Distortion Classification in Computer Vision Applications: Current Progress, Challenges, and Perspectives

Artificial Intelligence in the American Healthcare Industry: Looking Forward to 2030

Adaptive graph construction using data self-representativeness for pattern classification

Computer vision methods are wide-spread techniques mostly used for detecting cracks on structural components, extracting information from traffic flows, and analyzing safety in construction processes. In recent years, with increasing usage of machine learning techniques, computer vision applications are supported by machine learning approaches. So, several studies were conducted using machine learning techniques to apply image processing. As a result, this chapter offers a scientometric analysis for investigating current literature of image processing studies for civil engineering field in order to track the scientometric relationship between machine learning and image processing techniques.

Foreground extraction is an important and challenging problem in many applications of computer vision. Most existing algorithms either require user intervention as hard constraints or demand special inputs for extra information. Thus, an automatic foreground extraction algorithm from a single image is proposed in this paper. A Gaussian image pyramid is constructed and the gradient vector flow (GVF) snake is adopted at the coarsest level to generate a rough contour of the object which is then upsampled and serves as the initial input to GVF snake in the next level. This process repeats until the estimated contour is propagated to the finest level. Based on the result in the finest level, a binary mask can be generated accordingly and becomes the initial constraint in the segmentation. The proposed segmentation step includes two novel schemes, which simulate the Latent Dirichlet Allocation (LDA) generative model and a probabilistic stochastic process called Chinese restaurant process. With these mechanisms, the Gaussian Mixture Models adaptively determine the number of components for foreground and background individually. As a result, the proposed method is expected to not only produce a satisfactory result of foreground extraction automatically with more robustness and adaptation but also serve as a good preprocessing to improve the performance and accuracy for tasks in computer vision.

Video Analytics analyzes the video content and adds brains to the eyes which means analytics to the camera. It extracts contents from the video by monitoring the video in real-time. Normal and Abnormal human activity detection using deep learning models is a challenging task in computer vision. The detection of the same will help in detecting crime scenes which will help in preventing treacherous actions Proposed method focuses on classifying normal activities for humans in real-time scenarios. The pre-processing technique for redundant frame detection, elimination, and training the model e?ciently using Convolutional Neural Network for classifying the activities is the main research contribution. The proposed method shows improvement in accuracy as compared to the reference method which can be further implemented for on edge embedded platforms for real-time applications

Dehazing from a single hazy image has been a crucial task for both computer vision and computational photography applications. While various methods have been proposed in the past decades, estimation of the transmission map remains a challenging problem due to its ill-posed nature. Moreover, because of the inevitable noise generated during imaging process, visual artifacts could be extremely amplified in the recovered scene radiance in densely hazy regions. In this paper, a novel variational regularized single image dehazing (VRD) approach is proposed to accurately estimate the transmission map and suppress artifacts in the recovered haze-free image. Firstly, an initial transmission is coarsely estimated based on a modified haze-line model. After that, in order to preserve the local smoothness property and depth discontinuities in the transmission map, a novel non-local Total Generalized Variation regularization is introduced to refine the initial transmission. Finally, a transmission weighted non-local regularized optimization is proposed to recover a noise suppressed and texture preserved scene radiance. Compared with the state-of-the-art dehazing methods, both quantitative and qualitative experimental results on both real-world and synthetic hazy image datasets demonstrate that the proposed VRD method is capable of obtaining an accurate transmission map and a visually plausible dehazed image.

Moving Object Segmentation (MOS) is a fundamental task in computer vision. Due to undesirable variations in the background scene, MOS becomes very challenging for static and moving camera sequences. Several deep learning methods have been proposed for MOS with impressive performance. However, these methods show performance degradation in the presence of unseen videos; and usually, deep learning models require large amounts of data to avoid overfitting. Recently, graph learning has attracted significant attention in many computer vision applications since they provide tools to exploit the geometrical structure of data. In this work, concepts of graph signal processing are introduced for MOS. First, we propose a new algorithm that is composed of segmentation, background initialization, graph construction, unseen sampling, and a semi-supervised learning method inspired by the theory of recovery of graph signals. Second, theoretical developments are introduced, showing one bound for the sample complexity in semi-supervised learning, and two bounds for the condition number of the Sobolev norm. Our algorithm has the advantage of requiring less labeled data than deep learning methods while having competitive results on both static and moving camera videos. Our algorithm is also adapted for Video Object Segmentation (VOS) tasks and is evaluated on six publicly available datasets outperforming several state-of-the-art methods in challenging conditions.

