Search

Recycling tasks are the most effective method for reducing waste generation, protecting the environment, and boosting the overall national economy. The productivity and effectiveness of the recycling process are strongly dependent on the cleanliness and precision of processed primary sources. However, recycling operations are often labor intensive, and computer vision and deep learning (DL) techniques aid in automatically detecting and classifying trash types during recycling chores. Due to the dimensional challenge posed by pre-trained CNN networks, the scientific community has developed numerous techniques inspired by biology, swarm intelligence theory, physics, and mathematical rules. This research applies a new meta-heuristic algorithm called the artificial hummingbird algorithm (AHA) to solving the waste classification problem based on feature selection. However, the performance of the AHA is barely satisfactory; it may be stuck in optimal local regions or have a slow convergence. To overcome these limitations, this paper develops two improved versions of the AHA called the AHA-ROBL and the AHA-OBL. These two versions enhance the exploitation stage by using random opposition-based learning (ROBL) and opposition-based learning (OBL) to prevent local optima and accelerate the convergence. The main purpose of this paper is to apply the AHA-ROBL and AHA-OBL to select the relevant deep features provided by two pre-trained models of CNN (VGG19 & ResNet20) to recognize a waste classification. The TrashNet dataset is used to verify the performance of the two proposed approaches (the AHA-ROBL and AHA-OBL). The effectiveness of the suggested methods (the AHA-ROBL and AHA-OBL) is compared with that of 12 modern and competitive optimizers, namely the artificial hummingbird algorithm (AHA), Harris hawks optimizer (HHO), Salp swarm algorithm (SSA), aquila optimizer (AO), Henry gas solubility optimizer (HGSO), particle swarm optimizer (PSO), grey wolf optimizer (GWO), Archimedes optimization algorithm (AOA), manta ray foraging optimizer (MRFO), sine cosine algorithm (SCA), marine predators algorithm (MPA), and rescue optimization algorithm (SAR). A fair evaluation of the proposed algorithms' performance is achieved using the same dataset. The performance analysis of the two proposed algorithms is applied in terms of different measures. The experimental results confirm the two proposed algorithms' superiority over other comparative algorithms. The AHA-ROBL and AHA-OBL produce the optimal number of selected features with the highest degree of precision. [ABSTRACT FROM AUTHOR]

The registration of point clouds in a three-dimensional space is an important task in many areas of computer vision, including robotics and autonomous driving. The purpose of registration is to find a rigid geometric transformation to align two point clouds. The registration problem can be affected by noise and partiality (two point clouds only have a partial overlap). The Iterative Closed Point (ICP) algorithm is a common method for solving the registration problem. Recently, artificial neural networks have begun to be used in the registration of point clouds. The drawback of ICP and other registration algorithms is the possible convergence to a local minimum. Thus, an important characteristic of a registration algorithm is the ability to avoid local minima. In this paper, we propose an ICP-type registration algorithm (λ -ICP) that uses a multiparameter functional (λ -functional). The proposed λ -ICP algorithm generalizes the NICP algorithm (normal ICP). The application of the λ -functional requires a consistent choice of the eigenvectors of the covariance matrix of two point clouds. The paper also proposes an algorithm for choosing the directions of eigenvectors. The performance of the proposed λ -ICP algorithm is compared with that of a standard point-to-point ICP and neural network Deep Closest Points (DCP). [ABSTRACT FROM AUTHOR]

Context: YOLO (You Look Only Once) is an algorithm based on deep neural networks with real-time object detection capabilities. This state-of-the-art technology is widely available, mainly due to its speed and precision. Since its conception, YOLO has been applied to detect and recognize traffic signs, pedestrians, traffic lights, vehicles, and so on. Objective: The goal of this research is to systematically analyze the YOLO object detection algorithm, applied to traffic sign detection and recognition systems, from five relevant aspects of this technology: applications, datasets, metrics, hardware, and challenges. Method: This study performs a systematic literature review (SLR) of studies on traffic sign detection and recognition using YOLO published in the years 2016–2022. Results: The search found 115 primary studies relevant to the goal of this research. After analyzing these investigations, the following relevant results were obtained. The most common applications of YOLO in this field are vehicular security and intelligent and autonomous vehicles. The majority of the sign datasets used to train, test, and validate YOLO-based systems are publicly available, with an emphasis on datasets from Germany and China. It has also been discovered that most works present sophisticated detection, classification, and processing speed metrics for traffic sign detection and recognition systems by using the different versions of YOLO. In addition, the most popular desktop data processing hardwares are Nvidia RTX 2080 and Titan Tesla V100 and, in the case of embedded or mobile GPU platforms, Jetson Xavier NX. Finally, seven relevant challenges that these systems face when operating in real road conditions have been identified. With this in mind, research has been reclassified to address these challenges in each case. Conclusions: This SLR is the most relevant and current work in the field of technology development applied to the detection and recognition of traffic signs using YOLO. In addition, insights are provided about future work that could be conducted to improve the field. [ABSTRACT FROM AUTHOR]

