This study focuses on the problem of accurately delineating connected road structures from high-resolution remote sensing imagery-an important task with broad implications for smart city development, routing systems, and emergency management. Existing convolutional and transformer-based segmentation methods often struggle to capture fine structural details, maintain road connectivity, and preserve directional continuity. In this work, we propose fKAN (fractional Kolmogorov Arnold Networks)-UNet, a novel encoder-decoder architecture designed to address these challenges. The network primarily utilizes directional strip convolutions and a Feature Selective Fusion (FSF) block enhanced by a Squeeze-and-Excitation (SE) mechanism to refine feature representation. To further improve non-linear modeling and spectral selectivity, we incorporate fractional Jacobi Neural Blocks (fJNB) into the architecture. These blocks perform spectral transformations based on Jacobi polynomials of fractional order, enabling the model to effectively learn intricate spatial relationships and structures. To optimize the training, a hybrid objective is utilized, integrating Binary Cross-Entropy (BCE), dice, and boundary-based terms, which collectively enhance pixel-wise accuracy and edge consistency. A comprehensive evaluation, including detailed ablation analysis, was carried out using the MIT and DeepGlobe benchmark datasets. Compared to MSMDFFNet, fKAN-UNet achieves a 1.99% gain in IoU and a 1.54% boost in F1 score on the Massachusetts dataset. On the DeepGlobe dataset, it shows a 0.53% increase in IoU along with a 0.35% enhancement in the F1 metric. The code is available at: https://github.com/Jayku88/fKANUNet.

In this paper, containment control of a group of networked discrete-time dynamical systems has been investigated through differential privacy (DP) and communication constraints in the form of quantization. The networked systems are divided into followers and dynamical reference agents, wherein the followers’ dynamical models are a modified version of Friedkin-Johnsen (F-J) model-a popular model in opinion dynamics, while the reference agents follow affine dynamics. In order for the containment control problem to be private from adversaries, the followers’ and the reference agents’ states are masked with independent and identically distributed (iid) Laplacian noises before transmitting to other neighbours. The followers can both transmit and receive information from other followers, but can only receive communication from the reference agents, while the reference agents can both transmit and receive information from other reference agents. On the other hand, in a communication-constraint environment, instead of exchanging the real state values, every follower employs a uniform quantizer with a dynamic encoding-decoding scheme to send the quantized private states out to the other follower neighbour agents. The proposed work attempts to analyse the convergence of the containment control problem with the upper bound of the underlying quantization problem, and the DP achieved by the follower agents with respect to their transmitted quantized observation messages, while at the same time achieving the containment control. The simulation results verify the effectiveness of the proposed methodology.

Recent progress in image deblurring techniques focuses mainly on operating in both frequency and spatial domains using the Fourier transform (FT) properties. However, their performance is limited due to the dependency of FT on stationary signals and its lack of capability to extract spatial-frequency properties. In this paper, we propose a novel approach based on the Fractional Fourier Transform (FRFT), a unified spatial-frequency representation leveraging both spatial and frequency components simultaneously, making it ideal for processing non-stationary signals like images. Specifically, we introduce a Fractional Fourier Transformer (F2former), where we combine the classical fractional Fourier based Wiener deconvolution (F2WD) as well as a multi-branch encoder-decoder transformer based on a new fractional frequency aware transformer block (F2TB). We design F2TB consisting of a fractional frequency aware self-attention (F2SA) to estimate element-wise product attention based on important frequency components and a novel feed-forward network based on frequency division multiplexing (FM-FFN) to refine high and low frequency features separately for efficient latent clear image restoration. Experimental results for the cases of both motion deblurring as well as defocus deblurring show that the performance of our proposed method is superior to other state-of-the-art (SOTA) approaches.

Cyclones and floods are significant disasters seen by south- Asian countries. With cloud occlusions on the affected regions, monitoring the disaster becomes tedious. Synthetic Aperture Radars (SAR) can penetrate through the clouds (due to their microwave frequencies) and image the area under- Being active sensors, they also can image around the clock. These properties enable the domain experts to use SAR images for disaster monitoring; however, even professionals find it challenging to interpret the data since the human eye is unfamiliar with the impact of distance-dependent imaging, signal intensities observed in the radar spectrum, and image features associated to speckle or postprocessing procedures. This manuscript exploits the valuable imaging properties of SAR images to propose a Generative Adversarial Network (GAN) to synthesize realistic and semantic optical images by conditioning them over the microwave satellite images. It en- the model to synthesize optical images of an affected area in all weather and around the clock conditions, making it a critical disaster monitoring assistance tool.

Finger vein has become an appealing biometric trait due to its intrinsic nature, contactless acquisition and anti-spoofing capability when compared to other dominant biometric traits. The state-of-the-art intrinsic recognition derives vein patterns based on either curvature values, line tracking or deep neural networks. However, these methods extract artifacts such as noise, breaks and texture along with veins due to the problems such as irregular shading, poor contrast and blurriness in NIR images which affect the recognition accuracy. To deal with these issues, we propose a novel acquisition mechanism for vein patterns based on the pulsation of the veins. We propose to capture the pulsations from vein videos to accurately isolate the vein patterns. Besides, the proposed framework has an inherent method of detecting liveness along with recognition of the finger vein. To the best of our knowledge, this is the first work that utilizes the finger vein pulsations for biometric recognition. We acquired a finger vein video dataset, from 320 subjects, to evaluate the proposed method. The experimental results indicate that the proposed approach has a better recognition performance compared to the existing image-based approaches with an EER (%) of 0.8 and a recognition accuracy of 96.35%.

