Manish Khare

Moving object segmentation in Daubechies complex wavelet domain

Motion segmentation is a crucial step in video analysis and is associated with a number of computer vision applications. This paper introduces a new method for segmentation of moving object which is based on double change detection technique applied on Daubechies complex wavelet coefficients of three consecutive frames. Daubechies complex wavelet transform for segmentation of moving object has been chosen as it is approximate shift invariant and has a better directional selectivity as compared to real valued wavelet transform. Double change detection technique is used to obtain video object plane by inter-frame difference of three consecutive frames. Double change detection technique also provides automatic detection of appearance of new objects. The proposed method does not require any other parameter except Daubechies complex wavelet coefficients. Results of the proposed method for segmentation of moving objects are compared with results of other state-of-the-art methods in terms of visual performance and a number of quantitative performance metrics viz. Misclassification Penalty, Relative Foreground Area Measure, Pixel Classification Based Measure, Normalized Absolute Error, and Percentage of Correct Classification. The proposed method is found to have high degree of segmentation accuracy than the other state-of-the-art methods.

Single change detection-based moving object segmentation by using Daubechies complex wavelet transform

Research in motion analysis is a challenging field and it has a variety of video surveillance applications. For any video surveillance application, background detection and removal plays an important role in segmentation of the moving objects. This study proposes a new method for segmentation of the moving object, which is based on single change detection applied on Daubechies complex wavelet coefficients of two consecutive frames. The authors have chosen Daubechies complex wavelet transform as it is shift invariant and has a better directional selectivity as compared with real-valued wavelet transforms. Single change detection is a method to obtain video object plane by inter-frame difference of two consecutive frames, and it provides automatic detection of appearances of new objects. The proposed method does not require any other parameter except wavelet coefficients. Segmentation results of the moving objects after applying the proposed method are compared with those obtained after applying other spatial and wavelet domain segmentation methods in terms of visual performance and a number of quantitative measures viz misclassification penalty, relative position-based measure, structural content, normalised absolute error and average difference and the proposed method is found better than the other methods.

Dual Tree Complex Wavelet Transform Based Video Object Tracking

This paper presents a new method for tracking of an object in video sequence which is based on dual tree complex wavelet transforms. Real valued wavelet transform, mostly used in tracking applications, suffers from lack of shift invariance and have poor directional selectivity. We have used dual tree complex wavelet transform in tracking because it avoids shortcomings of real wavelet transform. In the proposed method, object is tracked in next frames by computing the energy of dual-tree complex wavelet coefficients corresponding to the object area and matching this energy to that of in the neighborhood area. The proposed method is simple and does not require any other parameter except complex wavelet coefficients. Experimental results demonstrate performance of the proposed method.

Adaptive real-time motion segmentation technique based on statistical background model

Abstract Motion segmentation is a crucial step for video analysis and has many applications. This paper proposes a method for motion segmentation, which is based on construction of statistical background model. Variance and Covariance of pixels are computed to construct the model for scene background. We perform average frame differencing with this model to extract the objects of interest from the video frames. Morphological operations are used to smooth the object segmentation results. The proposed technique is adaptive to the dynamically changing background because of change in the lighting conditions and in scene background. The method has the capability to relearn the background to adapt these variations. The immediate advantage of the proposed method is its high processing speed of 30 frames per second on large sized (high resolution) videos. We compared the proposed method with other five popular methods of object segmentation in order to prove the effectiveness of the proposed technique. Experimental results demonstrate the novelty of the proposed method in terms of various performance parameters. The method can segment the video stream in real-time, when background changes, lighting conditions vary, and even in the presence of clutter and occlusion

Moving shadow detection and removal – a wavelet transform based approach

Shadow detection and removal is an important problem in computer vision. The real challenge in moving shadow detection and removal is to classify moving shadow points which are many times misclassified as moving object points in a video sequences. Various shadow detection and removal algorithms have been proposed for images but only a few works have been done for moving objects. In this study, a novel method for shadow detection and removal is proposed using discrete wavelet transform (DWT). The authors have used DWT because of its multi-resolution property that decomposes an image into four different bands without loss of the spatial information. For detection and removal of shadow, they have proposed a new threshold in the form of relative standard deviation. The value of threshold is automatically determined and does not require any supervised learning or manual calibration. The proposed method is flexible and depends on only one parameter, namely, wavelet coefficients. Results of shadow detection and removal from moving object after applying the proposed method are compared with the results of other state-of-the-art methods in terms of visual performance and a number of quantitative performance parameters. The proposed method is found to be better and more robust than other methods.

