Deep reinforcement learning in computer vision: a comprehensive survey

Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have demonstrated the remarkable successes of deep reinforcement learning in various domains including finance, medicine, healthcare, video games, robotics, and computer vision. In this work, we provide a detailed review of recent and state-of-the-art research advances of deep reinforcement learning in computer vision. We start with comprehending the theories of deep learning, reinforcement learning, and deep reinforcement learning. We then propose a categorization of deep reinforcement learning methodologies and discuss their advantages and limitations. In particular, we divide deep reinforcement learning into seven main categories according to their applications in computer vision, i.e. (i) landmark localization (ii) object detection; (iii) object tracking; (iv) registration on both 2D image and 3D image volumetric data (v) image segmentation; (vi) videos analysis; and (vii) other applications. Each of these categories is further analyzed with reinforcement learning techniques, network design, and performance. Moreover, we provide a comprehensive analysis of the existing publicly available datasets and examine source code availability. Finally, we present some open issues and discuss future research directions on deep reinforcement learning in computer vision.

     

Learning relational structures: Applications in computer vision

We present and compare two new techniques for learning Relational Structures (RSs) as they occur in 2D pattern and 3D object recognition. These techniques, namely, Evidence-Based Networks (EBS-NNets) and Rulegraphs combine techniques from computer vision with those from machine learning and graph matching. The EBS-NNet has the ability to generalize pattern rules from training instances in terms of bounds on both unary (single part) and binary (part relation) numerical features. It also learns the compatibilities between unary and binary feature states in defining different pattern classes. Rulegraphs check this compatibility between unary and binary rules by combining evidence theory with graph theory. The two systems are tested and compared using a number of different pattern and object recognition problems.     

Automated human behavior analysis from surveillance videos: a survey

With increasing crime rates in today’s world, there is a corresponding awareness for the necessity of detecting abnormal activity. Automation of abnormal Human behavior analysis can play a significant role in security by decreasing the time taken to thwart unwanted events and picking them up during the suspicion stage itself. With advances in technology, surveillance systems can become more automated than manual. Human Behavior Analysis although crucial, is highly challenging. Tracking and recognizing objects and human motion from surveillance videos, followed by automatic summarization of its content has become a hot topic of research. Many researchers have contributed to the field of automated video surveillance through detection, classification and tracking algorithms. Earlier research work is insufficient for comprehensive analysis of human behavior. With the introduction of semantics, the context of a surveillance domain may be established. Such semantics may extend surveillance systems to perform event-based behavior analysis relevant to the domain. This paper presents a survey on research on human behavior analysis with a scope of analyzing the capabilities of the state-of-art methodologies with special focus on semantically enhanced analysis.     

Temporal and real-time databases: a survey

A temporal database contains time-varying data. In a real-time database transactions have deadlines or timing constraints. In this paper we review the substantial research in these two previously separate areas. First we characterize the time domain; then we investigate temporal and real-time data models. We evaluate temporal and real-time query languages along several dimensions. We examine temporal and real-time DBMS implementation. Finally, we summarize major research accomplishments to date and list several unanswered research questions     

Ocular recognition databases and competitions: a survey

The use of the iris and periocular region as biometric traits has been extensively investigated, mainly due to the singularity of the iris features and the use of the periocular region when the image resolution is not sufficient to extract iris information. In addition to providing information about an individual’s identity, features extracted from these traits can also be explored to obtain other information such as the individual’s gender, the influence of drug use, the use of contact lenses, spoofing, among others. This work presents a survey of the databases created for ocular recognition, detailing their protocols and how their images were acquired. We also describe and discuss the most popular ocular recognition competitions (contests), highlighting the submitted algorithms that achieved the best results using only iris trait and also fusing iris and periocular region information. Finally, we describe some relevant works applying deep learning techniques to ocular recognition and point out new challenges and future directions. Considering that there are a large number of ocular databases, and each one is usually designed for a specific problem, we believe this survey can provide a broad overview of the challenges in ocular biometrics.

     

Applications of structure from motion: a survey

Structure from motion (SfM) has been an active research area in computer vision for decades and numerous practical applications are benefiting from this research. While no previous work has tried to summarize the applications appearing in the literature, this paper deals with a comprehensive overview of recent applications of SfM by classifying them into 10 categories, namely augmented reality, autonomous navigation/guidance, motion capture, hand-eye calibration, image/video processing, image-based 3D modeling, remote sensing, image organization/browsing, segmentation and recognition, and military applications. The goal is to provide insights for researchers to position their work more appropriately in the context of existing techniques, and to perceive both new applications and relevant research problems.     

Interactive computer programs for education and research: A survey

In this paper, a survey is given of the development and use of interactive computer packages for education and research in the field of control engineering, signal analysis and parameter estimation. Relevant aspects are: aims and goals of the package, its design and structure, the interaction, the development of the software, the necessary hardware, the educational aspects, the contents of the package and possible future developments.     