In recent years, the breakthrough of neural networks and the rise of deep learning have led to the advancement of machine vision, which has been commonly used in the practical application of image recognition. Automobiles, drones, portable devices, behavior recognition, indoor positioning and many other industries also rely on the integrated application, and require the support of deep learning and machine vision. As for these technologies, there is a high demand for the accuracy related to the recognition of portraits or objects. The recognition of human figures is also a research goal that has drawn great attention in various fields. However, the portrait will be affected by various factors such as height, weight, posture, angle and whether it is covered or not, which affects the accuracy of recognition. This paper applies the application of deep learning to portraits with different poses and angles, especially the actual distance of a single lens for the shadowed portrait (depth estimation), so that it can be used for automatic control of drones in the future. Traditional methods for calculating depth using images are mainly divided into three types: one—single-lens estimation, two—lens estimation, and three—optical band estimation. In view of the fact that both the second and third categories require relatively large and expensive equipment to effectively perform distance calculations, numerous methods for calculating distance using a single lens have recently been produced. However, whether it is the use of traditional "units of distance measurement calibration", "defocus distance measurement", or the "three-dimensional grid space messages distance measurement method", all of these face corresponding difficulties and problems. Additionally, they have to deal with outside disturbances and process the shadowed image. Therefore, under the new research method, OpenPose, which is proposed by Carnegie Mellon University, this paper intends to propose a depth algorithm for a single-lens occluded portrait to estimate the actual portrait distance for different poses, angles of view and obscuration. [ABSTRACT FROM AUTHOR]

The Hough transform, interpreted as the discretization of the Radon transform, is a widely used tool in image processing and machine vision. The primary way to speed it up is to employ the Brady–Yong algorithm. However, the accuracy of the straight line discretization utilized in this algorithm is limited. In this study, we propose a novel algorithm called A S D 2 that offers fast computation of the Hough transform for images of arbitrary sizes. Our approach adopts a computation scheme similar to the Brady–Yong algorithm but incorporates the best possible line discretization for improved accuracy. By employing the Method of Four Russians, we demonstrate that for an image of size n × n where n = 8 q and q ∈ N , the computational complexity of the A S D 2 algorithm is O (n 8 / 3) when summing over O (n 2) digital straight line segments. [ABSTRACT FROM AUTHOR]

Surface roughness is one of the key characteristics of machined components as it affects the surface quality and, consequently, the lifetime of the components themselves. The most common method of measuring the surface roughness is contact profilometry. Although this method is still widely applied, it has several drawbacks, such as limited measurement speed, sensitivity to vibrations, and requirement for precise positioning of the measured samples. In this paper, machine vision, machine learning and evolutionary optimization algorithms are used to induce a model for predicting the surface roughness of automotive components. Based on the attributes extracted by a machine vision algorithm, a machine learning algorithm generates the roughness predictive model. In addition, an evolutionary algorithm is used to tune the machine vision and machine learning algorithm parameters in order to find the most accurate predictive model. The developed methodology is comparable to the existing contact measurement method with respect to accuracy, but advantageous in that it is capable of predicting the surface roughness online and in real time. [ABSTRACT FROM AUTHOR]

We present a method of using interactive image segmentation algorithms to reduce specific image segmentation problems to the task of finding small sets of pixels identifying the regions of interest. To this end, we empirically show the feasibility of automatically generating seeds for GrowCut, a popular interactive image segmentation algorithm. The principal contribution of our paper is the proposal of a method for automating the seed generation method for the task of whole-heart segmentation of MRI scans, which achieves competitive unsupervised results (0.76 Dice on the MMWHS dataset). Moreover, we show that segmentation performance is robust to seeds with imperfect precision, suggesting that GrowCut-like algorithms can be applied to medical imaging tasks with little modeling effort. [ABSTRACT FROM AUTHOR]

Small object detection is one of the most challenging and non-negligible fields in computer vision. Inspired by the location–focus–identification process of the avian visual system, we present our location-focused small-object-detection algorithm for video or image sequence, OTNet. The model contains three modules corresponding to the forms of saliency, which drive the strongest response of OT to calculate the saliency map. The three modules are responsible for temporal–spatial feature extraction, spatial feature extraction and memory matching, respectively. We tested our model on the AU-AIR dataset and achieved up to 97.95% recall rate, 85.73% precision rate and 89.94 F1 score with a lower computational complexity. Our model is also able to work as a plugin module for other object detection models to improve their performance in bird-view images, especially for detecting smaller objects. We managed to improve the detection performance by up to 40.01%. The results show that our model performs well on the common metrics on detection, while simulating visual information processing for object localization of the avian brain. [ABSTRACT FROM AUTHOR]

