Journal Article
Permanent URI for this collectionhttps://ir.daiict.ac.in/handle/123456789/37
Browse
18 results
Search Results
Publication Metadata only EEG/MEG source imaging in the absence of subject's brain MRI scan: Perspective on co-registration and MRI selection approach(Wiley, 01-01-2023) Gohel, Bakul; Khare, Manish; DA-IICT, GandhinagarEEG/MEG source localization requires a subject's brain MRI to compute the sourcemodel and headmodel.�As part of this computation, co-registration of the digitized head information and brain MRI scan is the essential step. However, in the absence of a brain MRI scan, an approximated sourcemodel and headmodel can be computed from the subject's digitized head information and brain MRI scans from other subjects. In the present work, we compared the fiducial (FID)- and iterative closet point (ICP)-based co-registration approaches for computing an approximated sourcemodel using single and multiple available brain MRI scans. We also evaluated the two different template MRI selection strategies: one is based on objective registration error, and another on sourcemodel approximation error. The outcome suggests that averaged approximated solutions using multiple template brain MRI scans showed better performance than single-template MRI-based solutions. The FID-based approach performed better than the ICP-based approach for co-registration of the digitized head surface and brain MRI scan. While selecting template MRIs, the selection approach based on objective registration error showed better performance than a sourcemodel approximation error-based criterion. Cross-dataset performance analysis showed a higher model approximation error than within-dataset analysis. In conclusion, the FID-based co-registration approach and objective registration error-based MRI selection criteria provide a simple, fast and more accurate solution to compute averaged approximated models compared with the ICP-based approach. The demography of brain MRI scans should be similar to that of the query subject whose brain MRI scan was unavailable.Publication Metadata only Rule-based multi-view human activity recognition system in real time using skeleton data from RGB-D sensor(Springer, 01-03-2021) Varshney, Neeraj; Bakariya, Brijesh; Kushwaha, Alok Kumar Singh; Khare, Manish; DA-IICT, GandhinagarIdentification of human activity with decent precision is a challenging task in the field of computer vision, especially when applying for surveillance purpose. A rule-based classifier method is proposed in this paper, which is capable of recognizing a view-invariant multiple human activity recognition in real time. A single Kinect sensor is used for the input of RGB-D data in real time. Initially, a skeleton-tracking algorithm is applied. After tracking the skeletons, activities are recognized from each individually tracked skeleton independently. Different rules are defined to recognize discrete skeleton positions and classify a particular order of multiple postures into activities. During the experimentation, we examine about 14 activities and found that the proposed method is robust and efficient concerning multiple views, scaling and phase variation activities during different realistic acts. A self-generated dataset in the controlled environment is used for the experiment. About 2 min of data was collected. Data from two different males were collected for multiple human activities. Experimental results show that the proposed method is flexible and efficient for multiple view activities as well as scale and phase variation activities. It provides a detection accuracy of 98%.Publication Metadata only Editorial Note: Visual and Sensory Data Processing for Real Time Intelligent Surveillance System(Springer, 01-12-2022) Kushwaha, Alok Kumar Singh; Prakash, Om; Khare, Manish; Gwak, Jeonghwan; Nguyen, Thanh Binh; Khare, Ashish; DA-IICT, GandhinagarMultimedia Tools and Applications�gratefully acknowledges the editorial work of the scholars listed below on the special issue entitled �Visual and Sensory Data Processing for Real Time Intelligent Surveillance System� (SI 1220).Publication Metadata only Human Activity Recognition Based On Video Summarization And Deep Convolutional Neural Network(Oxford University Press, 23-03-2024) Kushwaha, Arati; Khare, Manish; Bommisetty, Reddy Mounika; Khare, Ashish; DA-IICT, GandhinagarIn this technological era, human activity recognition (HAR) plays a significant role in several applications like surveillance, health services, Internet of Things, etc. Recent advancements in deep learning and video summarization have motivated us to integrate these techniques for HAR. This paper introduces a computationally efficient HAR technique based on a deep learning framework, which works well in realistic and multi-view environments. Deep convolutional neural networks (DCNNs) normally suffer from different constraints, including data size dependencies, computational complexity, overfitting, training challenges and vanishing gradients. Additionally, with the use of advanced mobile vision