Humans perceive the three-dimensional structure of the world with apparent ease. However, despite all of the recent advances in computer vision research, the dream of having a computer interpret an image at the same level as a two-year old remains elusive. Why is computer vision such a challenging problem and what is the current state of the art? Computer Vision: Algorithms and Applications explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both for specialized applications such as medical imaging, and for fun, consumer-level tasks such as image editing and stitching, which students can apply to their own personal photos and videos. More than just a source of recipes, this exceptionally authoritative and comprehensive textbook/reference also takes a scientific approach to basic vision problems, formulating physical models of the imaging process before inverting them to produce descriptions of a scene. These problems are also analyzed using statistical models and solved using rigorous engineering techniques Topics and features: structured to support active curricula and project-oriented courses, with tips in the Introduction for using the book in a variety of customized courses; presents exercises at the end of each chapter with a heavy emphasis on testing algorithms and containing numerous suggestions for small mid-term projects; provides additional material and more detailed mathematical topics in the Appendices, which cover linear algebra, numerical techniques, and Bayesian estimation theory; suggests additional reading at the end of each chapter, including the latest research in each sub-field, in addition to a full Bibliography at the end of the book; supplies supplementary course material for students at the associated website, http://szeliski.org/Book/. Suitable for an upper-level undergraduate or graduate-level course in computer science or engineering, this textbook focuses on basic techniques that work under real-world conditions and encourages students to push their creative boundaries. Its design and exposition also make it eminently suitable as a unique reference to the fundamental techniques and current research literature in computer vision.

/pdf/computer-vision-algorithms-and-applications-25dn6wu83j.pdf

Computer Vision: Algorithms and Applications

A new approach toward increasing spatial resolution is required to overcome the limitations of the sensors and optics manufacturing technology. One promising approach is to use signal processing techniques to obtain an high-resolution (HR) image (or sequence) from observed multiple low-resolution (LR) images. Such a resolution enhancement approach has been one of the most active research areas, and it is called super resolution (SR) (or HR) image reconstruction or simply resolution enhancement. In this article, we use the term "SR image reconstruction" to refer to a signal processing approach toward resolution enhancement because the term "super" in "super resolution" represents very well the characteristics of the technique overcoming the inherent resolution limitation of LR imaging systems. The major advantage of the signal processing approach is that it may cost less and the existing LR imaging systems can be still utilized. The SR image reconstruction is proved to be useful in many practical cases where multiple frames of the same scene can be obtained, including medical imaging, satellite imaging, and video applications. The goal of this article is to introduce the concept of SR algorithms to readers who are unfamiliar with this area and to provide a review for experts. To this purpose, we present the technical review of various existing SR methodologies which are often employed. Before presenting the review of existing SR algorithms, we first model the LR image acquisition process.

Super-resolution image reconstruction: a technical overview

Nearly all super-resolution algorithms are based on the fundamental constraints that the super-resolution image should generate low resolution input images when appropriately warped and down-sampled to model the image formation process. (These reconstruction constraints are normally combined with some form of smoothness prior to regularize their solution.) We derive a sequence of analytical results which show that the reconstruction constraints provide less and less useful information as the magnification factor increases. We also validate these results empirically and show that, for large enough magnification factors, any smoothness prior leads to overly smooth results with very little high-frequency content. Next, we propose a super-resolution algorithm that uses a different kind of constraint in addition to the reconstruction constraints. The algorithm attempts to recognize local features in the low-resolution images and then enhances their resolution in an appropriate manner. We call such a super-resolution algorithm a hallucination or reconstruction algorithm. We tried our hallucination algorithm on two different data sets, frontal images of faces and printed Roman text. We obtained significantly better results than existing reconstruction-based algorithms, both qualitatively and in terms of RMS pixel error.

/pdf/limits-on-super-resolution-and-how-to-break-them-401rdhxruv.pdf

Limits on super-resolution and how to break them

We analyze the super-resolution reconstruction constraints. In particular we derive a sequence of results which all show that the constraints provide far less useful information as the magnification factor increases. It is well established that the use of a smoothness prior may help somewhat, however for large enough magnification factors any smoothness prior leads to overly smooth results. We therefore propose an algorithm that learns recognition-based priors for specific classes of scenes, the use of which gives far better super-resolution results for both faces and text.

In many imaging systems, the detector array is not sufficiently dense to adequately sample the scene with the desired field of view. This is particularly true for many infrared focal plane arrays. Thus, the resulting images may be severely aliased. This paper examines a technique for estimating a high-resolution image, with reduced aliasing, from a sequence of undersampled frames. Several approaches to this problem have been investigated previously. However, in this paper a maximum a posteriori (MAP) framework for jointly estimating image registration parameters and the high-resolution image is presented. Several previous approaches have relied on knowing the registration parameters a priori or have utilized registration techniques not specifically designed to treat severely aliased images. In the proposed method, the registration parameters are iteratively updated along with the high-resolution image in a cyclic coordinate-descent optimization procedure. Experimental results are provided to illustrate the performance of the proposed MAP algorithm using both visible and infrared images. Quantitative error analysis is provided and several images are shown for subjective evaluation.

