BITS Faculty Publications
Permanent URI for this communityhttp://localhost:4000/handle/123456789/1867
Browse
11 results
Search Results
Item Low-Light Image Enhancement for UAVs With Multi-Feature Fusion Deep Neural Networks(IEEE, 2022-06) Narang, Pratik; Chamola, VinayObject detection in low-light aerial images is a challenging problem due to considerable variation in brightness and varying contrast. Deep learning-based approaches have recently demonstrated great promise in image enhancement. Many existing neural networks used for image quality enhancement first encode the input into low-resolution representations and then decode these representations back to a higher resolution for the contextual information. However, this method leads to the loss of semantic content. Recent research has demonstrated the advantage of maintaining high-resolution information along with lower resolution representations, which maintains image features throughout the network. In this letter, we propose a novel architecture named RNet for low-light image enhancement of aerial images. The proposed network contains multiresolution branches for better understanding of different levels of local and global context through different streams. The performance of RNet is evaluated on a recent synthetic dataset. We also present a comprehensive evaluation with a representative set of state-of-the-art enhancement techniques and neural net architectures.Item DroneSegNet: Robust Aerial Semantic Segmentation for UAV-Based IoT Applications(IEEE, 2022-04) Narang, Pratik; Chamola, VinayUnmanned Aerial Vehicles (UAVs) are the promising “Flying IoT” devices of the future, which can be equipped with various sensors and cognitive capabilities to perform numerous tasks related to remote sensing, search and rescue operations, object tracking, segmentation of roads and buildings, surveillance, etc. However, these AI-driven tasks require heavy computation and may lead to suboptimal performance with embedded processors on a power-constrained battery-operated drone. This work proposes a novel deep learning approach for performing robust semantic segmentation of aerial scenes captured by UAVs. In our setup, the power-constrained drone is used only for data collection, while the computationally intensive tasks are offloaded to a GPU cloud server. Our architecture performs robust semantic segmentation by learning the segmentation maps from jointly utilizing of aerial scenes along with the respective “elevation maps” in a semi-supervised approach. We propose a three-tier deep learning architecture, wherein the first module aims at preliminary feature extraction from aerial scenes using a backbone feature extractor. The second module captures the spatial dependency between the aerial scenes and their respective elevation maps to obtain better semantic information, which is achieved by a bi-directional LSTM. The third module is aimed at enhancing the performance of semantic segmentation through a semi-supervised approach with an encoder to generate segmentation maps and a decoder to reconstruct feature maps. This semi-supervised feature learning ensures robust extraction along with scalability. The proposed architecture was validated on real-world aerial datasets and achieves state-of-the-art results for aerial image segmentation.Item EraisNET: An Optical Flow based 3D ConvNET for Erasing Obstructions(IEEE, 2022) Narang, Pratik; Rajput, Amitesh SinghImages captured from behind a fence, window, or during rain generally face occlusions. Though prior works have addressed the problems of individually de-raining, reflection, and occlusion removal, a common approach that removes all the obstruction has found little attention in the literature. In this paper, we address the image occlusion problem by proposing a deep learning-based approach wherein the proposed method uses motion differences between two images and extracts important moving features from videos to separate the background and the obstruction. To accomplish this task, a novel 3D-convolution architecture is introduced, which is trained with synthetically blended videos. We have used learned layer-based CNN methods combined with dense-optical flow with generative networks for better output images. Moreover, a dataset for obstruction removal with sequences for reflection and fencing removal is proposed. The proposed approach is well experimented over a different variety of images and is found as a good candidate against state-of-the-art schemes.Item Multiclass Fake News Detection using Ensemble Machine Learning(IEEE, 2019) Narang, PratikOver the past few years, fake news and its influence have become a growing cause of concern in terms of debate and public discussions. Due to the availability of the Internet, a lot of user-generated content is produced across the globe in a single day using various social media platforms. Nowadays, it has become very easy to create fake news and propagate it worldwide within a short period of time. Despite receiving significant attention in the research community, fake news detection did not improve significantly due to insufficient context-specific news data. Most of the researchers have analyzed the fake news problem as a binary classification problem, but many more prediction classes exist. In this research work, experiments have been conducted using a tree-based Ensemble Machine Learning