devices, the demand for computationally efficient HAR algorithms with the requirement of limited computational resources is high. To address these issues, we used integration of DCNN with video summarization using keyframes. The proposed technique offers a solution that enhances performance with efficient resource utilization. For this, first, we designed a lightweight and computationally efficient deep learning architecture based on the concept of identity skip connections (features reusability), which preserves the gradient loss attenuation and can handle the enormous complexity of activity classes. Subsequently, we employed an efficient keyframe extraction technique to minimize redundancy and succinctly encapsulate the entire video content in a lesser number of frames. To evaluate the efficacy of the proposed method, we performed the experimentation on several publicly available datasets. The performance of the proposed method is measured in terms of evaluation parameters Precision, Recall, F-Measure and Classification Accuracy. The experimental results demonstrated the superiority of the presented algorithm over other existing state-of-the-art methods.Publication Metadata only A comprehensive survey on person re-identification approaches: various aspects(Springer, 01-05-2022) Singh, Nikhil Kumar; Khare, Manish; Jethva, Harikrishna B; DA-IICT, GandhinagarPerson re-identification (Re-ID) is an application of video surveillance and has become popular among Computer Vision and Image processing research communities since last decade due to having its strong safety and security potential. It is the process of identifying a person of interest in distributed non-overlapping camera views. Person re-identification has broad application in maintaining the security by re-identifying the malicious persons in networking cameras. Now a days terrorist and criminal activities are increasing day by day and it is utmost important to re-identify a person of interest at public places like � shopping malls, railway stations, airports, huge public events etc. A lot of challenges are involved in the re-identification process like variation in lighting condition, different poses and viewpoints, blurring effect, image resolution, background changes etc. Basically 2 types of datasets (image based, video based) are designed for re-identification purpose based on application and approaches. This paper includes the study of many popular datasets like ViPER, iLIDS, Market1501, DukeMTMC4ReID, CUHK01, CHUK02, CHUK03, PRID2011 etc. including the various parameters (no of persons, no of images, no of cameras, size of frames etc.) and challenges involved in that. In this paper various aspects of person re-identification approaches are discussed including temporal, spatial, feature, distance metric, machine learning, automation etc. to get the comprehensive and exhaustive idea of person re-identification methods.Publication Metadata only A Novel Algorithm for Efficient Utilization of GemStone using Genetic Algorithm(Springer, 14-01-2021) Sadani, Hiten M; Singh, Nikhil Kumar; Khare, Manish; DA-IICT, GandhinagarIn this paper, a novel method is used for fitting a polished and faceted object which is also called as a gem or diamond in a given rough gemstone using genetic algorithm. The goal of proposed Genetic Algorithm based Multiple Object Fitting algorithm is to maximize the utilization of the volume of rough gemstone by fitting the largest number of polished gemstones inside rough gemstone. One of the most difficult tasks is to fit the number of polished gemstones and positioning of each and every polished gemstone within the rough gemstone in order to minimize the waste. This is an optimization problem that is used to find the position, orientation, and scaling parameters of all the polished gemstones within a given rough gemstone such that the sum of volumes of all polished gemstones is maximized. The major novelty of proposed work is to fit more than one object in a given rough stone. The simulation results demonstrate the efficiency of our proposed algorithm.Publication Metadata only Integration of complex wavelet transform and Zernike moment for multi-class classification(Springer, 10-02-2021) Khare, Manish; Khare, Ashish; DA-IICT, GandhinagarMulticlass object classification is a crucial problem in computer vision research and have different emerging applications such as video surveillance. The task of multiclass object classification has more challenges because of highly variable nature and real time processing requirement of data. For tackling the multiclass object classification task, several existing methods adopt one feature or combination of features to classify objects. In this work, we propose a new combination of features-based algorithm for object classification. In the combination, the two features: (1) Daubechies complex wavelet transform (DCxWT) and (2) Zernike moments (ZM) have been used. The shift-invariance and symmetry properties of DCxWT facilitate the object classification in the wavelet domain. Specifically, the