Approximate constraint generation for efficient structured boosting

Object detection is a hot topic with various applications in computer vision, e.g., image understanding, autonomous driving, and video surveillance. Much of the progresses have been driven by the availability of object detection benchmark datasets, including PASCAL VOC, ImageNet, and MS COCO. However, object detection on the drone platform is still a challenging task, due to various factors such as view point change, occlusion, and scales. To narrow the gap between current object detection performance and the real-world requirements, we organized the Vision Meets Drone (VisDrone2018) Object Detection in Image challenge in conjunction with the 15th European Conference on Computer Vision (ECCV 2018). Specifically, we release a large-scale drone-based dataset, including 8, 599 images (6, 471 for training, 548 for validation, and 1, 580 for testing) with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc. Featuring a diverse real-world scenarios, the dataset was collected using various drone models, in different scenarios (across 14 different cities spanned over thousands of kilometres), and under various weather and lighting conditions. We mainly focus on ten object categories in object detection, i.e., pedestrian, person, car, van, bus, truck, motor, bicycle, awning-tricycle, and tricycle. Some rarely occurring special vehicles (e.g., machineshop truck, forklift truck, and tanker) are ignored in evaluation. The dataset is extremely challenging due to various factors, including large scale and pose variations, occlusion, and clutter background. We present the evaluation protocol of the VisDrone-DET2018 challenge and the comparison results of 38 detectors on the released dataset, which are publicly available on the challenge website: http://www.aiskyeye.com/. We expect the challenge to largely boost the research and development in object detection in images on drone platforms.

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.

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

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

Deformable models are a useful tool in computer vision and computer graphics. A deformable model is a curve (in two dimensions) or a surface (in three dimensions), whose shape, position, and orientation are controlled through a set of parameters. Deformable models can represent manufactured objects, human faces and skeletons, and even bodies of fluid. In computer graphics, we use deformable models for animations and simulations, whereas in computer vision applications, such as tracking and fitting, deformable models help to restrict the family of possible solutions. We introduce the use of a directed acyclic graph (DAG) to describe the position and Jacobian of each point on the surface of deformable models. This data structure, combined with a topological description of the points, is simple, powerful, and extremely useful for both computer vision and computer graphics applications. We show a computer vision application, 3D deformable face tracking, and a computer graphics application, cyberglove data visualization and calibration.

Vision begins in eyes, but truly takes place in the brain. So, in today’s world with the best high-definition cameras, high-speed computers, and artificial intelligence, computer vision was introduced. Computer vision is one of the latest advancements in technology that helps on giving the abilities of vision and understanding of the environment to computers so that they can extract high-level understanding from digital images and videos.Autonomous vehicles are the application of computer vision with main motive of eliminating human errors and drive the vehicles with high precision and remove the efforts taken by a person to drive.This paper provides a proof of concept for implementing an autonomous vehicle with a vehicle behaviour prediction model. It will be implemented over a small scale on a RC-sized car. The car would traverse autonomously in a demo map where we can simulate dynamic conditions and assess the model’s performance accordingly.This is the main motivation behind the project. To create a completely autonomous system capable of navigating around on its own. Detect, identify and follow traffic signs, signals and rules. Take appropriate actions for dynamic conditions and avoid any sort of loss. Provide user with an application interface to experience a safe journey to selected destination.The proposed system will be using LiDAR for mapping the telemetry and detecting surroundings of the vehicle, a camera module to identify the objects detected, a development board with the deployed autonomous driving model, being the brains of all the operations, and actuators for moving the car around. The autonomous driving model to be deployed, will be trained using YOLO for object detection and identification, along with a vehicle behaviour prediction subsystem assisting the dynamic decision-making subsystem to take some decisions based on the prediction to reduce severity of certain accidents or even avoid them, before they happen.

