Object Identification Research Articles

Enhanced Yolov8 with OpenCV for Blind-Friendly Object Detection and Distance Estimation

The development of computer technology and computer vision has had a significant positive impact on the daily lives of blind people, especially in efforts to improve their navigation abilities. This research has the main aim of introducing a superior object detection method, especially in supporting the sustainability and effectiveness of navigation for the blind. The main focus of the research is the use of YOLOv8, the latest version of YOLO, as an object detection method, and distance measurement technology from OpenCV. The main challenge to be addressed involves improving the accuracy and performance of object detection, which is an important key to ensuring safe and effective navigation for blind people. In this context, blind people often face obstacles in their mobility, especially when walking around environments that may be full of obstacles or obstacles. Therefore, better object detection methods become essential to ensure the identification of nearby objects, which may involve obstacles or potential threats, thereby preventing possible accidents or difficulties in daily commuting. Involving YOLOv8 as an object detection method provides the advantage of a high level of accuracy, although with a slight increase in detection duration and GPU power consumption compared to previous versions. The research results show that YOLOv8 provides a low error rate, with an average error percentage of 3.15%, indicating very optimal results. Using a combined performance evaluation approach of YOLOv8 and OpenCV distance measurement metrics, this research not only seeks to improve accuracy but also efficiency in detection time and power consumption. This research makes an important contribution in presenting technological solutions that can help improve mobility and safety for blind people, bringing a real positive impact in facilitating their daily lives.

Multi-scale aware turbulence network for underwater object recognition

Underwater imagery is subject to distortion, and the presence of turbulence in the fluid medium poses difficulties in accurately discerning objects. To tackle these challenges pertaining to feature extraction, this research paper presents a novel approach called the multi-scale aware turbulence network (MATNet) method for underwater object identification. More specifically, the paper introduces a module known as the multi-scale feature extraction pyramid network module, which incorporates dense linking strategies and position learning strategies to preprocess object contour features and texture features. This module facilitates the efficient extraction of multi-scale features, thereby enhancing the effectiveness of the identification process. Following that, the extracted features undergo refinement through comparison with positive and negative samples. Ultimately, the study introduces multi-scale object recognition techniques and establishes a multi-scale object recognition network for the precise identification of underwater objects, utilizing the enhanced multi-scale features. This process entails rectifying the distorted image and subsequently recognizing the rectified object. Extensive experiments conducted on an underwater distorted image enhancement dataset demonstrate that the proposed method surpasses state-of-the-art approaches in both qualitative and quantitative evaluations.

Research on Point Cloud Structure Detection of Manhole Cover Based on Structured Light Camera

This study introduced an innovative approach for detecting structural anomalies in road manhole covers using structured light cameras. Efforts have been dedicated to enhancing data quality by commencing with the acquisition and preprocessing of point cloud data from real-world manhole cover scenes. The RANSAC algorithm is subsequently employed to extract the road plane and determine the height of the point cloud structure. In the presence of non-planar point cloud exhibiting abnormal heights, the DBSCAN algorithm is harnessed for cluster segmentation, aiding in the identification of individual objects. The method culminates with the introduction of a sector fitting detection model, adept at effectively discerning manhole cover features within the point cloud and delivering comprehensive height and structural information. Experimental findings underscore the method’s efficacy in accurately gauging the degree of subsidence in manhole cover structures, with data errors consistently maintained within an acceptable range of 8 percent. Notably, the measurement speed surpasses that of traditional methods, presenting a notably efficient and dependable technical solution for road maintenance.

Research on Visual Localization and Gripping Technology of Robotic Arm Based on Deep Learning

With the continuous development of industrial automation, robotic arms are more and more widely used in production lines. In order to realize the autonomous positioning and grasping function of robotic arm, this paper studies the visual positioning and grasping technology of robotic arm based on deep learning. The deep learning algorithm processes and analyzes the image, realizes the automatic identification and localization of the target object, and then guides the robotic arm to carry out accurate grasping. The experimental results show that this technology can effectively improve the positioning accuracy and grasping success rate of the robotic arm, which provides strong support for the intelligent upgrade of industrial automation production lines.

Preliminary Evidence for Global Properties in Human Listeners During Natural Auditory Scene Perception.

