the dehazing ability. In the Transformer–Convolution fusion dehazing network, the classic self-encoder structure is used. This paper proposes a Transformer–Convolution hybrid layer, which uses an adaptive fusion strategy to make full use of the Swin-Transformer and convolutional neural network to extract and reconstruct image features. On the basis of previous research, this layer further improves the ability of the network to remove haze. A series of contrast experiments and ablation experiments not only proved that the Transformer–Convolution fusion dehazing network proposed in this paper exceeded the more advanced dehazing algorithm, but also provided solid and powerful evidence for the basic theory on which it depends. [ABSTRACT FROM AUTHOR]

In image classification with Deep Convolutional Neural Networks (DCNNs), the number of parameters in pointwise convolutions rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer. Existing studies demonstrated that a subnetwork can replace pointwise convolutional layers with significantly fewer parameters and fewer floating-point computations, while maintaining the learning capacity. In this paper, we propose an improved scheme for reducing the complexity of pointwise convolutions in DCNNs for image classification based on interleaved grouped filters without divisibility constraints. The proposed scheme utilizes grouped pointwise convolutions, in which each group processes a fraction of the input channels. It requires a number of channels per group as a hyperparameter C h . The subnetwork of the proposed scheme contains two consecutive convolutional layers K and L, connected by an interleaving layer in the middle, and summed at the end. The number of groups of filters and filters per group for layers K and L is determined by exact divisions of the original number of input channels and filters by C h . If the divisions were not exact, the original layer could not be substituted. In this paper, we refine the previous algorithm so that input channels are replicated and groups can have different numbers of filters to cope with non exact divisibility situations. Thus, the proposed scheme further reduces the number of floating-point computations (11%) and trainable parameters (10%) achieved by the previous method. We tested our optimization on an EfficientNet-B0 as a baseline architecture and made classification tests on the CIFAR-10, Colorectal Cancer Histology, and Malaria datasets. For each dataset, our optimization achieves a saving of 76%, 89%, and 91% of the number of trainable parameters of EfficientNet-B0, while keeping its test classification accuracy. [ABSTRACT FROM AUTHOR]

Simple Summary: The use of computer vision technology has improved the effectiveness of individual sheep identification, but existing methods face challenges such as large parameter sizes, slow recognition speeds, and difficult deployment. To address this issue, we have made improvements and optimizations based on the Retinaface face recognition model to create a balanced speed-accuracy sheep face recognition model. The optimized model has fewer parameters, simpler computations, faster inference speeds, and higher recognition accuracy, making it well-suited for deployment on resource-constrained edge devices. This research is expected to promote the application of deep learning-based sheep face recognition methods in production. The recognition of sheep faces based on computer vision has improved the efficiency and effectiveness of individual sheep identification, providing technical support for the development of smart farming. However, current recognition models have problems such as large parameter sizes, slow recognition speed, and difficult deployment. Therefore, this paper proposes an efficient and fast basic module called Eblock and uses it to build a lightweight sheep face recognition model called SheepFaceNet, which achieves the best balance between speed and accuracy. SheepFaceNet includes two modules: SheepFaceNetDet for detection and SheepFaceNetRec for recognition. SheepFaceNetDet uses Eblock to construct the backbone network to enhance feature extraction capability and efficiency, designs a bidirectional FPN layer (BiFPN) to enhance geometric location ability, and optimizes the network structure, which affects inference speed, to achieve fast and accurate sheep face detection. SheepFaceNetRec uses Eblock to construct the feature extraction network, uses ECA channel attention to improve the effectiveness of feature extraction, and uses multi-scale feature fusion to achieve fast and accurate sheep face recognition. On our self-built sheep face dataset, SheepFaceNet recognized 387 sheep face images per second with an accuracy rate of 97.75%, achieving an advanced balance between speed and accuracy. This research is expected to further promote the application of deep-learning-based sheep face recognition methods in production. [ABSTRACT FROM AUTHOR]

