Object recognition Object detection
Viewpoint Estimation · 2013
Cited by 0
Search 250 million research papers
Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.
About 10,000 papers for “Object detection”
Object Detection
Yuee Liu, Jinglan Zhang, Dian Tjondronegoro et al. · 2014
Semantic object detection is one of the most important and challenging problems in image analysis. Segmentation is an optimal approach to detect salient objects, but often fails to generate meaningful regions due to over-segmentation. This paper presents an improved semantic segmentation approach which is based on JSEG algorithm and utilizes multiple region merging criteria. The experimental results demonstrate that the proposed algorithm is encouraging and effective in salient object detection.
Cited by 0
Object detection
Pavel Vítek · Digital Repository (National Repository of Grey Literature) · 2022
This paper deals with object detection where a human figure is used as a model. The introductory chapter defines terms detection and object. The second chapter describes the basic theory of computer vision , such as image processing and its parts. A substantial part is also focused on the Canny edge detection, upper body detection and pose detection. The third chapter describes the MATLAB integrated development environment in which the image processing functions are implemented. The last chapter is a practical demonstration of object detection. Different upper body detection methods are compared there. In the last subsection, two methods of determining the deviations based on the template are compared. Finally, all methods are compared with respect to the obtained results.
Cited by 0
Object Detection
Long Peng, Yu Song · Elsevier eBooks · 2025
Cited by 0
Object detection
Baáš, Filip · Brno University of Technology Digital Library (Brno University of Technology) · 2017
Táto bakalárska práca sa zaoberá detekciou tvarovo nemenných objektov na snímkach. Pre detekciu je využitý algoritmus hranového vzdialenostného párovania, ktorý je na tieto účely stavaný. Prvá časť tejto práce je určená teoretickému vysvetleniu princípu tohto algoritmu. Sú tu vysvetlené najpoužívanejšie spôsoby prevedenia vzdialenostnej transformácie, potrebnej pre tento algoritmus. Ďalej je tu vysvetlený výpočet hranovej vzdialenosti a pyramídová reprezentácia informácií. Druhá časť je venovaná vývojovým nástrojom použitým v tejto práci, ktorými sú vývojové prostredie Visual Studio a knižnice OpenCV pre spracovanie obrazu a Qt pre tvorbu grafického používateľského rozhrania. V poslednej časti tejto práce je popísaná praktická realizácia detekcie objektov. Je tu popísaný spôsob akým sú objekty renderované, postup vytvorenia vzoru z renderovaného obrazu, spôsob vytvorenia sady vzorov, porovnanie rýchlostí vzdialenostných transformácií počítaných v rôznych metrikách, porovnanie obyčajnej a pyramídovej detekcie a spôsob vyhodnotenia detekcie. V závere práce sú zhrnuté dosiahnuté výsledky práce.
Cited by 0
Object Detection
Frascarelli, Antonio Ezio · KTH Publication Database DiVA (KTH Royal Institute of Technology) · 2015
During the last two decades the interest about computer vision raised steadily with multiple applications in fields like medical care, automotive, entertainment, retail, industrial, and security. Objectdetection is part of the recognition problem, which is the most important scope of the computervision environment.The target of this thesis work is to analyse and propose a solution for object detection in a real timedynamic environment. RoboCup@Home will be the benchmarking event for this system, which willbe equipped on a robot competing in the 2018 event. The system has to be robust and fast enoughto allow the robot to react to each environment change in a reasonable amount of time.The input hardware used to achieve such system comprise of a Microsoft Kinect, which providesan high definition camera and fast and reliable 3D scanner. Through the study and analysis ofstate-of-the-art algorithms regarding machine vision and object recognition, the more suitable oneshave been tested to optimise the execution on the targeted hardware. Porting of the application toan embedded platform is discussed.
