Surendra Ranganath

A novel unrestricted center-biased diamond search algorithm for block motion estimation

The widespread use of block-based interframe motion estimation for video sequence compression in both MPEG and H.263 standards is due to its effectiveness and simplicity of implementation. Nevertheless, the high computational complexity of the full-search algorithm has motivated a host of suboptimal but faster search strategies. A popular example is the three-step search (TSS) algorithm. However, its uniformly spaced search pattern is not well matched to most real-world video sequences in which the motion vector distribution is nonuniformly biased toward the zero vector. Such an observation inspired the new three-step search (NTSS) which has a center-biased search pattern and supports a halfway-stop technique. It is faster on average, and gives better motion estimation as compared to the well-known TSS. Later, the four-step search (4SS) algorithm was introduced to reduce the average case from 21 to 19 search points, while maintaining a performance similar to NTSS in terms of motion compensation errors. We propose a novel unrestricted center-biased diamond search (UCBDS) algorithm which is more efficient, effective, and robust than the previous techniques. It has a best case scenario of only 13 search points and an average of 15.5 block matches. This makes UCBDS consistently faster than the other suboptimal block-matching techniques. This paper also compares the above methods in which both the processing speed and the accuracy of motion compensation are tested over a wide range of test video sequences.

Automatic Sign Language Analysis: A Survey and the Future beyond Lexical Meaning

Research in automatic analysis of sign language has largely focused on recognizing the lexical (or citation) form of sign gestures as they appear in continuous signing, and developing algorithms that scale well to large vocabularies. However, successful recognition of lexical signs is not sufficient for a full understanding of sign language communication. Nonmanual signals and grammatical processes which result in systematic variations in sign appearance are integral aspects of this communication but have received comparatively little attention in the literature. In this survey, we examine data acquisition, feature extraction and classification methods employed for the analysis of sign language gestures. These are discussed with respect to issues such as modeling transitions between signs in continuous signing, modeling inflectional processes, signer independence, and adaptation. We further examine works that attempt to analyze nonmanual signals and discuss issues related to integrating these with (hand) sign gestures. We also discuss the overall progress toward a true test of sign recognition systems--dealing with natural signing by native signers. We suggest some future directions for this research and also point to contributions it can make to other fields of research. Web-based supplemental materials (appendicies) which contain several illustrative examples and videos of signing can be found at www.computer.org/publications/dlib.

Contour extraction from cardiac MRI studies using snakes

The author investigated automatic extraction of left ventricular contours from cardiac magnetic resonance imaging (MRI) studies. The contour extraction algorithms were based on active contour models, or snakes. Based on cardiac MR image characteristics, the author suggested algorithms for extracting contours from these large data sets. The author specifically considered contour propagation methods to make the contours reliable enough despite noise, artifacts, and poor temporal resolution. The emphasis was on reliable contour extraction with a minimum of user interaction. Both spin echo and gradient echo studies were considered. The extracted contours were used for determining quantitative measures for the heart and could also be used for obtaining graphically rendered cardiac surfaces.

Real-time gesture recognition system and application

Abstract In this paper, we consider a vision-based system that can interpret a users gestures in real time to manipulate windows and objects within a graphical user interface. A hand segmentation procedure first extracts binary hand blob(s) from each frame of the acquired image sequence. Fourier descriptors are used to represent the shape of the hand blobs, and are input to radial-basis function (RBF) network(s) for pose classification. The pose likelihood vector from the RBF network output is used as input to the gesture recognizer, along with motion information. Gesture recognition performances using hidden Markov models (HMM) and recurrent neural networks (RNN) were investigated. Test results showed that the continuous HMM yielded the best performance with gesture recognition rates of 90.2%. Experiments with combining the continuous HMMs and RNNs revealed that a linear combination of the two classifiers improved the classification results to 91.9%. The gesture recognition system was deployed in a prototype user interface application, and users who tested it found the gestures intuitive and the application easy to use. Real time processing rates of up to 22 frames per second were obtained.

Highly scalable wavelet-based video codec for very low bit-rate environment

We introduce a highly scalable video compression system for very low bit-rate videoconferencing and telephony applications around 10-30 kbits/s. The video codec first performs a motion-compensated three-dimensional (3-D) wavelet (packet) decomposition of a group of video frames, and then encodes the important wavelet coefficients using a new data structure called tri-zerotrees (TRI-ZTR). Together, the proposed video coding framework forms an extension of the original zero tree idea of Shapiro (1992) for still image compression. In addition, we also incorporate a high degree of video scalability into the codec by combining the layered/progressive coding strategy with the concept of embedded resolution block coding. With scalable algorithms, only one original compressed video bit stream is generated. Different subsets of the bit stream can then be selected at the decoder to support a multitude of display specifications such as bit rate, quality level, spatial resolution, frame rate, decoding hardware complexity, and end-to-end coding delay. The proposed video codec also allows precise bit rate control at both the encoder and decoder, and this can be achieved independently of the other video scaling parameters. Such a scheme is very useful for both constant and variable bit rate transmission over mobile communication channels, as well as video distribution over heterogeneous multicast networks. Finally, our simulations demonstrated comparable objective and subjective performance when compared to the ITU-T H.263 video coding standard, while providing both multirate and multiresolution video scalability.