Simple Summary: Constructing a contactless pig mass estimation method through computer vision technology can help us to adjust our pig breeding program to improve production efficiency. Due to the complexity of the actual production environment, there are few reports on pig mass estimation in an unconstrained environment. In this study, we constructed a pig mass estimate model based on deep learning without constraint. The experimental results proved that the pig body mass estimation model constructed in this paper can quickly and accurately obtain the body mass of pigs. The model can evaluate the body quality of sows in real-time in an unconstrained environment, thereby providing data support for grading and adjusting breeding plans, and has broad application prospects. The body mass of pigs is an essential indicator of their growth and health. Lately, contactless pig body mass estimation methods based on computer vision technology have gained attention thanks to their potential to improve animal welfare and ensure breeders' safety. Nonetheless, current methods require pigs to be restrained in a confinement pen, and no study has been conducted in an unconstrained environment. In this study, we develop a pig mass estimation model based on deep learning, capable of estimating body mass without constraints. Our model comprises a Mask R-CNN-based pig instance segmentation algorithm, a Keypoint R-CNN-based pig keypoint detection algorithm and an improved ResNet-based pig mass estimation algorithm that includes multi-branch convolution, depthwise convolution, and an inverted bottleneck to improve accuracy. We constructed a dataset for this study using images and body mass data from 117 pigs. Our model achieved an RMSE of 3.52 kg on the test set, which is lower than that of the pig body mass estimation algorithm with ResNet and ConvNeXt as the backbone network, and the average estimation speed was 0.339 s·frame−1 Our model can evaluate the body quality of pigs in real-time to provide data support for grading and adjusting breeding plans, and has broad application prospects. [ABSTRACT FROM AUTHOR]

Advances in deep learning techniques for remote sensing as well as the increased availability of high-resolution data enable the extraction of more detailed information from aerial images. One promising task is the semantic segmentation of roof segments and their orientation. However, the lack of annotated data is a major barrier for deploying respective models on a large scale. Previous research demonstrated the viability of the deep learning approach for the task, but currently, published datasets are small-scale, manually labeled, and rare. Therefore, this paper extends the state of the art by presenting a novel method for the automated generation of large-scale datasets based on semantic 3D city models. Furthermore, we train a model on a dataset 50 times larger than existing datasets and achieve superior performance while applying it to a wider variety of buildings. We evaluate the approach by comparing networks trained on four dataset configurations, including an existing dataset and our novel large-scale dataset. The results show that the network performance measured as intersection over union can be increased from 0.60 for the existing dataset to 0.70 when the large-scale model is applied on the same region. The large-scale model performs superiorly even when applied to more diverse test samples, achieving 0.635. The novel approach contributes to solving the dataset bottleneck and consequently to improving semantic segmentation of roof segments. The resulting remotely sensed information is crucial for applications such as solar potential analysis or urban planning. [ABSTRACT FROM AUTHOR]

With advancements in artificial intelligence and computer vision, machine learning has become widely employed in location and detection of road pavement distresses. Recently, recognition methods based on convolutional neural networks (CNNs) have been implemented to segment pavement cracks at pixel level in order to evaluate the pavement condition. However, this method usually consists of some common processes, including manually predetermining the approximate location of cracks followed by selecting the image containing the cracks and then performing pixel-level segmentation, which is why it is worth automating the preprocessing to replace the manual selection step. Moreover, the issues of a low proportion of positive samples, complex crack topologies, different inset conditions, and complex pavement background make the task of automatic pavement location more challenging. Therefore, this paper proposes a novel method for preprocessing crack recognition, which automatically locates cracks and yields great savings in labor costs. Specifically, a real-world road pavement crack data set obtained from a common digital camera mounted on a vehicle is built to test the proposed crack location method, called Double-Head. It improves the accuracy of crack object localization by using an independent fully connected head (fc-head) and a convolution head (conv-head). The results show that our method improves average precision (AP) 6.5% over Faster R-CNN using only a fc-head, and outperforms many advanced object detection methods. [ABSTRACT FROM AUTHOR]

Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model. [ABSTRACT FROM AUTHOR]

Global solar photovoltaic capacity has consistently doubled every 18 months over the last two decades, going from 0.3 GW in 2000 to 643 GW in 2019, and is forecast to reach 4240 GW by 2040. However, these numbers are uncertain, and virtually all reporting on deployments lacks a unified source of either information or validation. In this paper, we propose, optimize, and validate a deep learning framework to detect and map solar farms using a state-of-the-art semantic segmentation convolutional neural network applied to satellite imagery. As a final step in the pipeline, we propose a model to estimate the energy generation capacity of the detected solar energy facilities. Objectively, the deep learning model achieved highly competitive performance indicators, including a mean accuracy of 96.87%, and a Jaccard Index (intersection over union of classified pixels) score of 95.5%. Subjectively, it was found to detect spaces between panels producing a segmentation output at a sub-farm level that was better than human labeling. Finally, the detected areas and predicted generation capacities were validated against publicly available data to within an average error of 4.5% Deep learning applied specifically for the detection and mapping of solar farms is an active area of research, and this deep learning capacity evaluation pipeline is one of the first of its kind. We also share an original dataset of overhead solar farm satellite imagery comprising 23,000 images (256 × 256 pixels each), and the corresponding labels upon which the machine learning model was trained. [ABSTRACT FROM AUTHOR]

