Abdul Bais

Color based skin classification

Skin detection is used in applications ranging from face detection, tracking body parts and hand gesture analysis, to retrieval and blocking objectionable content. In this paper, we investigate and evaluate (1) the effect of color space transformation on skin detection performance and finding the appropriate color space for skin detection, (2) the role of the illuminance component of a color space, (3) the appropriate pixel based skin color modeling technique and finally, (4) the effect of color constancy algorithms on color based skin classification. The comprehensive color space and skin color modeling evaluation will help in the selection of the best combinations for skin detection. Nine skin modeling approaches (AdaBoost, Bayesian network, J48, Multilayer Perceptron, Naive Bayesian, Random Forest, RBF network, SVM and the histogram approach of Jones and Rehg (2002)) in six color spaces (IHLS, HSI, RGB, normalized RGB, YCbCr and CIELAB) with the presence or absence of the illuminance component are compared and evaluated. Moreover, the impact of five color constancy algorithms on skin detection is reported. Results on a database of 8991 images with manually annotated pixel-level ground truth show that (1) the cylindrical color spaces outperform other color spaces, (2) the absence of the illuminance component decreases performance, (3) the selection of an appropriate skin color modeling approach is important and that the tree based classifiers (Random forest, J48) are well suited to pixel based skin detection. As a best combination, the Random Forest combined with the cylindrical color spaces, while keeping the illuminance component outperforms other combinations, and (4) the usage of color constancy algorithms can improve skin detection performance.

Evaluation of UMTS security architecture and services

This paper presents an in-depth analysis and evaluation of the security of UMTS. Four classes of attacks and threats are discussed in detail. Thereafter, the available security mechanism and services of UMTS are reviewed and evaluated. It is found that most of the potential attacks and threats can be thwarted by the available security services and mechanisms of UMTS.

Landmark based global self-localization of mobile soccer robots

We present a stereo vision based global self-localization strategy for tiny autonomous mobile robots in a well-known dynamic environment. Global localization is required for an initial startup or when the robot loses track of its pose during navigation. Existing approaches are based on dense range scans, active beacon systems, artificial landmarks, bearing measurements using omni-directional cameras or bearing/range calculation using single frontal cameras, while we propose feature based stereo vision system for range calculation. Location of the robot is estimated using range measurements with respect to distinct landmarks such as color transitions, corners, junctions and line intersections. Unlike methods based on angle measurement, this method requires only two distinct landmarks. Simulation results show that robots can successfully localize themselves whenever two distinct landmarks are observed. As such marked minimization of landmarks for vision based self-localization of robots has been achieved.

Single landmark based self-localization of mobile robots

In this paper we discuss landmark based absolute localization of tiny autonomous mobile robots in a known environment. Landmark features are naturally occurring as it is not allowed to modify the environment with special navigational aids. These features are sparse in our application domain and are frequently occluded by other robots. This makes simultaneous acquisition of two or more landmarks difficult. Therefore, we propose a system that requires a single landmark feature. The algorithm is based on range measurement of a single landmark from two arbitrary points whose displacement can be measured using dead-reckoning sensors. Range estimation is done with a stereo vision system. Simulation results show that the robot can localize itself if it can estimates range of the same landmark from two different position and if the displacement between the two position is known.

A performance evaluation of SIFT and SURF for multispectral image matching

This paper evaluates the performance of SIFT and SURF for cross band matching of multispectral images. The evaluation is based on matching a reference spectral image with the images acquired at different spectral bands. The reference image possesses scale and (in-plane) rotational differences in addition to spectral variations. Additive white Gaussian noise is also added to compare performance degradation at different noise levels. We use the precision and repeatability criteria for performance evaluation. Experimental results demonstrate that SIFT performs better than SURF in multispectral environment.

