Real-time Object Research Articles

Effects of Data Augmentation Methods on YOLO v5s: Application of Deep Learning with Pytorch for Individual Cattle Identification

In this paper, we investigate the performance of the YOLO v5s (You Only Look Once) model for the identification of individual cattle in a cattle herd. The model is a popular method for real-time object detection, accuracy, and speed. However, since the videos obtained from the cattle herd consist of free space images, the number of frames in the data is unbalanced. This negatively affects the performance of the YOLOv5 model. First, we investigate the model performance on the unbalanced initial dataset obtained from raw images, then we stabilize the initial dataset using some data augmentation methods and obtain the model performance. Finally, we built the target detection model and achieved excellent model performance with an mAP (mean average precision) of 99.5% on the balanced dataset compared to the model on the unbalanced data (mAP of 95.8%). The experimental results show that YOLO v5s has a good potential for automatic cattle identification, but with the use of data augmentation methods, superior performance can be obtained from the model.

CAR VEHICLE IMAGE OBJECT DETECTION USING YOU ONLY LIVE ONCE (YOLO)

This research aims to analyze the performance of image object detection methods using You Only Live Once (YOLO) specifically in the context of car detection. YOLO-based object detection methods have gained great attention in the artificial intelligence community due to their ability to perform real-time object detection. In this research, we focus on using YOLO to detect car objects in images. The YOLO method will be tested for performance using a dataset of car images that have been collected from various sources. This dataset includes various lighting conditions, backgrounds, and car positions. The training process will be performed using the YOLO architecture that has been pre-trained with an extensive dataset. In the testing phase, the performance of the YOLO method in car object detection will be evaluated using standard evaluation metrics such as precision, detection speed, and recall. The results of this study will show the success rate of YOLO in car detection in images and provide a better understanding of the limitations and advantages of this method. The conclusion of this research is expected to provide valuable insight into the use of the YOLO method in car object detection. This information can be used as a basis for the development and improvement of YOLO-based object detection methods, and can be applied in various applications such as automated vehicle security systems and traffic analysis.

VEHICLE LICENSE PLATE DETECTION USING YOLO ALGORITHM

<p><em>Urban population growth has created challenges in efficient parking space management. Manual data collection is time-consuming and error-prone, especially at night. Modern technology-based solutions are urgently needed. This research focuses on an innovative parking management system using YOLO for real-time object detection, including license plates. The objective is to assess the YOLO algorithm's accuracy in license plate detection. The methodology follows software development best practices, utilizing Python and Tkinter GUI for an intuitive interface. YOLO and EasyOCR enable object detection and character recognition. Results show high accuracy: 88.8% for HD and 86.3% for sub-HD resolutions. YOLO proves reliable for license plate data collection, reducing manual intervention and enhancing parking management.</em></p>

Deep Surveillance System

This study has been undertaken to investigate and implement multiple detection systems into a single surveillance system and check whether the input videos may comprise and capture a variety of realistic anomalies or not. In this paper, we propose to learn various anomalies by exploiting both normal and anomalous videos and implemented it to new model. Real time object detection is a vast, vibrant and sophisticated area of computer vision aimed towards object identification and recognition. Object detection detects the semantic objects of a class objects using Open source Computer Vision, which is a library of programming functions mainly trained towards real time computer vision in digital images and videos. The main aim behind this real time object detection is to help the peoples to overcome their difficulty. Real time object detection finds its uses in the areas like tracking objects, video surveillance, pedestrian detection, people counting, self-driving cars, face detection, tracking in sports and many more. This is achieved using Convolution, Probabilistic Neural Networks, etc. which are a representative tool of Deep learning. This project acts as an aiding tool for peoples who wants to take care of everything inside, outside, and around their house just for their full security expectations. Surveillance is a must for small houses to large-scale industries as they fulfil our safety aspects because theft and burglary have always been a problem. By combining this Surveillance idea to IoT and some Machine Learning stuff this will be a major product. The proposed project is a single autonomous surveillance system, based on analysis and detection technology. The proposed system is capable of monitoring all actions at once and alerts the concerned officials immediately and precisely.