Theories of auditory and visual scene analysis suggest the perception of scenes relies on the identification and segregation of objects within it, resembling a detail-oriented processing style. However, a more global process may occur while analyzing scenes, which has been evidenced in the visual domain. It is our understanding that a similar line of research has not been explored in the auditory domain; therefore, we evaluated the contributions of high-level global and low-level acoustic information to auditory scene perception. An additional aim was to increase the field's ecological validity by using and making available a new collection of high-quality auditory scenes. Participants rated scenes on 8 global properties (e.g., open vs. enclosed) and an acoustic analysis evaluated which low-level features predicted the ratings. We submitted the acoustic measures and average ratings of the global properties to separate exploratory factor analyses (EFAs). The EFA of the acoustic measures revealed a seven-factor structure explaining 57% of the variance in the data, while the EFA of the global property measures revealed a two-factor structure explaining 64% of the variance in the data. Regression analyses revealed each global property was predicted by at least one acoustic variable (R2 = 0.33-0.87). These findings were extended using deep neural network models where we examined correlations between human ratings of global properties and deep embeddings of two computational models: an object-based model and a scene-based model. The results support that participants' ratings are more strongly explained by a global analysis of the scene setting, though the relationship between scene perception and auditory perception is multifaceted, with differing correlation patterns evident between the two models. Taken together, our results provide evidence for the ability to perceive auditory scenes from a global perspective. Some of the acoustic measures predicted ratings of global scene perception, suggesting representations of auditory objects may be transformed through many stages of processing in the ventral auditory stream, similar to what has been proposed in the ventral visual stream. These findings and the open availability of our scene collection will make future studies on perception, attention, and memory for natural auditory scenes possible.

Information Placement in Notarial Registries: Issues with Evaluating the Actions of Participants

Within the framework of improving legislation, the Federal Notary Chamber has been entrusted with the responsibility of maintaining a registry of notifications regarding the pledge of movable property and the cancellation of powers of attorney executed in simple written form. It should be noted that these changes have a positive impact on civil transactions. However, there are specific questions regarding the procedure for their implementation. The main issue is that neither the notary nor the person posting the relevant information about the pledge or cancellation of powers of attorney is held responsible for the accuracy of the information, which allows for the possibility of abuse. In defining the purpose of this research, attention should be paid to the evaluation and analysis of the procedural and legal aspects of maintaining the aforementioned registries, identifying specific cases of abuse of rights by individuals posting information in the respective registries. This necessitates finding a solution to the stated problem, namely: clarifying the procedure and limits of actions for the parties involved in the relevant legal relationships in order to prevent the possibility of their misconduct. The research is based on general scientific methods of cognition and legal hermeneutics. During the analysis of current legislation and legal practices, it has been determined that in the existing reality, there is a possibility of abuse by individuals posting information in notarial registries regarding the cancellation of powers of attorney and the registry of notifications about pledges. The legislation does not provide indications of sanctions against individuals who violate the prescribed registry procedure. The presumption of notification from the moment the information is posted in the registry by an interested party, despite possible errors that compromise the accuracy of electronic search or distortions in the information, which prevent proper identification of the sought-after object, leads to violations of property rights of participants in civil transactions.

An Efficient Object Detection System for the Blind People

As object recognition technology has developed recently, various technologies have been applied to autonomous vehicles, robots, and industrial facilities. However, the benefits of these technologies are not reaching the visually impaired, who need it the most. In this research, researchers proposed a deep learning based on object identification system for the visually impaired. Voice recognition technology is used to know what objects a blind person wants, and then to find the objects via object recognition. Furthermore, a voice guidance technique is used to inform sight impaired persons as to the location of objects. The object recognition deep learning model utilizes the single shot multi-box detector (SSD) neural network architecture, and voice recognition is designed through speech-to-text (STT) technology. In addition, a voice announcement is synthesized using text-to-speech (TTS) to make it easier for the blind to get information about objects. The system is built using python OpenCV tool. As a result, we implement an efficient object-detection system that helps the blind find objects in a specific space without help from others, and the system is analyse through experiments to verify performance. Keywords: Object detection system, blind people, Open CV, Voice Recognition

Deep Learning-Based Intelligent Video Surveillance System for Real-Time Motion Detection

