Article
Computer Science, Information Systems
Junaid Tariq, Amir Ijaz, Ammar Armghan, Hameedur Rahman, Hashim Ali, Fayadh Alenezi
Summary: This paper presents two novel methods to expedite the intra mode decision process of HEVC, which are using Histogram of Oriented Gradients (HOG) and modeling the difference between the Hardmard-cost of intra modes. These algorithms significantly improve the encoding speed of HEVC.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2022)
Article
Automation & Control Systems
Ren C. Luo, Wei-Lung Hsu
Summary: The article proposes a histogram of oriented depth model (HODM) and its extraction approach, aiming to address the issue of poor localization accuracy in indoor service robots when the environment is rearranged. HODM estimates indoor primary structures and floor layouts through histogram-based model matching, achieving lower localization error compared to traditional methods.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
Ren C. Luo, Wei-Lung Hsu
Summary: The article introduces a localization method based on Histogram of Oriented Depth Model (HODM) that reduces localization errors compared to traditional methods and has fast computational time.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Agricultural Engineering
Saad Abouzahir, Mohamed Sadik, Essaid Sabir
Summary: Early detection of weeds is crucial for sustaining productivity, and the use of Histogram of Oriented Gradients (HOG) within a Bag-of-Visual-Words (BOVW) framework can significantly improve weed detection accuracy. The proposed method demonstrates satisfactory results in practical tests across three different crop fields.
BIOSYSTEMS ENGINEERING
(2021)
Article
Geography, Physical
Lulu Chen, Yongqiang Zhao, Jonathan Cheung-Wai Chan, Seong G. Kong
Summary: This paper introduces a new method for extracting spatial-spectral features directly from mosaic spectral images and validates its effectiveness and generalizability through object tracking experiments. The proposed method outperformed state-of-the-art feature descriptors on datasets captured with snapshot spectral cameras, achieving significant improvements in success rate.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Chemistry, Multidisciplinary
Minghe Cao, Jianzhong Wang, Li Ming
Summary: The paper proposes a robust visual tracking approach that identifies the target and distractors using a scene analysis module, achieving impressive tracking performance in person tracking.
APPLIED SCIENCES-BASEL
(2021)
Article
Mathematics
Himanish Shekhar Das, Akalpita Das, Anupal Neog, Saurav Mallik, Kangkana Bora, Zhongming Zhao
Summary: This study aims to detect the early stage of Parkinson's disease through hand-drawn images, achieving high accuracy through the fusion of discrete wavelet transform coefficients and histograms of oriented gradient features, as well as the application of machine learning algorithms.
Article
Computer Science, Artificial Intelligence
Binod Bhattarai, Ronast Subedi, Rebati Raman Gaire, Eduard Vazquez, Danail Stoyanov
Summary: We propose a novel deep multi-task learning method for medical image segmentation. Instead of relying on ground truth annotations, we generate pseudo-labels for an auxiliary task using Histogram of Oriented Gradients (HOGs). By combining the ground truth semantic segmentation masks for the primary task and the pseudo-labels for the auxiliary task, we train deep networks to optimize the loss of both tasks jointly.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Engineering, Electrical & Electronic
Cleber Gustavo Dias, Kessia Lucas Rodrigues, Natan Colombo Menegasse, Wonder Alexandre Luz Alves, Luiz Carlos da Silva
Summary: This article proposes a novel approach for sensorless speed measurement of induction motors using time-domain stator current analysis. The approach utilizes histogram of oriented gradients (HOG) and artificial neural network predictor (ANNP) to estimate the rotor speed in squirrel cage IMs. Experimental tests on a 7.5 kW motor validated the effectiveness of the method, even under broken rotor bars and low slip conditions.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Shaojun Guo, Feng Liu, Xiaohu Yuan, Chunrong Zou, Li Chen, Tongsheng Shen
Summary: The paper introduces a new approach named HSPOG for image feature extraction, which provides stable feature vectors for images of any size by employing spatial pyramid segmentation and dynamic calculation of pixel sizes, significantly increasing the target detection rate in the image recognition process.
TSINGHUA SCIENCE AND TECHNOLOGY
(2021)
Article
Optics
Yongjie Xue, Zhiyong Ju
Summary: The study proposes a deep learning-based approach, using DCA-YOLO, residual network, and social force model to address the multiple pedestrian tracking problem in the first-person perspective. Experimental results demonstrate the effectiveness of the algorithm.
Article
Computer Science, Information Systems
Snehal Gaikwad, Sanjay Nalbalwar, Anil Nandgaonkar
Summary: The world is witnessing incredible developments in the field of machine learning for pattern recognition in various applications. Handwritten character recognition, especially in Devanagari script, poses challenges due to similar shapes. Pre-processing techniques like entropy-based skew correction and Mask-based approach are used to increase accuracy. The extracted Histograms of Oriented Gradients (HOG) features are further classified using AdaBoost ensemble boosting method, achieving high recognition accuracy.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Analytical
Farzaneh Jafari, Anup Basu
Summary: Hand gesture recognition is a crucial method of communication between humans and machines. This study proposes a novel model based on computer vision methods to improve the accuracy of hand gesture recognition by using features such as saliency maps and histogram of oriented gradients (HOG).
Article
Energy & Fuels
Esmail Hosseini-Fard, Amin Roshandel-Kahoo, Mehrdad Soleimani-Monfared, Keyvan Khayer, Ali Reza Ahmadi-Fard
Summary: A novel strategy based on the concept of HOG for texture attribute extraction is proposed for automatic seismic image segmentation and properties extraction. The method is applied on both synthetic models and field seismic data examples, showing promising results as an alternative for conventional image interpretation.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Ronny Gerhard Guendel, Francesco Fioranelli, Alexander Yarovoy
Summary: The paper introduces an alternative classification approach based on radar phase information extracted from high-resolution Range Maps, showing equivalent or superior classification results compared to traditional micro-Doppler processing. Additionally, feature fusion of different data domains, such as modulus of the RM with RM phase information, improves classification performance, especially for robust activity performances.
IEEE SENSORS JOURNAL
(2021)