Vision- and Lidar-Based Autonomous Docking and Recharging of a Mobile Robot for Machine Tending in Autonomous Manufacturing Environments

Autonomous docking and recharging are among the critical tasks for autonomous mobile robots that work continuously in manufacturing environments. This requires robots to demonstrate the following abilities: (i) detecting the charging station, typically in an unstructured environment and (ii) autonomously docking to the charging station. However, the existing research, such as that on infrared range (IR) sensor-based, vision-based, and laser-based methods, identifies many difficulties and challenges, including lighting conditions, severe weather, and the need for time-consuming computation. With the development of deep learning techniques, real-time object detection methods have been widely applied in the manufacturing field for the recognition and localization of target objects. Nevertheless, those methods require a large amount of proper and high-quality data to achieve a good performance. In this study, a Hikvision camera was used to collect data from a charging station in a manufacturing environment; then, a dataset for the wireless charger was built. In addition, the authors of this paper propose an autonomous docking and recharging method based on the deep learning model and the Lidar sensor for a mobile robot operating in a manufacturing environment. In the proposed method, a YOLOv7-based object detection method was developed, trained, and evaluated to enable the robot to quickly and accurately recognize the charging station. Mobile robots can achieve autonomous docking to the charging station using the proposed Lidar-based approach. Compared to other methods, the proposed method has the potential to improve recognition accuracy and efficiency and reduce the computation costs for the mobile robot system in various manufacturing environments. The developed method was tested in real-world scenarios and achieved an average accuracy of 95% in recognizing the target charging station. This vision-based charger detection method, if fused with the proposed Lidar-based docking method, can improve the overall accuracy of the docking alignment process.

Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection

Submarine garbage is constantly destroying the marine ecological environment and polluting the ocean. It is critical to use detection methods to quickly locate and identify submarine garbage. The background of submarine garbage images is much more complex than that of natural scene images, with object deformation and missing contours putting higher demands on the detection network. To solve the problem of low accuracy under complex backgrounds, full stage networks with auxiliary focal loss and multi-attention module are proposed for submarine garbage object detection based on YOLO. To maximize the gradient combination, a hierarchical fusion feature mechanism and a segmentation and merging strategy are used in this paper to optimize the difference in gradient combination to obtain full-stage features. Then the criss-cross attention module is used to precisely extract multi-scale features of small object dense regions while removing noise information from complex backgrounds. Finally, the auxiliary focal loss function addresses the issue of unbalanced positive and negative samples, focusing on the learning of difficult samples while improving overall detection precision. Based on comparative experiments and ablation experiments, the FSA networks achieved state-of-the-art performance, and is applicable to the real-time object detection of submarine garbage in complex backgrounds.

Staircase Recognition and Localization Using Convolutional Neural Network (CNN) for Cleaning Robot Application

Floor-cleaning robots are primarily designed to clean on a single floor, while multi-floor environments are usually not considered target applications. However, it is more efficient to have an autonomous floor-cleaning robot that can climb stairs and reach the next floors in a multi-floor building. To operate in such environments, the ability of a mobile robot to autonomously traverse staircases is very important. For this operation, staircase detection and localization are essential components for planning the traversal route on staircases. This article describes a deep learning approach using a convolutional neural network (CNN)-based robot operation system (ROS) framework for staircase detection, localization, and maneuvering of the robot to the detected stair. We present a real-time object detection framework to detect staircases in incoming images. We also localize these staircases using a contour detection algorithm to detect the target point: a point close to the center of the first step, and an angle of approach to the target point with respect to the current location of the robot. Experiments are performed with data from images captured on different types of staircases at different viewpoints/angles. The experimental results show that the presented approach can achieve an accuracy of 95% and a recall of 86.81%. A total runtime of 155 ms is taken to identify the presence of a staircase and the detection of the first step in the working environment, as well as being able to locate the target point with an accuracy of ±2 cm, ±1 degree.