Cited by 0Open access
Object Detection
B Sasikumar, Naveen Kumar M · International Journal of Advanced Research in Science Communication and Technology · 2024
With applications in image identification, augmented reality, autonomous driving, and surveillance, Itis crucial to this computer-vision. In this project uses sophisticated deep learning techniques to accomplish the thing detecting in Python. It makes use of neural networks using pre-trained convolutions (CNN) models, It is Used YOLO (You Only Look Once) or SSD (Single Shot Multibox Detector) in picture or video feeds to locate and identify things. Using popular libraries like PyTorch and Tensor Flow, when in this replica is developed, trained, and implemented using thispython programming language. Preprocessing procedures for handling incoming data, model training using annotated datasets, and inference on fresh photos or video frames are all included in the implementation. Additionally, the project investigates how accelerate inference so that real-time applications can use it.Evaluating the object identification system entails calculating important performance measures like F1 score, recall, and precision. The outcomes demonstrate how well the model can locate and recognize items in various circumstances. This work adds to the expanding machine vision and offers a useful manual for utilizing Python to achieve object of affection. The implementation's modular and flexible design makes it simple to modify for different use cases and datasets. The project's results demonstrate the possibility for more breakthroughs in practical uses, encouraging innovation in fields including image processing, autonomous systems, and surveillance.
Cited by 1Open access
Object Detection
Zhu, Kecheng, Gager, Zachary, Neal, Shelby et al. · VTechWorks (Virginia Tech) · 2022
Electronic theses and dissertations (ETDs) contain valuable knowledge that can be useful in a wide range of research areas. To effectively utilize the knowledge contained in ETDs, the data first needs to be parsed and stored in an XML document. However, since most of the ETDs available on the web are presented in PDF, parsing them is a challenge to make their data useful for any downstream task, including question-answering, figure search, table search, and summarizing. For information search and extraction, contextual information is needed to perform these tasks. However, such semantic information is hidden in PDF documents. In contrast, XML can explicitly share semantic information. The structure within XML documents can enforce semantic continuity within the tag elements. Accordingly, knowledge graphs can be more easily built from XML, rather than PDF, representations. The goal of this project was to extract different elements of scholarly documents such as metadata (title, authors, year), chapter headings and subheadings, equations, figures (and captions), tables (and captions), and paragraphs, and then package them into an XML document. Subsequently, a pipeline responsible for the conversion and a dataset to support the object detection step was developed. Over the semester, 200 ETDs, both born-digital and scanned, were annotated using a online tool called RoboFlow. A model based on Facebook’s open-sourced object detection model, Detectron2, was trained with the created dataset. Besides that, a pipeline that utilizes the model has been built that converts an ETD in PDF into an XML document, which can then be used for future downstream tasks and HTML for visualization. A dataset consisting of 200 annotated ETDs and a working pipeline were delivered to the client. From the project, the Object Detection Team learned numbers of libraries related to the task, built a sense of the importance of version control, and understood how to split a large task into smaller and more approachable pieces.
Cited by 0Open access
Object detection
Vítek, Pavel · Brno University of Technology Digital Library (Brno University of Technology) · 2022
Práce pojednává o detekci objektů, kde je lidská postava použita jako vzor. V úvodní kapitole jsou definovány pojmy detekce a objekt. V druhé kapitole jsou popsány základy teorie počítačového vidění, jako je např. zpracování obrazu a jeho součásti. Podstatná část je také věnována Cannyho detektoru hran, detekci horní části těla a detekci postoje. Třetí kapitola popisuje vývojové prostředí MATLAB, ve kterém jsou implementovány funkce pro zpracování obrazu. Poslední kapitola je praktickou ukázkou detekce objektů. Jsou zde srovnány různé metody detekce horní části těla. V poslední podkapitole jsou srovnány dva způsoby určení odchylek, které vycházejí z předlohy. Závěrem jsou komparovány veškeré metody s ohledem na dosažené výsledky.
Cited by 0
Object detection
Strašek, Petr · Brno University of Technology Digital Library (Brno University of Technology) · 2016
Tato bakalářská práce řeší problematiku detekce kontrastních objektů, hodnocení jejich symetrie a mezních stavů. Za tímto účelem byla vytvořena databáze snímků, na kterých byly algoritmy testovány. Práce dále popisuje konkrétní implementaci těchto algoritmů a jejich výsledky.