framework (Gradient Boosting) with optimized parameters combining content and context level features for fake news detection. Recently, adaptive boosting methods for classification problems have been derived as gradient descent algorithms. This formulation justifies key elements and parameters in the methods, which are chosen to optimize a single common objective function. Experiments are conducted using a multi-class dataset (FNC) and various machine learning models are used for classification. Experimental results demonstrate the effectiveness of the ensemble framework compared to existing benchmark results. Using the Gradient Boosting algorithm (an ensemble machine learning framework), we achieved an accuracy of 86% for multi-class classification of fake news having four classes.Item FNDNet – A deep convolutional neural network for fake news detection(Elsevier, 2020-06) Narang, PratikWith the increasing popularity of social media and web-based forums, the distribution of fake news has become a major threat to various sectors and agencies. This has abated trust in the media, leaving readers in a state of perplexity. There exists an enormous assemblage of research on the theme of Artificial Intelligence (AI) strategies for fake news detection. In the past, much of the focus has been given on classifying online reviews and freely accessible online social networking-based posts. In this work, we propose a deep convolutional neural network (FNDNet) for fake news detection. Instead of relying on hand-crafted features, our model (FNDNet) is designed to automatically learn the discriminatory features for fake news classification through multiple hidden layers built in the deep neural network. We create a deep Convolutional Neural Network (CNN) to extract several features at each layer. We compare the performance of the proposed approach with several baseline models. Benchmarked datasets were used to train and test the model, and the proposed model achieved state-of-the-art results with an accuracy of 98.36% on the test data. Various performance evaluation parameters such as Wilcoxon, false positive, true negative, precision, recall, F1, and accuracy, etc. were used to validate the results. These results demonstrate significant improvements in the area of fake news detection as compared to existing state-of-the-art results and affirm the potential of our approach for classifying fake news on social media. This research will assist researchers in broadening the understanding of the applicability of CNN-based deep models for fake news detection.Item ReViewNet: A Fast and Resource Optimized Network for Enabling Safe Autonomous Driving in Hazy Weather Conditions(IEEE, 2020) Narang, Pratik; Chamola, VinayAdverse weather conditions such as fog, haze, snow, mist and glare create visibility problems for applications of autonomous vehicles. To ensure safe and smooth operations in frequent bad weather scenarios, image dehazing is crucial to any vehicular motion and navigation task on road or air. Moreover, the commonly deployed mobile systems are resource constrained in nature. Therefore, it is important to ensure memory, compute and run-time efficiency of dehazing algorithms. In this manuscript we propose ReViewNet, a fast, lightweight and robust dehazing system suitable for autonomous vehicles. The network uses components like spatial feature pooling, quadruple color-cue, multi-look architecture and multi-weighted loss to effectively dehaze images captured by cameras of autonomous vehicles. The effectiveness of the proposed model is analyzed by exhaustive quantitative evaluation on five benchmark datasets demonstrating its supremacy over other existing state-of-the-art methods. Further, a component-wise ablation and loss weight ratio analysis demonstrates the contribution of each and every component of the network. We also show the qualitative analysis with special use cases and visual responses on distinctive vehicular vision instances, establishing the effectiveness of the proposed method in numerous hazy weather conditions for autonomous vehicular applications.Item EchoFakeD: improving fake news detection in social media with an efficient deep neural network(Springer, 2021-01) Narang, PratikThe increasing popularity of social media platforms has simplified the sharing of news articles that have led to the explosion in fake news. With the emergence of fake news at a very rapid rate, a serious concern has produced in our society because of enormous fake content dissemination. The quality of the news content is questionable and there exists a necessity for an automated tool for the detection. Existing studies primarily focus on utilizing information extracted from the news content. We suggest that user-based engagements and the context related group of people (echo-chamber) sharing the same opinions can play a vital role in the fake news detection. Hence, in this paper, we have focused on both the content of the news article and the existence of echo chambers in the social network for fake news detection. Standard factorization methods for fake news detection have limited effectiveness due to their unsupervised nature and primarily employed with traditional machine learning models. To design an effective deep learning model with tensor factorization approach is the priority. In our approach, the news content is fused with the tensor following