/pdf/joint-map-registration-and-high-resolution-image-estimation-nxfuinxwsn.pdf

Joint MAP registration and high-resolution image estimation using a sequence of undersampled images

The human visual system appears to be capable of temporally integrating information in a video sequence in such a way that the perceived spatial resolution of a sequence appears much higher than the spatial resolution of an individual frame. While the mechanisms in the human visual system that do this are unknown, the effect is not too surprising given that temporally adjacent frames in a video sequence contain slightly different, but unique, information. This paper addresses the use of both the spatial and temporal information present in a short image sequence to create a single high-resolution video frame. A novel observation model based on motion compensated subsampling is proposed for a video sequence. Since the reconstruction problem is ill-posed, Bayesian restoration with a discontinuity-preserving prior image model is used to extract a high-resolution video still given a short low-resolution sequence. Estimates computed from a low-resolution image sequence containing a subpixel camera pan show dramatic visual and quantitative improvements over bilinear, cubic B-spline, and Bayesian single frame interpolations. Visual and quantitative improvements are also shown for an image sequence containing objects moving with independent trajectories. Finally, the video frame extraction algorithm is used for the motion-compensated scan conversion of interlaced video data, with a visual comparison to the resolution enhancement obtained from progressively scanned frames.

Extraction of high-resolution frames from video sequences

A surveillance and guidance method and system for use with autonomously guided, man-on-the-loop or man-in-the-loop guided vehicles where the presence of obstacles must be considered in guiding the vehicle towards a target includes a navigation system configured to determine the position of the vehicle on which it is equipped. A communication system is configured for data exchange between the vehicle, neighboring vehicles and ground stations. A surveillance system is configured to detect and locate fixed or moving targets and obstacles. A computer is configured to track the position of targets and obstacles and to provide guidance commands or 4D flight paths to perform collision avoidance with respect to traffic regulations and procedures, and operational airspace restrictions. Additional computer tasks include station keeping or interception of targets. A command and control system is configured to interact with a user interface and control the vehicle's actuators.

Adaptive surveillance and guidance system for vehicle collision avoidance and interception

Subpixel Motion Estimation for Super-Resolution Image Sequence Enhancement

This paper explains and implements our efficient multi-frame super-resolution mosaicking algorithm. In this algorithm, feature points between images are matched using SIFT, and then random M-least squares is used to estimate the homography between frames. Next, separate frames are registered and the overlapping region is extracted. A generative model is then adopted and combined with maximum a posteriori estimation to construct the underdetermined sparse linear system. To solve the ill-posed large-scale inverse system, we derive and implement a new hybrid regularization (bilateral total variance Hubert) method. Cross validation is utilized to estimate the derivative of the blur kernel as well as the regularization parameter. Super-resolution is then applied to the individual sub-frames from the overlapping region. Finally, multi-band blending is used to stitch these resolution-enhanced frames to form the final image. The whole process is semi-real time (roughly 30 seconds for 35 frames) and the effectiveness of our algorithm is validated by applying it to real and synthetic UAV video frames.

Super-resolution mosaicking of UAV surveillance video

To integrate Unmanned Aircraft Systems (UAS) into the U.S. National Airspace (NAS), the Federal Aviation Administration (FAA) requires “an equivalent level of safety, comparable to see -and -avoid requirements for manned aircraft.” A pr oposed FAA rulemaking would mandate Automatic Dependent Surveillance – Broadcast ( ADS -B) out equipage by 2020, forcing aircraft flying in the NAS to broadcast their state vector to Air Traffic Control (ATC) and aircraft equipped with ADS -B in capability . With the advent of lightweight, low power, and low -cost ADS -B units, the equipage and the use of ADS -B transceivers on small UAS are no longer limited by payload and power capabilities , and represent promising opportunities for the regulated operation of sm all UAS in the NAS. T he University of North Dakota (UND) has been actively developing enabling sense and avoid (SAA) technologies under a series of projects funded by the Department of Defense , and is now turning to ADS -B as the central component for mid -air collision avoidance . This paper presents the results of modeling collision avoidance algorithms using ADS -B derived information in a software -in -the -loop (SWIL) environment . Upon extensive testing, the system is designed to be integrated seamlessly in to a hardware -in -the -loop (HWIL) environment, and ultimately in a flight test environment aboard a small UAS.

Richard R. Schultz

Papers

Extraction of high-resolution frames from video sequences

Adaptive surveillance and guidance system for vehicle collision avoidance and interception

Subpixel Motion Estimation for Super-Resolution Image Sequence Enhancement

Super-resolution mosaicking of UAV surveillance video

Unmanned Aircraft Systems Sense and Avoid Avionics Utilizing ADS -B Transceiver