Tracking is regarded as one of the most fundamental tasks in computer vision. It is used in many computer vision applications in fields such as surveillance, robotic navigation and 3D reconstruction to name but a few. Despite decades of research, the goal of fully automatic tracking of arbitrary types of objects in real world conditions is still an open problem. In this paper, we take a step toward the goal of general real-world tracking, and demonstrate a unified generative model for Bayesian multifeature, adaptive target tracking, or AMFT for short (Adaptive Multiple Feature Tracker). We derive a unified generative model for multi-sensory adaptive tracking which cleanly integrates tracking and the modeling of appearance change across multiple features in the same framework. The unified multi-feature observation model ensures that if one feature is not confident, e.g., color after an object crosses into a region of shadow, it is automatically down-weighted in its contribution to the appearance model update. In this way, without pre-training of specific object models, we achieve an extensible tracker for general object types, robust to real-world problems of clutter, appearance/lighting change and target model drift. The standard modeling assumptions made by a non-adaptive generative model are illustrated by the probabilistic graphical model in Figure 1(a). The unknown target state (e.g., location, size, velocity) xt is assumed to change with time t according to some process parameterized by A. At every time t, we make some noisy observations zt of the target xt (e.g., raw image or color histograms). The target is then tracked online by computing the posterior, p(xt |z1:t) over the true target location recursively. In the case of the Kalman filter (KF), all the distributions involved are Gaussian. In the case of the particle filter (PF), all the distributions involved are represented non-parametrically by a set of samples [1]. The true target model, e.g., the appearance or color histogram to search for, is assumed to be part of the parameters H, i.e., it is known and fixed by an operator or initialized by some external process. In many cases however, the true appearance of the target H may change significantly in time, e.g., the appearance changes when a subject moves between shade and sunlight. This is the case for outdoor surveillance applications and is the motivation for this research. Adaptive trackers [2, 3, 4, 6] have been proposed to update the target appearance online in various heuristic ways. We can formalise this more general modeling assumption generatively, by the generalized dynamic Bayesian network illustrated in Figure 1(b). In contrast to Figure 1(a), the true target model which was previously included in the fixed parameters H, is now included as the the initial condition y0 of a dynamic latent variable yt , formalizing the modeling assumption that the target appearance can change over time. In addition to the target state xt , the target appearance yt will therefore be incrementally and recursively updated as part of the process of inferring the latent variables in this model p(xt ,yt |z1:t). The latent space is of course now greatly expanded, and poses a more challenging inference problem than that of Figure 1(a). In Section 2 of the paper, we detail the specific parametric form of the model and an efficient inference algorithm. We evaluate our method (AMFT) against three contemporary trackers: A standard single feature particle filter (PF), mean-shift (MS) [5] and incremental visual tracking (IVT) [4]. The PF and MS trackers are non-adaptive color-based trackers, while IVT aims for pose and illumination change robustness by performing online adaptation in a subspace appearance model. Note that the AMFT, PF and IVT trackers track object scale, but MS does not. We evaluated these methods on a series of challenging video clips exhibiting a wide variety of data and object types for tracking, including far-field indoor and outdoor pedestrians with and without carried objects, vehicle tracking, and near-field indoor face trackH 1 x2 x3

Toward designing intelligent PDEs for computer vision: An optimal control approach

Recent work in machine learning has significantly benefited semantic extraction tasks in computer vision, particularly for object recognition and image retrieval. We argue that the computer vision techniques that have been successfully applied in those settings can effectively be translated to other domains, such as audio. This claim is supported by recent results in music vs. speech classification, structure from sound, robust music identification and sound object recognition. This paper focuses on two such audio applications and demonstrates how ideas from computer vision map naturally to these problems.

Object detection is a hot topic in the field of machine vision. In the innovation and development of modern technology, the integration of machine learning, pattern recognition, image processing and other multidisciplinary knowledge can effectively solve the image problem. In computer vision and digital image processing technology in the development of innovation, target detection theory research and practical application has achieved excellent results, although there are many problems need to solve, but a lot of new technology and new method has yet to be developed, so countries scholars gradually strengthen the scientific research strength, strong adaptability are put forword technique, high precision and good robustness. In this paper, based on the understanding of the research status of object detection, according to the basic theory of image processing, the application of computer vision in object detection is analyzed. The final experimental results show that shadow detection, image enhancement and filtering methods can effectively improve the application effect.

