Face Recognition and Human Tracking Using GMM, HOG and SVM in Surveillance Videos

Dadi, Harihara Santosh; Pillutla, Gopala Krishna Mohan; Makkena, Madhavi Latha

doi:10.1007/s40745-017-0123-2

Cited by 21 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The previous works typically rely on the storage of large time segments of video data or image crops, degrading privacy preservation. Similarly, many works propose facial recognition techniques [35][36][37][38][39], which also gravely compromises the privacy of tracked persons, requiring the pre-loaded and long-term storage of personally identifiable information like a facial database. At the same time, existing approaches typically analyzes the data offline with the ability to move forward and backward in time to maximize their algorithm accuracy scores, making edge deployable operation of these approaches impractical.…”

Section: Related Work a Pedestrian Detection Re-identificationmentioning

confidence: 99%

REVAMP²T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

Neff

Mendieta

Mohan

et al. 2020

IEEE Internet Things J.

View full text Add to dashboard Cite

This article presents REVAMP 2 T, Real-time Edge Video Analytics for Multi-camera Privacy-aware Pedestrian Tracking, as an integrated end-to-end IoT system for privacybuilt-in decentralized situational awareness. REVAMP 2 T presents novel algorithmic and system constructs to push deep learning and video analytics next to IoT devices (i.e. video cameras). On the algorithm side, REVAMP 2 T proposes a unified integrated computer vision pipeline for detection, re-identification, and tracking across multiple cameras without the need for storing the streaming data. At the same time, it avoids facial recognition, and tracks and re-identifies pedestrians based on their key features at runtime. On the IoT system side, REVAMP 2 T provides infrastructure to maximize hardware utilization on the edge, orchestrates global communications, and provides system-wide re-identification, without the use of personally identifiable information, for a distributed IoT network. For the results and evaluation, this article also proposes a new metric, Accuracy • Efficiency (AE), for holistic evaluation of IoT systems for real-time video analytics based on accuracy, performance, and power efficiency. REVAMP 2 T outperforms current state-of-the-art by as much as thirteen-fold AE improvement.

show abstract

Section: Related Work a Pedestrian Detection Re-identificationmentioning

confidence: 99%

REVAMP²T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

Neff

Mendieta

Mohan

et al. 2020

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…However, the task becomes much more challenging when only one sample per person is available for training the face recognition model. Dadi et al [17] extracted histogram of oriented gradients (HOG) features and employ support vector machine (SVM) for classification. Li et al [41] combined Gabor wavelets and feature space transformation (FST) based on fusion feature matrix.…”

Section: Face Recognition With Single Sample Per Personmentioning

confidence: 99%

“…In this experiment, we compared another implementation of our proposed method with both enriched intra-variation and enriched invariant features (see Figure 3b) with the following methods: (i) traditional methods, namely HOG+SVM [17], G-FST [41], and FT-LPP [42]; and (ii) deep learning methods, namely FaceNet [22], CDA [34], TDL [33], and KCFT [43]. For fair comparison, we used multiple samples per person database, CelebA, as the generic data to pretrain three of the matchers.…”

Section: Effectiveness Of Enriching Both Intra-variation and Invarianmentioning

confidence: 99%

“…They constructed a manifold from patches for every individual and formulated face recognition as a manifold-manifold matching problem to identify the unlabeled subjects. Dadi et al [17] proposed to represent human faces by Histogram of Oriented Gradients (HOG), which captures edge or gradient structure and is invariant to local geometric and photometric transformations [18]. Local Binary Pattern (LBP) texture features extractor proposed by Ahonen et al [19] has also been explored for face recognition thanks to its computational efficiency and invariance to monotonic gray-level changes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved Single Sample Per Person Face Recognition via Enriching Intra-Variation and Invariant Features

Duoji

Zhao

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Face recognition using a single sample per person is a challenging problem in computer vision. In this scenario, due to the lack of training samples, it is difficult to distinguish between inter-class variations caused by identity and intra-class variations caused by external factors such as illumination, pose, etc. To address this problem, we propose a scheme to improve the recognition rate by both generating additional samples to enrich the intra-variation and eliminating external factors to extract invariant features. Firstly, a 3D face modeling module is proposed to recover the intrinsic properties of the input image, i.e., 3D face shape and albedo. To obtain the complete albedo, we come up with an end-to-end network to estimate the full albedo UV map from incomplete textures. The obtained albedo UV map not only eliminates the influence of the illumination, pose, and expression, but also retains the identity information. With the help of the recovered intrinsic properties, we then generate images under various illuminations, expressions, and poses. Finally, the albedo and the generated images are used to assist single sample per person face recognition. The experimental results on Face Recognition Technology (FERET), Labeled Faces in the Wild (LFW), Celebrities in Frontal-Profile (CFP) and other face databases demonstrate the effectiveness of the proposed method.

show abstract

“…& Makkena, M.L. [1] presented a novel algorithm for face recognition and human tracking. Human is tracked using Gaussian Mixture Model.…”

Section: Existing Related Workmentioning

confidence: 99%

Video Based Human Activity Detection, Recognition and Classification of actions using SVM

Basavaiah

Patil²

2018

TMLAI

View full text Add to dashboard Cite

Human motion analysis which includes activity detection and action recognition is currently gaining attention from computer vision researchers. Automatic monitoring of human activities and actions using computers has found significant applications in video surveillance, monitoring of patients and sports applications. With the tremendous advancement and development in digital video libraries, automatic interpretation of videos will save human effort in analysis and interpretation. This has led to the development of robust techniques in the field of computer vision. Human activity detection and recognition includes detection of human, tracking of human and recognition of actions. In this paper, detection of human is done using Gaussian Mixture Model, tracking is done using optical flow, recognition and classification of actions is done using SVM Classifier. The experiment is carried out with two public datasets KTH and Weizmann which are the videos with constant background. The classification accuracy for KTH dataset is 92.48% and for Weizmann dataset the classification accuracy is 93.64%.

show abstract

Face Recognition and Human Tracking Using GMM, HOG and SVM in Surveillance Videos

Cited by 21 publications

References 19 publications

REVAMP²T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

REVAMP²T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

Improved Single Sample Per Person Face Recognition via Enriching Intra-Variation and Invariant Features

Video Based Human Activity Detection, Recognition and Classification of actions using SVM

Contact Info

Product

Resources

About

Face Recognition and Human Tracking Using GMM, HOG and SVM in Surveillance Videos

Cited by 21 publications

References 19 publications

REVAMP2T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

REVAMP2T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

Improved Single Sample Per Person Face Recognition via Enriching Intra-Variation and Invariant Features

Video Based Human Activity Detection, Recognition and Classification of actions using SVM

Contact Info

Product

Resources

About

REVAMP²T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

REVAMP²T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking