Object Detection Research Articles

Dissecting of the two-stages object detection models architecture and performance

Artificial intelligence (AI) is the discipline focused on enabling computers to operate autonomously without explicit programming. Within AI, computer vision is an emerging field tasked with endowing machines with the ability to interpret visual data from images and videos. Over recent decades, computer vision has found applications in diverse fields such as autonomous vehicles, information retrieval, surveillance, and understanding human behavior. Object detection, a key aspect of computer vision, employs deep neural networks to continually advance detection accuracy and speed. Its goal is to precisely identify objects within images or videos and assign them to specific classes. Object detection models typically consist of three components: a backbone network for feature extraction, a neck model for feature aggregation, and a head for prediction. The focus of this study lies on two stage detectors. This study aims to provide a comprehensive review of two stage detectors in object detection, followed by benchmarking to offer insights for researchers and scientists. By analyzing and understanding the efficacy of these models, this research seeks to guide future developments in the field of object detection within computer vision.

Object detection of the bornean orangutan nests using drone and YOLOv5

<p class="tm6">Object detection methods when applied to ecology and conservation can help to identify and monitor endangered species and their habitats. Using drones for this purpose has become increasingly popular due to their ability to cover large areas quickly and efficiently. In this study, we aim to implement object detection using YOLOv5 to detect orangutan nests in forests. To conduct our experiment, we collect drone imagery under different conditions. We propose to use the original YOLOv5 to implement our model. The detection and monitoring of orangutan nests can help conservationists to identify critical habitats, monitor population, and design effective conservation strategies. Additionally, the use of drones can reduce the need for on-the-ground surveys, which can be time-consuming, expensive, and logistically challenging. In our study proposes a model for detecting orangutan nests in forests using a drone and the YOLOv5. Our model predicted 1,970 training images and 414 labeled orangutan nests, with a precision of 0.973, recall 0.949, accuracy mean average precision (mAP)_0.5 is 0.969, and mAP_0.5:0.95 is 0.630. The model finished 217 epochs in 58 hours and had a high object detection accuracy. The model has a 99.9% accuracy in detecting the number of orangutan nests.</p>

Face recognition with occluded face using improve intersection over union of region proposal network on Mask region convolutional neural network

Face recognition entails detecting and identifying facial attributes. Mask region convolutional neural network (R-CNN) method is a prominent approach, while prior research predominantly delved into refining loss functions and perfecting object and face detection, recognizing, and identifying faces using imperfect data remained relatively unexplored. This study focuses on an occluded dataset comprising Indonesian faces, wherein 'occluded' denotes facial data that lacks complete visibility-encompassing instances where objects obscure faces or are partially cropped. This investigation involves a deliberate experiment that tailors the intersection over union (IoU) of the region proposal network (RPN) to suit the nuances of occluded Indonesian faces, thereby augmenting accuracy in recognition and segmentation tasks. The innovation IoU in the strategic utilization of Anchors, which involves the exclusion of anchors falling beyond the image borders to optimize computational efficiency. The outcomes of this research are striking; it showcases a remarkable 14.75%, 10.9%, and 12.97% surge based on mean average precision (mAP), mean average recall (mAR), and F1-Scores compared to the conventional Mask R-CNN approach. Notably, our proposed model elevates the average accuracy by 10% to 15% and decreases running time by 21%, a noteworthy enhancement compared to the preceding model. This progress is substantiated by validation utilizing 300 instances dataset, reinforcing the robustness of our approach.

A Miniaturized and Intelligent Lensless Holographic Imaging System With Auto-Focusing and Deep Learning-Based Object Detection for Label-Free Cell Classification

A Miniaturized and Intelligent Lensless Holographic Imaging System With Auto-Focusing and Deep Learning-Based Object Detection for Label-Free Cell Classification