A Swift and Memory Efficient Hough Transform for Systems with Limited Fast Memory

This paper focuses on implementation of a speedy Hough Transform (HT) which considers the memory constraints of the system. Because of high memory demand, small systems (DSPs, tiny robots) cannot realize efficient implementation of HT. Keeping this scenario in mind, the paper discusses an effective and memory-efficient method of employing the HT for extraction of line features from a gray scale image. We demonstrate the use of a circular buffer for extraction of image edge pixels and store the edge image in a manner that is different from the conventional way. Approximation of the two dimensional Hough Space by a one dimensional array is also discussed. The experimental results reveal that the proposed algorithm produces better results, on small and large systems, at a rapid pace and is economical in terms of memory usage.

On fair and optimal multi-source IP-multicast

We investigate the problem of maximizing multicast throughput under a fairness constraint. Multiple server nodes wish to communicate to their intended set of client nodes over a shared network infrastructure. Our goal is to devise distributed algorithms to construct multicast sessions, one for each server node, such that (a) the network infrastructure is optimally utilized and (b) the network resources are fairly distributed between multicast sessions, i.e., no individual session claims more than a prescribed share of the network bandwidth resources. We are particularly interested in multi-tree multicast strategies in which every multicast session may contain many multicast trees. We show how the use of multiple trees increases network throughput and the load distribution in the network. We propose a class of round-robin algorithms that are based on successive selection of multicast trees for each multicast session, in a loosely cooperative, yet distributed fashion. Our best algorithm, the Cooperative Shortest Path Tree Packing (CSPTP) algorithm, performs well in a variety of scenarios, ranging from very sparse to dense applications. Through extensive simulations on random networks, we compare the performance of our algorithms with those commonly used in IP-multicast as well as theoretical upper bounds derived from network coding formulations. We show that the CSPTP can improve the throughput, and often achieves about 90% of the theoretical upper bound.

Location tracker for a mobile robot

This paper presents landmark based self-localization of a two-wheeled differential drive autonomous mobile robot in a known but highly dynamic environment. The robot is equipped with a pivoted stereo vision system, two digital encoders, a gyro sensor, two lOg accelerometers and a magnetic compass. Global position of the robot is estimated using range measurements of distinct features such as color transitions, corners, junctions and line intersections in the robot environment. However, due to scarcity of distinct features, it is not possible to extract the minimum required features for global position estimation from everywhere in the state space. Therefore, the robot position is tracked between intermittent global localization to have an all time position estimate available to the robot. The robot observation vector is composed of range and bearing measurements of distinct features in the robot environment which is merged with the current position estimate to suppress the accumulating errors. Simulation results illustrate the performance of the location tracker.

Active single landmark based global localization of autonomous mobile robots

This paper presents landmark based global self-localization of autonomous mobile robots in a known but highly dynamic environment. The algorithm is based on range estimation to naturally occurring distinct features as it is not possible to modify the environment with special navigational aids. These features are sparse in our application domain and are frequently occluded by other robots. To enable the robot to estimate its absolute position with respect to a single landmark it is equipped with dead-reckoning sensors in addition to the stereo vision system mounted on a rotating head. The pivoted stereo vision system of the robot enables it to measure range and use bi/trilateration based methods as they require fewer landmarks compared to angle based triangulation. Further reduction of landmarks is achieved when robot orientation is estimated independently. Simulation results are presented which illustrate the performance of our algorithm.

Simple stereo vision system for real-time object recognition for an autonomous mobile robot

Intelligent sensors for mobile robots play an important role in many technical applications. In this paper, a real-time stereo object recognition system for a tiny mobile robot is presented, capable of detecting objects in real-time at a frame rate of up to 60frames/s. In order to get an all around view the stereo camera system is mounted on a pivoted head. We propose an object recognition algorithm that is optimized for the detection of well known objects on deeply embedded systems. The detection algorithm is based on a combination of edge and color detection and uses a fixed model for each object to be recognized. The stereo algorithm is a simple matching of two independently performed algorithms for each camera. Results of the ball recognition application show that its relative coordinates are found within <10ms