In the tracking‐by‐detection approach of online multiple object tracking (MOT), a major challenge is how to associate object detections on the new video frame with previously tracked objects. Two important aspects that directly influence the performance of MOT are quality of detection and accuracy in data association. The authors propose an efficient and unified MOT framework for improved object detection, followed by enhanced object tracking. The object detection and tracking are considered as two independent functions in the tracking‐by‐detection paradigm. In this study, object detection accuracy has been increased by employing a faster region‐based convolutional neural network (Faster R‐CNN) modified with the feedback region proposals from the tracker. Target association is performed by the correlation filter‐based Siamese CNN model, which finds the similarity score between the input image patches. The Siamese CNN is trained using a supervised hard sample mining strategy. An optical flow‐based motion model is employed to predict the next probable location of the targets from the tracker and these region proposals are fed back to the classifier module of Faster R‐CNN. The authors’ extensive analysis of publicly available MOT benchmark datasets and comparison with the state‐of‐the‐art tracking methods demonstrate competitive tracking performance of the proposed MOT framework.

Due to high variability in shape, structure and occurrence; the non-palpable breast masses are often missed by the experienced radiologists. To aid them with more accurate identification, computer-aided detection (CAD) systems are widely used. Most of the developed CAD systems use complex handcrafted features which introduce difficulties for further improvement in performance. Deep or high-level features extracted using deep learning models already have proven its superiority over the low or middle-level handcrafted features. In this paper, we propose an automated deep CAD system performing both the functions: mass detection and classification. Our proposed framework is composed of three cascaded structures: suspicious region identification, mass/no-mass detection and mass classification. To detect the suspicious regions in a breast mammogram, we have used a deep hierarchical mass prediction network. Then we take a decision on whether the predicted lesions contain any abnormal masses using CNN high-level features from the augmented intensity and wavelet features. Afterwards, the mass classification is carried out only for abnormal cases with the same CNN structure. The whole process of breast mass classification including the extraction of wavelet features is automated in this work. We have tested our proposed model on widely used DDSM and INbreast databases in which mass prediction network has achieved the sensitivity of 0.94 and 0.96 followed by a mass/no-mass detection with the area under the curve (AUC) of 0.9976 and 0.9922 respectively on receiver operating characteristic (ROC) curve. Finally, the classification network has obtained an accuracy of 98.05% in DDSM and 98.14% in INbreast database which we believe is the best reported so far.

Convolutional Neural networks(CNN) are one of the most powerful tools in the present era of science. There has been a lot of research done to improve their performance and robustness while their internal working was left unexplored to much extent. They are often defined as black boxes that can map non-linear data effectively. This paper answers the question, “How does a CNN look at an image?”. Visual results are also provided to strongly support the proposed method. The proposed algorithm exploits the basic math behind CNN to backtrack the important pixels. This is a generic approach which can be applied to any architecture of a neural network. This doesn't require any additional training or architectural changes. In literature, few attempts have been made to explain how learning happens in CNN internally, by exploiting the convolution filter maps. This is a simple algorithm as it does not involve any cost functions, filter exploitation, gradient calculations or probability scores. Further, we demonstrate that the proposed scheme can be used in some important computer vision tasks such as object detection, salient region proposal, etc.

Human Activity Recognition (HAR) has been a compelling problem in the field of computer vision since a long time. Our focus is to address the problem of trimmed activity recognition which is to identify the class of human activity in a video which is temporally trimmed to contain only those periods where human activity is present. In the past few years there has been a transition from handcrafted features for classification to deep convolutional neural networks which work on raw video data to extract features and classify human activities. 3D convolutional neural networks learn features from both the temporal as well as spatial dimensions and prove to be very powerful in finding correlations in signals containing spatiotemporal information. 3D-CNNs have been extremely successful in activity recognition. We explore the shortcomings of a 3D-CNN architecture and propose ensembling with a 2D-CNN to overcome these for a significantly better performance in activity recognition.

Visual Object tracking research has undergone significant improvement in the past few years. The emergence of tracking by detection approach in tracking paradigm has been quite successful in many ways. Recently, deep convolutional neural networks have been extensively used in most successful trackers. Yet, the standard approach has been based on correlation or feature selection with minimal consideration given to motion consistency. Thus, there is still a need to capture various physical constraints through motion consistency which will improve accuracy, robustness and more importantly rotation adaptiveness. Therefore, one of the major aspects of this paper is to investigate the outcome of rotation adaptiveness in visual object tracking. Among other key contributions, the paper also includes various consistencies that turn out to be extremely effective in numerous challenging sequences than the current state-of-the-art.

Although visual object tracking algorithms are capable of handling various challenging scenarios individually, none of them are robust enough to handle all the challenges simultaneously. For any online tracking by detection method, the key issue lies in detecting the target over the whole frame and updating systematically a target model based on the last detected appearance to avoid the drift phenomenon. This paper aims at proposing a novel robust tracking algorithm by fusing the frame level detection strategy of tracking, learning, & detection with the systematic model update strategy of Kernelized Correlation Filter tracker. The risk of drift is mitigated by the fact that the model updates are primarily driven by the detections that occur in the spatial neighborhood of the latest detections. The motivation behind the selection of trackers is their complementary nature in handling tracking challenges. The proposed algorithm efficiently combines the two state-of-the-art tracking algorithms based on conservative correspondence measure with strategic model updates, which takes advantages of both and outperforms them on their short ends by virtue of other. Extensive evaluation of the proposed method based on different metrics is carried out on the data sets ALOV300++, Visual Tracker Benchmark, and Visual Object Tracking. We demonstrated its performance in terms of robustness and success rate by comparing with state-of-the-art trackers.