InceptB: A CNN Based Classification Approach for Recognizing Traditional Bengali Games

The design and development of image processing units (IPUs) has traditionally involved trade-offs between cost, real-time properties, portability, and ease of programming. A standard PC can be turned into an IPU relatively easily with the help of readily available computer vision libraries, but the end result will not be portable, and may be costly. Similarly, one can use field programmable gate arrays (FPGAs) as the base for an IPU, but they are expensive and require hardware-level programming. Finally, general purpose embedded hardware tends to be under-powered and difficult to develop for due to poor support for running advanced software. In recent years a new option has surfaced: single-board computers (SBCs). These generally inexpensive embedded devices would be attractive as a platform on which to develop IPUs due to their inherent portability and good compatibility with existing computer vision (CV) software. However, whether their performance is sufficient for real-time image processing has thus far remained an open question. Most SBCs (especially the ultra-low-cost ones which we target) do not offer CUDA/OpenCL support which makes it difficult to port GPU-based CV applications. In order to utilize the full power of the SBCs, their GPUs need to be used. In our attempts at doing this, we have observed that the CV algorithms which an IPU uses have to be re-designed according to the OpenGL support available on these devices. This work presents a framework where a selection of CV algorithms have been designed in a way that they optimize performance on SBCs while still maintaining portability across devices which offer OpenGL ES 2.0 support. Furthermore, this paper demonstrates an IPU based on a representative SBC (namely the Raspberry Pi) along with two CV applications backed by it. The robustness of the applications as well as the performance of the IPU are evaluated to show that SPCs can be used to build IPUs capable of producing accurate data in real time. This opens the possibilities of large scale economically deployment of vision system especially in remote and barren lands. Finally, the software developed as a part of this work has been released open source.

Advanced Driver Assistance Systems (ADAS) have emerged as a critical technology in enhancing vehicle safety, providing convenience to drivers, and facilitating the transition toward fully autonomous vehicles. The core of these systems relies heavily on computer vision (CV) technologies, which enable vehicles to interpret and understand their surrounding environment in real time. The integration of computer vision in ADAS allows vehicles to recognize and process various objects such as pedestrians, vehicles, traffic signs, and lane markings, significantly improving both safety and the driving experience. In this paper, we explore the pivotal role of computer vision in the development and implementation of ADAS in autonomous vehicles. We begin by reviewing the evolution of ADAS, detailing the different sub-systems such as lane departure warning, automatic emergency braking, adaptive cruise control, and parking assistance, all of which depend on sophisticated image processing techniques. Furthermore, the paper examines the intersection of computer vision with other emerging technologies such as machine learning, deep learning, and sensor fusion. We discuss how these innovations enable ADAS to function more effectively in complex, dynamic environments. The methodology section focuses on cutting-edge algorithms used for object detection, semantic segmentation, and real-time image processing, which are integral to the functionality of modern ADAS. Additionally, we evaluate the challenges that computer vision systems face in real-world applications, including issues with sensor calibration, environmental conditions, computational limitations, and the integration of data from multiple sensors (e.g., cameras, LiDAR, radar). The paper also presents an analysis of the results obtained from various real-world implementations of ADAS technologies, highlighting improvements in driver safety and the reduction of traffic-related accidents. We explore the potential of computer vision in enabling fully autonomous driving by addressing the current gaps in technology and the advancements needed to close these gaps. Finally, the paper concludes with a discussion on the future of ADAS and the role of computer vision in realizing fully autonomous, reliable, and efficient transportation systems. We argue that continued research and development in computer vision, combined with innovations in deep learning and sensor technologies, are critical to advancing the capabilities and reliability of autonomous vehicles in the near future.

One of the most fundamental problems in image processing and computer vision is the inherent ambiguity that exists between texture edges and object boundaries in real-world images and video. Despite this ambiguity, many applications in computer vision and image processing often use image edge strength with the assumption that these edges approximate object depth boundaries. However, this assumption is often invalidated by real world data, and this discrepancy is a significant limitation in many of today's image processing methods. We address this issue by introducing a simple, low-level, and patch-consistency assumption that leverages the extra information present in video data to resolve this ambiguity. Through analyzing how well patches can be modeled by simple transformations over time, we can obtain an indication of which image edges correspond to texture edges versus object boundaries. Our approach is simple to implement and has the potential to improve a wide range of image and video-based applications by suppressing the detrimental effects of strong texture edges on regularization terms. We validate our approach by presenting results on a variety of scene types and directly incorporating our augmented edge map into existing image segmentation and optical flow applications, showing results that better correspond to object boundaries.