Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
Computer Vision Center（计算机视觉中心）；Czech Technical University in Prague（布拉格捷克理工大学）；Arraiy, Inc.（Arraiy公司）
This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. The package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. Inspired by OpenCV, Kornia is composed of a set of modules containing operators that can be inserted inside neural networks to train models to perform image transformations, camera calibration, epipolar geometry, and low level image processi…
This literature has proposed three fast and easy computable image features to improve computer vision by offering more human-like vision power. These features are not based on image pixels absolute or relative intensity; neither based on shape or colour. So, no complex pixel by pixel calculation is required. For human eyes, pixel by pixel calculation is like seeing an image with maximum zoom which is done only when a higher level of details is required. Normally, first we look at an image to get an overall idea about it to know whether it deserves further investigation or not. This capacity of…
Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Institut de Robòtica i Informàtica Industrial（工业机器人与信息技术研究所）；Czech Technical University in Prague（布拉格捷克理工大学）；The Chinese University of Hong Kong（香港中文大学）
This work presents Kornia, an open source computer vision library built upon a set of differentiable routines and modules that aims to solve generic computer vision problems. The package uses PyTorch as its main backend, not only for efficiency but also to take advantage of the reverse auto-differentiation engine to define and compute the gradient of complex functions. Inspired by OpenCV, Kornia is composed of a set of modules containing operators that can be integrated into neural networks to train models to perform a wide range of operations including image transformations,camera calibration…
Recently, deep learning algorithms, especially fully convolutional network based methods, are becoming very popular in the field of remote sensing. However, these methods are implemented and evaluated through various datasets and deep learning frameworks. There has not been a package that covers these methods in a unifying manner. In this study, we introduce a computer vision package termed Geoseg that focus on building segmentation and outline extraction. Geoseg implements over nine state-of-the-art models as well as utility scripts needed to conduct model training, logging, evaluating and vi…
East China University of Science and Technology（华东理工大学）
Computer vision has been introduced to estimate calories from food images. But current food image data sets don't contain volume and mass records of foods, which leads to an incomplete calorie estimation. In this paper, we present a novel food image data set with volume and mass records of foods, and a deep learning method for food detection, to make a complete calorie estimation. Our data set includes 2978 images, and every image contains corresponding each food's annotation, volume and mass records, as well as a certain calibration reference. To estimate calorie of food in the proposed data …
We survey a number of data visualization techniques for analyzing Computer Vision (CV) datasets. These techniques help us understand properties and latent patterns in such data, by applying dataset-level analysis. We present various examples of how such analysis helps predict the potential impact of the dataset properties on CV models and informs appropriate mitigation of their shortcomings. Finally, we explore avenues for further visualization techniques of different modalities of CV datasets as well as ones that are tailored to support specific CV tasks and analysis needs.
We introduce the MNIST-C dataset, a comprehensive suite of 15 corruptions applied to the MNIST test set, for benchmarking out-of-distribution robustness in computer vision. Through several experiments and visualizations we demonstrate that our corruptions significantly degrade performance of state-of-the-art computer vision models while preserving the semantic content of the test images. In contrast to the popular notion of adversarial robustness, our model-agnostic corruptions do not seek worst-case performance but are instead designed to be broad and diverse, capturing multiple failure modes…
National Institute of Technology, Warangal（瓦朗加尔国家理工学院）；Aarhus University（奥胡斯大学）
Recent developments in video analysis of sports and computer vision techniques have achieved significant improvements to enable a variety of critical operations. To provide enhanced information, such as detailed complex analysis in sports like soccer, basketball, cricket, badminton, etc., studies have focused mainly on computer vision techniques employed to carry out different tasks. This paper presents a comprehensive review of sports video analysis for various applications high-level analysis such as detection and classification of players, tracking player or ball in sports and predicting th…
A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn't hold in many applications. Instead, ample labeled data might exist in a particular `source' domain while inference is needed in another, `target' domain. Domain adaptation methods leverage labeled data from both domains to improve classification on unseen data in the target domain. In this work we survey domain transfer learning methods for various application domains with focus on recent work in Computer Vision.
Humboldt-Universität zu Berlin（柏林洪堡大学）；The BioRobotics Institute, Scuola Superiore Sant’Anna（圣安娜高等学校生物机器人研究所）；Adaptive Systems Group, Department of Computer Science（计算机科学系自适应系统组）
This document presents novel datasets, constructed by employing the iCub robot equipped with an additional depth sensor and color camera. We used the robot to acquire color and depth information for 210 objects in different acquisition scenarios. At this end, the results were large scale datasets for robot and computer vision applications: object representation, object recognition and classification, and action recognition.
