Target localization is an important task for a broad range of ubiquitous computing applications. A great deal of previous work has focused on applying advanced machine learning methods to address image-based target detection and localization problems. Some work has also explored the localizing capabilities of radar signals that describe target distances and velocities. This paper proposes a novel machine learning architecture, SoliNet, to localize target positions from radar images alone. Radar data were acquired by Google’s Soli sensors and processed to generate range-Doppler images describing the motion of a radar target. Corresponding camera images of the target were used as validation data. Over 60 experiments including six unique target trajectories were performed using a robotic actuator rig. The SoliNet machine learning architecture was then trained to accomplish localization using the known location of the target over time as dictated by the programmed robot trajectory. SoliNet is an end-to-end trained combination of deep convolutional and recurrent neural networks. Experimental results showed an overall accuracy of 98.6% and equivalent effectiveness to camera-based target localization, demonstrating the promising capabilities of the proposed technique.

We introduce a new edge-directed interpolator based on locally defined, straight line approximations of image isophotes. Spatial derivatives of image intensity are used to describe the principal behavior of pixel-intersecting isophotes in terms of their slopes. The slopes are determined by inverting a tridiagonal matrix and are forced to vary linearly from pixel-to-pixel within segments. Image resizing is performed by interpolating along the approximated isophotes. The proposed method can accommodate arbitrary scaling factors, provides state-of-the-art results in terms of PSNR as well as other quantitative visual quality metrics, and has the advantage of reduced computational complexity that is directly proportional to the number of pixels.

In this paper, we describe a pixel based approach for automated segmentation of tumor components from MR images. Sparse coding with data-adapted dictionaries has been successfully employed in several image recovery and vision problems. Since it is trivial to obtain sparse codes for pixel values, we propose to consider their non-linear similarities to perform kernel sparse coding in a high dimensional feature space. We develop the kernel K-lines clustering procedure for inferring kernel dictionaries and use the kernel sparse codes to determine if a pixel belongs to a tumorous region. By incorporating spatial locality information of the pixels, contiguous tumor regions can be efficiently identified. A low complexity segmentation approach, which allows the user to initialize the tumor region, is also presented. Results show that both of the proposed approaches lead to accurate tumor identification with a low false positive rate, when compared to manual segmentation by an expert.

We introduce a new edge-directed interpolator based on locally defined, straight line approximations to image isophotes. The first spatial derivatives of image intensity are used to describe the behavior of pixel-intersecting isophotes in terms of their slopes. Slopes are determined by inverting a tridiagonal matrix and are forced to vary linearly from pixel to pixel. Image resizing is performed using standard, 1D interpolators along the approximated isophotes. The proposed method can accommodate arbitrary scaling factors, provides state-of-the-art results in terms of PSNR as well as other quantitative quality metrics, and has the advantage of computational complexity that is directly proportional to the number of pixels.

Video deinterlacing is a key technique in digital video processing, particularly with the widespread usage of LCD and plasma TVs. This paper proposes a novel spatio-temporal video deinterlacing technique that adaptively chooses between results from segment adaptive gradient angle interpolation (SAGA), vertical temporal filter (VTF) and temporal line averaging (LA). The proposed method performs better than several popular benchmarking methods in terms of both visual quality and PSNR and requires minimal computational overhead. The algorithm performs better than existing approaches on fine moving edges and semi-static regions of videos, which are recognized as particularly challenging deinterlacing cases.

A new technique is presented for interpolating between grey-scale images in a medical data set. Registration between neighboring slices is achieved with a modified control grid interpolation algorithm that selectively accepts displacement field updates in a manner optimized for performance. A cubic interpolator is then applied to pixel intensities correlated by the displacement fields. Special considerations are made for efficiency, interpolation quality, and compression in the implementation of the algorithm. Experimental results show that the new method achieves good quality, while offering dramatic improvement in efficiency relative to the best competing method.

Atmospheric turbulence is a naturally occurring phenomenon that can severely limit the resolution of long distance optical and infrared sensors. Because atmospheric turbulence can degrade the appearance of video captured by these sensors, many of which are already deployed in the field, there is much interest in employing enhancement/restoration processing to improve data quality after acquisition. This paper presents a signal processing approach to suppressing atmospheric turbulence effects in sensor video using an adaptive control grid interpolation method. In this method, a dense dynamic motion vector field is derived from the characteristics of the atmospheric turbulence as seen in the data. The vector field is used in turn as part of the distortion compensation process, while preserving naturally occurring motion, such as that associated with the movement of objects within the stationary scene. The resulting algorithm is shown to produce enhanced video with quality significantly higher than that of the original.