The proliferation of surveillance systems demands advanced solutions to effectively monitor and analyze video feeds for security and safety purposes. In this paper, we propose a Deep Learning-Based Intelligent Video Surveillance System (DIVSS) designed to enhance traditional Closed-Circuit Television (CCTV) setups. DIVSS integrates state-of-the-art deep learning techniques for real-time motion detection and object recognition, enabling proactive threat detection and automated response mechanisms. The system utilizes convolutional neural networks (CNNs) for robust feature extraction and classification, enabling accurate identification of objects of interest amidst complex backgrounds and varying[1] lighting conditions. Furthermore, DIVSS incorporates region of interest (ROI) monitoring to focus attention on specific areas within the surveillance footage, optimizing computational resources and improving response times. We evaluate the performance of DIVSS through comprehensive experiments conducted on diverse surveillance scenarios, demonstrating its effectiveness in enhancing security measures and providing actionable[3] insights for surveillance operators. The proposed system represents a significant advancement in video surveillance technology, offering unparalleled capabilities for proactive threat detection and real-time response in dynamic environments. Keywords— Deep learning has transformed video surveillance, enabling real-time motion detection and object recognition using Convolutional Neural Networks (CNNs). This technology provides proactive threat detection, intelligent systems for ROI monitoring, and enhances overall security measures.

NEW ERA OF VISION TO ENVISION USING YOLO

We provide a new approach to crowd counting in this research that makes use of the You Only Look Once (YOLO) algorithm. We show how well YOLO performs in precisely identifying and counting people in congested environments. Our method seeks to overcome the difficulties associated with crowd observation and analysis in real time. Urban planning, public safety, and event management are just a few of the many areas where crowd counting is important and dynamic. Occlusions, size variations, and congested settings are only a few of the challenges that traditional approaches frequently face in providing precise and timely crowd estimates. This study presents a unique method for accurate and efficient crowd counting that leverages the You Only Look Once (YOLO) algorithm. Through the utilization of YOLO's sophisticated object identification capabilities, our suggested approach provides a reliable way to compute crowd sizes in real-time situations. We provide an in-depth examination of the difficulties involved in crowd counting and show, by intensive testing and assessment on many datasets, how successful our YOLO-based method is. Our findings demonstrate the People counting, Image-based crowd estimation, Video analytics, Data preprocessing, Performance evaluation. Keywords— Crowd counting, Object detection, YOLO (You Only Look Once), Deep learning, Computer vision, Convolutional neural networks (CNNs), Image processing, Crowd analysis, Real-time monitoring, Surveillance systems,

FACIAL RECOGNITION ATTENDANCE SYSTEM

Colleges have historically faced a great deal of difficulty with student attendance, necessitating a large time and effort investment from staff in manual tracking. Even though they are in place, the existing biometric attendance systems are not entirely automated, which causes delays in processing fingerprints, maintenance issues, and inefficiencies in time. Given that almost everyone has a smartphone and is continuously online in this day and age, a more simplified method is necessary. This study suggests using sophisticated object identification algorithms to check attendance using faculty members' smartphones. Because of its effectiveness in face detection and the addition of Microsoft Azure's face API for database recognition, YOLO V3 (You Only Look Once) is the preferred option among these. One special feature of the system is that it takes pictures of the classroom at the start and finish of every class to make sure everyone is present. After determining the number of students in each photograph, YOLO V3 separates the faces that are known and those that are unknown, creating distinct spreadsheets. Monthly email reminders are also sent to teachers, parents, and students. The system that has been put into place shows strong real-time performance in counting and detecting jobs, with excellent facial recognition accuracy and overall efficiency. Keywords:, OpenCV, Local Binary Pattern Histogram (LBPH), Real-time Tracking, Facial Analysis, You Only Look Once (YOLO V3), Firebase Database.