A rule-based approach for robust clump splitting

This paper presents a robust rule-based approach for the splitting of binary clumps that are formed by objects of diverse shapes and sizes. First, the deepest boundary pixels, i.e., the concavity pixels in a clump, are detected using a fast and accurate scheme. Next, concavity-based rules are applied to generate the candidate split lines that join pairs of concavity pixels. A figure of merit is used to determine the best split line from the set of candidate lines. Experimental results show that the proposed approach is robust and accurate.

Pose-invariant face recognition using a 3D deformable model

The paper proposes a novel, pose-invariant face recognition system based on a deformable, generic 3D face model, that is a composite of: (1) an edge model, (2) a color region model and (3) a wireframe model for jointly describing the shape and important features of the face. The first two submodels are used for image analysis and the third mainly for face synthesis. In order to match the model to face images in arbitrary poses, the 3D model can be projected onto different 2D viewplanes based on rotation, translation and scale parameters, thereby generating multiple face-image templates (in different sizes and orientations). Face shape variations among people are taken into account by the deformation parameters of the model. Given an unknown face, its pose is estimated by model matching and the system synthesizes face images of known subjects in the same pose. The face is then classified as the subject whose synthesized image is most similar. The synthesized images are generated using a 3D face representation scheme which encodes the 3D shape and texture characteristics of the faces. This face representation is automatically derived from training face images of the subject. Experimental results show that the method is capable of determining pose and recognizing faces accurately over a wide range of poses and with naturally varying lighting conditions. Recognition rates of 92.3% have been achieved by the method with 10 training face images per person.

Face recognition using transform features and neural networks

Abstract In this paper we considered face recognition using two Radial Basis Function Network (RBFN) architectures and compared performance with the nearest neighbor algorithm. Performance was also evaluated for feature vectors extracted from face images by using principal component analysis as well as wavelet transform. Raw recognition rates as well as rates with confidence measures were considered. In the RBFN1 architecture, one network was used to discriminate among the classes, while the RBFN2 architecture used one network per class. From the point of view of computations RBFN2 was more efficient than RBFN1 with PCA feature vectors, but its recognition performance was slightly worse than RBFN1. Other experiments showed that RBFN1 was largely superior to the NNA when the amount of computations in both methods was similar. With the use of wavelet features, performance dropped 5–10% in relation to features extracted by PCA. However, in a given implementation, this must be weighed in conjunction with the advantages of using wavelet features, namely, no storage is required for eigenvectors, and they are simpler to compute.

Cooperative Multitarget Tracking With Efficient Split and Merge Handling

For applications such as behavior recognition it is important to maintain the identity of multiple targets, while tracking them in the presence of splits and merges, or occlusion of the targets by background obstacles. Here we propose an algorithm to handle multiple splits and merges of objects based on dynamic programming and a new geometric shape matching measure. We then cooperatively combine Kalman filter-based motion and shape tracking with the efficient and novel geometric shape matching algorithm. The system is fully automatic and requires no manual input of any kind for initialization of tracking. The target track initialization problem is formulated as computation of shortest paths in a directed and attributed graph using Dijkstras shortest path algorithm. This scheme correctly initializes multiple target tracks for tracking even in the presence of clutter and segmentation errors which may occur in detecting a target. We present results on a large number of real world image sequences, where upto 17 objects have been tracked simultaneously in real-time, despite clutter, splits, and merges in measurements of objects. The complete tracking system including segmentation of moving objects works at 25 Hz on 352times288 pixel color image sequences on a 2.8-GHz Pentium-4 workstation

Multi-Camera Target Tracking in Blind Regions of Cameras with Non-overlapping Fields of View

In this paper, we propose a real time system for tracking targets across blind regions of multiple cameras with non-overlapping fields of views (FOVs) using camera topology, and targets’ motion and shape information. Kalman filters are used to robustly track each target’s shape and motion in each camera view and the common ground plane view composed of all camera views. The target’s track in the blind region between cameras is obtained using Kalman filter predictions. For multi-camera correspondence matching we compute the Gaussian distributions of the tracking parameters across cameras for the target motion and position in the ground plane view. Matching of targets across camera views uses a graph based track initialization scheme, which accumulates information from occurrences of target in several consecutive frames of the video. Probabilistic matching is carried out by using the track parameters for new tracks obtained from the graph in a camera view with the parameters of the terminated tracks learnt by Kalman filters in the other camera views and ground plane view. We obtain 85% accuracy for corresponding matching while tracking vehicles observed from two cameras monitoring a highway.