WAID: A Large-Scale Dataset for Wildlife Detection with Drones

Drones are widely used for wildlife monitoring. Deep learning algorithms are key to the success of monitoring wildlife with drones, although they face the problem of detecting small targets. To solve this problem, we have introduced the SE-YOLO model, which incorporates a channel self-attention mechanism into the advanced real-time object detection algorithm YOLOv7, enabling the model to perform effectively on small targets. However, there is another barrier; the lack of publicly available UAV wildlife aerial datasets hampers research on UAV wildlife monitoring algorithms. To fill this gap, we present a large-scale, multi-class, high-quality dataset called WAID (Wildlife Aerial Images from Drone), which contains 14,375 UAV aerial images from different environmental conditions, covering six wildlife species and multiple habitat types. We conducted a statistical analysis experiment, an algorithm detection comparison experiment, and a dataset generalization experiment. The statistical analysis experiment demonstrated the dataset characteristics both quantitatively and intuitively. The comparison and generalization experiments compared different types of advanced algorithms as well as the SE-YOLO method from the perspective of the practical application of UAVs for wildlife monitoring. The experimental results show that WAID is suitable for the study of wildlife monitoring algorithms for UAVs, and SE-YOLO is the most effective in this scenario, with a mAP of up to 0.983. This study brings new methods, data, and inspiration to the field of wildlife monitoring by UAVs.

Virtual Reality's Effect on Educational E-learning Platforms

Students now rely more on online learning than on-campus instruction. As a result, we intend to create a project that will assist students in understanding topics through the use of augmented reality (AR). The only aspect of e-learning being studied at the moment is knowledge transmission online. We want to upgrade e-learning with AR due to time restraints and other technological issues. In order to virtualize the notion for students studying three-dimensional geometry, our objective is to create an e-learning framework for three-dimensional geometry. Students may quickly understand the idea visually with the aid of modern mobile phones by placing their phones on the actual QR code readers. Using AR, it will provide a clear and visual explanation of the idea. For instance, if the student holds up his phone in front of the switch or router, it will clearly explain the components. Then, it may be used in any subject or industry. We want to employ Vuforia and UNITY 3-D software to accomplish our aim. The software development kit (SDK) for augmented reality (AR) on mobile devices called Vuforia facilitates the development of AR apps. It recognizes and tracks planar pictures and 3D objects in real time using computer vision technologies. Games and other visuals in both 2D and 3D may be made with Unity.

Exploring the Confluence of IoT and Metaverse: Future Opportunities and Challenges

The Internet of Things (IoT) and the metaverse are two rapidly evolving technologies that have the potential to shape the future of our digital world. IoT refers to the network of physical devices, vehicles, buildings, and other objects that are connected to the internet and capable of collecting and sharing data. The metaverse, on the other hand, is a virtual world where users can interact with each other and digital objects in real time. In this research paper, we aim to explore the intersection of the IoT and metaverse and the opportunities and challenges that arise from their convergence. We will examine how IoT devices can be integrated into the metaverse to create new and immersive experiences for users. We will also analyse the potential use cases and applications of this technology in various industries such as healthcare, education, and entertainment. Additionally, we will discuss the privacy, security, and ethical concerns that arise from the use of IoT devices in the metaverse. A survey is conducted through a combination of a literature review and a case study analysis. This review will provide insights into the potential impact of IoT and metaverse on society and inform the development of future technologies in this field.

Thermal Imaging Detection System: A Case Study for Indoor Environments.

Currently, there is an increasing need for reliable mechanisms for automatically detecting and localizing people-from performing a people-flow analysis in museums and controlling smart homes to guarding hazardous areas like railway platforms. A method for detecting people using FLIR Lepton 3.5 thermal cameras and Raspberry Pi 3B+ computers was developed. The method creates a control and capture library for the Lepton 3.5 and a new person-detection technique that uses the state-of-the-art YOLO (You Only Look Once) real-time object detector based on deep neural networks. A thermal unit with an automated configuration using Ansible encapsulated in a custom 3D-printed enclosure was used. The unit has applications in simple thermal detection based on the modeling of complex scenes with polygonal boundaries and multiple thermal camera monitoring. An easily deployable person-detection and -localization system based on thermal imaging that supports multiple cameras and can serve as an input for other systems that take actions by knowing the positions of people in monitored environments was created. The thermal detection system was tested on a people-flow analysis performed in the Czech National Museum in Prague. The contribution of the presented method is the development of a small and simple detection system that is easily mountable with wide indoor as well as outdoor applications. The novelty of the system is in the utilization of the YOLO model for thermal data.

