Hierarchical GMM to handle sharp changes in moving object detection

This work proposes a fast background learning algorithm for foreground detection under changing illumination. Gaussian Mixture Model (GMM) is an effective statistical model in background learning. We first focus on Titterington's online EM algorithm that can be used for real-time unsupervised GMM learning, and then advocate a deterministic data assignment strategy to avoid Bayesian computation. The color of the foreground is apt to be influenced by the environmental illumination that usually produce undesirable effect for GMM updating, however, a collinear feature of pixel intensity under changing light is discovered in RGB color space. This feature is afterward used as a reliable clue to decide which part of mixture to update under changing light. A foreground detection step proposed in early version of this work is employed to extract foreground objects by comparing the estimated background model with the current video frame. Experiments have shown the proposed method is able to achieve satisfactory static background images of scenes as well as is also superior to some mainstream methods in detection performance under both indoor and outdoor scenes.

Moving object detection is vitally used in video surveillance applications. Traditional Gaussian mixture model (GMM) based background subtraction (BGS) methods are usually performs well when background is stationary. However, they require parameter tuning to deal with dynamic backgrounds, whose background pixel values change over time. Particularly, the threshold which determines the pixels associated with moving objects from the resultant of BGS. To tackle this problem there is no ultimate solution. Considering that, this paper intents to present a novel idea to update the threshold of GMM based BGS with respect to color distortion, similarity and illumination measures in pixel level. Extensive experiments were carried out to demonstrate the effectiveness of the proposed method in comparison to some of the long-familiar GMM based BGS methods in literature. However, note that this paper is not attempted to provide a real-time technique, but rather to investigate the potential utilization of the aforementioned measures to set a threshold automatically to detect moving objects in video sequences.

Deep expectation-maximization network for unsupervised image segmentation and clustering

Object detection is an important task for computer vision applications. Many researchers have proposed a number of methods to detect the objects through background modeling. To adapt to “illumination changes” in the background, local feature-based background models are proposed. They assume that local features are not affected by background changes. However, “motion changes”, such as the movement of trees, affect the local features in the background significantly. Therefore, it is difficult for local feature-based models to handle motion changes in the background. To solve this problem, we propose a new background model in this paper by applying a statistical framework to a local feature-based approach. Our proposed method combines the concepts of statistical and local feature-based approaches into a single framework. In particular, we use illumination invariant local features and describe their distribution by Gaussian Mixture Models (GMMs). The local feature has the ability to tolerate the effects of “illumination changes”, and the GMM can learn the variety of “motion changes”. As a result, this method can handle both background changes. Some experimental results show that the proposed method can detect the foreground objects robustly against both illumination changes and motion changes in the background.

The background subtraction is a widely used approach for Detecting Moving Objects (DMO) by a static camera using a simple algorithm; however, it is very sensitive to the local gradual changes of illumination, shadows, non-rigid moving objects and partial or full target occlusion. In order to overcome these issues, and to bring more potential to the solution, we propose an effective method for object detection based on active contour with camera motion compensation. The principle of active contours is to evolve an initial curve towards the object of interest that corresponds to the boundaries of the moving objects. Once the object has been detected, then it can be tracked by the Kalman filter. This latter requires many preassumptions about models and noise characteristics. As an alternative, a new method based on the Smooth Variable Structure Filter (SVSF) is implemented. The SVSF was introduced in an effort to provide a more robust estimation strategy. Detection and tracking algorithms require stable images to recognize a real moving target position. Therefore, the captured image from cameras which are placed on the moving platform, have undesired jitters, shakes and blurs. Video stabilization becomes an indispensable technique which is focusing on removing unnecessary camera vibrations from image sequences using a homographic matrix by extracting features using FAST corner detector and FREAK feature descriptor. The proposed algorithm is validated in real-world and the obtained results confirm the efficiency and robustness of our approach.

Moving object detection is an important component of a traffic surveillance system. Usual background subtraction approaches often poorly perform on a long outdoor traffic video due to vehicles waiting at an intersection and gradual changes of illumination and background shadow position. We present a fast and robust background subtraction algorithm based on unified spatio-temporal background and foreground modeling. The correlation between neighboring pixels provides high levels of detection accuracy in the dynamic background scene. Our Bayesian fusion method, which establishes the traffic scene model, combines both background and foreground models and considers prior probabilities to adapt changes of background in each frame. We explicitly model both temporal and spatial information based on the kernel density estimation (KDE) formulation for background modeling. Then, we use a Gaussian formulation to describe the spatial correlation of moving objects for foreground modeling. In the updating step, a fusion background frame is generated, and reasonable updating rates are also proposed for the traffic scene. The experimental results show that the proposed method outperforms the previous work with less computation and is better suited for the traffic scenes.

Gaussian mixture model (GMM) is one of the best models for modeling a background scene with gradual changes and repetitive motions. However, it fails in segmenting moving objects when the scene changes sharply. To handle this problem, a novel background modeling algorithm - memorizing GMM is proposed, which is inspired by the way human perceive the environment. It can make the GMM remember what the scene has ever been during the learning and updating period. Experimental results show that it can help segmenting moving objects precisely when the scene changes sharply.

Moving object detection in the presence of complex dynamic backgrounds such as swaying of trees, spouting of water from fountain, ripples in water, flag fluttering in the wind, camera jitters, noise, etc., is known to be very difficult and challenging task. In addition to this, illumination variation, camouflage and real-time constraint aggravate the problem further. Background subtraction (BS) is a widely used algorithm for moving object detection in the presence of static cameras. Its performance purely depends on the choice of features used for background modeling. In this paper, we have proposed a novel multi-feature and multi-modal based background subtraction using Local Binary Pattern (LBP) and Histogram of oriented Gradients (HOG) for complex dynamic scene. Each pixel is modeled as a set of multi-feature calculated from its neighborhood and multi-modal BS is performed using Gaussian mixture model (GMM). To show its efficacy, the proposed algorithm is compared with some of the state-of-the-art BS techniques. In order to evaluate the algorithm in uncontrolled environments, a collection of publicly available database has been used. Quantitative and qualitative results justify our algorithm for efficient moving object detection in the presence of swaying of trees, camouflage and ripples in the water surface.