Comparing hybrid models for recognising objects in thermal images at nighttime

This research aims to revolutionize urban object recognition by developing cloud-based Python programs using intelligent algorithms. Unlike current models that focus on colour enhancement in nighttime thermal images, this work addresses the critical challenge of accurate object detection in urban landscapes. The proposed method incorporates a binary generative adversarial network (GAN) generator that can switch bidirectionally between daytime colour (DC) and nighttime infrared (NTIR) images. memory-based visual image memory (MVAM), system extracts important descriptive information from urban landscape images, reducing problems related to small sample sizes. This discussion presents a comprehensive improvement and evaluation of a deep learning image classification pipeline using Google Colab, demonstrating advanced image processing. Using TensorFlow, Keres and scikit image libraries combined with advanced algorithms such as DenseNet121 and MobileNetV2 presents a clear approach. We created a Bidirectional GAN + MVAM for object recognition in this work. Our method performed well, with an accuracy of 81.43%, precision of 51.16, recall of 50.11, and F-score of 46.37. The systematic presentation of the code presents a careful strategy to ensure optimal performance, stability, and efficiency of deep learning and image processing tasks.

A lightweight YOLOv5 for real-time dangerous weapons detection

Deep neural networks are currently employed to detect weapons, and although these techniques provide a high level of accuracy, it still suffers from large weight parameters and a slow inference speed. When it comes to real-world applications, such as weapon detection, these methods are often not suitable for deployment on embedded devices. Because of the huge number of parameters and poor efficiency. The most recent object detection technique, which belongs to the YOLOv5 class, is commonly used for detecting weapons. However, it faces some difficulties such as high computational parameters and an unfavorable detection rate. to solve these shortcomings. an enhanced lightweight Yolov5s approach is suggested. Which consists of a combination of YOLOv5 and GhostNet modules. To evaluate the efficacy of the suggested technique, a set of experiments was performed on the Sohas weapon dataset., which is commonly used as a reference dataset in the field. Compared to the original YOLOv5, the results indicate a slight increase in the proposed model's mean Average Precision (mAP). Furthermore, there has been a reduction of 2.7 in GFLOPs and weights, and the number of model parameters has decreased by 1.42.

AI Driven Lab-on-chip Cartridge for Automated Urinalysis

After haematology, urinalysis is the most common biological test performed in clinical settings. Hence, simplified workflow and automated analysis of urine elements are of absolute necessities. In the present work, a novel lab-on-chip cartridge (Gravity Sedimentation Cartridge) for the auto analysis of urine elements is developed. The GSC consists of a capillary chamber that uptakes a raw urine sample by capillary force and performs particles and cells enrichment within 5 min through a gravity sedimentation process for the microscopic examination. Centrifugation, which is necessary for enrichment in the conventional method, was circumvented in this approach. The AI100 device (Image based autoanalyzer) captures microscopic images from the cartridge at 40x magnification and uploads them into the cloud. Further, these images were auto-analyzed using an AI-based object detection model, which delivers the reports. These reports were available for expert review on a web-based platform that enables evidence-based tele reporting. A comparative analysis was carried out for various analytical parameters of the data generated through GSC (manual microscopy, tele reporting, and AI model) with the gold standard method. The presented approach makes it a viable product for automated urinalysis in point-of-care and large-scale settings.

Improving industrial security device detection with convolutional neural networks

<p>Employee safety is paramount in the manufacturing industry to ensure their well-being and protection. Technological advancements, particularly convolutional neural networks (CNN), have significantly enhanced this safety aspect by facilitating object detection and recognition. This project aims to utilize CNN technology to detect personal protective equipment and implement a safety implement detection system. The CNN architecture with the YOLOv5x model was employed to train a dataset. Dataset videos were converted into frames, with resolution scale adjustments made during the data collection phase. Subsequently, the dataset was labeled, underwent data cleaning, and label and bounding box revisions. The results revealed significant metrics in safety equipment detection in industrial settings. Helmet precision reached 91%, with a recall of 74%. Goggles achieved 85% precision and an 87% recall. Mask absence recorded 92% precision and an 89% recall. The YOLOv5x model exhibited commendable performance, showcasing its robust ability to accurately locate and detect objects. In conclusion, the utilization of a CNN-based safety equipment detection system, such as YOLOv5x, has yielded substantial improvements in both speed and accuracy. These findings lay a solid foundation for future industrial security applications aimed at safeguarding workers, fostering responsible workplace behavior, and optimizing the utilization of information technology resources.</p>

