A robust background subtraction method for changing background

In this paper we propose a novel method for object tracking in video images. The method is based on image segmentation and pattern matching. All moving and still objects in video images can be detected accurately with the help of efficient image segmentation techniques. We propose a hybrid algorithm for image segmentation using the notion of Particle Swarm Optimization (PSO) and Fuzzy-C-Means (FCM) clustering techniques. The results obtained using segmentation of successive frames are exploited for pattern matching in a simple feature space. As a consequence, multiple moving and still objects in video images are tracked simultaneously. We perform simulation experiments on object tracking to validate the efficiency of our proposed algorithm. The algorithm outperforms the existing algorithm in context of accuracy and time complexity.

Ship detection and tracking is an essential requirement for maritime surveillance systems. Background subtraction is used for detecting moving objects in video images. Then the moving targets are segmented by an improved method using extended-maxima transform with an adaptive threshold. Furthermore, a compensation method is proposed so as not to miss target information due to a gradual change when target in or out of the field of view. And then the target will be tracked with an inter-frame correlation method. Finally, the centroids of the target region in each frame are obtained to perform a ship tracking. The experimental results demonstrate that the proposed method is very efficient. The approach could be applied to automatic video monitoring in sea port security, maritime transportation, and ocean engineering managements.

Recognition of moving objects in video images is mainly based on acquiring the target information in a certain time series. After image processing, relevant algorithms are used to get the internal features and effectively identify the target object. However, image background, noise, definition and other factors will have impacts on mobile object recognition. Therefore, the mobile objects in video images are more complicated than the static objects in the fixed images. The traditional convolutional neural network (CNN) uses gradient descent algorithm for learning and training, and uses gradient descent algorithm to determine the initial thresholds, weights, which may cause the training to fall into a local optimal state. Therefore, this paper proposes an improved adaptive genetic algorithm combined with CNN. The thresholds and weights of CNN can be optimized by using adaptive genetic algorithm (AGA), which can overcome the shortcomings of the original genetic algorithm such as slow convergence. Experimental results shows that the recognition accuracy rate of the experiment increased from 83.75% to 92%, the method can effectively improve the accuracy and efficiency of mobile object recognition.

This paper attempts to develop a segmentation algorithm applicable to the issue of recognizing objects in video images. The paper presents the steps of the algorithm with a discussion of techniques used in mathematical morphology, filtration and gradient methods. Also there were presented examples of the results of a verification researches.

This work presents hardware architecture to determine the position of objects in video images. The architecture was developed based on a programmable logic device, taking advantage of some characteristics of the standard video signals to achieve the real time operation requirements. A component-labeling algorithm is proposed to adapt the centroid determination process to the architecture. It is also presented an application example demonstrating the architecture's efficiency.

Multi-feature fusion based fast video flame detection

The purpose of the article is to develop a methodology for automating the detection and selection of moving objects. The detection and separation of moving objects based on impulse and recurrence neural networks simulation. The result of the work is a developed motion detector based on impulse and recurrence neural networks and an automated system developed on the basis of this detector for detecting and separating moving objects and is ready for practical application. The feasibility of integrating the developed motion detector with Emgu CV (OpenCV) image processing package, multimedia framework functions, and DirectShow application programming interface were investigated. The proposed approach and software for the detection and separating of moving objects in video images using neural networks can be integrated into more sophisticated specialized computer-aided video surveillance systems, IoT (Internet of Things), IoV (Internet of Vehicles), etc.

Digital image processing is an actual task in the digital communication systems, IP-telephony and video conferencing, in digital television, and video surveillance. Digital processing of large video images takes a lot of time, especially if it happens in a real-time system. And, processing speed plays an important role in recognition of objects in video images received from IP-cameras in real time. This requires the use of modern technologies, and fast algorithms that increase the acceleration of digital image processing. Acceleration problems have not been fully resolved till present. Today's realities are such that the development of accelerated image processing programs requires a good knowledge of parallel and distributed computing. Both of these areas are united by the fact that both parallel and distributed software consists of several processes that together solve one common problem. This article proposes an accelerated method for the tasks of recognizing objects in video images received from IP-cameras using parallel and distributed computing technologies

By the localization and recognition of human moving target in video image, combined with the information of human motion feature in video image, the moving target localization and visual reconstruction is realized, this paper analyzes the feature quantity of moving objects in video image, improves the training level, and proposes a moving objects positioning technology of video image based on computer vision and 3D feature point reconstruction. According to the moving feature position of human body, the 3D information modeling and image acquisition of moving target is carried out by using video information acquisition and spatial feature scanning methods. The moving feature points of the collected moving target video image are calibrated and arranged, and the 3D edge outlines feature point set of human skeleton is extracted and represented as a high dimensional vector to form the regular feature database of moving target video image. The moving points in the regular feature database of moving target video image are fusion to realize the reconstruction of moving target video image and the location of moving target. The simulation results show that the method has good real-time and accuracy in moving target location of video image, has strong ability of 3D marking of human moving points, and has high accuracy of extracting moving motion features.