a coupled matrix–tensor factorization method to get a latent representation of both news content as well as social context. We have designed our model with a different number of filters across each dense layer along with dropout. To classify on news content and social context-based information individually as well as in combination, a deep neural network (our proposed model) was employed with optimal hyper-parameters. The performance of our proposed approach has been validated on a real-world fake news dataset: BuzzFeed and PolitiFact. Classification results have demonstrated that our proposed model (EchoFakeD) outperforms existing and appropriate baselines for fake news detection and achieved a validation accuracy of 92.30%. These results have shown significant improvements over the existing state-of-the-art models in the area of fake news detection and affirm the potential use of the technique for classifying fake news.Item AI-Enabled Object Detection in UAVs: Challenges, Design Choices, and Research Directions(IEEE, 2021-08) Narang, Pratik; Chamola, VinayUnmanned aerial vehicles (UAVs) are emerging as a powerful tool for various industrial and smart city applications. UAVs coupled with various sensors can perform many cognitive tasks such as object detection, surveillance, traffic management, and urban planning. Deep learning has emerged as a popular technique to speed up the processing of high-dimensional data like images and videos, which has led to several applications in surveillance and autonomous driving. However, the area of aerial object detection has been understudied. This work proposes a deep learning approach for detection of objects in aerial scenes captured by UAVs. Our work first categorizes the current methods for aerial object detection using deep learning techniques and discusses how the task is different from general object detection scenarios. We delineate the specific challenges involved and experimentally demonstrate the key design decisions that significantly affect the accuracy and robustness of models. We further propose an optimized architecture that utilizes these optimal design choices along with the recent Res-NeSt backbone to achieve superior performance in aerial object detection. Lastly, we propose several research directions to inspire further advancement in aerial object detection.Item AENeT: an attention-enabled neural architecture for fake news detection using contextual features(Springer, 2021) Narang, Pratik; Sharma, YashvardhanIn the current era of social media, the popularity of smartphones and social media platforms has increased exponentially. Through these electronic media, fake news has been rising rapidly with the advent of new sources of information, which are highly unreliable. Checking off a particular news article is genuine or fake is not easy for any end user. Search engines like Google are also not capable of telling about the fakeness of any news article due to its restriction with limited query keywords. In this paper, our end goal is to design an efficient deep learning model to detect the degree of fakeness in a news statement. We propose a simple network architecture that combines the use of contextual embedding as word embedding and uses attention mechanisms with relevant metadata available. The efficacy and efficiency of our models are demonstrated on several real-world datasets. Our model achieved 46.36% accuracy on the LIAR dataset, which outperforms the current state of the art by 1.49%.Item Background Invariant Faster Motion Modeling for Drone Action Recognition(MDPI, 2021-07) Narang, PratikVisual data collected from drones has opened a new direction for surveillance applications and has recently attracted considerable attention among computer vision researchers. Due to the availability and increasing use of the drone for both public and private sectors, it is a critical futuristic technology to solve multiple surveillance problems in remote areas. One of the fundamental challenges in recognizing crowd monitoring videos’ human action is the precise modeling of an individual’s motion feature. Most state-of-the-art methods heavily rely on optical flow for motion modeling and representation, and motion modeling through optical flow is a time-consuming process. This article underlines this issue and provides a novel architecture that eliminates the dependency on optical flow. The proposed architecture uses two sub-modules, FMFM (faster motion feature modeling) and AAR (accurate action recognition), to accurately classify the aerial surveillance action. Another critical issue in aerial surveillance is a deficiency of the dataset. Out of few datasets proposed recently, most of them have multiple humans performing different actions in the same scene, such as a crowd monitoring video, and hence not suitable for directly applying to the training of action recognition models. Given this, we have proposed a novel dataset captured from top view aerial surveillance that has a good variety in terms of actors, daytime, and environment. The proposed architecture has shown the capability to be applied in different terrain as it removes the background before using the action recognition model. The proposed architecture is validated through the experiment with varying investigation levels and achieves a remarkable performance of 0.90 validation accuracy in aerial action recognition.