Due to high rise in demand for video processing on hardware FPGA implementation of various image processing algorithm has become a necessity. Lot of research work is being done in the field of image processing and video processing on FPGA. In this paper we specifically concentrate on working Background identification, moving object detection and tracking. Keeping in mind the previous work dons in this area we have selected Gaussian mixture model for the implementation. The main work carried out by Gaussian mixture model is to is a common feature in many video processing systems. The paper speaks about two block of implementation mainly the image block generation and the RGB to YCbCr conversion. It has been proved from the design that it is efficient for high definition (HD) video sequences with frame size 1920 × 1080. Both the bocks are targeted on commercial field-programmable gate-array (FPGA) devices. When implemented on Atrix7 100t it uses 3% of FPGA logic resources. The second block takes like 2% of the FPGA resource. The total time required to process single frame is less than 2ns.

Moving object detection is one of the most important tasks in intelligent visual surveillance systems. Gaussian Mixture Model (GMM) has been most widely used for moving object detection, because of its robustness to variable scenes. However, to the best of our knowledge, existing GMM based methods can not detect moving objects which gradually stop and keep still state for a while. In this paper, we present an Enhanced Gaussian MixtureModel, called EGMM, to handle this problem. We integrate an Initial Gaussian Background Model (IGBM) and an extended Kalman filter based tracker with GMM, to enhance its performance. Experimental results show that our EGMM based method has a lower miss rate at the same false positives per image comparing to GMM based method for moving pedestrian detection, and it also has a higher detection rate for abandoned object detection comparing to GMM based method.

A normalized gaussian network (NGnet) (Moody & Darken, 1989) is a network of local linear regression units. The model softly partitions the input space by normalized gaussian functions, and each local unit linearly approximates the output within the partition. In this article, we propose a new on-line EMalgorithm for the NGnet, which is derived from the batch EMalgorithm (Xu, Jordan, &Hinton 1995), by introducing a discount factor. We show that the on-line EM algorithm is equivalent to the batch EM algorithm if a specific scheduling of the discount factor is employed. In addition, we show that the on-line EM algorithm can be considered as a stochastic approximation method to find the maximum likelihood estimator. A new regularization method is proposed in order to deal with a singular input distribution. In order to manage dynamic environments, where the input-output distribution of data changes over time, unit manipulation mechanisms such as unit production, unit deletion, and unit division are also introduced based on probabilistic interpretation. Experimental results show that our approach is suitable for function approximation problems in dynamic environments. We also apply our on-line EM algorithm to robot dynamics problems and compare our algorithm with the mixtures-of-experts family.

Moving object detection is an important and basic step in any video surveillance application. Detected object has used an input to higher level tasks such as tracking, event detection, and behavioral analysis. There are several challenges in moving object detection such as illumination changes, occlusion, shadow, bootstrap, dynamic background etc. Detection of moving object having similar color as background structure is called as camouflage, which is another big challenge. The method of detecting camouflage moving object is known as Decamouflaging. In recent years, the researchers are attracted towards the camouflage moving object detection due to its application in the military. In this review paper, different techniques using various features for camouflaged moving obj ect detection were studied.

Background subtraction is a widely used method for moving object detection in computer vision. It is usually applied in video surveillance systems. There are two major kinds of background subtraction approaches: pixel-based and block based. Yet there are three problems that can not be simultaneously solved by either method: the robustness to illumination changes, the effectiveness in suppressing shadows, and the smoothness of foregroundpsilas boundary. In order to solve these problems, a pixel-wise local information-based background subtraction method is proposed in this paper. In the proposed method, Gabor filters are performed to extract the spatial feature vectors for each pixel from the source image sequence. Then, the spatial feature vectors are modeled by Gaussian Mixture Model, and then moving objects are detected. Experiments show the validity of the proposed method.

Aiming at the traditional Gaussian mixture model has poor adaptability to the complex scenes, we proposes an improved moving object detection algorithm based on Gaussian mixture model and HSV space. The motion region is first extracted by the improved three-frame difference method. With the matching results, region segmentation of current frame is realized. Then different regions adopt different update strategy that improves the ability to reflect the illumination and scenes change. Next, utilizing characteristics of HSV color space and image first-order gradient achieve shadow detection. It effectively reduces interference of shadows, especially the pixels of foreground which has similar brightness properties with background. Experimental results show that the algorithm has good robustness and real-time performance.

For elderly people of living alone, falls and consequent resulting physical-psychological injuries even injury-related deaths are a major health hazard. How to analyze and utilize the captured videos by public places based on image processing is one hot research topic. Abnormal fall detection consists of four parts, which are captured video pre-processing, moving object detection, fall behavior recognition and experimental analysis. In this paper, dilation and corrosion, Gaussian filtering and median filtering are adopted to complete frame image sequences preprocessing to remove noises. Then, an improved background subtraction method based on Gaussian mixture model is used to detect moving objects. Based on extracted trajectory feature and shape feature of foreground objects, three-level hierarchical detectors are utilized to complete fall behavior recognition. At last, experimental analysis is done based on testing the system performance. Image processing speeds of our system is 15 frames per second if the lights are stable, which meets the requirements of real-time detection. Moreover, both the moving objects real-time detection rate and falling behavior detection accuracy rate are more than 95% in our experiments.