Understanding minority costumes: a computer vision perspective

Multimedia Systems - It is an extremely interesting work to understand the minority costumes in computer vision and ethnology community. It explored some crucial clue for understanding minority...     

Agent-based computer vision in a dynamic, real-time environment

For computer vision systems to operate in many real-world environments, processing must occur in real-time under dynamic conditions. An agent-based methodology offers an approach to increase flexibility and scalability to accommodate the demands of a real-time, dynamic environment. This paper presents an agent-based architecture that uses a utility optimization technique to guarantee that important vision tasks are fulfilled even under resource constraints. To ensure that the processing of vision tasks is both reliable and flexible, multiple behaviors are utilized to accomplish the vision application's requirements. A vision behavior consists of a grouping of vision algorithms and a set of service levels associated with these algorithms. Utility functions are adopted to evaluate the performance of all possible behaviors that can address the requirements of a vision application within resource constraints. The maximum overall utility corresponds to the optimal behavior. Two example systems using this model are presented to show the applicability of the architecture. Experimental results show that this agent-based architecture outperforms traditional non-agent-based approaches.     

Detecting faces in images: a survey

Images containing faces are essential to intelligent vision-based human-computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face, regardless of its 3D position, orientation and lighting conditions. Such a problem is challenging because faces are non-rigid and have a high degree of variability in size, shape, color and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future research     

MINPRAN: a new robust estimator for computer vision

MINPRAN is a new robust estimator capable of finding good fits in data sets containing more than 50% outliers. Unlike other techniques that handle large outlier percentages, MINPRAN does not rely on a known error bound for the good data. Instead, it assumes the bad data are randomly distributed within the dynamic range of the sensor. Based on this, MINPRAN uses random sampling to search for the fit and the inliers to the fit that are least likely to have occurred randomly. It runs in time O(N²+SN log N), where S is the number of random samples and N is the number of data points. We demonstrate analytically that MINPRAN distinguished good fits to random data and MINPRAN finds accurate fits and nearly the correct number of inliers, regardless of the percentage of true inliers. We confirm MINPRAN's properties experimentally on synthetic data and show it compares favorably to least median of squares. Finally, we apply MINPRAN to fitting planar surface patches and eliminating outliers in range data taken from complicated scenes     

MinGPU: a minimum GPU library for computer vision

In the field of computer vision, it is becoming increasingly popular to implement algorithms, in sections or in their entirety, on a graphics processing unit (GPU). This is due to the superior speed GPUs offer compared to CPUs. In this paper, we present a GPU library, MinGPU, which contains all of the necessary functions to convert an existing CPU code to GPU. We have created GPU implementations of several well known computer vision algorithms, including the homography transformation between two 3D views. We provide timing charts and show that our MinGPU implementation of homography transformations performs approximately 600 times faster than its C++ CPU implementation.

Context modeling in computer vision: techniques,implications, and applications

In recent years there has been a surge of interest in context modeling for numerous applications in computer vision. The basic motivation behind these diverse efforts is generally the same—attempting to enhance current image analysis technologies by incorporating information from outside the target object, including scene analysis as well as metadata. However, many different approaches and applications have been proposed, leading to a somewhat inchoate literature that can be difficult to navigate. The current paper provides a ‘roadmap’ of this new research, including a discussion of the basic motivation behind context-modeling, an overview of the most representative techniques, and a discussion of specific applications in which contextual modeling has been incorporated. This review is intended to introduce researchers in computer vision and image analysis to this increasingly important field as well as provide a reference for those who may wish to incorporate context modeling in their own work.     

DroneRTEF:development of a novel adaptive framework for railroad track extraction in drone images

Pattern Analysis and Applications - Railroad track health monitoring is a challenging yet important task as it affects the safety of railroad systems. Railroad track extraction presents an...     

Query verification schemes for cloud-hosted databases: a brief survey

Database query verification schemes provide correctness guarantees for database queries. Typically such guarantees are required and advisable where queries are executed on untrusted servers. This need to verify query results, even though they may have been executed on one’s own database, is something new that has arisen with the advent of cloud services. The traditional model of hosting one’s own databases on one’s own servers did not require such verification because the hardware and software were both entirely within one’s control, and therefore fully trusted. However, with the economical and technological benefits of cloud services beckoning, many are now considering outsourcing both data and execution of database queries to the cloud, despite obvious risks. This survey paper provides an overview into the field of database query verification and explores the current state of the art in terms of query execution and correctness guarantees provided for query results. We also provide indications towards future work in the area.     

Object-oriented databases: definition and research directions

An object-oriented database is defined and justified on the basis of a small set of central object-oriented concepts. A number of common misconceptions about object-oriented databases are discussed. The results of relevant recent research in object-oriented databases are outlined. Directions for future research in object-oriented databases are provided