Residual neural network (ResNet) is a Deep Learning model introduced by He et al. in 2015 to enhance traditional convolutional neural networks proposed to solve computer vision problems. It uses skip connections over some layer blocks to avoid vanishing gradient problem. Currently, many researches are focused to test and prove the efficiency of the ResNet on different domains such as genomics. In fact, the study of human genomes provides important information on the detection of diseases and their best treatments. Therefore, most of the scientists opted for bioinformatics solutions to get results in a reasonable time. In this paper, our interest is to show the effectiveness of the ResNet model on genomics. For that, we propose two new ResNet models to enhance the results of two genomic problems previously resolved by CNN models. The obtained results are very promising and they proved the performance of our ResNet models compared to the CNN models. [ABSTRACT FROM AUTHOR]

Human facial expressions are an essential and fundamental component for expressing the state of the human mind. The automatic analysis of these nonverbal facial expressions has become a fascinating and quite challenging problem in computer vision, with its application in different areas, such as psychology, human–machine interaction, health, and augmented reality. Recently, deep learning (DL) has become a widespread technique for studying human nonverbal facial sentiment expressions, and some research attempts have been made to propose a certain model on this topic. The purpose of this paper is to apply the appropriate convolutional neural network (CNN) approach by adding several layers of different dimensions, which allows the CNN approach to efficiently classify human facial sentiment expressions with data augmentation capable of recognizing seven basic human facial expressions: anger, sadness, fear, disgust, happiness, surprise, and neutral. In particular, this study mainly proposes a convolution neural network architecture, as well as learning factors that minimize the memory space and total training time of the proposed network due to the shallow architecture of the model. Following that, we demonstrated our proposed model's network complexity, computational cost, and classification accuracy on the three benchmark datasets: FER2013, KDEF, and JAFFE. As a result, our proposed approach achieves accuracy of 6 7. 5 % , 7 9. 5 % , 9 0. 0 % in the FER2013, KDEF, and JAFFE, respectively, which is better compared to other state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Students' disengagement problem has become critical in the modern scenario due to various distractions and lack of student‐teacher interactions. This problem is exacerbated with large offline classrooms, where it becomes challenging for teachers to monitor students' engagement and maintain the right‐level of interactions. Traditional ways of monitoring students' engagement rely on self‐reporting or using physical devices, which have limitations for offline classroom use. Student's academic affective states (e.g., moods and emotions) analysis has potential for creating intelligent classrooms, which can autonomously monitor and analyse students' engagement and behaviours in real‐time. In recent literature, a few computer vision based methods have been proposed, but they either work only in the e‐learning domain or have limitations in real‐time processing and scalability for large offline classes. This paper presents a real‐time system for student group engagement monitoring by analysing their facial expressions and recognizing academic affective states: 'boredom,' 'confuse,' 'focus,' 'frustrated,' 'yawning,' and 'sleepy,' which are pertinent in the learning environment. The methodology includes certain pre‐processing steps like face detection, a convolutional neural network (CNN) based facial expression recognition model, and post‐processing steps like frame‐wise group engagement estimation. For training the CNN model, we created a dataset of the aforementioned facial expressions from classroom lecture videos and added related samples from three publicly available datasets, BAUM‐1, DAiSEE, and YawDD, to generalize the model predictions. The trained model has achieved train and test accuracy of 78.70% and 76.90%, respectively. The proposed methodology gave promising results when compared with self‐reported engagement levels by students. [ABSTRACT FROM AUTHOR]