Technology trends in deep learning networks for real-time object detection in drone environment

With the recent announcement of the Defense Innovation 4.0 Basic Plan by the Ministry of National Defense, the role and operational scope of drones are expanding as a key force in AI-based, unmanned, and autonomous systems. Consequently, the significance of real-time object detection technology is emphasized as drones take on diverse missions, including delivering, analyzing, and assessing real-time, target-related information. The emergence of recent deep learning has led to substantial advancements in the field of computer vision, particularly in object detection. Deep learning-based object detection is actively being researched, with a focus on algorithms suited for embedded and mobile environments such as drones. This research predominantly aims to develop deep learning-based object detection models that ensure real-time performance and accurately identify objects’ various forms and sizes. Recent object-detection models have been categorized into backbone networks, neck networks, and head networks. By utilizing these three network components, design considerations can be tailored to fulfill the requirements of drone operations. In this paper, we investigate the technology trends of deep learning network models that can be loaded into drones for real-time object detection. Thus we contribute to strengthening effective drone operation in military operations and supporting research and decision-making processes.

Longitudinal Quantitative Ultrawidefield Angiographic Features in Diabetic Retinopathy Treated with Aflibercept from the Intravitreal Aflibercept as Indicated by Real-Time Objective Imaging to Achieve Diabetic Retinopathy Improvement Trial

To report longitudinal trends of quantitative ultrawidefield fluorescein angiography (qUWFA) biomarkers in the Intravitreal Aflibercept as Indicated by Real-Time Objective Imaging to Achieve Diabetic Retinopathy Improvement (PRIME) diabetic retinopathy (DR) clinical trial. Post hoc analysis of the PRIME prospective randomized DR clinical trial comparing intravitreal aflibercept treatment based on the DR severity score (DRSS) or quantitative leakage index for DR improvement (ClinicalTrials.gov identifier: NCT03531294). Patients were enrolled with a DRSS level of 47A to 71A and best-corrected visual acuity of 20/800 or better. Key exclusion criteria were previous intravitreal injection, panretinal photocoagulation, vitrectomy, central-involving macular edema, or vitreous hemorrhage. A previously validated, machine learning-based qUWFA analysis platform was used for panretinal leakage index assessment and differentiation of generalized and perivascular leakage phenotypes. Additionally, microaneurysm count and ischemic index were quantified in panretinal and macular regions. The trends in these biomarkers and therapeutic response were studied over 1 year. Longitudinal trends of qUWFA biomarkers. The impact of these qUWFA metrics on treatment response was assessed by studying their associations with time to 2-step DRSS improvement and number of treatment-free days. Forty eyes from 40 subjects with DR were enrolled. Lower baseline generalized leakage was noted in eyes that attained the 2-step DRSS improvement in < 16 weeks (1.9% vs. 2.8%; P= 0.026). Baseline macular perivascular-generalized leakage ratio had a significant correlation with the number of treatment-free days (r= 0.4; P= 0.012). At the end of 1 year, therapy significantly reduced the mean panretinal (3.9% vs. 5.8%; P= 0.002) and macular (6.2% vs. 12.2%; P= 0.008) generalized leakage indices compared with baseline, as well as the mean panretinal perivascular leakage index (1.5% vs. 2.3%; P= 0.002). The mean panretinal ischemic index demonstrated a small but likely clinically insignificant decrease from 12.5% at baseline to 11.6% at year 1 (P= 0.016). Down-trending leakage indices and microaneurysm counts were demonstrated over 1 year of anti-VEGF therapy. At baseline, DR eyes with lower generalized leakage responded to therapy more rapidly. Eyes with greater perivascular leakage relative to generalized leakage showed a longer-lasting anti-VEGF treatment response. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