n the last decade, there has been an active digitalization of industrial production based on rapidly developing information technologies, including artificial intelligence technologies. This is largely due to the development of deep learning methods and their applications in computer vision. Since the mid 2010s convolutional neural networks demonstrate exceptional efficiency in solving problems such as the detection, classification and segmentation of various objects. As a result, computer vision methods are beginning to be actively used in the problems of quality control of raw materials and finished products. All this applies to the mining industry. However, in the Russian scientific literature there are practically no systematic reviews of computer vision applications in this area. The present study aims to fill this gap. The paper provides a systematic review of the history of development and the current state of the methods and technologies of machine vision used in the mining industry for the analysis of solid materials, demonstrates the latest achievements in this area and examples of their application in the mining industry. The authors have analyzed 29 research papers in the field of application of computer vision in the mining industry and classified the stages of technology development from the mid-1980s, when computer vision was used without the use of machine learning, and ending with modern research based on the use of deep convolutional neural networks for solving problems of classification and segmentation. The effectiveness of the methods used is compared, their advantages and disadvantages are discussed, and forecasts are made for the development of computer vision methods in the mining industry in the near future. Examples are given showing that the use of convolutional neural networks made it possible to move to a qualitatively higher level of quality in solving problems of classification and segmentation as applied to the analysis of output volume, particle size distribution, including flakiness, angularity and roughness, dust and clay content, bulk density and emptiness, etc.

Intrinsic image decomposition is an important topic in computer vision and computer graphics applications. However, this is a challenging problem by adopting the information of a single image. Therefore, additional priors or supplementary information such as multiply images or user interactions are necessary to address this problem. In this paper, we propose a novel scheme to use multiple images for intrinsic image decomposition, based on a similar strategy in robust principal component analysis (RPCA). RPCA utilizes the fact that the reflectance layer is common in multiple lights of a scene, and attempts to decompose the data matrix constructed from input images into a low-rank matrix and a sparse matrix. This is possible if the sparse matrix is sufficiently sparse, which is often not the case in computer vision applications. Moreover, the weighting parameter between the low-rank and sparse matrices greatly affects the accuracy of the results, and tuning this parameter can be tricky. This paper proposes a rank-constrained PCA algorithm (RCPCA) for solving background recovering problems. Fixing the rank of the low-rank matrix to be 1 allows RCPCA to better recover the low-rank matrix from the data matrix. Comprehensive tests show that RCPCA produces more stable and accurate results than RP-CA.

This paper presents a novel framework for importance-aware adaptive data transmission, designed specifically for real-time computer vision (CV) applications where taskspecific fidelity is critical. An importance-weighted mean square error (IMSE) metric is introduced, assigning data importance based on bit positions within pixels and semantic relevance within visual segments, thus providing a task-oriented measure of reconstruction quality. To minimize IMSE under the total power constraint, a data-importance-aware waterfilling approach is proposed to optimally allocate transmission power according to data importance and channel conditions. Simulation results demonstrate that the proposed approach significantly outperforms margin-adaptive waterfilling and equal power allocation strategies, achieving more than 7 dB and 10 dB gains in normalized IMSE at high SNRs (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$&gt;10 ~\text{dB}$</tex>), respectively. These results highlight the potential of the proposed framework to enhance data efficiency and robustness in real-time CV applications, especially in bandwidth-limited and resource-constrained environments.

Today, Computer Vision is one of the most well-liked and critical research areas in the Computer Science field. Moving object detection is the first and foremost step in any computer vision applications. The detection of moving object in any computer vision application is a very critical task. The most widely used method for moving object detection is Frame differencing based background subtraction method. The most of the researchers address the various challenges of background subtraction algorithm to detect the object accurately, the segmentation of objects from non stationary objects is critical, adaptation of illumination changes and handling of camouflage and etc. But they are more CPU and I/O intensive one. Cloud Computing is the new buzz word in computer field which provides computational power on demand basis which requires the representation of e-science workflow model for such kind of large-scale scientific applications. There are four different types of scientific work flow models viz Montage, LIGO, SIPHT, and Cybershake are exist which are varied by either CPU intensive or I/O intensive application. But the Temporal frame differencing based real time object detection is both CPU and I/O intensive one. Hence which could not be expresses as a single workflow model for cloud computing. So, we proposed a hybrid workflow model (Montage and SIPHT) of temporal frame differencing algorithm for real time object detection and the performance of such workflow model is tested and analyzed in already existing scheduling algorithm in workflowsim.