Left ventricular non-compaction (LVNC) is a rare cardiomyopathy characterized by abnormal trabeculations in the left ventricle cavity. Although traditional computer vision approaches exist for LVNC diagnosis, deep learning-based tools could not be found in the literature. In this paper, a first approach using convolutional neural networks (CNNs) is presented. Four CNNs are trained and tuned to automatically segment the compacted and trabecular areas of the left ventricle for a population of patients diagnosed with hypertrophic cardiomyopathy. We have evaluated them in the learning phase with an NVIDIA Turing GPU and 2 competitive Xeon CPUs. Inference results confirm that deep learning-based approaches can achieve excellent results in the diagnosis and measurement of LVNC. The final proposal enables real-time analysis of 15-slice MRI studies on both GPU and CPU, obtaining noticeable speed-ups with regard to manual, semi-automatic and fully automatic approaches. Additionally, a subjective evaluation of the output images with the identified zones is performed by expert cardiologists, with a perfect visual agreement for all the slices, outperforming already existing automatic tools. [ABSTRACT FROM AUTHOR]

Background: Maize (Zea mays L.) is one of the most important food sources in the world and has been one of the main targets of plant genetics and phenotypic research for centuries. Observation and analysis of various morphological phenotypic traits during maize growth are essential for genetic and breeding study. The generally huge number of samples produce an enormous amount of high-resolution image data. While high throughput plant phenotyping platforms are increasingly used in maize breeding trials, there is a reasonable need for software tools that can automatically identify visual phenotypic features of maize plants and implement batch processing on image datasets. Results: On the boundary between computer vision and plant science, we utilize advanced deep learning methods based on convolutional neural networks to empower the workflow of maize phenotyping analysis. This paper presents Maize-IAS (Maize Image Analysis Software), an integrated application supporting one-click analysis of maize phenotype, embedding multiple functions: (I) Projection, (II) Color Analysis, (III) Internode length, (IV) Height, (V) Stem Diameter and (VI) Leaves Counting. Taking the RGB image of maize as input, the software provides a user-friendly graphical interaction interface and rapid calculation of multiple important phenotypic characteristics, including leaf sheath points detection and leaves segmentation. In function Leaves Counting, the mean and standard deviation of difference between prediction and ground truth are 1.60 and 1.625. Conclusion: The Maize-IAS is easy-to-use and demands neither professional knowledge of computer vision nor deep learning. All functions for batch processing are incorporated, enabling automated and labor-reduced tasks of recording, measurement and quantitative analysis of maize growth traits on a large dataset. We prove the efficiency and potential capability of our techniques and software to image-based plant research, which also demonstrates the feasibility and capability of AI technology implemented in agriculture and plant science. [ABSTRACT FROM AUTHOR]

For a long time, learning spatiotemporal features with deep neural networks has been a difficult task in the field of computer vision. In this paper, we present a novel deep architecture, termed as Bifurcated Convolutional Neural Network (BifurcatedNet) to learn the discriminative video representation in an end-to-end manner. In our work, the BifurcatedNet is built upon the stacking bifurcated blocks that aim at simultaneously capturing the static appearance information and the temporal dynamic from input data. Specifically, the bifurcated block is composed of two separated branch, i.e., an appearance branch and a dynamic branch. The appearance branch employs 2D convolutional operation to obtain the spatial responses of image pixels or filters of each input frame, while the design of the dynamic branch is based on the spatio-temporal convolutional operation to exploit the temporal dynamic between pixels and filter response across multiple frames. Multiple experiments are conducted on two popular action recognition benchmarks: UCF101 and HMDB51. With only RGB input, the BifurcatedNet obtains the superior performance over the existing state-of-the-art models under the same experimental setting. The proposed BifurcatedNet is also implemented in a two-stream fashion by using both RGB and optical flow input, and still achieves the state-of-the-art performance, demonstrating the effectiveness of the network design. Furthermore, in order to evaluate the generalization ability, we conduct experiments on the Chalearn LAP IsoGD dataset and find that our model works well in gesture recognition tasks. [ABSTRACT FROM AUTHOR]

Rail corrugation is a common wear mechanism of high-speed railways and subways, which can cause derailment and running noise. However, rail corrugation only has slight texture change on the rail surface, so it is difficult to detect accurately by traditional detection methods. In this paper, a real-time detection method of rail corrugation based on machine vision and a convolutional neural network is proposed, which effectively improves the accuracy and efficiency of rail corrugation detection. Combined with the gray features of each part of the image, a rail surface segmentation method based on the gray maximum value of the sliding window is also proposed. Moreover, the obtained rail surface image is clearer and the feature information of the rail surface can be completely retained, compared with the adaptive threshold segmentation and edge detection segmentation. ShuffleNet V2, a lightweight convolutional neural network, was selected as the corrugation detection model. The squeeze-and-excitation module was integrated into its basic unit to improve its channel attention, and the activation function was re-selected to make the detection have better real-time performance and accuracy. Through experimental verification, the average detection time of a single image of the improved model is 4.01ms, and the detection accuracy is 2.78% higher than that of the unimproved ShuffleNet V2. The research results will be beneficial to the development of the intelligent real-time detection of rail corrugation. [ABSTRACT FROM AUTHOR]