Maritime vessels equipped with visible and infrared cameras can complement other conventional sensors for object detection. However, application of computer vision techniques in maritime domain received attention only recently. The maritime environment offers its own unique requirements and challenges. Assessment of the quality of detections is a fundamental need in computer vision. However, the conventional assessment metrics suitable for usual object detection are deficient in the maritime setting. Thus, a large body of related work in computer vision appears inapplicable to the maritime set…
Proceedings of the Second Croatian Computer Vision Workshop (CCVW 2013, http://www.fer.unizg.hr/crv/ccvw2013) held September 19, 2013, in Zagreb, Croatia. Workshop was organized by the Center of Excellence for Computer Vision of the University of Zagreb.
Computer vision has been thriving since AI development was gaining thrust. Using deep learning techniques has been the most popular way which computer scientists thought the solution of. However, deep learning techniques tend to show lower performance than manual processing. Using deep learning is not always the answer to a problem related to computer vision.
Omnidirectional (360°) video has got quite popular because it provides a highly immersive viewing experience. For computer vision algorithms, it poses several challenges, like the special (equirectangular) projection commonly employed and the huge image size. In this work, we give a high-level overview of these challenges and outline strategies how to adapt computer vision algorithm for the specifics of omnidirectional video.
A negative result is when the outcome of an experiment or a model is not what is expected or when a hypothesis does not hold. Despite being often overlooked in the scientific community, negative results are results and they carry value. While this topic has been extensively discussed in other fields such as social sciences and biosciences, less attention has been paid to it in the computer vision community. The unique characteristics of computer vision, particularly its experimental aspect, call for a special treatment of this matter. In this paper, I will address what makes negative results i…
Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models. The issue is exacerbated when the task involves complex structured outputs, as it becomes harder to design procedures which address this misalignment. In natural language processing, this is often addressed using reinforcement learning techniques that align models with a task reward. We adopt this approach and show its surprising effectiveness across multiple computer vision tasks, such as object detection, panoptic segmentation, colorization and image captioning. We belie…
University of Connecticut（康涅狄格大学）；Saint Johns’ Episcopal Hospital（圣约翰圣公会医院）；Plainview Medical Center（普莱恩维尤医疗中心）；Northwell Health（诺斯韦尔健康中心）
Abnormal gait, its associated falls and complications have high patient morbidity, mortality. Computer vision detects, predicts patient gait abnormalities, assesses fall risk and serves as clinical decision support tool for physicians. This paper performs a systematic review of how computer vision, machine learning models perform an abnormal patient's gait assessment. Computer vision is beneficial in gait analysis, it helps capture the patient posture. Several literature suggests the use of different machine learning algorithms such as SVM, ANN, K-Star, Random Forest, KNN, among others to perf…
Advancements in deep learning have ignited an explosion of research on efficient hardware for embedded computer vision. Hardware vision acceleration, however, does not address the cost of capturing and processing the image data that feeds these algorithms. We examine the role of the image signal processing (ISP) pipeline in computer vision to identify opportunities to reduce computation and save energy. The key insight is that imaging pipelines should be designed to be configurable: to switch between a traditional photography mode and a low-power vision mode that produces lower-quality image d…
UC San Diego（加州大学圣地亚哥分校）；ATG Robotics（ATG机器人公司）；University of Bristol（布里斯托尔大学）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
As an important component of autonomous systems, autonomous car perception has had a big leap with recent advances in parallel computing architectures. With the use of tiny but full-feature embedded supercomputers, computer stereo vision has been prevalently applied in autonomous cars for depth perception. The two key aspects of computer stereo vision are speed and accuracy. They are both desirable but conflicting properties, as the algorithms with better disparity accuracy usually have higher computational complexity. Therefore, the main aim of developing a computer stereo vision algorithm fo…
In this thesis, we present new schemes which leverage a constrained clustering method to solve several computer vision tasks ranging from image retrieval, image segmentation and co-segmentation, to person re-identification. In the last decades clustering methods have played a vital role in computer vision applications; herein, we focus on the extension, reformulation, and integration of a well-known graph and game theoretic clustering method known as Dominant Sets. Thus, we have demonstrated the validity of the proposed methods with extensive experiments which are conducted on several benchmar…
To address the SMC'17 data challenge -- "Data mining atomically resolved images for material properties", we first used the classic "blob detection" algorithms developed in computer vision to identify all atom centers in each STEM image frame. With the help of nearest neighbor analysis, we then found and labeled every atom center common to all the STEM frames and tracked their movements through the given time interval for both Molybdenum or Selenium atoms.