Introduction. Many computer vision applications often use procedures for recognizing various shapes and estimating their dimensional characteristics. The entire pipeline of such processing consists of several stages, each of which has no clearly defined boundaries. However, it can be divided into low, medium, and high-level processes. Low-level processes only deal with primitive operations such as preprocessing to reduce noise, enhance contrast, or sharpen images. The processes of this level are characterized by the fact that there are images at the input and output. Image processing at the middle level covers tasks such as segmentation, description of objects, and their compression into a form convenient for computer processing. Middle-level processes are characterized by the presence of images only at the input, and only signs and attributes extracted from images are received at the output. High-level processing involves “understanding” a set of recognized objects and recognizing their interactions. Using the example of the developed software models for recognizing figures and estimating their characteristics, it is shown that the image processing process is reduced to transforming spatial image data into metadata, compressing the amount of information, which leads to a significant increase in the importance of data. This indicates that at the input of the middle level, the image should be as informative as possible (with high contrast, no noise, artifacts, etc.) because after the transformation of the spatial image data into metadata, no further the procedures are not able to correct the data obtained by the video sensors in the direction of improving or increasing the information content. Recognition of figures in an image can be realized quite efficiently through the use of the procedure for determining the contours of figures. To do this, you need to determine the boundaries of objects and localize them in the image, often the first step for procedures such as separating objects from the background, image segmentation, detection and recognition of various objects, etc. The purpose of the article is to study the image processing pipeline from the moment of image fixation to the recognition of a certain set of figures (for example, geometric shapes, such as a triangle, quadrilateral, etc.) in an image, the development of software models for recognizing figures in an image, determining the center of mass figures by means of computer vision. Results. We proposed and tested some variants of nonlinear estimating problem. The properties of such problems depend on value of regulating parameter. The dependence of estimation on value of parameter was studied. It was defined a range for parameter's value for which estimating problem gives adequate result for initial task. Numerical examples show how much volume of calculations reduces when using a dynamic branching tree. Conclusions. The results obtained can be used in many applications of computer vision, for example, counting objects in a scene, estimating their parameters, estimating the distance between objects in a scene, etc. Keywords: contour, segmentation, image binarization, computer vision, histogram.

english

991013340459703412 HKUST Electronic Theses Open-set recognition and its applications in computer vision by Jun Cen thesis 2024 1 online resource (xiv, 92 pages) : illustrations (chiefly color) Current deep learning models are trained to fit the training set distribution. Despite…Read more ›

The accurate understanding of occlusion region is critical for trustworthy estimation of optical flow to prevent the negative influence of occluded pixels on disocclusion regions. However, occlusion is the result of motion. In contrast, estimating accurate optical flow is necessary to locate reliable occlusions. Hence, one of the key challenges that required further exploration and research is the accuracy at the boundaries of the moving objects. This paper presents the work in process approach that can detect occlusion regions by using some constraints such as pixel-wise coherence, segment-wise confidence and edge-motion coherence. Comparing to the previous methods, our method achieves the same efficiency by solving only one Partial Differential Equation (PDE) problem. The proposed method is faster and provides better coverage rates for occlusion regions than variation techniques in various numbers of benchmark datasets. With these improved results, we can apply and extend our approach to a wider range of applications in computer vision, such as: motion estimation, object detection and tracking, robot navigation, 3D reconstruction, image registration.

Detecting small objects in challenging lighting conditions is a critical task with broad applications in computer vision, surveillance, and medical imaging. Small objects are especially vulnerable to detection errors due to their size and the significant impact of varying lighting conditions, such as low-light environments or high glare. Furthermore, the lack of a benchmark dataset that accurately simulates real-world scenarios makes it difficult to evaluate the performance of detection models in such conditions. In the proposed paper, we address these challenges by developing a comprehensive dataset specifically designed for car logo detection under diverse and challenging lighting environments. The dataset incorporates variations in lighting, viewing angles, and object scales to replicate real-world conditions. We also introduce a detection pipeline integrating EnlightenGAN for low-light image enhancement, which preserves fine details and textures, and YOLOv7 and YOLOv8 for improved detection accuracy. By enhancing image quality and refining object detection models, our approach significantly boosts the detection of small car logos, even in challenging lighting scenarios where traditional models tend to fail. Experimental results show that YOLOv8 outperforms YOLOv7 by approximately 7%, with YOLOv8 achieving a mean Average Precision (mAP) of 73.3% on the augmented dataset compared to 68.4% for the original dataset and 67.2% for the processed images. These results validate the effectiveness of GAN-based enhancement techniques in preserving small object details and improving detection performance. Additionally, introducing a new dataset and benchmark provides a valuable resource for future research in small object detection under complex lighting conditions.