Object detection studies aim to solve safety problems at industrial sites; however, improving object detection performance and ensuring real-time capabilities simultaneously remains challenging in multi-complex industrial environments. This paper proposes an unconditionally protected detector to address this problem. The detector's backbone network uses a residual block with a bottleneck structure to reduce computation and enhance real-time performance. Additionally, a selective attention network enhances object detection by extracting important features based on the morphological characteristics of the feature map in the neck structure. The method includes a whole-body estimation to locate individuals obstructed by obstacles, thereby preventing collisions with vehicles and avoiding hazardous situations in restricted areas. The proposed method enables real-time object detection and risk assessment for nearby objects, enhancing safety for industrial vehicle drivers and workers. Moreover, it can lead to further improvements in object detection performance in research fields such as autonomous driving and AI CCTV utilizing cameras. • Build dataset of industrial sites and improve the object detection performance on various complex backgrounds • Deep learning-based object detection method for accident prevention in industrial and construction environments • Unconditionally protected detector based on a selective attention network to extract and strengthen important features • Application of various model optimization techniques to shorten learning time and achieve efficient learning • Whole-body estimation method to detect location of an actual person to prevent dangerous situations at industrial sites [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have facilitated substantial progress on various problems in computer vision and image processing. However, applying them to image fusion has remained challenging due to the lack of the labelled data for supervised learning. This paper introduces a deep image fusion network (DIF-Net), an unsupervised deep learning framework for image fusion. The DIF-Net parameterizes the entire processes of image fusion, comprising of feature extraction, feature fusion, and image reconstruction, using a CNN. The purpose of DIF-Net is to generate an output image which has an identical contrast to high-dimensional input images. To realize this, we propose an unsupervised loss function using the structure tensor representation of the multi-channel image contrasts. Different from traditional fusion methods that involve time-consuming optimization or iterative procedures to obtain the results, our loss function is minimized by a stochastic deep learning solver with large-scale examples. Consequently, the proposed method can produce fused images that preserve source image details through a single forward network trained without reference ground-truth labels. The proposed method has broad applicability to various image fusion problems, including multi-spectral, multi-focus, and multi-exposure image fusions. Quantitative and qualitative evaluations show that the proposed technique outperforms existing state-of-the-art approaches for various applications. [ABSTRACT FROM AUTHOR]

Image colorization, as an essential problem in computer vision (CV), has attracted an increasing amount of researchers attention in recent years, especially deep learning-based image colorization techniques(DLIC). Generally, most recent image colorization methods can be regarded as knowledge-based systems because they are usually trained by big datasets. Unlike the existing reviews, this paper adopts a unique deep learning-based perspective to review the latest progress in image colorization techniques systematically and comprehensively. In this paper, a comprehensive review of recent DLIC approaches from algorithm classification to existing challenges is provided to facilitate researchers' in-depth understanding of DLIC. In particular, we review DLIC algorithms from various perspectives, including color space, network structure, loss function, level of automation, and application fields. Furthermore, other important issues are discussed, such as publicly available benchmark datasets and performance evaluation metrics. Finally, we discuss several open issues of image colorization and outline future research directions. This survey can serve as a reference for researchers in image colorization and related fields. [ABSTRACT FROM AUTHOR]

• The Hybrid-SSR framework is proposed to perform real-time hand gesture recognition. • The Enhanced Xception (E-Xception) architecture is utilized as a backbone network. • Mitigates the misclassification problem encountered by the conventional models. • The proposed model is evaluated on MITI-HD, NUSHP-II and Senz-3D datasets. In-situ detection and recognition of hand gestures in an unconstrained environment is a crucial task in the field of machine vision and video recognition. Hand gesture recognizing task is perhaps more complicated, with varying lighting conditions and background. Robust, accurate hand detection and classification becomes necessary to facilitate the Graphical User Interface, Tele-surgery, etc. In this paper, a Convolutional Neural Network (CNN) based Hybrid Single Stage Recognition (Hybrid-SSR) framework is proposed for real-time hand gesture recognition. The time-efficient Enhanced Xception (E-Xception) CNN model is proposed for feature extraction. The framework is evaluated using three separate datasets (NUSHP-II, Senz-3D, and MITI-HD). The performance of the framework is evaluated for the range of IoU from 0.5 to 0.95. In comparison with the conventional single-stage hand gesture recognition system, the Hybrid-SSR model resulted in higher precision values (99.60 % on AP 0.5 , 97.80 % on AP 0.75 , and 88.20 % on AP 0.5:0.95) for the MITI-HD dataset. The Hybrid-SSR model with Adam Optimizer surpasses the other optimization techniques. The proposed model achieved comparatively higher precision and recall values for focusing parameter (γ) = 2 and weighting parameter (α) = 0.5. The misclassification problem encountered by the conventional single-stage models is mitigated by implementing the focal loss function in the classification sub-network. The computation cost of Hybrid-SSR (12 ms) is significantly lower compared to other single-stage hand gesture recognition frameworks. [ABSTRACT FROM AUTHOR]