Despite significant progress of deep learning in the field of computer vision, there has not been a software library that covers these methods in a unifying manner. We introduce ChainerCV, a software library that is intended to fill this gap. ChainerCV supports numerous neural network models as well as software components needed to conduct research in computer vision. These implementations emphasize simplicity, flexibility and good software engineering practices. The library is designed to perform on par with the results reported in published papers and its tools can be used as a baseline for …
In this paper, we explore some of the applications of computer vision to sports analytics. Sport analytics deals with understanding and discovering patterns from a corpus of sports data. Analysing such data provides important performance metrics for the players, for instance in soccer matches, that could be useful for estimating their fitness and strengths. Team level statistics can also be estimated from such analysis. This paper mainly focuses on some the challenges and opportunities presented by sport video analysis in computer vision. Specifically, we use our multi-camera setup as a framew…
Department of Computer Science, University of Wisconsin -Milwaukee, WI, USA IEEE Member, Uppsala, Sweden
Image features detection and description is a longstanding topic in computer vision and pattern recognition areas. The Scale Invariant Feature Transform (SIFT) is probably the most popular and widely demanded feature descriptor which facilitates a variety of computer vision applications such as image registration, object tracking, image forgery detection, and 3D surface reconstruction. This work introduces a Software as a Service (SaaS) based implementation of the SIFT algorithm which is freely available at http://siftservice.com for any academic, educational and research purposes. The service…
School of Computing Technologies, RMIT University（皇家墨尔本理工大学计算技术学院）
In this report we analysed a possibility of using computer vision techniques for automated reading of utility meters. In our study, we focused on two computer vision techniques: an open-source solution Tensorflow Object Detection (Tensorflow) and a commercial solution Anyline. This report extends our previous publication: We start with presentation of a structured analysis of related approaches. After that we provide a detailed comparison of two computer vision technologies, Tensorflow Object Detection (Tensorflow) and Anyline, applied to semi-automated reading of utility meters. In this paper…
Recently, several clustering algorithms have been used to solve variety of problems from different discipline. This dissertation aims to address different challenging tasks in computer vision and pattern recognition by casting the problems as a clustering problem. We proposed novel approaches to solve multi-target tracking, visual geo-localization and outlier detection problems using a unified underlining clustering framework, i.e., dominant set clustering and its extensions, and presented a superior result over several state-of-the-art approaches.
The number of road vehicles significantly increased in recent decades. This trend accompanied a build-up of road infrastructure and development of various control systems to increase road traffic safety, road capacity and travel comfort. In traffic safety significant development has been made and today's systems more and more include cameras and computer vision methods. Cameras are used as part of the road infrastructure or in vehicles. In this paper a review on computer vision systems in vehicles from the stand point of traffic engineering is given. Safety problems of road vehicles are presen…
Vanderbilt University（范德堡大学）；Vanderbilt University Medical Center（范德堡大学医学中心）；Siemens Healthineers（西门子医疗）
Although deep learning prediction models have been successful in the discrimination of different classes, they can often suffer from poor calibration across challenging domains including healthcare. Moreover, the long-tail distribution poses great challenges in deep learning classification problems including clinical disease prediction. There are approaches proposed recently to calibrate deep prediction in computer vision, but there are no studies found to demonstrate how the representative models work in different challenging contexts. In this paper, we bridge the confidence calibration from …
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek（奥西耶克电气工程、计算机科学与信息技术学院）
Visually impaired persons have significant problems in their everyday movement. Therefore, some of our previous work involves computer vision in developing assistance systems for guiding the visually impaired in critical situations. Some of those situations includes crosswalks on road crossings and stairs in indoor and outdoor environment. This paper presents an evaluation framework for computer vision-based guiding of the visually impaired persons in such critical situations. Presented framework includes the interface for labeling and storing referent human decisions for guiding directions an…
We are proceeding towards the age of automation and robotic integration of our production lines [5]. Effective quality-control systems have to be put in place to maintain the quality of manufactured components. Among different quality-control systems, vision-based inspection systems have gained considerable amount of popularity [8] due to developments in computing power and image processing techniques. In this paper, we present a vision-based inspection system (VBI) as a quality-control system, which not only detects the presence of defects, such as in conventional VBIs, but also leverage deve…
We show the closed-form solution to the maximization of trace(A'R), where A is given and R is unknown rotation matrix. This problem occurs in many computer vision tasks involving optimal rotation matrix estimation. The solution has been continuously reinvented in different fields as part of specific problems. We summarize the historical evolution of the problem and present the general proof of the solution. We contribute to the proof by considering the degenerate cases of A and discuss the uniqueness of R.
