Proceedings ArticleDOI
Comparison of Image processing techniques for detecting human presence in an image
K Padmavathi,S. Nithin +1 more
TLDR
The performance analysis of Haar-like features and Histogram of Oriented Gradients suited for detecting human presence in an image is presented here.Abstract:
The performance analysis of Haar-like features and Histogram of Oriented Gradients suited for detecting human presence in an image is presented here. The algorithms are implemented using OpenCV on an embedded platform. The algorithms were evaluated for a dataset comprising of 2850 images. The implementation details, comparison of algorithms and results obtained are discussed in detail.read more
Citations
More filters
Proceedings ArticleDOI
Low Cost Multipurpose UV-C Sterilizer box for protection against COVID’19
Rahul Santhosh,Sudha Yadav +1 more
TL;DR: In this article, the authors describe the construction of a low cost UV-C Sterilizer Box where UV radiation is taking place in a closed environment and safety features are also incorporated to prevent humans from UV light exposure.
Proceedings ArticleDOI
Smart Door System with COVID-19 Risk Factor Evaluation, Contactless Data Acquisition and Sanitization
TL;DR: In this article, the authors proposed a smart door system, which evaluates the COVID-19 risk factors and collects the data of person before entering into any place, thereby ensuring that non-infected people are only entering to the place and thus the spread of virus can be avoided.
Proceedings ArticleDOI
A comparative study of machine learning and deep learning algorithms for recognizing facial emotions
Amritha Krishnadas,S. Nithin +1 more
TL;DR: In this article, the authors compared the performance of three algorithms for facial emotion recognition (FER) in real-time on a live video stream, including SVM, CNN and VGG16.
Journal ArticleDOI
Body Weight Estimation using 2D Body Image
TL;DR: A novel computer-vision based method for body weight estimation using only 2D images of people is proposed, and the results obtained are much faster due to the reduced complexities of the proposed models, with facial models performing better than full body models.
Proceedings ArticleDOI
Comparative study of pedestrian detection techniques for driver assistance system
S. Akshayaa,S. Nithin +1 more
TL;DR: In this paper, the performance of YOLO v3 and HOG SVM model on INRIA person dataset containing pedestrians in different pose, shape and lighting conditions was compared.
References
More filters
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Proceedings ArticleDOI
Rapid object detection using a boosted cascade of simple features
Paul A. Viola,Michael Jones +1 more
TL;DR: A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
Journal ArticleDOI
Robust Real-Time Face Detection
Paul A. Viola,Michael Jones +1 more
TL;DR: In this paper, a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates is described. But the detection performance is limited to 15 frames per second.
Book ChapterDOI
Human detection using oriented histograms of flow and appearance
TL;DR: A detector for standing and moving people in videos with possibly moving cameras and backgrounds is developed, testing several different motion coding schemes and showing empirically that orientated histograms of differential optical flow give the best overall performance.
Proceedings ArticleDOI
Fast Human Detection Using a Cascade of Histograms of Oriented Gradients
TL;DR: This work integrates the cascade-of-rejectors approach with the Histograms of Oriented Gradients features to achieve a fast and accurate human detection system that can process 5 to 30 frames per second depending on the density in which the image is scanned, while maintaining an accuracy level similar to existing methods.