Moving shadow removal based on invariant texture feature

Shadow detection for moving objects based on texture analysis

This paper describes a new background subtraction method for detecting moving foreground objects in video from a static camera. The background model assumes that for each frame, every pixel is described as either an image patch, or a texture patch. An image patch describes the local appearance of an image, and is suitable when the background is structured and of fixed appearance. A texture patch is useful for describing a pixel which is part of a larger region containing a consistent patterning of pixels, but for which the local appearance is either indistinct (e.g. uniform regions), or time varying (e.g. the surface of the sea). Textures tend to correspond to regions rather than specific locations, so the texture descriptions are calculated globally (i.e. over the entire image). Over time, each pixel is represented as a weighted mixture of modes, as in the Stauffer and Grimson method. But instead of each mode being an image intensity with a variance, each mode now corresponds to either an image or a texture patch. The proposed background model is applied to the nine video sequences from the I2R data set, and compared to the provided foreground ground-truth. When the error is measured on a per pixel basis, the proposed method performs better than the alternative methods tested.

The key of background subtraction which is widely used in moving object detecting is to set up and update the background model. This paper presents a block background subtraction method based on ViBe, using the spatial correlation and time continuity of the video sequence. Set up the video sequence background model firstly. Then, update the background model through block processing. Finally employ the difference between the current frame and background model to extract moving objects.

An effective rotation and scale invariant log-polar wavelet texture feature for image retrieval was proposed. The feature extraction process involves a log-polar transform followed by an adaptive row shift invariant wavelet packet transform. The log-polar transform converts a given image into a rotation and scale invariant but row- shifted image, which is then passed to the adaptive row shift invariant wavelet packet transform to generate adaptively some subbands of rotation and scale invariant wavelet coefficients with respect to an information cost function. An energy signature is computed for each subband of these wavelet coefficients. In order to reduce feature dimensionality, only the most dominant log-polar wavelet energy signatures are selected as feature vector for image retrieval. The whole feature extraction process is quite efficient and involves only O (n/spl middot/log n) complexity. Experimental results show that this rotation and scale invariant texture feature is effective and outperforms the traditional wavelet packet signatures.

Prostate cancer is one of the most frequent cancers in men and is a major cause of mortality in the most of countries. In many diagnostic and treatment procedures for prostate disease accurate detection of prostate boundaries in transrectal ultrasound(TRUS) images is required. This is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a method for automatic prostate segmentation in TRUS images using Gabor feature extraction and snake-like contour is presented. This method involves preprocessing, extracting Gabor feature, training, and prostate segmentation. The speckle reduction for preprocessing step has been achieved by using stick filter and top-hat transform has been implemented for smoothing the contour. A Gabor filter bank for extraction of rotation- invariant texture features has been implemented. A support vector machine(SVM) for training step has been used to get each feature of prostate and nonprostate. Finally, the boundary of prostate is extracted by the snake-like contour algorithm. A number of experiments are conducted to validate this method and results showed that this new algorithm extracted the prostate boundary with less than 10.2% of the accuracy which is relative to boundary provided manually by experts Keywords—Gabor Filter Bank, Support Vector Machines, Prostate Segmentation

Detecting moving objects by using an adaptive background model is a critical component for many vision-based applications. In this paper, we propose a novel background modeling algorithm for traffic video surveillance based on objects dynamicity. Our algorithm is based on the definition of background as a set of static objects and on the observation that a static object is a set of pixels having the same appearance in long time interval. The normalized RGB color is used to describe the appearance under change lighting conditions, and a binary label is introduced to capture the dynamicity of objects over time. Finally, the cardinality function, calculated in each continued time period, is used to select persistent appearance corresponding to background objects. An update formula is proposed to reconstruct background model periodically based on current frame and last background image. Experimental results from several video sequences validate the effectiveness of the proposed algorithm

This paper proposes a moving target detection scheme suitable for camera motion. Firstly, the background model is initialized by a Gaussian mixture model algorithm. Then Kanade-Lucas-Tomasi Feature Tracker (KLT) method is used to detect optical flow feature points of two adjacent frames, RANdom SAmple Consensus (RANSAC) algorithm is used to filter out the correct matching points and obtain a homography matrix, which can recover the background model matching the current frame, the new background model is used to detect moving target of the current frame. In the foreground detection stage, the current pixel is first compared with its own background model, and then compared with the background model of its 8 neighborhood pixels, the algorithm is speeded up without reducing the detection accuracy in this way; In the update stage of the background model, in order to adapt to the background changes caused by camera motion, an age value variable is set for each pixel. The experimental results show that the improved algorithm has a significant improvement in detection accuracy and running time compared to Gaussian mixture background modeling.

Shadows detection is a fundamental step in visual surveillance and monitoring systems. Shadow points are often misclassified as object points causing errors in localization, segmentation, measurements, tracking and classification of moving objects. In order to detect potential shadow points an automatic segmentation procedure is performed and, for all moving pixels, the approach evaluates the compatibility of photometric properties with shadow characteristics. The approach is improved using a new method focused on the similarity between little textured patches: this method is based on the observation that shadow regions present same textural characteristics in each frame of the gray-level video-sequence and in the corresponding adaptive background model. We suggest a new approach to describe textural information in terms of redundant functions. The algorithm is designed to be unaffected by scene type, background type or light conditions. Results validate the algorithm 's performance on a benchmark suite of indoor and outdoor video sequences.