An effective local feature descriptor for object detection in real scenes

In this study, we advocate the importance of robust local features that allow object form to be distinguished from other objects for detection purpose. We start from the grid of Histogram of oriented gradients (HOG) and integrate Scale Invariant Feature Transform (SIFT) within them. In HOG features an objects appearance is detected by the distribution of local intensity gradients or edge directions for different cells. In the proposed method we have computed the SIFT despite of computing intensity gradients for these cells. In this way, the proposed approach does not only provide more significant information than just providing intensity gradients but also proves to deal with following challenges: (i) scale invariance; (ii) rotation invariance; (iii) change in illumination; and (iv) change in view points. With qualitative and quantitative experimental evaluation on standard INRIA dataset, we have compared the proposed method with other state of the art object detection methods and demonstrated better performance over them.

Automatic multiple human detection and tracking for visual surveillance system

Object Tracking is an important task in video processing because of its variety of applications in visual surveillance, human activity monitoring and recognition, traffic flow management etc. Multiple object detection and tracking in outdoor environment is a challenging task because of the problems raised by poor lighting conditions, variation in poses of human object, shape, size, clothing, etc. This paper proposes a novel technique for detection and tracking of multiple human objects in a video. A classifier is trained for object detection using Haar-like features from training image set. Human objects are detected with help of this trained detector and are tracked using particle filter. The experimental results show that the proposed technique can detect and track multiple humans in a video adequately fast in the presence of poor lighting conditions, variation in poses of human objects, shape, size, clothing etc. and the technique can handle varying number of human objects in a video at various points of time.

Curvelet transform based moving object segmentation

In this paper, we have proposed a new method for segmentation of moving objects, which is based on single change detection applied on curvelet coefficients of two consecutive frames. The wavelet transform is widely used in moving object segmentation but it can not describe curve discontinuities. Therefore we have used curvelet transform for segmentation of moving objects. The proposed method is simple and does not require any other parameter except curvelet coefficients. Results after applying the proposed method for segmentation of moving object are compared with other state-of-the-art methods in terms of visual as well as quantitative performance measures viz. Misclassification penalty, Relative position based measure and Structural content. The proposed method is found to be better than other methods.

Dual tree complex wavelet transform based shadow detection and removal from moving objects

Presence of shadow degrades performance of any computer vision system as a number of shadow points are always misclassified as object points. Various algorithms for shadow detection and removal exist for still images but very few algorithms have been developed for moving objects. This paper introduces a new method for shadow detection and removal from moving object which is based on Dual tree complex wavelet transform. We have chosen Dual tree complex wavelet transform as it is shift invariant and have a better edge detection property as compared to real valued wavelet transform. In the present work, shadow detection and removal has been done by thresholding wavelet coefficients of Dual tree complex wavelet transform of difference of reference frame and the current frame. Standard deviation of wavelet coefficients is used as an optimal threshold. Results after visual and quantitative performance metrics computation shows that the proposed method for shadow detection and removal is better than other state-of-theart methods.

An approach towards wavelet transform based multiclass object classification

Object classification is an important problem in computer vision, in which multiclass object classification is more difficult one in comparison to single class object classification. In this paper, we proposed a new method for multiclass object classification based on discrete wavelet transform. We have used discrete wavelet transform coefficients as a feature of object, because of its multi-resolution property. We have used multiclass support vector machine as a classifier for classification of objects. The proposed method has been tested on own dataset prepared by authors of this paper. We have tested the proposed method on multiple levels of discrete wavelet transform. Quantitative evaluation results shows that the proposed method gives better performance for multiclass object classification at higher level of discrete wavelet transform and other state-of-the-art methods.