A Lightweight Model for Real-Time Monitoring of Ships

Real-time monitoring of ships is crucial for inland navigation management. Under complex conditions, it is difficult to balance accuracy, real-time performance, and practicality in ship detection and tracking. We propose a lightweight model, YOLOv8-FAS, to address this issue for real-time ship detection and tracking. First, FasterNet and the attention mechanism are integrated and introduced to achieve feature extraction simply and efficiently. Second, the lightweight GSConv convolution method and a one-shot aggregation module are introduced to construct an efficient network neck to enhance feature extraction and fusion. Furthermore, the loss function is improved based on ship characteristics to make the model more suitable for ship datasets. Finally, the advanced Bytetrack tracke is added to achieve the real-time detection and tracking of ship targets. Compared to the YOLOv8 model, YOLOv8-FAS reduces computational complexity by 0.8×109 terms of FLOPs and reduces model parameters by 20%, resulting in only 2.4×106 parameters. The mAP-0.5 is improved by 0.9%, reaching 98.50%, and the real-time object tracking precision of the model surpasses 88%. The YOLOv8-FAS model combines light weight with high precision, and can accurately perform ship detection and tracking tasks in real time. Moreover, it is suitable for deployment on hardware resource-limited devices such as unmanned surface ships.

AG-YOLO: Attention-guided network for real-time object detection

AG-YOLO: Attention-guided network for real-time object detection

Real Time Object Detection using Deep Learning and SSD Algorithm

Real time object detection is a complex area of computer vision, vast and vibrant. If there is a single object to be detected in an image, it is known as Image Localization and if there are multiple objects in an image, then it is Object Detection. Real time object identification to find and recognize real objects such as cars, bicycles, TV, flowers and people from pictures or videos. Object identification technique allows you to find out image or video details, as it allows detection, localization and multiple detection Objects in pictures or videos. Identifying objects in a video or image stream can be done through processes such as pre-processing. segmentation, foreground and background extraction, feature extraction. We will try to add new features related to the real world in future versions. In today's scenario, the Single Shot Multi-Box Detector (SSD) algorithm is considered the fastest approach for object detection using a single layer of a convolutional network. In our paper, we have focused on enhancing the classification accuracy of object detection while maintaining the algorithm's speed. Experimental results have confirmed that our proposed improved SSD algorithm achieves high accuracy.

Deep Neural Network-Based Dynamical Object Recognition and Robust Multiobject Tracking Technique for Onboard Unmanned Aerial Vehicle’s Computer Vision-Based Systems

Computer vision-based systems seem highly perspective for semantic analysis of the dynamical objects. However, considering dynamical object recognition and tracking from the unmanned aerial vehicle the task to design a robust model for data association is highly challenging due to additional issues, e.g., image degradation, non-fixed object camera distance and shooting focus, and real-time issues. Thus, we propose an accurate deep neural network-based dynamical object recognition and robust multi-object tracking technique based on bidirectional LSTM with the optimized motion and appearance gates as a multi-object tracking backbone, supported by an advanced single-shot detector network improved with residual prediction model and implemented DenseNet network as well as YOLOv4eff network as feature extraction. The technique has been trained on VisDrone 2022 and UAVDT datasets with the side-shoot dynamical objects at a height of up to 50 meters. The performance analysis on the test stage performed on 7 metrics demonstrate that the proposed technique surpasses by accuracy and robustness ability of other state-of-the-art techniques based on 2 cumulative MOTA and MOTP, as well as MT and IDsw. In particular, we have dramatically decreased the number of IDsw which implies a better capability to handle several occlusions, which is a desirable property in real-time multiple object tracking. We have pointed out the sensitivity of the tracking performance of our technique on the number of utilizing different sequence lengths and have defined an optimum. Finally, the applicability and reliability of the proposed technique for onboard UAV computer-based systems have been discussed.