Cross-attention Based Text-image Transformer for Visual Question Answering

Background: Visual question answering (VQA) is a challenging task that requires multimodal reasoning and knowledge. The objective of VQA is to answer natural language questions based on corresponding present information in a given image. The challenge of VQA is to extract visual and textual features and pass them into a common space. However, the method faces the challenge of object detection being present in an image and finding the relationship between objects. Methods: In this study, we explored different methods of feature fusion for VQA, using pretrained models to encode the text and image features and then applying different attention mechanisms to fuse them. We evaluated our methods on the DAQUAR dataset. Results: We used three metrics to measure the performance of our methods: WUPS, Acc, and F1. We found that concatenating raw text and image features performs slightly better than selfattention for VQA. We also found that using text as query and image as key and value performs worse than other methods of cross-attention or self-attention for VQA because it might not capture the bidirectional interactions between the text and image modalities Conclusion: In this paper, we presented a comparative study of different feature fusion methods for VQA, using pre-trained models to encode the text and image features and then applying different attention mechanisms to fuse them. We showed that concatenating raw text and image features is a simple but effective method for VQA while using text as query and image as key and value is a suboptimal method for VQA. We also discussed the limitations and future directions of our work.

The Concept of Electronic Pensioner in Some Countries Versus Romania

We aim to introduce the concept of e-pensioner (EP) with the intention of having this term used as a document within the European Union’s strategy on Artificial Intelligence (AI) for the period 2023-2027 and after implemented into the legislation of member countries. The relationship between older generations and emerging forms of digitalization and artificial intelligence is the focal point, aiming to provide an easily approachable dimension for pensioners. This article presents an analytical framework and approaches for integrating pensioners into the digital era. Following the exposition of theoretical foundations, the article delineates the use of pensioner cards in select countries worldwide. The intersection of pensioners with the digital era proves to be a fertile entry point for examining regulatory ordinances in the digital realm. A novel digital form, the AI-based digital portal, involves a technique of facial authentication for pensioners to send digital life certificates. Two key factors are named across all examined countries. The primary driver of digital transformation is propelled by the desire to enhance the efficiency and efficacy of public administration, which becomes particularly crucial as populations age, leading to increased demand for social services and competition for limited resources in the developed public sector. The innovative application of technology presents opportunities for streamlining processes, enhancing productivity, and reducing costs while concurrently improving service quality. The use of artificial intelligence (AI) in the management and administration of public pension funds stands for a natural progression of technology in the public domain. In an environment characterized by complexity and volatility, AI can provide a level of analysis and prediction that exceeds human ability. Presently, there exists a wide array of AI-powered tools for object detection, natural language processing, understanding and inference, optical character recognition, predictive analytics, anomaly detection, noise elimination, model forecasting, recommendation systems, and monitoring and observability.

Multi-granularity tooth analysis via YOLO-based object detection models for effective tooth detection and classification

Accurate detection and classification of teeth is the first step in dental disease diagnosis. However, the same class of tooth exhibits significant variations in surface appearance. Moreover, the complex geometrical structure poses challenges in learning discriminative features among the different tooth classes. Due to these complex features, tooth classification is one of the challenging research domains in deep learning. To address the aforementioned issues, the presented study proposes discriminative local feature extraction at different granular levels using YOLO models. However, this necessitates a granular intra-oral image dataset. To facilitate this requirement, a dataset at three granular levels (two, four, and seven teeth classes) is developed. YOLOv5, YOLOv6, and YOLOv7 models were trained using 2,790 images. The results indicate superior performance of YOLOv6 for two-class classification problems. The model generated a mean average precision (mAP) value of 94%. However, as the granularity level is increased, the performance of YOLO models decreases. For, four and seven-class classification problems, the highest mAP value of 87% and 79% was achieved by YOLOv5 respectively. The results indicate that different levels of granularity play an important role in tooth detection and classification. The YOLO’s performance gradually decreased as the granularity decreased especially at the finest granular level.