Convolutional neural networks have a broad spectrum of practical applications in computer vision. Currently, much of the data come from images, and it is crucial to have an efficient technique for processing these large amounts of data. Convolutional neural networks have proven to be very successful in tackling image processing tasks. However, the design of a network structure for a given problem entails a fine-tuning of the hyperparameters in order to achieve better accuracy. This process takes much time and requires effort and expertise from the domain. Designing convolutional neural networks' architecture represents a typical NP-hard optimization problem, and some frameworks for generating network structures for a specific image classification tasks have been proposed. To address this issue, in this paper, we propose the hybridized monarch butterfly optimization algorithm. Based on the observed deficiencies of the original monarch butterfly optimization approach, we performed hybridization with two other state-of-the-art swarm intelligence algorithms. The proposed hybrid algorithm was firstly tested on a set of standard unconstrained benchmark instances, and later on, it was adapted for a convolutional neural network design problem. Comparative analysis with other state-of-the-art methods and algorithms, as well as with the original monarch butterfly optimization implementation was performed for both groups of simulations. Experimental results proved that our proposed method managed to obtain higher classification accuracy than other approaches, the results of which were published in the modern computer science literature. [ABSTRACT FROM AUTHOR]

Over the past few decades, convolutional neural networks (CNNs) have achieved outstanding results in addressing a broad scope of computer vision problems. Despite these improvements, fully convolutional Siamese neural networks (FCSNN) still hardly adapt to complex scenes, such as appearance change, scale change, similar objects interference, etc. The present study focuses on an enhanced FCSNN based on convolutional block hyperparameters optimization, a new activation function (ModReLU) and Gaussian low pass filter. The optimization of hyperparameters is an important task, as it has a crucial ascendancy on the tracking process performance, especially when it comes to the initialization of weights and bias. They have to work efficiently with the following activation function layer. Inadequate initialization can result in vanishing or exploding gradients. In the first method, we propose an optimization strategy for initializing weights and bias in the convolutional block to ameliorate the learning of features so that each neuron learns as much as possible. Next, the activation function normalizes the output. We implement the convolutional block hyperparameters optimization by setting the convolutional weights initialization to constant, the bias initialization to zero and the Leaky ReLU activation function at the output. In the second method, we propose a new activation, ModReLU, in the activation layer of CNN. Additionally, we also introduce a Gaussian low pass filter to minimize image noise and improve the structures of images at distinct scales. Moreover, we add a pixel-domain-based color adjustment implementation to enhance the capacity of the proposed strategies. The proposed implementations handle better rotation, moving, occlusion and appearance change problems and improve tracking speed. Our experimental results clearly show a significant improvement in the overall performance compared to the original SiamFC tracker. The first proposed technique of this work surpasses the original fully convolutional Siamese networks (SiamFC) on the VOT 2016 dataset with an increase of 15.42% in precision, 16.79% in AUPC and 15.93% in IOU compared to the original SiamFC. Our second proposed technique also reveals remarkable advances over the original SiamFC with 18.07% precision increment, 17.01% AUPC improvement and an increase of 15.87% in IOU. We evaluate our methods on the Visual Object Tracking (VOT) Challenge 2016 dataset, and they both outperform the original SiamFC tracker performance and many other top performers. [ABSTRACT FROM AUTHOR]

There is presently a need for more robust navigation algorithms for autonomous industrial vehicles. These have reasonably guaranteed the adequate reliability of the navigation. In the current work, the stability of a modified algorithm for collision-free guiding of this type of vehicle is ensured. A lateral control and a longitudinal control are implemented. To demonstrate their viability, a stability analysis employing the Lyapunov method is carried out. In addition, this mathematical analysis enables the constants of the designed algorithm to be determined. In conjunction with the navigation algorithm, the present work satisfactorily solves the localization problem, also known as simultaneous localization and mapping (SLAM). Simultaneously, a convolutional neural network is managed, which is used to calculate the trajectory to be followed by the AGV, by implementing the artificial vision. The use of neural networks for image processing is considered to constitute the most robust and flexible method for realising a navigation algorithm. In this way, the autonomous vehicle is provided with considerable autonomy. It can be regarded that the designed algorithm is adequate, being able to trace any type of path. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNNs) are broadly used in numerous applications such as computer vision and image classification. Although CNN models deliver state-of-the-art accuracy, they require heavy computational resources that are not always affordable or available on every platform. Limited performance, system cost, and energy consumption, such as in edge devices, argue for the optimization of computations in neural networks. Toward this end, we propose herein the value-locality-based compression (VELCRO) algorithm for neural networks. VELCRO is a method to compress general-purpose neural networks that are deployed for a small subset of focused specialized tasks. Although this study focuses on CNNs, VELCRO can be used to compress any deep neural network. VELCRO relies on the property of value locality, which suggests that activation functions exhibit values in proximity through the inference process when the network is used for specialized tasks. VELCRO consists of two stages: a preprocessing stage that identifies output elements of the activation function with a high degree of value locality, and a compression stage that replaces these elements with their corresponding average arithmetic values. As a result, VELCRO not only saves the computation of the replaced activations but also avoids processing their corresponding output feature map elements. Unlike common neural network compression algorithms, which require computationally intensive training processes, VELCRO introduces significantly fewer computational requirements. An analysis of our experiments indicates that, when CNNs are used for specialized tasks, they introduce a high degree of value locality relative to the general-purpose case. In addition, the experimental results show that without any training process, VELCRO produces a compression-saving ratio in the range 13.5–30.0% with no degradation in accuracy. Finally, the experimental results indicate that, when VELCRO is used with a relatively low compression target, it significantly improves the accuracy by 2–20% for specialized CNN tasks. [ABSTRACT FROM AUTHOR]