Kalyan Kumar Halder

Geometric correction of atmospheric turbulence-degraded video containing moving objects

Long-distance surveillance is a challenging task because of atmospheric turbulence that causes time-varying image shifts and blurs in images. These distortions become more significant as the imaging distance increases. This paper presents a new method for compensating image shifting in a video sequence while keeping real moving objects in the video unharmed. In this approach, firstly, a highly accurate and fast optical flow technique is applied to estimate the motion vector maps of the input frames and a centroid algorithm is employed to generate a geometrically correct frame in which there is no moving object. The second step involves applying an algorithm for detecting real moving objects in the video sequence and then restoring it with those objects unaffected. The performance of the proposed method is verified by comparing it with that of a state-of-the-art approach. Simulation experiments using both synthetic and real-life surveillance videos demonstrate that this method significantly improves the accuracy of image restoration while preserving moving objects.

Model-free prediction of atmospheric warp based on artificial neural network

This paper presents the application of artificial neural network for predicting the warping of images of remote objects or scenes ahead of time. The algorithm is based on estimating the pattern of warping of previously captured short-exposure frames through a generalized regression neural network (GRNN) and then predicting the warping of the upcoming frame. A high-accuracy optical flow technique is employed to estimate the dense motion fields of the captured frames, which are considered as training data for the GRNN. The proposed approach is independent of the pixel-oscillatory model unlike the state-of-the-art Kalman filter (KF) approach. Simulation experiments on synthetic and real-world turbulence degraded videos show that the proposed GRNN-based approach performs better than the KF approach in atmospheric warp prediction.

Simple and efficient approach for restoration of non-uniformly warped images

A high accuracy image dewarping method is proposed to restore images from non-uniformly warped video sequences degraded by atmospheric turbulence. This approach contains three major steps. First, a non-rigid image registration technique is employed to register all the frames in the sequence to a reference frame and estimate the motion fields. Second, an iterative First Register Then Average And Subtract (iFRTAAS) method is applied to correct the geometric deformations of the warped frames. The third step involves applying a non-local means filter for the compensation of noise and to improve the signal-to-noise ratio (SNR) of the restored reference frame. Simulations are carried out by applying the method to synthetic and real-life turbulence degraded videos and by determining various quality metrics. A performance comparison is presented between the proposed method and two earlier methods, which verifies that the proposed method provides significant improvement on the image restoration accuracy.

A fast restoration method for atmospheric turbulence degraded images using non-rigid image registration

In this paper, a fast image restoration method is proposed to restore the true image from an atmospheric turbulence degraded video. A non-rigid image registration algorithm is employed to register all the frames of the video to a reference frame and determine the shift maps. The First Register Then Average And Subtract-variant (FRTAASv) method is applied to correct the geometric distortion of the reference frame. A performance comparison is presented between the proposed restoration method and the earlier Minimum Sum of Squared Differences (MSSD) image registration based FRTAASv method, in terms of processing time and accuracy. Simulation results show that the proposed method requires shorter processing time to achieve the same geometric accuracy.

High Precision Restoration Method for Non-uniformly Warped Images

This paper proposes a high accuracy image restoration technique to restore a quality image from the atmospheric turbulence degraded video sequence of a static scenery. This approach contains two major steps. In the first step, we employ a coarse-to-fine optical flow estimation technique to register all the frames of the video to a reference frame and determine the shift maps. In the second step, we use an iterative First Register Then Average And Subtract (iFRTAAS) method to correct the geometric distortions of the reference frame. We present a performance comparison between our proposed method and existing statistical method in terms of restoration accuracy. Simulation experiments show that our proposed method provides higher accuracy with substantial gain in processing time.

Target tracking in dynamic background using generalized regression neural network

In this paper, we present a new approach to track moving objects in videos having a dynamic background. At first, we apply an object detection algorithm that deals with the detection of real objects in a degraded video by separating them from turbulence-induced motions using a two-level thresholding technique. Then, a generalized regression neural network is used to track the detected objects throughout the frames in the video. The proposed approach utilizes the features of centroid and area of moving objects and creates the reference regions instantly by selecting the objects within a circle. The performance of the proposed approach is compared with that of an existing approach by applying them to turbulence degraded videos, and competitive results are obtained.

A new pixel shiftmap prediction method based on Generalized Regression Neural Network

This paper proposes a new atmospheric warp estimation method based on Artificial Neural Network (ANN). We employed a Generalized Regression Neural Network (GRNN) for a-priori estimation of the upcoming warped frames using history of the previous frames. A non-rigid image registration technique is used for determining pixel shifts of the captured frames with respect to the reference frame. The proposed method is independent of the pixel-wander model. The performance of the method is evaluated using various quality metrics. Simulation results show that the proposed method provides substantial estimation of the upcoming frames with considerable errors.

An Improved Restoration Method for Non-Uniformly Warped Images Using Optical Flow Technique

A high precision and fast image restoration method is proposed to restore a geometrically corrected image from the atmospheric turbulence degraded video sequence of a static scenery. In this approach, we employ an optical flow technique to register all the frames of the distorted video to a reference frame and determine the flow fields. We use the First Register Then Average And Subtract-variant (FRTAASv) method to correct the geometric distortions using the computed flow fields. We present a performance comparison between our proposed restoration method and earlier Minimum Sum of Squared Differences (MSSD) image registration based FRTAASv method in terms of computational time and accuracy. Simulation experiments show that our proposed method provides higher accuracy with quicker processing time.

Moving object detection and tracking in videos through turbulent medium

This paper addresses the problem of identifying and tracking moving objects in a video sequence having a time-varying background. This is a fundamental task in many computer vision applications, though a very challenging one because of turbulence that causes blurring and spatiotemporal movements of the background images. Our proposed approach involves two major steps. First, a moving object detection algorithm that deals with the detection of real motions by separating the turbulence-induced motions using a two-level thresholding technique is used. In the second step, a feature-based generalized regression neural network is applied to track the detected objects throughout the frames in the video sequence. The proposed approach uses the centroid and area features of the moving objects and creates the reference regions instantly by selecting the objects within a circle. Simulation experiments are carried out on several turbulence-degraded video sequences and comparisons with an earlier method confirms that the proposed approach provides a more effective tracking of the targets.

Speckle reduction and deblurring of ultrasound images using artificial neural network

Ultrasound (US) imaging is widely used in clinical diagnostics as it is an economical, portable, painless, comparatively safe, and non-invasive real-time tool. However, the image quality of US imaging is severely affected by the presence of speckle noise during the acquisition process. It is essential to achieve speckle-free high resolution US imaging for better clinical diagnosis. In this paper, we propose a speckle and blur reduction algorithm for US imaging based on artificial neural networks (ANNs). Here, speckle noise is modelled as a multiplicative noise following a Rayleigh distribution, whereas blur is modelled as a Gaussian blur function. The noise and blur variances are estimated by a cascade-forward back propagation (CFBP) neural network using a set of intensity and wavelet features of the US image. The estimated noise and blur variances are then used for speckle reduction by solving the inverse Rayleigh function, and for de-blurring, using the Lucy-Richardson algorithm. The proposed approach gives improved results for both qualitative and quantitative measures.