Object Detection Model: An Enhanced SSD

Abstract: Object Detection plays a significant role in today’s era. Object detection plays a crucial role in various applications such as surveillance, medical images, and autonomous vehicles. The primary goal of object detection is to accurately detect the boundaries of objects of interest and classify those objects into predefined categories. In this research paper, we enhanced an object detection technique i.e. Single shot multibox detector (SSD) which is one of the top object detection technique in both aspect accuracy and speed. SSD is an object detection model that predicts object bounding boxes and class probabilities in a single forward pass. It uses multiple feature maps at different scales to cater to various object sizes and aspect ratios.The main contribution of this research is to enhance the accuracy, recall time, precision time and mean average time (mAP). The performance of this object detection technique is improved as the number of feature maps is increases, improved backbone, and enhanced activation functions, additional layers for enhanced detection and loss function modifications. An accuracy of 0.75 indicates that the model correctly predicts the class label for approximately 75% of all objects in the dataset. The enhanced model showed these results: a precision score of 0.75 implies that 75% of the objects identified by the model as positive (detected objects) are indeed true positives. A recall of 0.73 indicates that the model successfully identifies and detects 73% of all positive instances in the dataset. A mAP of 75.25 signifies the average precision across all classes, computed at different IOU thresholds (e.g., 0.5, 0.75).

Survey of Techniques and Applications in Object Recognition

Abstract: Object detection, which is closely related to video analysis and image comprehension, has received attention in years from researchers. Traditional approaches to object detection rely on crafted features and shallow trainable architectures. However, these methods face challenges. Often reach a plateau, in performance improvement. To overcome these limitations complex ensembles are often created by combining low-level image features with high-level context from object detectors and scene classifiers. The emergence of learning has introduced powerful tools that can learn semantics high level and deeper features. These tools address the limitations of architectures by introducing network structures training strategies and optimization functions. This paper provides a review of learning-based frameworks for object detection. The review starts with an overview of the history of learning with a particular emphasis on the Convolutional Neural Network (CNN) as an exemplary tool. It then delves into generic object detection architectures exploring modifications and effective strategies for improving detection performance. Recognizing the characteristics of detection tasks, the paper also briefly surveys several tasks such, as salient object detection, face detection, crowd analysis, and pedestrian detection.

Conversion of an Entire Image into a 3D Scene with Object Detection and Single 3D Models

Abstract: The paper presents a framework for the extraction of objects from 2D images using object detection techniques in open CV and then generating 3D models of the segmented objects. To achieve precise object detection, the suggested methodology blends deep learning and computer vision methods. The 3D models that are produced have fine-grained geometric and textural features, which improves the object reconstruction's accuracy. The usefulness and robustness of our technique in various settings are demonstrated by experimental findings on a variety of datasets. For use in robotics, virtual reality, and the preservation of cultural heritage, where precise 3D models of actual objects are essential, this research shows great promise.

Real-Time Object Detection and Recognition with Computer Vision

Abstract: Object detection, a fundamental aspect of computer vision, is essential for identifying and localizing objects within images or video frames, leveraging advancements in deep learning, particularly convolutional neural networks (CNNs), to enhance precision and speed. Its applications span diverse domains, from autonomous vehicles and surveillance systems to augmented reality and human-computer interaction. Our project focuses on engineering a real-time object detection system, integrating deep learning and computer vision methodologies. Anchored on the robust Single Shot Multibox Detector (SSD) architecture and reinforced by the efficiency and accuracy of the MobileNetV3 backbone, our system utilizes a pre-trained SSD MobileNetV3 model and comprehensive annotations from the COCO dataset to adeptly detect and recognize a wide array of objects within live video streams or archived footage. It seamlessly processes video frames from various sources, annotating detected objects in real-time to provide instant visual feedback. Offering customizable confidence thresholds and support for multiple video sources, our project showcases the transformative potential of deep learning and computer vision, advancing realtime object detection across domains like surveillance and interactive systems. By pushing the boundaries of object detection technology, our project aims to enhance safety, efficiency, and user experiences in various applications, promising to redefine the landscape of computer vision with innovation and advancement.

