Data-Driven Foreground Object Detection from a Non-stationary Camera

This paper presents a hybrid pixel-based background (HPB) model, which is constructed by single stable record and multi-layer astable records after initial learning. The image foreground object detection must face the problems of moving background, illumination changes, chaotic, etc. in real word applications. In our approach, the HPB model can be used for background subtraction to extract objects precisely in various complex scenes. Using the multi-layer astable records, we also propose the homogeneous background subtraction that can detect the foreground object with less record memory. Based on the benchmark videos, the experimental results show that single stable and 3-layer multi-layer astable records can be enough for background model construction and then updated quickly to overcome the background variation. The proposed approach can improve the averages Error Rate of foreground object detection up to 86% when comparing with the latest works.

Processing optimization of digital radiographs requires the knowledge of the location and characteristics of both diagnostically relevant and irrelevant image regions. An algorithm has been developed that can automatically detect and extract foreground, background, and anatomy regions from a digital radiograph. This algorithm is independent of exam-type information and can deal with multiple-exposed computed radiography (CR) images. First, the image is subsampled, and the processing is done on the sub-sampled image to improve subsequent processing efficiency and reduce algorithm dependency on image noise and detector characteristics. Second, an initial background is detected using adaptive thresholding on the cumulative histogram of significant transition pixels and an iterative process, based on background variance. Third, foreground detection is conducted by: (1) classifying all significant transitions using a smart-edge detection, (2) delineating all lines that are possible collimation blades using Hough transform, (3) finding candidate partition blade pairs if the image has several radiation fields, (4) partitioning the image into sub-images containing only one radiation field using a divide-and-conquer process, and (5) identifying the best collimation for each sub-image from a tree-structured hypothesis list. Fourth, the background is regenerated using a region-growing process from identified background “seeds.” Fifth, the background and foreground regions are merged and removed; the rest of the image is labeled and those large, connected regions are identified as anatomy regions. The algorithm has been trained and tested separately with two image sets from a wide variety of exam types. Each set consists of more than 2700 CR images acquired with KODAK DIRECTVIEW CR 800 Systems. The overall success rate in detecting both foreground and background is 97%.

We introduce the notion of semantic background subtraction, a novel framework for motion detection in video sequences. The key innovation consists to leverage object-level semantics to address the variety of challenging scenarios for background subtraction. Our framework combines the information of a semantic segmentation algorithm, expressed by a probability for each pixel, with the output of any background subtraction algorithm to reduce false positive detections produced by illumination changes, dynamic backgrounds, strong shadows, and ghosts. In addition, it maintains a fully semantic background model to improve the detection of camouflaged foreground objects. Experiments led on the CDNet dataset show that we managed to improve, significantly, almost all background subtraction algorithms of the CDNet leaderboard, and reduce the mean overall error rate of all the 34 algorithms (resp. of the best 5 algorithms) by roughly 50% (resp. 20%).

Visual discomfort is one of the most frequent complaints of the viewers when watching stereo images or videos. It has been the subject of considerable research in relation to stereo display system. To predict the effects induced by three-dimensional contents on visual discomfort, a new objective visual comfort assessment (VCA) method of stereo image is proposed based on scene mode classification. Scene modes are defined and real scenes are classified into ten kinds of scene modes according to the properties of two aspects. These aspects include the crossed / uncrossed disparity type of foreground object (FGO) and background region (BGR), and the other is the whether locate on zone of comfortable viewing of FGO and BGR in scene. In the process of mode classification and selection, disparity map is first utilized to segment stereo image into FGOs and BGRs adaptively. Then, some features, including disparity angle of both the FGOs and BGRs, and width angle of FGOs, are utilized to build an objective VCA models in various scene modes. The experimental results show that the proposed method performs higher assessment accuracy than some state-of-the-art methods.

Mobile edge computing provides low-latency service computing for the Internet of Things (IoT). Considering the computational cost of high-quality image steganography in practical mobile applications, we believe that mobile edge computing could provide real-time service computing for covert communications. As a mainstream approach to convert communication, image steganographic algorithms prefer to hide secret data in well-textured regions in order to reduce the possibility of being detected. Recently, the generative adversarial networks (GAN) has become one of the most popular architectures for image steganography. However, the GAN-based image steganographic algorithms directly conduct the secret data embedding on the entire cover images and do not sufficiently take the regional texture complexity into account, which will compromise the anti-detection ability. To address this issue, we propose a novel image steganographic algorithm on the generated foreground object region with rich textures. More specifically, the foreground object region is generated onto a given cover image by the GAN, and the secret data is embedded in the foreground object region simultaneously during the generation of the region. The experimental results show that the proposed method can resist steganalysis effectively without significant degradation of image quality and achieve real-time processing.

