Faculty Publications

Now showing 1 - 3 of 3

Robust infrared target tracking using discriminative and generative approaches
(Elsevier B.V., 2017) Asha, C.S.; Narasimhadhan, A.V.
The process of designing an efficient tracker for thermal infrared imagery is one of the most challenging tasks in computer vision. Although a lot of advancement has been achieved in RGB videos over the decades, textureless and colorless properties of objects in thermal imagery pose hard constraints in the design of an efficient tracker. Tracking of an object using a single feature or a technique often fails to achieve greater accuracy. Here, we propose an effective method to track an object in infrared imagery based on a combination of discriminative and generative approaches. The discriminative technique makes use of two complementary methods such as kernelized correlation filter with spatial feature and AdaBoost classifier with pixel intesity features to operate in parallel. After obtaining optimized locations through discriminative approaches, the generative technique is applied to determine the best target location using a linear search method. Unlike the baseline algorithms, the proposed method estimates the scale of the target by Lucas-Kanade homography estimation. To evaluate the proposed method, extensive experiments are conducted on 17 challenging infrared image sequences obtained from LTIR dataset and a significant improvement of mean distance precision and mean overlap precision is accomplished as compared with the existing trackers. Further, a quantitative and qualitative assessment of the proposed approach with the state-of-the-art trackers is illustrated to clearly demonstrate an overall increase in performance. © 2017 Elsevier B.V.
Gearbox fault diagnosis based on Multi-Scale deep residual learning and stacked LSTM model
(Elsevier B.V., 2021) Ravikumar, K.N.; Yadav, A.; Kumar, H.; Gangadharan, K.V.; Narasimhadhan, A.V.
Fault diagnosis methods based on signal analysis techniques are widely used to diagnose faults in gear and bearing. This paper introduces a fault diagnosis model that includes a multi-scale deep residual learning with a stacked long short-term memory (MDRL-SLSTM) to address sequence data in a gearbox health prediction task in an internal combustion (IC) engine. In the MDRL-SLSTM network, CNN and residual learning is firstly utilized for local feature extraction and dimension reduction. The experiment is carried out on the gearbox of an IC engine setup, two datasets are used; one is from bearing and the other from 2nd driving gear of gearbox. To reduce the number of parameters, down-sampling is carried out on input data before giving to the architecture. The model achieved better diagnostic performance with vibration data of gearbox. Classification accuracy of 94.08% and 94.33% are attained on bearing datasets and 2nd driving gear of gearbox respectively. © 2021 Elsevier Ltd
Knowledge distillation: A novel approach for deep feature selection
(Elsevier B.V., 2023) C, D.; Shetty, A.; Narasimhadhan, A.V.
High dimensional data in hyperspectral remote sensing leads to computational, analytical, and storage complexities. Dimensionality reduction serves as an efficient tool to remove redundant, irrelevant, and highly correlated features. Recently, deep learning approaches have received remarkable progress in hyperspectral data analysis. In this paper, a new end-to-end deep learning framework based on a teacher-student network inspired by knowledge distillation is proposed for deep feature selection. Initially, a complicated teacher deep neural network is employed on complex high dimensional data to learn its corresponding best low dimensional representation. Then, the knowledge from the network is transferred to a simple student network that performs feature selection. Hence, it eventually leads to deep neural network compression which is of prime concern in hyperspectral remote sensing. Limited studies have been carried out to explore the benefits of knowledge distillation on hyperspectral data. The proposed method could be employed to choose deep features for both supervised and unsupervised tasks. Experimental results reveal the performance of the proposed scheme using limited features. In comparison to 1D and simple autoencoder models, the 2D model based on convolutional autoencoder delivers greater classification accuracies, with a classification accuracy value of 96.15% for the Indian Pines dataset and 97.82% for the Pavia University dataset. A similar trend is reported with unsupervised learning as well. Furthermore, the proposed model has a low degree of sensitivity to parameter selection. © 2022 National Authority of Remote Sensing & Space Science

Faculty Publications

Browse

Filters

Settings

Sort By

Results per page

Search Results