A Seamless Deep Learning Approach for Apple Detection, Depth Estimation, and Tracking Using YOLO Models Enhanced by Multi-Head Attention Mechanism

Considering precision agriculture, recent technological developments have sparked the emergence of several new tools that can help to automate the agricultural process. For instance, accurately detecting and counting apples in orchards is essential for maximizing harvests and ensuring effective resource management. However, there are several intrinsic difficulties with traditional techniques for identifying and counting apples in orchards. To identify, recognize, and detect apples, apple target detection algorithms, such as YOLOv7, have shown a great deal of reflection and accuracy. But occlusions, electrical wiring, branches, and overlapping pose severe issues for precisely detecting apples. Thus, to overcome these issues and accurately recognize apples and find the depth of apples from drone-based videos in complicated backdrops, our proposed model combines a multi-head attention system with the YOLOv7 object identification framework. Furthermore, we provide the ByteTrack method for apple counting in real time, which guarantees effective monitoring of apples. To verify the efficacy of our suggested model, a thorough comparison assessment is performed with several current apple detection and counting techniques. The outcomes adequately proved the effectiveness of our strategy, which continuously surpassed competing methods to achieve exceptional accuracies of 0.92, 0.96, and 0.95 with respect to precision, recall, and F1 score, and a low MAPE of 0.027, respectively.

3SHNet: Boosting image–sentence retrieval via visual semantic–spatial self-highlighting

In this paper, we propose a novel visual Semantic-Spatial Self-Highlighting Network (termed 3SHNet) for high-precision, high-efficiency and high-generalization image–sentence retrieval. 3SHNet highlights the salient identification of prominent objects and their spatial locations within the visual modality, thus allowing the integration of visual semantics–spatial interactions and maintaining independence between two modalities. This integration effectively combines object regions with the corresponding semantic and position layouts derived from segmentation to enhance the visual representation. And the modality-independence guarantees efficiency and generalization. Additionally, 3SHNet utilizes the structured contextual visual scene information from segmentation to conduct the local (region-based) or global (grid-based) guidance and achieve accurate hybrid-level retrieval. Extensive experiments conducted on MS-COCO and Flickr30K benchmarks substantiate the superior performances, inference efficiency and generalization of the proposed 3SHNet when juxtaposed with contemporary state-of-the-art methodologies. Specifically, on the larger MS-COCO 5K test set, we achieve 16.3%, 24.8%, and 18.3% improvements in terms of rSum score, respectively, compared with the state-of-the-art methods using different image representations, while maintaining optimal retrieval efficiency. Moreover, our performance on cross-dataset generalization improves by 18.6%.

A Comparative Analysis of Object Identification Labelling Platforms: Basketball Perspective

Manual object identification labelling is laborious, time-consuming and prone to inconsistencies hindering advancements in various computer vision tasks.These inconsistencies can lead to inaccurate models with poor performance. Considering these potential consequences, highlights the importance of addressing labelling challenges for ethical and responsible AI development. To address this our study evaluates several popular platforms for their suitability in tackling these challenges. Roboflow, Makesense.ai, SentiSight.ai, Labelbox and SuperAnnotate are the five different data labelling platforms that have been taken for assessment. The study identifies strengths and weaknesses of each platform in the context of basketball detection using YOLO v8, a deep learning model for object detection, image classification, and image segmentation. Each platform is analysed based on features, ease of use, pricing, and support for image annotation, object detection, and YOLO v8 integration. After analysing these factors, a final recommendation is made, highlighting the platform that demonstrably offers the best balance of features, efficiency, and cost-effectiveness for this specific task. The study helps in deeper exploration of the potential of YOLO v8. It is mainly aimed at assisting the Video Assistant Referees(VARs) for accurate and unbiased decision-making and also empowers the development of AI technology across the domain of sports.

Ultrafast Dual‐Band Imaging Using Solution‐Processed Stacked Perovskite Diodes

AbstractMultispectral imaging that captures multiple band information for effective environmental or object identification is of great interest in medical, vision, military, and space applications. Monolithic stacked detectors based on epitaxial electronics have been the principal option for infrared dual‐band imagers. However, the integration of these single‐band units would inevitably lead to performance reduction, high fabrication cost, and low reproducibility yield, which limits the widespread application of such technology. Here, a high‐throughput blade coating process is demonstrated to fabricate monolithic double‐perovskite‐layer photodiodes with preferential crystallographic morphology and high reproductivity. The device delivers electrically switchable dual‐band response with a dark current below 10−9 mA cm−2, a selective spectral response of 300–1100 nm, and bandwidths of 16.5/>20 MHz for two distinct bands. Furthermore, such device configuration can concurrently capture dual‐color spectral information under an AC‐driven mode, enabling the complementary dual‐spectral imaging for bioimaging and environmental monitoring.