Cited by 0
Object Detection
Wang Shen, Chongjie Si, Chen Yang et al. · 2026
Cited by 0
Object Detection
Kecheng Zhu, Zachary Gager, Shelby Neal et al. · VTechWorks (Virginia Tech) · 2022
Electronic theses and dissertations (ETDs) contain valuable knowledge that can be useful in a wide range of research areas. To effectively utilize the knowledge contained in ETDs, the data first needs to be parsed and stored in an XML document. However, since most of the ETDs available on the web are presented in PDF, parsing them is a challenge to make their data useful for any downstream task, including question-answering, figure search, table search, and summarizing. For information search and extraction, contextual information is needed to perform these tasks. However, such semantic information is hidden in PDF documents. In contrast, XML can explicitly share semantic information. The structure within XML documents can enforce semantic continuity within the tag elements. Accordingly, knowledge graphs can be more easily built from XML, rather than PDF, representations. The goal of this project was to extract different elements of scholarly documents such as metadata (title, authors, year), chapter headings and subheadings, equations, figures (and captions), tables (and captions), and paragraphs, and then package them into an XML document. Subsequently, a pipeline responsible for the conversion and a dataset to support the object detection step was developed. Over the semester, 200 ETDs, both born-digital and scanned, were annotated using a online tool called RoboFlow. A model based on Facebook’s open-sourced object detection model, Detectron2, was trained with the created dataset. Besides that, a pipeline that utilizes the model has been built that converts an ETD in PDF into an XML document, which can then be used for future downstream tasks and HTML for visualization. A dataset consisting of 200 annotated ETDs and a working pipeline were delivered to the client. From the project, the Object Detection Team learned numbers of libraries related to the task, built a sense of the importance of version control, and understood how to split a large task into smaller and more approachable pieces.
Cited by 0Open access
Object detection
Strašek, Petr · Brno University of Technology Digital Library (Brno University of Technology) · 2016
Tato bakalářská práce řeší problematiku detekce kontrastních objektů, hodnocení jejich symetrie a mezních stavů. Za tímto účelem byla vytvořena databáze snímků, na kterých byly algoritmy testovány. Práce dále popisuje konkrétní implementaci těchto algoritmů a jejich výsledky.
Cited by 0
Object Detection
Frascarelli, Antonio Ezio · KTH Publication Database DiVA (KTH Royal Institute of Technology) · 2015
During the last two decades the interest about computer vision raised steadily with multiple applications in fields like medical care, automotive, entertainment, retail, industrial, and security. Objectdetection is part of the recognition problem, which is the most important scope of the computervision environment.The target of this thesis work is to analyse and propose a solution for object detection in a real timedynamic environment. RoboCup@Home will be the benchmarking event for this system, which willbe equipped on a robot competing in the 2018 event. The system has to be robust and fast enoughto allow the robot to react to each environment change in a reasonable amount of time.The input hardware used to achieve such system comprise of a Microsoft Kinect, which providesan high definition camera and fast and reliable 3D scanner. Through the study and analysis ofstate-of-the-art algorithms regarding machine vision and object recognition, the more suitable oneshave been tested to optimise the execution on the targeted hardware. Porting of the application toan embedded platform is discussed.
Cited by 0Open access
Object Detection
Dinh, Kevin, Dinh, Brian, Leavitt, Andrew et al. · VTechWorks (Virginia Tech) · 2023
For this project, our team took 20,000 image samples from ETDs and annotated them using a Python package called PyLabel. PyLabel is an open-source Python library used to label PDFs. PyLabel can also take a trained dataset and use it for AI-aided annotations. We also created a pipeline in order to divide the dataset into equal pieces, where a user can select the number of samples they want to annotate. Then old sample data is cleared out and replaced with new sample data that contains classes with low accuracy. Finally, we saved the annotations as a YOLOv7 .txt file which is accumulated in order to retrain the model with 10,000 annotated images and finally with 20,000 annotated pages. With these annotated pages we conducted an experiment timing how long it takes to annotate the pages to see the improvement of the average time per page to annotate as the different models were trained. We concluded that the model trained with 10,000 pages was significantly faster than the original model.