Real-time segmentation of moving objects in video sequences is a fundamental step for surveillance systems. One of successful methods for complex background is to use a multicolor background model per pixel. However, Common problem for this approach is that it suffers from illumination changing environment, in addition, it is incapable of removing shadows of moving objects. This paper proposed an effective scheme to improve the adaptive background model for each pixel by introducing a background training parameter into every Gaussian model, and region-based scheme is applied to judgment by utilizing both spatial and temporal information. Experimental results will be presented to validate proposed algorithm keep robustness in the situation of illumination changes, shadow can be removed in foreground mask, results shows False Alarm Rate can be reduced from 34.9% to 35.8% while the overlap varies within normal range from 0.4 to 0.6 compared with conventional Gaussian mixture model.

This article proposes a robust method for tracking sparse point features that is stable to long video sequences. To improve the stability of feature tracking in a long sequence, we use feature trajectories of tracked points. We predict feature states in the current image frame and compute rough estimates of feature locations. A search window is positioned at each estimated location and a similarity measure is computed within the window. Through the refinement using the similarity measure, an accurate feature position is determined. To reduce false matches, an outlier rejection stage is also introduced. Experimental results from several real video sequences showed that the proposed method stably tracks point features for long frame sequences.KeywordsVideo SequenceCurrent FrameScale Invariant Feature TransformSearch WindowFeature TrackingThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Video compression is the process of reducing the amount of data required to represent digital video while preserving an acceptable video quality. Recent studies on video compression have focused on multimedia transmission, videophones, teleconferencing, high definition television (HDTV), CD-ROM storage, etc. The idea of compression techniques is to remove the redundant information that exists in the video sequences. 
\nMotion compensated predictive coding is the main coding tool for removing temporal redundancy of video sequences and it typically accounts for 50-80% of the video encoding complexity. This technique has been adopted by all of the existing international video coding standards. It assumes that the current frame can be locally modelled as a translation of the reference frames. The practical and widely method used to carry out motion compensated prediction is block matching algorithm. In this method, video frames are divided into a set of non-overlapped macroblocks; each target macroblock of the current frame is compared with the search area in the reference frame in order to find the best matching macroblock. This will carry out displacement vectors that stipulate the movement of the macroblocks from one location to another in the reference frame. Checking all these locations is called full Search, which provides the best result. However, this algorithm suffers from long computational time, which necessitates improvement. Several methods of Fast Block Matching algorithm were developed to reduce the computation complexity. 
\nThis thesis focuses on two classifications: the first is called the lossless block matching algorithm process, in which the computational time required to determine the matching macroblock of the full search is decreased while the resolution of the predicted frames is the same as for the full search. The second is called the lossy block matching algorithm process, which reduces the computational complexity effectively but the search result’s quality is not the same as for the full search.

Given a video sequence decompressed from a compressed video sequence associated with motion vector information for each image frame, this short note presents an efficient predictive watershed-based video segmentation algorithm using motion vectors. The proposed algorithm has much computation-saving merit since the next frame can inherit the segmented results of the current frame according to the motion vector information of the next frame. Experimental results demonstrate that with little perceptual segmentation degradation, the proposed algorithm has better execution-time performance when compared to the previous Chien et al.'s video segmentation algorithm whose input video sequence is assumed to have no motion vector information. Further, the alleviation of the over-segmentation problem existed in both algorithms is investigated.

This paper presents a fast method for detecting textured objects moving in a video sequence. It is based on a known background estimation and a fixed camera position. The algorithm is able to detect the presence of moving objects and locates them on-line. It is a frame-by-frame method. First, a difference image is computed from the background and the current frame. This yields three classes of pixels, those for which something changed with respect to the background, those for which nothing changed, and finally the pixels for which no decision can be made. Then an a contrario model allows an automatic clustering, by using adapted rectangular windows, of the pixels for which changes have been detected. If necessary, these regions are corrected in order to better fit the moving objects' boundaries. Experimental results show that the algorithm is very robust with respect to noise and to the quality of the background estimation. The choice of the model parameters is quite natural and user friendly. The algorithm has been successfully tested on video sequences coming from different databases, including indoor and outdoor sequences.

In this paper, we introduce a new method to reliably ex- tract humans from a video sequence even when the humans are static for long periods of time. The proposed method addresses a common problem in background subtraction techniques whereby humans that are static are mistaken for new additions to the background scene and are consequently absorbed into the background model. In the proposed method, codebook background subtraction is used to identify foreground regions in the video frame. A motion based particle filter is then used to track one or more human heads in the frame and determine which of these foreground regions represent people. The background model is then selectively updated given this knowledge thus ensuring that people will never be absorbed into the background model once detected, even when indefinitely static. Simulation results confirm that a human body is robustly extracted using this method in a non-static environment. (5 pages)

Automated traffic surveillance systems are widely used in intelligent transportation systems (ITS). However, the accuracy of video-based Vehicle Detection is heavily affected by complex environmental factors such as shadows, rain, illumination and glare. This paper introduces an approach to motion vehicle detection in complex condition over highway surveillance video. The framework is composed of two parts: background estimation and multi-feature extraction. A fast constrained Delaunay triangulation (CDT) algorithm based on constrained-edge priority is presented instead of complicated segmentation algorithms. We present a background block update modeling theory based on triangulation to estimate background self-adaptively. Consequently, we can get the difference between the current frame and the background model. After extracting features in triangular candidates, multi-feature eigenvector is created for each vehicle with Principal Component Analysis (PCA). We design a classifier to classify triangular candidate as a part of a real vehicle or not by Support Vector Machine (SVM). And then, a parallelogram is used to represent the vehicle's shape robustly. Finally, experiments using real video sequence are performed to verify the method proposed for complex environmental factors.