Anomaly‐background separation and particle swarm optimization based band selection for hyperspectral anomaly detection

AbstractAs one of the dimensionality reduction techniques of hyperspectral image (HSI), band selection (BS) does not change the spectral characteristics and physical meaning of HSIs, which is beneficial to the identification and analysis of surface objects. Recently, many BS methods for target detection have achieved promising results by making full use of the priori spectral features of the target to be detected. Conversely, anomaly detection separates the anomaly based solely on the statistical distribution difference between anomaly and background without any prior information. Therefore, the development of BS for anomaly detection has lagged far behind that of BS for target detection. To this end, this paper proposes a novel BS algorithm dedicated to anomaly detection tasks, named anomaly‐background separation and particle swarm optimization (PSO)‐based BS. Specifically, an anomaly‐background separation framework (ABSF) is established to predetermine a priori knowledge of anomaly distribution. Then, three band prioritization criteria are constructed with the anomaly‐background constraints generated by ABSF. Finally, PSO is used to find the optimal subset of bands in the solution space. The experiments on two real datasets demonstrate that the proposed method yields better detection results and greater stability compared to other BS methods discussed in this paper.

Human–machine collaboration using gesture recognition in mixed reality and robotic fabrication

This research presents an innovative approach that integrated gesture recognition into a Mixed Reality (MR) interface for human–machine collaboration in the quality control, fabrication, and assembly of the Unlog Tower. MR platforms enable users to interact with three-dimensional holographic instructions during the assembly and fabrication of highly custom and parametric architectural constructions without the necessity of two-dimensional drawings. Previous MR fabrication projects have primarily relied on digital menus and custom buttons within the interface for user interaction between virtual and physical environments. Despite this approach being widely adopted, it is limited in its ability to allow for direct human interaction with physical objects to modify fabrication instructions within the virtual environment. The research integrates user interactions with physical objects through real-time gesture recognition as input to modify, update, or generate new digital information. This integration facilitates reciprocal stimuli between the physical and virtual environments, wherein the digital environment is generative of the user’s tactile interaction with physical objects. Thereby providing user with direct, seamless feedback during the fabrication process. Through this method, the research has developed and presents three distinct Gesture-Based Mixed Reality (GBMR) workflows: object localization, object identification, and object calibration. These workflows utilize gesture recognition to enhance the interaction between virtual and physical environments, allowing for precise localization of objects, intuitive identification processes, and accurate calibrations. The results of these methods are demonstrated through a comprehensive case study: the construction of the Unlog Tower, a 36’ tall robotically fabricated timber structure.

Metody zwiększania ilości danych termowizyjnych w uczeniu maszynowym

Machine learning is increasingly being applied in the processing and analysis of thermal imaging for object recognition and identification. This article presents a study on the impact of data augmentation on the effectiveness of machine learning in the context of thermal image analysis. The publicly available FLIR ADAS dataset, which includes labeled thermal and visible light images, was used for this study. The research focuses on the use of Convolutional Neural Networks, specifically the YOLOv8 architecture, for object detection in thermal images. As part of the study, the FLIR ADAS dataset underwent preprocessing and augmentation, and was then used to train two different models: one based on grayscale images and another using a color palette. The results of the experiment indicate that data augmentation can significantly impact the effectiveness of the model, and the use of colors in thermal images may, in certain situations, further improve detection accuracy.

Design, Simulation, Building, and Testing of a Microcontroller-Based Automatic Drowsiness Detection, Vehicle Braking, and Alert System