Computer Vision, either alone or combined with other technologies such as radar or Lidar, is one of the key technologies used in Advanced Driver Assistance Systems (ADAS). Its role understanding and analysing the driving scene is of great importance as it can be noted by the number of ADAS applications that use this technology. However, porting a vision algorithm to an embedded automotive system is still very challenging, as there must be a trade-off between several design requisites. Furthermore, there is not a standard implementation platform, so different alternatives have been proposed by …
University of Bristol（布里斯托大学）；Zalando SE（Zalando公司）；Occidental College（西方学院）；Cornell University（康奈尔大学）；Sandia National Laboratories（桑迪亚国家实验室）；Microsoft（微软）；University of Oxford（牛津大学）；Simon Fraser University（西蒙弗雷泽大学）
In this paper we present the details of Women in Computer Vision Workshop - WiCV 2020, organized in alongside virtual CVPR 2020. This event aims at encouraging the women researchers in the field of computer vision. It provides a voice to a minority (female) group in computer vision community and focuses on increasingly the visibility of these researchers, both in academia and industry. WiCV believes that such an event can play an important role in lowering the gender imbalance in the field of computer vision. WiCV is organized each year where it provides a.) opportunity for collaboration with …
Toyota Technological Institute at Chicago（芝加哥丰田技术研究院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Optimization within a layer of a deep-net has emerged as a new direction for deep-net layer design. However, there are two main challenges when applying these layers to computer vision tasks: (a) which optimization problem within a layer is useful?; (b) how to ensure that computation within a layer remains efficient? To study question (a), in this work, we propose total variation (TV) minimization as a layer for computer vision. Motivated by the success of total variation in image processing, we hypothesize that TV as a layer provides useful inductive bias for deep-nets too. We study this hypo…
Recent technological advances have made lightweight, head mounted cameras both practical and affordable and products like Google Glass show first approaches to introduce the idea of egocentric (first-person) video to the mainstream. Interestingly, the computer vision community has only recently started to explore this new domain of egocentric vision, where research can roughly be categorized into three areas: Object recognition, activity detection/recognition, video summarization. In this paper, we try to give a broad overview about the different problems that have been addressed and collect a…
University of Florence（佛罗伦萨大学）；Princeton University（普林斯顿大学）；UC Berkeley（加州大学伯克利分校）；Occidental College（occidental学院）；University of Oxford（牛津大学）；Universitat Politecnica de Catalunya（加泰罗尼亚理工大学）
In this paper we present the Women in Computer Vision Workshop - WiCV 2019, organized in conjunction with CVPR 2019. This event is meant for increasing the visibility and inclusion of women researchers in the computer vision field. Computer vision and machine learning have made incredible progress over the past years, but the number of female researchers is still low both in academia and in industry. WiCV is organized especially for the following reason: to raise visibility of female researchers, to increase collaborations between them, and to provide mentorship to female junior researchers in…
Dalian University of Technology（大连理工大学）；Microsoft Research Asia（微软亚洲研究院）；The Chinese University of Hong Kong（香港中文大学）
Many computer vision and image processing problems can be posed as solving partial differential equations (PDEs). However, designing PDE system usually requires high mathematical skills and good insight into the problems. In this paper, we consider designing PDEs for various problems arising in computer vision and image processing in a lazy manner: \emph{learning PDEs from real data via data-based optimal control}. We first propose a general intelligent PDE system which holds the basic translational and rotational invariance rule for most vision problems. By introducing a PDE-constrained optim…
Towards a Better Understanding of the Computer Vision Research Community in Africa
University of California, Davis（加州大学戴维斯分校）；German University in Cairo（开罗德国大学）；Nile University（尼罗河大学）；University College London（伦敦大学学院）；University of Angers（昂热大学）；University of Sfax（斯法克斯大学）；Ashesi University（阿希西大学）
Indian Institute of Space Science and Technology（印度空间科学技术学院）
In this work, we try to implement Image Processing techniques in the area of autonomous vehicles, both indoor and outdoor. The challenges for both are different and the ways to tackle them vary too. We also showed deep learning makes things easier and precise. We also made base models for all the problems we tackle while building an autonomous car for Indian Institute of Space science and Technology.
Solving problems with Artificial intelligence in a competitive manner has long been absent in Bangladesh and Bengali-speaking community. On the other hand, there has not been a well structured database for Bengali Handwritten digits for mass public use. To bring out the best minds working in machine learning and use their expertise to create a model which can easily recognize Bengali Handwritten digits, we organized Bengali.AI Computer Vision Challenge.The challenge saw both local and international teams participating with unprecedented efforts.
This draft summarizes some basics about geometric computer vision needed to implement efficient computer vision algorithms for applications that use measurements from at least one digital camera mounted on a moving platform with a special focus on automotive applications processing image streams taken from cameras mounted on a car. Our intention is twofold: On the one hand, we would like to introduce well-known basic geometric relations in a compact way that can also be found in lecture books about geometric computer vision like [1, 2]. On the other hand, we would like to share some experience…
In this paper we discuss certain theoretical properties of algorithm selection approach to image processing and to intelligent system in general. We analyze the theoretical limits of algorithm selection with respect to the algorithm selection accuracy. We show the theoretical formulation of a crisp bound on the algorithm selector precision guaranteeing to always obtain better than the best available algorithm result.