In turning, the wear control of a cutting tool benefits product quality enhancement, tool-related costs' optimisation, and assists in avoiding undesired events. In small series and individual production, the machine operator is the one who determines when to change a cutting tool, based upon their experience. Bad decisions can often lead to greater costs, production downtime, and scrap. In this paper, a Tool Condition Monitoring (TCM) system is presented that automatically classifies tool wear of turning tools into four classes (no, low, medium, high wear). A cutting tool was monitored with infrared (IR) camera immediately after the cut and in the following 60 s. The Convolutional Neural Network Inception V3 was used to analyse and classify the thermographic images, which were divided into different groups depending on the time of acquisition. Based on classification result, one gets information about the cutting capability of the tool for further machining. The proposed model, combining Infrared Thermography, Computer Vision, and Deep Learning, proved to be a suitable method with results of more than 96% accuracy. The most appropriate time of image acquisition is 6–12 s after the cut is finished. While existing temperature based TCM systems focus on measuring a cutting tool absolute temperature, the proposed system analyses a temperature distribution (relative temperatures) on the whole image based on image features. [ABSTRACT FROM AUTHOR]

Automated pavement distress recognition is a key step in smart infrastructure assessment. Advances in deep learning and computer vision have improved the automated recognition of pavement distresses in road surface images. This task remains challenging due to the high variation of defects in shapes and sizes, demanding a better incorporation of contextual information into deep networks. In this paper, we show that an attention-based multi-scale convolutional neural network (A+MCNN) improves the automated classification of common distress and non-distress objects in pavement images by (i) encoding contextual information through multi-scale input tiles and (ii) employing a mid-fusion approach with an attention module for heterogeneous image contexts from different input scales. A+MCNN is trained and tested with four distress classes (crack, crack seal, patch, pothole), five non-distress classes (joint, marker, manhole cover, curbing, shoulder), and two pavement classes (asphalt, concrete). A+MCNN is compared with four deep classifiers that are widely used in transportation applications and a generic CNN classifier (as the control model). The results show that A+MCNN consistently outperforms the baselines by 1∼26% on average in terms of the F-score. A comprehensive discussion is also presented regarding how these classifiers perform differently on different road objects, which has been rarely addressed in the existing literature. [ABSTRACT FROM AUTHOR]

Super resolution (SR) enables to generate a high-resolution (HR) image from one or more low-resolution (LR) images. Since a variety of CNN models have been recently studied in the areas of computer vision, these approaches have been combined with SR in order to provide higher image restoration. In this paper, we propose a lightweight CNN-based SR method, named multi-scale channel dense network (MCDN). In order to design the proposed network, we extracted the training images from the DIVerse 2K (DIV2K) dataset and investigated the trade-off between the SR accuracy and the network complexity. The experimental results show that the proposed method can significantly reduce the network complexity, such as the number of network parameters and total memory capacity, while maintaining slightly better or similar perceptual quality compared to the previous methods. [ABSTRACT FROM AUTHOR]

The new coronavirus disease (COVID-19), pneumonia, tuberculosis, and breast cancer have one thing in common: these diseases can be diagnosed using radiological studies such as X-rays images. With radiological studies and technology, computer-aided diagnosis (CAD) results in a very useful technique to analyze and detect abnormalities using the images generated by X-ray machines. Some deep-learning techniques such as a convolutional neural network (CNN) can help physicians to obtain an effective pre-diagnosis. However, popular CNNs are enormous models and need a huge amount of data to obtain good results. In this paper, we introduce NanoChest-net, which is a small but effective CNN model that can be used to classify among different diseases using images from radiological studies. NanoChest-net proves to be effective in classifying among different diseases such as tuberculosis, pneumonia, and COVID-19. In two of the five datasets used in the experiments, NanoChest-net obtained the best results, while on the remaining datasets our model proved to be as good as baseline models from the state of the art such as the ResNet50, Xception, and DenseNet121. In addition, NanoChest-net is useful to classify radiological studies on the same level as state-of-the-art algorithms with the advantage that it does not require a large number of operations. [ABSTRACT FROM AUTHOR]