Advanced method for Image detection using OpenCV

Abstract: In computer vision, object detection is an essential job with many real-world applications, such as robots, autonomous cars, and surveillance. Because of its great accuracy and speed, the YOLO (You Only Look Once) method is a well-liked realtime object recognition technique that has attracted a lot of attention. This technique is perfect for time-sensitive applications since it examines the full image at once and predicts bounding boxes and class probabilities for recognized items. YOLO has undergone many iterations, with YOLO v5 being the most recent and sophisticated version. It utilizes anchor boxes and a feature pyramid network (FPN) to increase the accuracy of object recognition. Our goal in this research is to apply YOLO v5 to realtime picture and object identification applications stage. The model will be trained using an appropriate dataset, and its performance will be assessed against a range of benchmarks and advanced object detection methods. The project's output will offer a reliable and effective real-time object detection system that will facilitate prompt decision-making in the identification of item types and their corresponding placements. It has useful uses in robotics, autonomous driving, and surveillance.

Senior-Centric Object Detection for Independent Living

Abstract: The need for creative solutions that help seniors preserve their independence is growing as a result of the worldwide population aging issue. A major obstacle that many seniors encounter is the possibility of a loss in their physical and cognitive abilities, which can make it difficult for them to carry out everyday chores. This study introduces a senior-oriented object detecting system in order to address this urgent problem. The technology assists elderly people in recognizing and locating things in their living areas by utilizing sophisticated computer vision techniques and machine learning algorithms. It aims to improve seniors' safety and autonomy through real-time support, ultimately leading to a better quality of life. This system is carefully designed to accommodate the special requirements of senior citizens, providing a viable means of fostering autonomous live in a population that is aging. This initiative is a big step forward in the fight to empower seniors and improve their well-being in an aging society because of its creative approach and emphasis on user-centric design

Review of Advanced Methods in Hardware Acceleration for Deep Neural Networks

Abstract: Convolutional neural networks have become very efficient in performing tasks like Object Detection providing human like accuracy. However, their practical implementation needs significant hardware resources and memory bandwidth. In recent past a lot of research is being carried out for achieving higher efficiency in implementing such neural networks in hardware. We talk about FPGAs for hardware implementation due to their flexibility for customisation for such neural network architectures. In this paper we will discuss the metrics for efficient hardware accelerator and general methods available for achieving an efficient design. Further, we will discuss the actual methods used by recent research for implementation of deep neural networks particularly for object detection related applications. These methods range from actual ASIC design like TPUs [1] for on chip acceleration, state of the art open source designs like Gemini to methods like hardware reuse, re-configurable nodes and approximation in computations as a trade-off between speed and accuracy. This paper will be a valuable summary for the researchers starting in the field of hardware accelerators design for neural networks

A Comprehensive Study on Detection of Water Bodies using Satellite Imagery

Abstract: Satellite imagery plays a crucial role in overseeing and safeguarding natural resources, particularly water bodies like lakes, rivers, and oceans, which hold significant environmental and human value. Detecting water body pixels in satellite images is a key aspect of environmental management and planning. Recent advancements in deep learning, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), offer promising solutions for tasks like object detection and segmentation in image processing. This study leverages CNNs and RNNs to precisely identify water body pixels in satellite images, aiming to develop a model capable of accurately distinguishing between water and non-water pixels. Such a model holds practical significance for environmental monitoring and management efforts

Unauthorized Drone Detection Using Deep Learning

Abstract: The growing concerns over drone misuse in national airspace, including activities like drug smuggling and privacy violations, demand advanced drone detection systems. Traditional methods struggle to accurately identify drones among various airborne objects. YOLO v8, renowned for its efficient single-pass object detection, presents a sophisticated solution. Through training on annotated datasets featuring drones in diverse environments and fine-tuning with aerial imagery, YOLO v8 excels at recognizing drones amidst complex backgrounds. Its multi-scale detection capabilities enable it to detect drones of varying sizes, crucial for different distances from the camera. Real-time prediction ensures timely detection, vital for immediate responses to unauthorized intrusions. Integration with drone tracking systems enhances situational awareness, facilitating proactive measures. Furthermore, employing adaptive thresholding and post-processing techniques like Kalman filtering refines drone detection accuracy, reducing false positives. YOLO v8 thus emerges as a potent tool in mitigating risks associated with drone misuse, bolstering defenses against unauthorized activities in national airspace.