Cited by 0Open access
Object Detection
Machado, Pedro, McGinnity, T.M. · Zenodo (CERN European Organization for Nuclear Research) · 2019
CNCR Lab @ NTU - Object detection This repository was created storing the object detection source code. Details Object classification using YOLO3 and an Intel RealSense D435. Requirements Documentation Biotac SP sensors with ROS integration AR 10 hand Sawyer Robot Software Ubuntu 18.04 LTS ROS Melodic librealsense2 pyrealsense 2 Hardware Intel Realsense D435 Biotac SP sensors Sawyer Robotic ARM AR 10 hand Setup instructions Step 1 Install OpenCV 4 Run the installation script <pre><code>$ ./install_opencv4-0-1.sh</code></pre> Test the installation. <pre><code class="language-bash">$ python3</code></pre> <pre><code> import cv2 > cv2.__version__</code></pre> <strong>NOTE:</strong> Open a new teminal if it fails. Installation procedure retrieved from here Step 2 Install the librealsense 2 Follow the steps described here Step 3 Install the pyrealsense 2 Follow the steps described here Running the application <pre><code class="language-bash">$ python3 objectClassification.py</code></pre> Troubleshooting profile error. Check the USB cable and make sure that the camera is being detected as USB3 Adjust the parameters Authors Pedro Machado pedro.baptistamachado@ntu.ac.uk Prof. Martin McGinnity martin.mcginnity@ntu.ac.uk License 2019 (c) CNCR@NTU, All rights reserved
Cited by 0Open access
Object detection
Low, Cheng Feng · DR-NTU (Nanyang Technological University) · 2025
Object detection has become a cornerstone of modern computer vision, with applications spanning diverse industries. Convolutional Neural Networks (CNNs) have played a transformative role in this domain, enabling automated systems to extract hierarchical features from images for tasks like classification and object detection. Building on CNNs, the R-CNN family introduced a two-stage approach that combined region proposal techniques with CNN feature extraction, setting a benchmark for object detection accuracy. Further advancements, such as YOLO (You Only Look Once), revolutionized the field by treating object detection as a single regression problem, achieving real-time performance with remarkable speed and competitive accuracy. This project explores the evolution of object detection algorithms, starting with CNNs and R-CNN, progressing to the first YOLO algorithm, and culminating in the latest YOLOv11. Leveraging the YOLO algorithm to develop an efficient inventory tracking system. By utilizing YOLOv11’s advanced detection capabilities, the system ensures accurate object localization and identification, meeting industrial standards for quality management. This innovative approach will significantly enhance inventory processes, allowing for better tracking and management of resources
Cited by 0
Object detection
Filip Baáš · Digital Repository (National Repository of Grey Literature) · 2017
This bachelor thesis deals with detection of rigid objects in images. Chamfer matching algorithm, which is built for this kind of tasks is used as detection algorithm. First part of this work is dedicated to theoretical explanation of the algorithm. Most commonly used metrics of distance transform are explained, which is needed for the algorithm. Also explanation of chamfer distance calculation and pyramid representation of information is here. Next part is dedicated to development tools used in this work, which is integrated development environment Visual Studio and libraries OpenCV for image processing and Qt for graphical user interface creation. In last part of this work, practical implementation of object detection is described. This part explains the way objects are rendered, steps for creating a template from rendered image, method to create set of templates, comparison of speed of distance transformation calculation in different metrics, comparison of speed of common and pyramid detection and method of score calculation. The conclusion summarizes reached goals of this work.
Cited by 0
Object detection
Petr Strašek · Digital Repository (National Repository of Grey Literature) · 2016
This thesis solves the problem of detecting contrast subjects, assessing their symmetry and limit states. For this purpose, a database of photographs had been created, that were used for testing algorithms. The thesis also describes the specific implementation of these algorithms and their results.
Cited by 0
Object Detection
Kevin Dinh, Brian Dinh, Andrew Leavitt et al. · VTechWorks (Virginia Tech) · 2022
For this project, our team took 20,000 image samples from ETDs and annotated them using a Python package called PyLabel. PyLabel is an open-source Python library used to label PDFs. PyLabel can also take a trained dataset and use it for AI-aided annotations. We also created a pipeline in order to divide the dataset into equal pieces, where a user can select the number of samples they want to annotate. Then old sample data is cleared out and replaced with new sample data that contains classes with low accuracy. Finally, we saved the annotations as a YOLOv7 .txt file which is accumulated in order to retrain the model with 10,000 annotated images and finally with 20,000 annotated pages. With these annotated pages we conducted an experiment timing how long it takes to annotate the pages to see the improvement of the average time per page to annotate as the different models were trained. We concluded that the model trained with 10,000 pages was significantly faster than the original model.
Cited by 0Open access