In recent years, the technology of artificial intelligence (AI) and robots is rapidly spreading to countries around the world. More and more scholars and industry experts have proposed AI deep learning models and methods to solve human life problems and improve work efficiency. Modern people's lives are very busy, which led us to investigate whether the demand for Bento buffet cafeterias has gradually increased in Taiwan. However, when eating at a buffet in a cafeteria, people often encounter two problems. The first problem is that customers need to queue up to check out after they have selected and filled their dishes from the buffet. However, it always takes too much time waiting, especially at lunch or dinner time. The second problem is sometimes customers question the charges calculated by cafeteria staff, claiming they are too expensive at the checkout counter. Therefore, it is necessary to develop an AI-enabled checkout system. The AI-enabled self-checkout system will help the Bento buffet cafeterias reduce long lineups without the need to add additional workers. In this paper, we used computer vision and deep-learning technology to design and implement an AI-enabled checkout system for Bento buffet cafeterias. The prototype contains an angle steel shelf, a Kinect camera, a light source, and a desktop computer. Six baseline convolutional neural networks were applied for comparison on food recognition. In our experiments, there were 22 different food categories in a Bento buffet cafeteria employed. Experimental results show that the inception_v4 model can achieve the highest average validation accuracy of 99.11% on food recognition, but it requires the most training and recognition time. AlexNet model achieves a 94.5% accuracy and requires the least training time and recognition time. We propose a hierarchical approach with two stages to achieve good performance in both the recognition accuracy rate and the required training and recognition time. The approach is designed to perform the first step of identification and the second step of recognizing similar food images, respectively. Experimental results show that the proposed approach can achieve a 96.3% accuracy rate on our test dataset and required very little recognition time for input images. In addition, food volumes could be estimated using the depth images captured by the Kinect camera, and a framework of visual checkout system was successfully built. [ABSTRACT FROM AUTHOR]

Deep-learning methods, especially convolutional neural networks (CNN), have become the first choice for hyperspectral image (HSI) classification to date. It is a common procedure that small cubes are cropped from hyperspectral images and then fed into CNNs. However, standard CNNs find it difficult to extract discriminative spectral–spatial features. How to obtain finer spectral–spatial features to improve the classification performance is now a hot topic of research. In this regard, the attention mechanism, which has achieved excellent performance in other computer vision, holds the exciting prospect. In this paper, we propose a double-branch network consisting of a novel convolution named pyramidal convolution (PyConv) and an iterative attention mechanism. Each branch concentrates on exploiting spectral or spatial features with different PyConvs, supplemented by the attention module for refining the feature map. Experimental results demonstrate that our model can yield competitive performance compared to other state-of-the-art models. [ABSTRACT FROM AUTHOR]

In recent years, benefiting from the rapid development of deep learning technology in the field of computer vision, the study of hyperspectral image (HSI) classification has also made great progress. However, compared with ordinary RGB images, HSIs are more like 3D cubes; therefore, it is necessary and beneficial to explore classification methods suitable for the very special data structure of HSIs. In this paper, we propose Multiple Spectral Resolution 3D Convolutional Neural Network (MSR-3DCNN) for HSI classification tasks. In MSR-3DCNN, we expand the idea of multi-scale feature fusion and dilated convolution from the spatial dimension to the spectral dimension, and combine 3D convolution and residual connection; therefore, it can better adapt to the 3D cubic form of hyperspectral data and make efficient use of spectral information in different bands. Experimental results on four benchmark datasets show the effectiveness of the proposed approach and its superiority as compared with some state-of-the-art (SOTA) HSI classification methods. [ABSTRACT FROM AUTHOR]