shift-invariance property of DCxWT is effective for translated object representation whereas the symmetry property yields perfect reconstruction for retaining object boundaries (i.e., edges). Moreover, translation and rotation-invariance properties of ZM are especially beneficial for the representation of varying pose and orientation of the objects. For these reasons, the composite of the two features brings about significant synthesized benefits over each single feature and the other widely used features. The multi-class support vector machine classifier is used for classifying different objects. The proposed method has been tested on standard datasets as well as our own dataset prepared by authors of this paper. Experimental results demonstrated the significant outperformance of the proposed method through quantitative evaluations and also suggest that the proposed hybridization of features is preferable for the classification problem.Publication Metadata only Effect of Reconstruction Losses in Discriminative and Generative Learning based Networks for the Person Re-identification(Elsevier, 31-01-2023) Shah, Abhishek; Srivastava, Noopur; Khare, Manish; DA-IICT, Gandhinagar; Shah, Abhishek (202011017)The Person Re-identification (Re-ID) task has gained popularity in recent times. Researchers are continuously looking to improve the accuracy of the existing person Re-ID systems. Identifying the person from the surveillance footage can be essential to security concerns. Currently, there are many state-of-art Person Re-ID systems available. Deep learning frameworks are also adopted for designing Re-ID systems. Apart from deep learning-based approaches, the Generative Adversarial Networks (GAN) based approach also gained substantial interest in Person Re-ID tasks. Augmentation of training data has significantly improved the performance of the system. Our primary objective is to analyze the effect of applying different reconstruction losses and their combinations on the GAN-based approach. The Discriminative and Generative Learning (DG-Net) approach is chosen for carrying out this study from other existing GAN-based systems. DG-Net is currently considered benchmarked in the GAN-based method for person Re-ID. Analysis shows that the proposed idea of using a variety of reconstruction losses simultaneously significantly improves the existing system's performance. Using the proposed technique of fusing multiple Losses simultaneously, we achieved a massive performance gain of 20.57% over the current benchmarked approach on the Market1501 dataset. This paper includes a thorough study of different loss functions and their effect on the generated images for performing Person Re-ID tasks.Publication Metadata only Human activity recognition by combining external features with accelerometer sensor data using deep learning network model(Springer, 01-10-2022) Varshney, Neeraj; Bakariya, Brijesh; Kushwaha, Alok Kumar Singh; Khare, Manish; DA-IICT, GandhinagarVarious Human Activities are classified through time-series data generated by the sensors of wearable devices. Many real-time scenarios such as Healthcare Surveillance, Smart Cities and Intelligent surveillance etc. are based upon Human Activity Recognition. Despite the popularity of local features-based approaches�and machine learning approaches, it fails to capture adequate temporal information. In this paper, the deep convolutional neural model has been proposed by combining external features, i.e. orientation invariant (Publication Metadata only Multi-resolution approach to human activity recognition in video sequence based on combination of complex wavelet transform, Local Binary Pattern and Zernike moment(Springer, 01-10-2022) Khare, Manish; Jeon, Moongu; DA-IICT, GandhinagarHuman activity recognition is a challenging problem of computer vision and it has different emerging applications. The task of recognizing human activities from video sequence exhibits more challenges because of its highly variable nature and requirement of real time processing of data. This paper proposes a combination of features in a multiresolution framework for human activity recognition. We exploit multiresolution analysis through Daubechies complex wavelet transform (DCxWT). We combine Local binary pattern (LBP) with Zernike moment (ZM) at multiple resolutions of Daubechies complex wavelet decomposition. First, LBP coefficients of DCxWT coefficients of image frames are computed to extract texture features of image, then ZM of these LBP coefficients are computed to extract the shape feature from texture feature for construction of final feature vector. The Multi-class support vector machine classifier is used for classifying the recognized human activities. The proposed method has been tested on various standard publicly available datasets. The experimental results demonstrate that the proposed method works well for multiview human activities as well as performs better than some of the other state-of-the-art methods in terms of different quantitative performance measures