Alireza Moini

Segmentation of the face and hands in sign language video sequences using color and motion cues

We present a hand and face segmentation methodology using color and motion cues for the content-based representation of sign language video sequences. The methodology consists of three stages: skin-color segmentation; change detection; face and hand segmentation mask generation. In skin-color segmentation, a universal color-model is derived and image pixels are classified as skin or nonskin based on their Mahalanobis distance. We derive a segmentation threshold for the classifier. The aim of change detection is to localize moving objects in a video sequences. The change detection technique is based on the F test and block-based motion estimation. Finally, the results from skin-color segmentation and change detection are analyzed to segment the face and hands. The performance of the algorithm is illustrated by simulations carried out on standard test sequences.

An insect vision-based motion detection chip

The architectural and circuit design aspects of a mixed analog/digital very large scale integration (VLSI) motion detection chip based on models of the insect visual system are described. The chip comprises two one-dimensional 64-cell arrays as well as front-end analog circuitry for early visual processing and digital control circuits. Each analog processing cell comprises a photodetector, circuits for spatial averaging and multiplicative noise cancellation, differentiation, and thresholding. The operation and configuration of the analog cells is controlled by digital circuits, thus implementing a reconfigurable architecture which facilitates the evaluation of several newly designed analog circuits. The chip has been designed and fabricated in a 1.2-/spl mu/m CMOS process and occupies an area of 2/spl times/2 mm/sup 2/.

Hand and face segmentation using motion and color cues in digital image sequences

In this paper, we present a hand and face segmentation algorithm using motion and color cues. The algorithm is proposed for the content based representation of sign language image sequences, where the hands and face constitute a video object. Our hand and face segmentation algorithm consists of three stages, namely color segmentation, temporal segmentation, and video object plane generation. In color segmentation, we model the skin color as a normal distribution and classify each pixel as skin or non-skin based on its Mahalanobis distance. The aim of temporal segmentation is to localize moving objects in image sequences. A statistical variance test is employed to detect object motion between two consecutive images. Finally, the results from color and temporal segmentation are analyzed to yield a change detection mask. The performance of the algorithm is illustrated by simulation carried out on the silent test sequence.

Automatic thresholding for change detection in digital video

In this paper we propose a thresholding technique for change detection in digital video. The technique assumes that the difference image generated from two frames of a video sequence has a trimodal Gaussian distribution and a computationally efficient fitting criterion is employed to find the best match between the data and model. Results show that the technique is capable of detecting true motion in very images.

An analog implementation of early visual processing in insects

An analog VLSI implementation which mimics the early visual processing stages in insects is described. The system is composed of sixty parallel channels of integrated photodetectors and processing elements. It serves as the front end processor for a motion detection chip. The photodetection circuitry includes p-well junction diodes on a 2 mu m CMOS process and a logarithmic compression to increase the dynamic range of the system. The processing elements consist of an analog differentiator behind each photodetector. The differentiators are low frequency and have been designed using subthreshold design methods.<<ETX>>

Motion Perception Using Analog VLSI

Motion perception is arguably a fundamental mechanism used by natural species to accomplish a number of tasks, such as navigating freely in an unknown environment. Traditional motion perception methods tend to be computationally intensive, requiring powerful computers and large memories. However, by copying biological mechanisms, such as elementary motion discrimination at the early stages of the visual processing paths, it should be possible to build small and efficient motion perception systems. This paper describes the manner in which a simple motion perception model based on the insect visual system has been implemented using mixed analog/digital VLSI. The device has been fabricated in a 2 micron double metal, double polysilicon process, and comprises 61 photo-detectors, and associated analog and digital circuitry. While not entirely successful in that component mismatches hamper the detection of dark-to-bright changes in contrast, the results clearly show the feasibility of using such a device in autonomous control systems.

A micro-sensor based on insect vision

A major problem faced by artificial vision systems is the computational bottleneck. The problem can be addressed by incorporating preliminary parallel signal processing in the sensor itself, thereby alleviating subsequent processing requirements. The authors describe a vision system implemented in analog and digital VLSI incorporating sensors and a processing unit. It extracts information such as range, depth and motion of objects in the visual environment. Advantages are its small size and its wide dynamic range which make it very suitable for real-life applications, particularly in robotics.

Multiplicative noise cancellation (MNC) in analog VLSI vision sensors

The operation of analog VLSI sensors can be significantly affected by multiplicative noise caused by specular reflections of light from artificial sources. The paper describes the implementation of a proposed architecture and circuits for multiplicative noise cancellation (MNC). The circuit has been used in a motion detection chip, and simulation results indicate about ten times improvement in the signal to noise ratio.<<ETX>>

A smart visual micro-sensor

This article describes a smart VLSI micro-sensor inspired by early visual processing of insects. The chip serves as a real-time visual micro-sensor; it accepts a time-varying optical image and provides outputs indicating direction of motion, bearing, and speed of objects in the environment. The chip has been fabricated and tested. It was initially designed for autonomous robot navigation, but it can be used in other applications such as smart cameras, smart rear vision mirrors, and smart bumper bars for collision avoidance.<<ETX>>

Two-dimensional motion detector based on insect vision

Implementing motion detection algorithms using analog VLSI techniques has proven to be a challenging task due to several obstacles, including the limitations of analog VLSI, the algorithmic limitations brought forward by complex motion detection schemes, and the effect of various types of noise. Insect vision has been an inspiring model for motion detectors, as insects heavily rely on motion detection for navigation, and the natural complexity of their neuro-visual circuitry is also less than that of vertebrates. In an effort to implement the so called template model of insect vision, a comparative study of various analog differentiators was undertaken by implementing different candidates on a test chip. Based on the results, a 64 by 4 motion detector has been designed and fabricated. The chip is designed in a 0.8 micrometer 3M-1P CMOS process, and the 2-D array occupies an area of 1.5 multiplied by 3.1 mm2. Each cell comprises a bipolar-mode photodetector, an adaptive amplifier, the improved analog differentiator, and thresholding circuits.