Semantic Proximity Update of GNSS/INS/VINS for Seamless Vehicular Navigation Using Smartphone Sensors

The advancement of microelectromechanical systems (MEMS) and the Internet of Things (IoT) have enabled a wide range of applications based on smartphones. However, the existing navigation methods using these low-cost MEMS sensors cannot provide acceptable information for location-based applications in various environments. Their technical limitations, such as severe signal attenuation, reflections, blockages, error accumulation, and low quality of images degrade the performance of GNSS, INS, and camera. To mitigate these limitations, especially in indoor vehicle navigation, we first analyze the performance of the existing fusion algorithm, then we propose Semantic Proximity Update (SPU) based on a pre-trained model of real-time object detection to enhance the integration of Global Navigation Satellite System (GNSS), Inertial Navigation System (INS) and Visual Inertial Navigation System (VINS). SPU consists of the detection of geo-referenced objects and the relative movement to infer the absolute position. The proposed INS/GNSS/VINS/SPU can maintain long-term acceptable accuracy regardless of the indoor/outdoor environment. It only requires the use of smartphone sensors; thus, this scheme has no additional cost for users. Experimental results indicated that the errors of this scheme in horizontal positioning and three-dimensional positioning were 51.6% and 86.8% lower, respectively than those of a conventional integration.

Development of vehicle- recognition method on water surfaces using LiDAR data: SPD2 (spherically stratified point projection with diameter and distance)

Swarm robot systems are an important application of autonomous unmanned surface vehicles on water surfaces. For monitoring natural environments and conducting security activities within a certain range using a surface vehicle, the swarm robot system is more efficient than the operation of a single object as the former can reduce cost and save time. It is necessary to detect adjacent surface obstacles robustly to operate a cluster of unmanned surface vehicles. For this purpose, a LiDAR (light detection and ranging) sensor is used as it can simultaneously obtain 3D information for all directions, relatively robustly and accurately, irrespective of the surrounding environmental conditions. Although the GPS (global-positioning-system) error range exists, obtaining measurements of the surface-vessel position can still ensure stability during platoon maneuvering. In this study, a three-layer convolutional neural network is applied to classify types of surface vehicles. The aim of this approach is to redefine the sparse 3D point cloud data as 2D image data with a connotative meaning and subsequently utilize this transformed data for object classification purposes. Hence, we have proposed a descriptor that converts the 3D point cloud data into 2D image data. To use this descriptor effectively, it is necessary to perform a clustering operation that separates the point clouds for each object. We developed voxel-based clustering for the point cloud clustering. Furthermore, using the descriptor, 3D point cloud data can be converted into a 2D feature image, and the converted 2D image is provided as an input value to the network. We intend to verify the validity of the proposed 3D point cloud feature descriptor by using experimental data in the simulator. Furthermore, we explore the feasibility of real-time object classification within this framework.

Deep features fusion for KCF-based moving object tracking

Real-time object tracking and occlusion handling are critical research areas in computer vision and machine learning. Developing an efficient and accurate object-tracking method that can operate in real-time while handling occlusion is essential for various applications, including surveillance, autonomous driving, and robotics. However, relying solely on a single hand-crafted feature results in less robust tracking. As a hand-crafted feature extraction technique, HOG effectively detects edges and contours, which is essential in localizing objects in images. However, it does not capture fine details in object appearance and is sensitive to changes in lighting conditions. On the other hand, the grayscale feature has computational efficiency and robustness to changes in lighting conditions. The deep feature can extract features that express the image in more detail and discriminate between different objects. By fusing different features, the tracking method can overcome the limitations of individual features and capture a complete representation of the object. The deep features can be generated with transfer learning networks. However, selecting the right network is difficult, even in real-time applications. This study integrated the deep feature architecture and hand-crafted features HOG and grayscale in the KCF method to solve this problem. The object images were obtained through at least three convolution blocks of transfer learning architecture, such as Xception, DenseNet, VGG16, and MobileNet. Once the deep feature was extracted, the HOG and grayscale features were computed and combined into a single stack. In the KCF method, the stacked features acquired the actual object location by conveying a maximum response. The result shows that this proposed method, especially in the combination of Xception, grayscale, and HOG features, can be implemented in real-time applications with a small center location error.