Aims: The premier practical aspect of this research drive is to propose, build, simulate, and evaluate an Arduino-built automatic vehicle driver drowsiness detection and alert system.
 Study Design: The pivotal role of a reliable braking system in vehicular safety cannot be overstated, particularly considering the escalating frequency of traffic accidents, notably prevalent in Indonesia where human factors take center stage as the primary accident catalyst. An insightful poll underscores physical fatigue or drowsiness while driving as the foremost concern. Acknowledging the nuanced disparities between conventional air systems and electric systems, this research strategically directs its attention toward crafting a new system characteristic that mirrors the efficiency of the existing systems.
 Place and Period of Study: The research action engaged by the authors in a bunch of two students under the command of a professor as a part of one of his course capstone projects for the Bachelor of Science in Electrical and Electronic Engineering degree at the American International University Bangladesh (AIUB), Dhaka, Bangladesh. The authors performed their investigative tasks at AIUB from June 2023 to January 2024.
 Methodology: Recognizing the imperative to fortify vehicular safety, the integration of artificial intelligence emerges as a vital solution to assist drivers in ensuring the safety of individuals both within and outside the vehicle. This focused study, tailored specifically for Electric Vehicles (EVs), centers on the innovative application of object and distance identification methodologies to provide a comprehensive braking action indicator. Leveraging a minicomputer and a sophisticated neural network approach, images captured by a stereo camera undergo meticulous machine learning processes. This facilitates the precise categorization and measurement of distances between objects, with subsequent priority decisions determining the optimal degree of braking action. Employing an intelligent methodology, specifically fuzzy logic, the study demonstrates a successful outcome by constructing a curve while concurrently enhancing the dynamics of the pre-existing system. Moreover, a finely tuned Pulse Width Modulation (PWM) signal for braking, lasting 10 milliseconds, is intricately devised based on the study's discerning results.
 Results: The system is simulated in Proteus and tested in real time to check its functionality. The outcomes of the test showed that the system can produce the appropriate signals based on the detection of any kind of driver’s drowsiness and can stop the car.
 Conclusion: This comprehensive approach ensures the seamless replacement of components while concurrently elevating the overall performance of the braking system

Teacher–Student Model Using Grounding DINO and You Only Look Once for Multi-Sensor-Based Object Detection

Object detection is a crucial research topic in the fields of computer vision and artificial intelligence, involving the identification and classification of objects within images. Recent advancements in deep learning technologies, such as YOLO (You Only Look Once), Faster-R-CNN, and SSDs (Single Shot Detectors), have demonstrated high performance in object detection. This study utilizes the YOLOv8 model for real-time object detection in environments requiring fast inference speeds, specifically in CCTV and automotive dashcam scenarios. Experiments were conducted using the ‘Multi-Image Identical Situation and Object Identification Data’ provided by AI Hub, consisting of multi-image datasets captured in identical situations using CCTV, dashcams, and smartphones. Object detection experiments were performed on three types of multi-image datasets captured in identical situations. Despite the utility of YOLO, there is a need for performance improvement in the AI Hub dataset. Grounding DINO, a zero-shot object detector with a high mAP performance, is employed. While efficient auto-labeling is possible with Grounding DINO, its processing speed is slower than YOLO, making it unsuitable for real-time object detection scenarios. This study conducts object detection experiments using publicly available labels and utilizes Grounding DINO as a teacher model for auto-labeling. The generated labels are then used to train YOLO as a student model, and performance is compared and analyzed. Experimental results demonstrate that using auto-generated labels for object detection does not lead to degradation in performance. The combination of auto-labeling and manual labeling significantly enhances performance. Additionally, an analysis of datasets containing data from various devices, including CCTV, dashcams, and smartphones, reveals the impact of different device types on the recognition accuracy for distinct devices. Through Grounding DINO, this study proves the efficacy of auto-labeling technology in contributing to efficiency and performance enhancement in the field of object detection, presenting practical applicability.

Background separation network for video anomaly detection

Video anomaly detection refers to the automatic identification of abnormal behaviors, objects, or events in videos. However, current methods for anomaly detection based on original frames lack a comprehensive understanding of the importance of foreground information, making it challenging to efficiently address video anomaly detection in the presence of complex background interference. In this paper, we propose a video anomaly detection algorithm based on Background Separation Network (BSN) to address this issue. Firstly, we utilize a video stabilization algorithm to reduce video jitter and enhance the quality of input video frames. Secondly, BSN shifts the focus from the entire frame to the foreground region with higher anomaly detection value. BSN utilizes the motion pixel distribution of the video as the basis for foreground extraction, enabling pixel-level background separation to obtain more accurate and complete foreground targets. Lastly, a certain proportion of foreground targets in the foreground image are masked as background, reducing the interference caused by redundant targets on the detection results. The proposed method achieves an accuracy of 96.2% on the UCSD ped2 dataset, demonstrating its effectiveness. This method contributes to accurately detecting abnormal behaviors in real-world surveillance videos to protect the safety of public lives and assets.