A new algorithm for segmenting and tracking deformable (shape-changing) linear (thin and long with negligible diameter) objects in video images is presented. The core of the algorithm is to detect the two boundary curves of a deformable linear object within adaptive tracking windows. The boundaries are found by analyzing the gray value gradients within the tracking windows, The algorithm provides a robust tracking of the shape- and width-changing object by using a fuzzy estimation of the object's membership function at the tracked points. The result of the segmentation is a list of base describing the shape of the object. This list is used to define features for shape change detection. For the feature analysis, we propose an algorithm which works well for several classes of feature curves. Experiments on robotic applications using both algorithms show promising results.

The variant of representation of various objects on video images in the form of samples of space-subband vectors is resulted. The technique of estimation of differences of parameters of distribution of multidimensional space-subband vectors of objects image is given. As indicators of closeness of two regions of localization of space-subband vectors of different objects, the vector of modules of difference of eigenvalues of corresponding spectral matrices of different objects, received from corresponding subband covariance matrices of objects, is used. Experimental estimations of differences in localization regions of different objects of Copter type using their video images are given. It is shown that when there is an obvious external similarity of objects, the areas of their localization differ significantly in size and orientation. It is shown that the localization region parameters of object vectors are practically invariant to object rotations on the image. The possibility of using spatially sub-band vectors and their estimates to build the decisive rules for the recognition of different objects on video images is shown.

This paper addresses our proposed algorithm to automatically segment out moving objects in video images. The algorithm is based on the region-based frame difference and adjusted background subtraction. An adaptive threshold technique is employed to choose the threshold value to segment the moving foreground objects from the still background. The experimental results demonstrate that both the accuracy and processing speed are very promising. Furthermore, the algorithm is robust to the changes of lighting condition and can be applied for the practical use.

We propose a grouping algorithm for tracking and recognition of complex objects in video images. The algorithm is based on region-growing image segmentation for dividing each image into its constituent elements or segments and feature matching using the characteristic features of these elements. All segments in video images, which can be viewed as simple objects, can be detected and tracked with this algorithm no matter whether they are moving or not. But, for complex-object tracking and recognition, it is additionally necessary to group all elements belonging to these complex objects based on common characteristic features. As a result of the grouping method, the proposed algorithm is able to detect and track moving complex objects like e.g. cars in video images. This paper describes the proposed algorithm in detail and verifies its capabilities by simulation results with MATLAB [1].

Reference objects in video images can be used to indicate urban waterlogging depths. The detection of reference objects is the key step to obtain waterlogging depths from video images. Object detection models with convolutional neural networks (CNNs) have been utilized to detect reference objects. These models require a large number of labeled images as the training data to ensure the applicability at a city scale. However, it is hard to collect a sufficient number of urban flooding images containing valuable reference objects, and manually labeling images is time-consuming and expensive. To solve the problem, we present a method to synthesize image data as the training data. Firstly, original images containing reference objects and original images with water surfaces are collected from open data sources, and reference objects and water surfaces are cropped from these original images. Secondly, the reference objects and water surfaces are further enriched via data augmentation techniques to ensure the diversity. Finally, the enriched reference objects and water surfaces are combined to generate a synthetic image dataset with annotations. The synthetic image dataset is further used for training an object detection model with CNN. The waterlogging depths are calculated based on the reference objects detected by the trained model. A real video dataset and an artificial image dataset are used to evaluate the effectiveness of the proposed method. The results show that the detection model trained using the synthetic image dataset can effectively detect reference objects from images, and it can achieve acceptable accuracies of waterlogging depths based on the detected reference objects. The proposed method has the potential to monitor waterlogging depths at a city scale.

A new algorithm for segmenting and tracking deformable (shape-changing) linear (thin and long with negligible diameter) objects in video images is presented. The core of algorithm is to detect the two boundary curves of a deformable linear object within adaptive tracking windows. The boundaries are found by analyzing the gray value gradients within the tracking windows. The algorithm allows moderate changes in the image brightness by introducing tolerance parameters to the algorithm. It also provides a robust tracking of the shape- and width-changing object by using a fuzzy estimation of the object's membership function at the tracked points. The result describes the shape of the object and is used to define features for shape change detection.