Algorithms for People Recognition in Digital Images: A Systematic Review and Testing

Intriago-Pazmiño, Monserrate; Vargas-Sandoval, Vanessa; Moreno-Díaz, Jorge; Salazar-Jácome, Elizabeth; Salazar-Grandes, Mayra

doi:10.1007/978-3-319-56538-5_44

Cited by 5 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, a set of relevant studies will be presented in chronological order from the oldest to the most recent. In 2017, Intriago-Pazmiño et al [9] presents a comprehensive evaluation of works published in the last decade and identify, implement, and test the most-used and best-rated algorithms. A feature extraction approach similar to Histograms of Oriented Gradients (HOG) as well as two classification algorithms, AdaBoost and Support Vector Machine(SVM), have been discovered by us.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Neural Network (CNN) Model to Mobile Remote Surveillance System for Home Security

Ayad¹,

Al-Khalidi²

2023

IJCDS

View full text Add to dashboard Cite

Every citizen wants to eliminate any potential threat to themselves or their belongings. A proper and modern surveillance system is necessary given the enormous increase in the security needs of both persons and organizations. Remote surveillance is one of the major issues which attracted the attention of researchers recently. Surveillance cameras, commonly known as closed-circuit television (CCTV) have grown rapidly in popularity over the last few decades. Nowadays, video surveillance is quite essential. It greatly aids in reducing crime rates and can be used to keep track of the condition of buildings. In this paper, a remote surveillance system using the Convolutional Neural Networks (CNN) model was proposed. This system consists of a camera that takes more than one image of the object that passes in front of it and sends these images to the mobile phone of the intended person (the owner of the place). Images taken by the security camera may be analyzed using the CNN model depending on the region of interest for detection. The system will be delivering an alarm to the user depending on intelligent detection depending on a deep learning approach that can improve a smart home automation structure by detection people. The results of the experiments demonstrate a high degree of accuracy in detecting human beings , the accuracy of the system reached 100% in an ideal time.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Accuracy SVM-HOG [9] 96.00 Adaboost-HOG [9] 72.00 Xiao and Liu [10] 91.00 CNN [11] 96.00 Gajjar et al [19] 91.4 CNN-MufHAS [21] 99.80 Proposed 100.00…”

Section: Approachmentioning

confidence: 99%

Convolutional Neural Network (CNN) Model to Mobile Remote Surveillance System for Home Security

Ayad¹,

Al-Khalidi²

2023

IJCDS

View full text Add to dashboard Cite

show abstract

“…Detection Accuracy HOG [3] 67.76% Adaboost [61] 72.23% SVM-HOG [62] 78.93% Adaboost-HOG [62] 85.14% R-FCN [59] 86.31% YOLO [9] 88.73% Fast R-CNN [60] 90.38% Ours 91.4% Figure 10: Results of different detection Brussels dataset using standard evaluation settings.…”

Section: Approachmentioning

confidence: 99%

“…Detection Accuracy HOG [3] 67.76% Adaboost [61] 72.23% SVM-HOG [62] 78.93% Adaboost-HOG [62] 85.14% R-FCN [59] 86.31% YOLO [9] 88.73% Fast R-CNN [60] 90.38% Ours 91.4% To further improve the detection performance, we perform ablation experiments. Using both the dataset's training images; we trained the network and tested the model on test images of the individual dataset.…”

Section: Approachmentioning

confidence: 99%

ViS-HuD: Using Visual Saliency to Improve Human Detection with Convolutional Neural Networks

Gajjar

Khandhediya

Gumani

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

The paper presents a technique to improve human detection in still images using deep learning. Our novel method, ViS-HuD, computes visual saliency map from the image. Then the input image is multiplied by the map and product is fed to the Convolutional Neural Network (CNN) which detects humans in the image. A visual saliency map is generated using ML-Net and human detection is carried out using DetectNet. ML-Net is pre-trained on SALICON while, DetectNet is pre-trained on ImageNet database for visual saliency detection and image classification respectively. The CNNs of ViS-HuD were trained on two challenging databases -Penn Fudan and TUD-Brussels Benchmark. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on Penn Fudan Dataset with 91.4% human detection accuracy and it achieves average miss-rate of 53% on the TUD-Brussels benchmark.

show abstract

Method for Improving the Performance of Technical Analysis Indicators By Neural Network Models

Shi

Long

et al. 2021

Comput Econ

View full text Add to dashboard Cite

Algorithms for People Recognition in Digital Images: A Systematic Review and Testing

Cited by 5 publications

References 25 publications

Convolutional Neural Network (CNN) Model to Mobile Remote Surveillance System for Home Security

Convolutional Neural Network (CNN) Model to Mobile Remote Surveillance System for Home Security

ViS-HuD: Using Visual Saliency to Improve Human Detection with Convolutional Neural Networks

Method for Improving the Performance of Technical Analysis Indicators By Neural Network Models

Contact Info

Product

Resources

About