With the increasing popularity of artificial intelligence, deep learning has been applied to various fields, especially in computer vision. Since artificial intelligence is migrating from cloud to edge, deep learning nowadays should be edge-oriented and adaptive to complex environments. Aiming at these goals, this paper proposes an ICONet (illumination condition optimized network). Based on OTSU segmentation algorithm and fuzzy c-means clustering algorithm, the illumination condition classification subnet increases the environmental adaptivity of our network. The reduced time complexity and optimized size of our convolutional neural network (CNN) model enables the implementation of ICONet on edge devices. In the field of fatigue driving, we test the performance of ICONet on YawDD and self-collected datasets. Our network achieves a general accuracy of 98.56% and our models are about 590 kilobytes. Compared to other proposed networks, the ICONet shows significant success and superiority. Applying ICONet to fatigue driving detection is helpful to solve the symmetry of the needs of edge-oriented detection under complex illumination condition environments and the scarcity of related approaches. [ABSTRACT FROM AUTHOR]

This study proposed an automated method for manifesting construction activity scenes by image captioning – an approach rooted in computer vision and natural language generation. A linguistic description schema for manifesting the scenes is developed initially and two unique dedicated image captioning datasets are created for method validation. A general model architecture of image captioning is then instituted by combining an encoder-decoder framework with deep neural networks, followed by three experimental tests involving the selection of model learning strategies and performance evaluation metrics. It is demonstrated the method's performance is comparable with that of state-of-the-art computer vision methods in general. The paper concludes with a discussion of the feasibility of the practical application of the proposed approach at the current technical level. • A new method for manifesting construction activity scenes via image captioning • A linguistic description schema of construction activity scenes for method validation • A model integrating a CNN, an RNN and word embedding for sentence generation • Two dedicated scene-based datasets for training and evaluating the proposed model • The method's proven comparability with the state-of-the-art in CV community [ABSTRACT FROM AUTHOR]

In the manuscript, the issue of detecting and segmenting out pavement defects on highway roads is addressed. Specifically, computer vision (CV) methods are developed and applied to the problem based on deep learning of convolutional neural networks (ConvNets). A novel neural network structure is considered, based on a pipeline of three ConvNets and endowed with the capacity for context awareness, which improves grid-based search for defects on orthoframes by considering the surrounding image content—an approach, which essentially draws inspiration from how humans tend to solve the task of image segmentation. Also, methods for assessing the quality of segmentation are discussed. The contribution also describes the complete procedure of working with pavement defects in an industrial setting, involving the workcycle of defect annotation, ConvNet training and validation. The results of ConvNet evaluation provided in the paper hint at a successful implementation of the proposed technique. [ABSTRACT FROM AUTHOR]

With the rapid development of surveying and spatial information technologies, more and more attention has been given to positioning. In outdoor environments, people can easily obtain positioning services through global navigation satellite systems (GNSS). In indoor environments, the GNSS signal is often lost, while other positioning problems, such as dead reckoning and wireless signals, will face accumulated errors and signal interference. Therefore, this research uses images to realize a positioning service. The main concept of this work is to establish a model for an indoor field image and its coordinate information and to judge its position by image eigenvalue matching. Based on the architecture of PoseNet, the image is input into a 23-layer convolutional neural network according to various sizes to train end-to-end location identification tasks, and the three-dimensional position vector of the camera is regressed. The experimental data are taken from the underground parking lot and the Palace Museum. The preliminary experimental results show that this new method designed by us can effectively improve the accuracy of indoor positioning by about 20% to 30%. In addition, this paper also discusses other architectures, field sizes, camera parameters, and error corrections for this neural network system. The preliminary experimental results show that the angle error correction method designed by us can effectively improve positioning by about 20%. [ABSTRACT FROM AUTHOR]

In Taiwan, mushrooms are an agricultural product with high nutritional value and economic benefit. However, global warming and climate change have affected plant quality. As a result, technological greenhouses are replacing traditional tin houses as locations for mushroom planting. These greenhouses feature several complex parameters. If we can reduce the complexity such greenhouses and improve the efficiency of their production management using intelligent schemes, technological greenhouses could become the expert assistants of farmers. In this paper, the main goal of the developed system is to measure the mushroom size and to count the amount of mushrooms. According to the results of each measurement, the growth rate of the mushrooms can be estimated. The proposed system also records the data of the mushrooms and broadcasts them to the mobile phone of the farmer. This improves the effectiveness of the production management. The proposed system is based on the convolutional neural network of deep learning, which is used to localize the mushrooms in the image. A positioning correction method is also proposed to modify the localization result. The experiments show that the proposed system has a good performance concerning the image measurement of mushrooms. [ABSTRACT FROM AUTHOR]