The problem of foreground detection in real‐time video surveillance applications is addressed. Proposes is a framework, which is computationally cheap and has low memory requirements. It combines two simple processing blocks, both of which are essentially background subtraction algorithms. The main novelty of the approach is a combination of an autoregressive moving average filter with two background models having different adaptation speeds. The first model, having a lower adaptation speed, models long‐term background and detects foreground objects by finding areas in the current frame which significantly differ from the proposed background model. The second model, with a higher adaptation speed, models the short‐term background and is responsible for finding regions in the scene with a high foreground object activity. The final foreground detection is built by combining the outputs from these building blocks. The foreground obtained by the long‐term modelling block is verified by the output of the short‐term modelling block, i.e. only the objects exhibiting significant motion are detected as real foreground objects. The proposed method results in a very good foreground detection performance at a low computational cost.

Background subtraction is a widely used technique for detecting moving objects in image sequences. Very often background subtraction approaches assume the availability of one or more clear frames (i.e., without foreground objects) at the beginning of the image sequence in input. This strong assumption is not always correct, especially when dealing with dynamic background. In this paper, we present the results of an on-line and real-time background initialization method, called IMBS, which generates a reliable initial background model even if no clear frames are available. The accuracy of the proposed approach is calculated on a set of seven publicly available benchmark sequences. Experimental results demonstrate that IMBS generates accurate background models with respect to eight different quality metrics.

Real-time foreground object extraction is an important subject for computer vision applications. Model-based background subtraction methods have been used to extract the foreground objects. Different from previous methods, this paper introduces a hybrid codebook-based background subtraction method by combining the mixture of Gaussian (MOG) with the codebook (CB) method. We propose an ellipsoid CB model for modeling the dynamic background with highlight and shadow, and develop a modified shadow/ highlight removal method to overcome the influence of illumination change. Our method can avoid extracting the false foreground pixels (e.g., dark background) or missing the real foreground pixels (e.g., bright foreground). Finally, we have done two experiments to compare the performance of our method with the others based on [18] and the change detection benchmark dataset provided in CVPR 2011, respectively.

In this paper, we propose a novel background subtraction method which enables reliable detection of foreground objects in a long surveillance video stream. Recently, although much progress has been made in the field of background subtraction, there are still challenging scenarios (e.g., high frequency motion of dynamic texture, non-stationary motion of camera, abrupt changes of illumination, etc.) in the long surveillance videos in which even state-of-the-art methods are often prone to fail. To cope with these challenging scenarios effectively, in the proposed method, a background model is initialized in a low-dimensional subspace and then updated periodically based on a novel recursive on-line ${(2{\rm D})}^2{\rm PCA}$ algorithm developed in this paper. Moreover, a threshold map is also updated in a scene-adaptive manner for labeling each pixel in a scene either foreground or background independently. Based on this on-line framework, the background of a surveillance video stream is reconstructed over time, thereby facilitating the detection of foreground objects reliably. In extensive experiments, we demonstrate that the proposed background subtraction method can cope with the aforementioned challenging scenarios more favorably than the state-of-the-art methods.

Cut set-based Dynamic Key frame selection and Adaptive Layer-based Background Modeling for background subtraction

Non-parametric representation of pixel intensity distribution is quite effective to construct proper background model and to detect foreground objects accurately. However, from the viewpoint of practical application, the computation cost of the distribution estimation should be reduced. In this paper, we present fast estimation of the probability density function (PDF) of pixel value using Parzen density estimation and foreground object detection based on the estimated PDF. Here, the PDF is computed by partially updating the PDF estimated at the previous frame, and it greatly reduces the computation cost of the PDF estimation. Thus, the background model adapts quickly to changes in the scene and, therefore, foreground objects can be robustly detected. Several experiments show the effectiveness of our approach.

Recovering low-rank and sparse matrix based on the truncated nuclear norm

Background modeling and foreground object detection are crucial techniques for embedded image surveillance systems. The popular and accurate methods are mostly pixel based, taking up more memory and requiring longer execution times. Thus, these techniques are not suitable for embedded platforms. This paper presents a block-based major color background modeling and a foreground detection algorithm that possesses efficient processing and low memory requirement in a complex scene, making them feasible for embedded platforms. Our proposed approach consumes 37% less memory and increases accuracy by at least 2.5% compared to other existing methods. Last, implementing the object detection algorithm on the 2.83GHz CPU, we can achieve 26 frames per second for the benchmark video with image size 768×576.

Background subtraction in real applications: Challenges, current models and future directions

Human pose assessment from video plays an important role in various applications such as measuring physical exercises, sign language recognition and full body gesture control. For example, it can be the basis for yoga, dance, and exercise applications. It can also enable the overview of digital content and information at the top of the physics world in augmented reality. Here we propose, Newfangled 3d Human pose estimation using MediaPipe with foreground object detection (HPEM), model uses MediaPipe library. MediaPipe pose is applied for faster pose estimation of humans, prior in which the humans and other objects are detected and classified in foreground object detection. This paper conducted various experiments, and the results proved superior and the success of this algorithm.